Reinforcement Learning for Electric Power System Decision and Control: Past Considerations and Perspectives
In this paper, we review past (including very recent) research considerations in using reinforcement learning (RL) to solve electric power system decision and control problems. The RL considerations are reviewed in terms of specific electric power system problems, type of control and RL method used....
Saved in:
| Published in | IFAC-PapersOnLine Vol. 50; no. 1; pp. 6918 - 6927 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
01.07.2017
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 2405-8963 2405-8963 |
| DOI | 10.1016/j.ifacol.2017.08.1217 |
Cover
Loading…
| Abstract | In this paper, we review past (including very recent) research considerations in using reinforcement learning (RL) to solve electric power system decision and control problems. The RL considerations are reviewed in terms of specific electric power system problems, type of control and RL method used. We also provide observations about past considerations based on a comprehensive review of available publications. The review reveals the RL is considered as viable solutions to many decision and control problems across different time scales and electric power system states. Furthermore, we analyse the perspectives of RL approaches in light of the emergence of new-generation, communications, and instrumentation technologies currently in use, or available for future use, in power systems. The perspectives are also analysed in terms of recent breakthroughs in RL algorithms (Safe RL, Deep RL and path integral control for RL) and other, not previously considered, problems for RL considerations (most notably restorative, emergency controls together with so-called system integrity protection schemes, fusion with existing robust controls, and combining preventive and emergency control). |
|---|---|
| AbstractList | In this paper, we review past (including very recent) research considerations in using reinforcement learning (RL) to solve electric power system decision and control problems. The RL considerations are reviewed in terms of specific electric power system problems, type of control and RL method used. We also provide observations about past considerations based on a comprehensive review of available publications. The review reveals the RL is considered as viable solutions to many decision and control problems across different time scales and electric power system states. Furthermore, we analyse the perspectives of RL approaches in light of the emergence of new-generation, communications, and instrumentation technologies currently in use, or available for future use, in power systems. The perspectives are also analysed in terms of recent breakthroughs in RL algorithms (Safe RL, Deep RL and path integral control for RL) and other, not previously considered, problems for RL considerations (most notably restorative, emergency controls together with so-called system integrity protection schemes, fusion with existing robust controls, and combining preventive and emergency control). |
| Author | Ernst, Damien Glavic, Mevludin Fonteneau, Raphaël |
| Author_xml | – sequence: 1 givenname: Mevludin surname: Glavic fullname: Glavic, Mevludin organization: Dept. of Electrical Engineering and Computer Science, University of Liège, Allée de la découverte 10, 4000 Liège, Belgium – sequence: 2 givenname: Raphaël surname: Fonteneau fullname: Fonteneau, Raphaël email: raphael.fonteneau@ulg.ac.be organization: Dept. of Electrical Engineering and Computer Science, University of Liège, Allée de la découverte 10, 4000 Liège, Belgium – sequence: 3 givenname: Damien surname: Ernst fullname: Ernst, Damien organization: Dept. of Electrical Engineering and Computer Science, University of Liège, Allée de la découverte 10, 4000 Liège, Belgium |
| BookMark | eNqFkFtLwzAYhoNMcM79BCF_YDVp06bVC5E5DzBweLgO2devktklIwmT_XvbzQvxZlff8X3hfc7JwDqLhFxylnDGi6tVYhoNrk1SxmXCyoSnXJ6QYSpYPimrIhv86c_IOIQVYyytCiGrcki-XtHYxnnANdpI56i9NfaTdis6axGiN0AX7hs9fduFiGt6j2CCcZZqW9Ops9G79poudIj9FEyNXsfuHvYPC_Rh09mYLYYLctroNuD4t47Ix8Psffo0mb88Pk_v5hMQooyTHECwqtCASy5xCTk0hSzKPNeai6oShcxY0wBrqiXIupCs5nldV6XWQmAm02xE8oMveBeCx0ZtvFlrv1OcqR6aWqkDNNVDU6xUPbROd_NPBybus0SvTXtUfXtQYxdta9CrAAYtYG18B0DVzhxx-AHyMI9q |
| CitedBy_id | crossref_primary_10_1016_j_epsr_2022_108487 crossref_primary_10_1016_j_engappai_2022_105557 crossref_primary_10_1016_j_artmed_2021_102193 crossref_primary_10_1109_ACCESS_2022_3160710 crossref_primary_10_1109_ACCESS_2024_3396449 crossref_primary_10_23919_IEN_2024_0027 crossref_primary_10_1016_j_ifacol_2019_08_260 crossref_primary_10_1049_tje2_12065 crossref_primary_10_1109_ACCESS_2024_3350207 crossref_primary_10_1016_j_rser_2021_111459 crossref_primary_10_1016_j_epsr_2020_106615 crossref_primary_10_1016_j_rser_2020_110647 crossref_primary_10_3390_en17092167 crossref_primary_10_1038_s41598_025_91940_x crossref_primary_10_1016_j_physa_2021_126488 crossref_primary_10_1109_TSG_2019_2933191 crossref_primary_10_3390_app11031209 crossref_primary_10_1016_j_engappai_2019_08_014 crossref_primary_10_21105_joss_05616 crossref_primary_10_1016_j_ijepes_2023_109117 crossref_primary_10_1088_1757_899X_327_2_022060 crossref_primary_10_1109_TIA_2024_3402198 crossref_primary_10_3390_electronics12143024 crossref_primary_10_1007_s10115_024_02291_4 crossref_primary_10_1109_JIOT_2020_2968631 crossref_primary_10_1016_j_ijhydene_2021_11_257 crossref_primary_10_3390_en15196920 crossref_primary_10_1109_ACCESS_2020_3003568 crossref_primary_10_1134_S1064230720050111 crossref_primary_10_1016_j_egyai_2022_100179 crossref_primary_10_1109_TIA_2024_3462891 crossref_primary_10_1016_j_apenergy_2022_119530 crossref_primary_10_1109_JPROC_2020_2988715 crossref_primary_10_1109_TPWRS_2020_2990179 crossref_primary_10_1146_annurev_environ_020220_061831 crossref_primary_10_1109_TNNLS_2020_3029573 crossref_primary_10_1109_TSG_2021_3050419 crossref_primary_10_1088_1742_6596_2176_1_012076 crossref_primary_10_1109_TPEL_2020_3024914 crossref_primary_10_1145_3485128 crossref_primary_10_1016_j_jclepro_2023_139947 crossref_primary_10_1109_TPWRS_2019_2948132 crossref_primary_10_1002_cta_3370 crossref_primary_10_1016_j_apenergy_2021_117634 crossref_primary_10_1109_JPROC_2022_3175070 crossref_primary_10_1088_1742_6596_2176_1_012082 crossref_primary_10_1016_j_apenergy_2024_123680 crossref_primary_10_1177_0020294020944952 crossref_primary_10_1016_j_conengprac_2020_104598 crossref_primary_10_3233_JHS_200641 crossref_primary_10_1049_stg2_12003 crossref_primary_10_1002_2050_7038_12531 crossref_primary_10_1016_j_knosys_2024_112637 crossref_primary_10_1016_j_rser_2025_115573 crossref_primary_10_1088_1742_6596_2176_1_012095 crossref_primary_10_3390_app14146214 crossref_primary_10_3389_fenrg_2023_879041 crossref_primary_10_1007_s12667_021_00448_6 crossref_primary_10_1016_j_aei_2020_101229 crossref_primary_10_3390_en13153928 crossref_primary_10_1016_j_apenergy_2019_03_027 crossref_primary_10_1016_j_apenergy_2024_123435 crossref_primary_10_1016_j_engappai_2023_106693 crossref_primary_10_1051_matecconf_201822604018 crossref_primary_10_3390_en13051226 crossref_primary_10_1016_j_amc_2022_127182 crossref_primary_10_1007_s40866_019_0074_0 crossref_primary_10_3390_f14122456 crossref_primary_10_1109_ACCESS_2023_3263547 crossref_primary_10_1109_ACCESS_2022_3172697 crossref_primary_10_3390_en13112830 crossref_primary_10_1109_LCSYS_2022_3181122 crossref_primary_10_1155_2021_9372803 crossref_primary_10_1109_TSG_2021_3052998 crossref_primary_10_1186_s43067_022_00048_z crossref_primary_10_3390_math11224667 crossref_primary_10_1109_TPAMI_2023_3292075 crossref_primary_10_1016_j_apenergy_2022_120212 crossref_primary_10_3390_en11102528 crossref_primary_10_1080_00207160_2024_2339243 crossref_primary_10_1088_1742_6596_2176_1_012028 crossref_primary_10_1007_s10489_022_04105_y crossref_primary_10_1109_ACCESS_2021_3125102 crossref_primary_10_1038_s41586_020_2939_8 crossref_primary_10_1016_j_segan_2022_100919 crossref_primary_10_1016_j_engappai_2022_105721 crossref_primary_10_1016_j_cec_2023_100040 crossref_primary_10_1016_j_prime_2024_100856 crossref_primary_10_3390_en12152891 crossref_primary_10_1016_j_apenergy_2022_120500 crossref_primary_10_1016_j_solener_2023_01_027 crossref_primary_10_33889_IJMEMS_2020_5_4_057 crossref_primary_10_1016_j_energy_2020_117708 crossref_primary_10_1007_s40095_019_0302_3 crossref_primary_10_1109_TPWRS_2024_3404472 crossref_primary_10_1016_j_egyai_2021_100092 crossref_primary_10_1016_j_apenergy_2024_124978 crossref_primary_10_1109_ACCESS_2023_3297274 crossref_primary_10_1109_TSG_2019_2903756 crossref_primary_10_1016_j_arcontrol_2019_09_008 crossref_primary_10_1109_TPWRS_2021_3095179 |
| Cites_doi | 10.1201/b19664-17 10.1109/TPWRS.2011.2166091 10.1109/TIA.2015.2466622 10.1016/j.ijepes.2010.12.008 10.1016/j.epsr.2011.11.024 10.1016/j.automatica.2012.05.043 10.1561/2200000049 10.1109/TSG.2012.2235864 10.1109/37.856179 10.1371/journal.pone.0157088 10.1016/S0378-7796(02)00088-3 10.1109/TSG.2015.2410171 10.1109/TSTE.2015.2467190 10.1109/TPWRS.2004.831259 10.1016/j.ijepes.2015.11.057 10.1561/2200000006 10.1049/iet-gtd.2009.0168 10.1109/TSMCB.2008.2007630 10.1016/j.epsr.2009.05.005 10.1038/nature14539 10.1109/NAPS.2006.359598 10.1016/j.isatra.2012.06.010 10.1109/TPWRD.2010.2046917 10.1109/TSG.2015.2393059 10.1109/PROC.1974.9541 10.1016/j.epsr.2016.06.041 10.5220/0006250803220327 10.1016/j.automatica.2016.05.008 10.1109/TSG.2014.2346740 10.1109/TSMCC.2010.2044174 10.1109/TCST.2005.847339 10.1137/120867263 10.1038/nature16961 10.1109/TPWRS.2014.2314359 10.1038/nature14236 10.1109/TIFS.2016.2607701 10.1109/TSG.2016.2517211 10.1109/TIE.2015.2420792 10.1162/154247603322493212 10.1016/j.ijepes.2006.03.002 10.1109/TSMCC.2012.2218596 10.1109/TNNLS.2016.2514358 10.1109/TPWRS.2010.2102372 10.1109/TPWRS.2003.821457 10.1109/TPWRS.2006.882467 10.1109/TPWRS.2011.2157180 10.1049/ip-gtd:19990426 10.1109/TPWRS.2004.841146 10.1109/TPWRS.2006.888977 10.1007/BF00992698 10.1109/TSG.2015.2495145 10.1109/TPWRS.2007.907589 10.1109/JPETS.2016.2558471 10.1109/JESTPE.2014.2331188 10.1016/j.neunet.2014.09.003 10.1007/s10479-012-1248-5 |
| ContentType | Journal Article |
| Copyright | 2017 |
| Copyright_xml | – notice: 2017 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ifacol.2017.08.1217 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2405-8963 |
| EndPage | 6927 |
| ExternalDocumentID | 10_1016_j_ifacol_2017_08_1217 S2405896317317238 |
| GroupedDBID | 0R~ 0SF 457 AAJQP AALRI AAXUO ABMAC ACGFS ADBBV ADVLN AEXQZ AFTJW AGHFR AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ ATDSJ EBS EJD FDB HX~ KQ8 O9- ROL AAYWO AAYXX CITATION |
| ID | FETCH-LOGICAL-c448t-5cc4096aceb17ebc5cf676855aa149946730ffc0f9bc7d670d15dd98aa44e3723 |
| ISSN | 2405-8963 |
| IngestDate | Thu Apr 24 23:07:58 EDT 2025 Tue Jul 01 02:06:02 EDT 2025 Sat Feb 22 15:41:37 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | false |
| Issue | 1 |
| Keywords | Electric power system control decision reinforcement learning |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c448t-5cc4096aceb17ebc5cf676855aa149946730ffc0f9bc7d670d15dd98aa44e3723 |
| OpenAccessLink | https://doi.org/10.1016/j.ifacol.2017.08.1217 |
| PageCount | 10 |
| ParticipantIDs | crossref_primary_10_1016_j_ifacol_2017_08_1217 crossref_citationtrail_10_1016_j_ifacol_2017_08_1217 elsevier_sciencedirect_doi_10_1016_j_ifacol_2017_08_1217 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2017-07-01 |
| PublicationDateYYYYMMDD | 2017-07-01 |
| PublicationDate_xml | – month: 07 year: 2017 text: 2017-07-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | IFAC-PapersOnLine |
| PublicationYear | 2017 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Francois-Lavet, V., Gemine, Q., Ernst, D., and Fonteneau, R. (2016a). Towards the minimization of the levelized energy costs of microgrids using both long-term and short-term storage devices. Smart Grid: Networking, Data Management, and Business Models, 295–319. Ghavamzadeh, Mannor, Pineau, Tamar (bib0023) 2015; 8 Li, Wu (bib0040) 1999; 6 Ruelens, F., Claessens, B.J., Vandael, S., Schutter, B.D., Babuska, R., and Belmans, R. (2016). Residential demand response of thermostatically controlled loads using batch reinforcement learning. IEEE Trans. Smart Grid, In Press, 1–11. Francois-Lavet, V., Taralla, D., Ernst, D., and Fonteneau, R. (2016b). Deep reinforcement learning solutions for energy microgrids management. In European Workshop on Reinforcement Learning. Vandael, Claessens, Ernst, Holvoet, Deconinck (bib0063) 2015; 6 Vlachogiannis, Hatziargyriou, Hatziargyriou (bib0065) 2004; 19 Busoniu, Babuska, Schutter, Ernst (bib0005) 2010 Yu, Wang, Zhou, Chen, Tang (bib0075) 2012; 27 Hasselt, Guez, Silver (bib0031) 2015 Wang, Glavic, Wehenkel (bib0066) 2014; 29 Theodorou, Buchli, Schaal (bib0060) 2010; 11 Xu, Zhang, Liu, Ferrese (bib0071) 2012; 42 Gao, Jiang, Jiang, Chai (bib0020) 2016; 72 Glavic (bib0024) 2005; 13 (bib0049) 2008 Yan, J., He, H., Zhong, X., and Tang, Y. (2016). Q-learning based vulnerability analysis of smart grid against sequential topology attacks. IEEE Trans. Inf Forens. Secur., In Press, 1–11. Zarabbian, Belkacemi, Babalola (bib0079) 2016; 141 Yu, Zhou, Chan, Chen, Yang (bib0077) 2011; 26 Otomega, Glavic, Van Cutsem (bib0048) 2007; 22 Nanduri, Das (bib0046) 2007; 22 Dubois, A., Wehenkel, A., Fonteneau, R., Olivier, F., and Ernst, D. (2017). An app-based algorithmic approach for harvesting local and renewable energy using electric vehicles. In Proceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017), 1-6. ICAART. Hadidi, Jeyasurya (bib0029) 2013; 4 Yu, Zhou, Chan, Yuan, Yang, Wu (bib0078) 2012; 48 Ekanayake, Liyanage, Wu, Jenkins (bib0012) 2012 Tang, He, Wen, Liu (bib0059) 2015; 6 Fonteneau, Ernst (bib0015) 2017 Aittahar, François-Lavet, Lodeweyckx, Ernst, Fonteneau (bib0003) 2015 Krause, Beck, Cherkaoui, Germond, Andersson, Ernst (bib0037) 2006; 28 Ye, Zhang, Sutanto (bib0073) 2011; 26 LeCun, Bengio, Hinton (bib0039) 2015; 521 Ademoye, Feliachi (bib0001) 2012; 86 Hasselt, H.V. (2010). Double Q-learning. In Advances in Neural Information Processing Systems, 2613-2621. Dalal, G., Gilboa, E., and Mannor, S. (2016). Hierarchical decision making in electricity grid management. In Proceedings of The 33rd International Conference on Machine Learning, 2197-2206. Mohagheghi, Venayagamoorthy, Harley (bib0045) 2006; 21 Yu, Zhang, Zhou, Chan (bib0076) 2016; 78 Venayagamorthy, Sharma, Gautam, Ahmadi (bib0064) 2016; 27 Schmidhuber (bib0055) 2015; 61 Sutton, Barto (bib0057) 1998 Watkins, Dayan (bib0068) 1992; 8 Gemine, Q., Ernst, D., and Cornelusse, B. (2014). Active network management for electrical distribution systems: problem formulation, benchmark, and approximate solution. arXiv preprint arXiv:1405.2806. Li, Wu, He, Chen (bib0041) 2012; 51 Mnih, Kavukcuoglu, Silver, Rusu, Veness, Bellemare, Graves, Riedmiller, Fidje-land, Ostrovski (bib0044) 2015; 518 Ahamed, Rao, Sastry (bib0002) 2002; 63 Schaul, T., Quan, J., Antonoglou, I., and Silver, D. (2015). Prioritized experience replay. arXiv preprint arXiv:1511.05952. Olivier, Aristidou, Ernst, Van Cutsem (bib0047) 2016; 7 Madani, Novosel, Horowitz, Adamiak, Amantegui, Karlsson, Imai, Apostolov (bib0043) 2010; 25 Garcia, Fernandez (bib0021) 2015; 16 Rochet, Tirole (bib0051) 2003; 1 Szabo (bib0058) 1997 Ruiz-Vega, Glavic, Ernst (bib0053) 2003 Harp, Brignone, Wollenberg, Samad (bib0030) 2000; 20 Fonteneau, Ernst, Boigelot, Louveaux (bib0016) 2013; 51 Kim, Zhang, van der Schaar, Lee (bib0036) 2016; 7 Wei, Zhang, Qiao, Qu (bib0070) 2015; 62 Daneshfar, Bevrani (bib0009) 2010; 4 Thomas, P.S. (2015). Safe Reinforcement Learning. PhD Dissertation, The University of Massachusetts Amherst, Amherst. Karimi, Eftekharnejad, Feliachi (bib0034) 2009; 79 Khorramabady, Bakhshai, Bakhshai (bib0035) 2015; 3 Glavic, Ernst, Wehenkel (bib0027) 2005; 13 Yousefian, Kamalsadan, Kamalsadan (bib0074) 2016; 52 Kydd, Anstrom, Heitmann, Komara, Crouse (bib0038) 2016; 3 Glavic, Alvarado (bib0025) 2016 Glavic, M., Ernst, D., and Wehenkel, L. (2006). Damping control by fusion of reinforcement learning and control Lyapunov functions. In Proc. of f the 38th North American Power Symposium (NAPS 2006), 1-7. NAPS. Ernst, Glavic, Capitanescu, Wehenkel (bib0013) 2009; 39 Glavic, Ernst, Wehenkel (bib0026) 2005; 20 Wang, Lin, Pedram (bib0067) 2016; 7 Castronovo, Ernst, Couetoux, Fonteneau (bib0006) 2016; 11 Dalal, Mannor (bib0008) 2015 Jasmin, Ahamed, Raj (bib0033) 2011; 33 Silver, Huang, Maddison, Guez, Sifre, Driessche, Schrittwieser, Antonoglou, Panneershelvam, Lanctot (bib0056) 2016; 529 Rahimiyan, Mashhadi, Mashhadi (bib0050) 2010; 40 Wehenkel, Glavic, Geurts, Ernst (bib0069) 2006 Ernst, Glavic, Wehenkel (bib0014) 2004; 19 Bengio (bib0004) 2009; 2 DyLiacco (bib0011) 1974; 62 Fonteneau, Murphy, Wehenkel, Ernst (bib0017) 2013; 208 Lincoln, Galloway, Stephen, Burt (bib0042) 2012; 27 US-DoE (2004). Final report on the august 14, 2003 blackout in the united states and canada: Causes and recommendations. Technical report, US Department of Energy, US-Canada Power System Outage Task Force. Rochet (10.1016/j.ifacol.2017.08.1217_bib0051) 2003; 1 10.1016/j.ifacol.2017.08.1217_bib0010 10.1016/j.ifacol.2017.08.1217_bib0054 Bengio (10.1016/j.ifacol.2017.08.1217_bib0004) 2009; 2 Szabo (10.1016/j.ifacol.2017.08.1217_bib0058) 1997 Tang (10.1016/j.ifacol.2017.08.1217_bib0059) 2015; 6 Vandael (10.1016/j.ifacol.2017.08.1217_bib0063) 2015; 6 Wei (10.1016/j.ifacol.2017.08.1217_bib0070) 2015; 62 Yu (10.1016/j.ifacol.2017.08.1217_bib0077) 2011; 26 Glavic (10.1016/j.ifacol.2017.08.1217_bib0026) 2005; 20 Yu (10.1016/j.ifacol.2017.08.1217_bib0076) 2016; 78 Aittahar (10.1016/j.ifacol.2017.08.1217_bib0003) 2015 10.1016/j.ifacol.2017.08.1217_bib0019 10.1016/j.ifacol.2017.08.1217_bib0018 Castronovo (10.1016/j.ifacol.2017.08.1217_bib0006) 2016; 11 Daneshfar (10.1016/j.ifacol.2017.08.1217_bib0009) 2010; 4 Glavic (10.1016/j.ifacol.2017.08.1217_bib0025) 2016 Ademoye (10.1016/j.ifacol.2017.08.1217_bib0001) 2012; 86 Khorramabady (10.1016/j.ifacol.2017.08.1217_bib0035) 2015; 3 (10.1016/j.ifacol.2017.08.1217_bib0049) 2008 Ruiz-Vega (10.1016/j.ifacol.2017.08.1217_bib0053) 2003 Fonteneau (10.1016/j.ifacol.2017.08.1217_bib0017) 2013; 208 Li (10.1016/j.ifacol.2017.08.1217_bib0041) 2012; 51 10.1016/j.ifacol.2017.08.1217_bib0052 Rahimiyan (10.1016/j.ifacol.2017.08.1217_bib0050) 2010; 40 Wang (10.1016/j.ifacol.2017.08.1217_bib0067) 2016; 7 Silver (10.1016/j.ifacol.2017.08.1217_bib0056) 2016; 529 Theodorou (10.1016/j.ifacol.2017.08.1217_bib0060) 2010; 11 DyLiacco (10.1016/j.ifacol.2017.08.1217_bib0011) 1974; 62 Kydd (10.1016/j.ifacol.2017.08.1217_bib0038) 2016; 3 Karimi (10.1016/j.ifacol.2017.08.1217_bib0034) 2009; 79 Kim (10.1016/j.ifacol.2017.08.1217_bib0036) 2016; 7 Mnih (10.1016/j.ifacol.2017.08.1217_bib0044) 2015; 518 Ernst (10.1016/j.ifacol.2017.08.1217_bib0013) 2009; 39 10.1016/j.ifacol.2017.08.1217_bib0007 Mohagheghi (10.1016/j.ifacol.2017.08.1217_bib0045) 2006; 21 Glavic (10.1016/j.ifacol.2017.08.1217_bib0024) 2005; 13 Li (10.1016/j.ifacol.2017.08.1217_bib0040) 1999; 6 Madani (10.1016/j.ifacol.2017.08.1217_bib0043) 2010; 25 Otomega (10.1016/j.ifacol.2017.08.1217_bib0048) 2007; 22 Yousefian (10.1016/j.ifacol.2017.08.1217_bib0074) 2016; 52 Sutton (10.1016/j.ifacol.2017.08.1217_bib0057) 1998 Olivier (10.1016/j.ifacol.2017.08.1217_bib0047) 2016; 7 Vlachogiannis (10.1016/j.ifacol.2017.08.1217_bib0065) 2004; 19 Yu (10.1016/j.ifacol.2017.08.1217_bib0078) 2012; 48 Fonteneau (10.1016/j.ifacol.2017.08.1217_bib0015) 2017 Glavic (10.1016/j.ifacol.2017.08.1217_bib0027) 2005; 13 Ye (10.1016/j.ifacol.2017.08.1217_bib0073) 2011; 26 Krause (10.1016/j.ifacol.2017.08.1217_bib0037) 2006; 28 Busoniu (10.1016/j.ifacol.2017.08.1217_bib0005) 2010 10.1016/j.ifacol.2017.08.1217_bib0032 Yu (10.1016/j.ifacol.2017.08.1217_bib0075) 2012; 27 Dalal (10.1016/j.ifacol.2017.08.1217_bib0008) 2015 Ernst (10.1016/j.ifacol.2017.08.1217_bib0014) 2004; 19 Fonteneau (10.1016/j.ifacol.2017.08.1217_bib0016) 2013; 51 Ghavamzadeh (10.1016/j.ifacol.2017.08.1217_bib0023) 2015; 8 Ekanayake (10.1016/j.ifacol.2017.08.1217_bib0012) 2012 Wang (10.1016/j.ifacol.2017.08.1217_bib0066) 2014; 29 Xu (10.1016/j.ifacol.2017.08.1217_bib0071) 2012; 42 Jasmin (10.1016/j.ifacol.2017.08.1217_bib0033) 2011; 33 LeCun (10.1016/j.ifacol.2017.08.1217_bib0039) 2015; 521 Watkins (10.1016/j.ifacol.2017.08.1217_bib0068) 1992; 8 Hadidi (10.1016/j.ifacol.2017.08.1217_bib0029) 2013; 4 10.1016/j.ifacol.2017.08.1217_bib0072 Nanduri (10.1016/j.ifacol.2017.08.1217_bib0046) 2007; 22 10.1016/j.ifacol.2017.08.1217_bib0022 Venayagamorthy (10.1016/j.ifacol.2017.08.1217_bib0064) 2016; 27 10.1016/j.ifacol.2017.08.1217_bib0028 Ahamed (10.1016/j.ifacol.2017.08.1217_bib0002) 2002; 63 Garcia (10.1016/j.ifacol.2017.08.1217_bib0021) 2015; 16 Schmidhuber (10.1016/j.ifacol.2017.08.1217_bib0055) 2015; 61 Gao (10.1016/j.ifacol.2017.08.1217_bib0020) 2016; 72 Lincoln (10.1016/j.ifacol.2017.08.1217_bib0042) 2012; 27 Zarabbian (10.1016/j.ifacol.2017.08.1217_bib0079) 2016; 141 Harp (10.1016/j.ifacol.2017.08.1217_bib0030) 2000; 20 Hasselt (10.1016/j.ifacol.2017.08.1217_bib0031) 2015 10.1016/j.ifacol.2017.08.1217_bib0062 Wehenkel (10.1016/j.ifacol.2017.08.1217_bib0069) 2006 10.1016/j.ifacol.2017.08.1217_bib0061 |
| References_xml | – volume: 13 start-page: 743 year: 2005 end-page: 751 ident: bib0024 article-title: Design of a resistive brake controller for power system stability enhancement using reinforcement learning publication-title: IEEE Trans. Contr. Syst. Tech. – volume: 11 start-page: 3137 year: 2010 end-page: 3181 ident: bib0060 article-title: A generalized path integral control approach to reinforcement learning publication-title: Journal of Machine Learning Research – volume: 86 start-page: 34 year: 2012 end-page: 40 ident: bib0001 article-title: Reinforcement learning tuned decentralized synergetic control of power systems publication-title: Elec. Power Syst. Research – volume: 51 start-page: 3355 year: 2013 end-page: 3385 ident: bib0016 article-title: Min max generalization for deterministic batch mode reinforcement learning: relaxation schemes publication-title: SIAM Journal on Control and Optimization – volume: 13 start-page: 81 year: 2005 end-page: 88 ident: bib0027 article-title: A reinforcement learning based discrete supplementary control for power system transient stability enhancement publication-title: Engineering Intelligent Systems for Electrical Engineering and Communications – start-page: 1 year: 2015 end-page: 15 ident: bib0003 article-title: Imitative learning for online planning in microgrids publication-title: International Workshop on Data Analytics for Renewable Energy Integration – volume: 26 start-page: 2434 year: 2011 end-page: 2441 ident: bib0073 article-title: A hybrid multiagent framework with Q-learning for power grid systems restoration publication-title: IEEE Trans. Power Syst. – volume: 8 start-page: 279 year: 1992 end-page: 292 ident: bib0068 article-title: Q-learning publication-title: Machine learning – volume: 79 start-page: 1511 year: 2009 end-page: 1520 ident: bib0034 article-title: Reinforcement learning based backstepping control of power system oscillations publication-title: Elec. Power Syst. Research – volume: 4 start-page: 489 year: 2013 end-page: 497 ident: bib0029 article-title: Reinforcement learning based real-time wide-area stabilizing control agents to enhance power system stability publication-title: IEEE Trans. Smart Grid – year: 2008 ident: bib0049 publication-title: Power System Dynamics, Stability and Control – reference: Glavic, M., Ernst, D., and Wehenkel, L. (2006). Damping control by fusion of reinforcement learning and control Lyapunov functions. In Proc. of f the 38th North American Power Symposium (NAPS 2006), 1-7. NAPS. – volume: 19 start-page: 427 year: 2004 end-page: 435 ident: bib0014 article-title: Power systems stability control: Reinforcement learning framework publication-title: IEEE Trans. Power Syst. – volume: 72 start-page: 37 year: 2016 end-page: 45 ident: bib0020 article-title: Output-feedback adaptive optimal control of interconnected systems based on robust adaptive dynamic programming publication-title: Automatica – volume: 51 start-page: 743 year: 2012 end-page: 751 ident: bib0041 article-title: Optimal control in microgrid using multi-agent reinforcement learning publication-title: ISA Transactions – volume: 141 start-page: 179 year: 2016 end-page: 190 ident: bib0079 article-title: Reinforcement learning approach for congestion management and cascading failure prevention with experimental application publication-title: Elec. Power Syst. Research – volume: 7 start-page: 77 year: 2016 end-page: 86 ident: bib0067 article-title: A near-optimal model-based control algorithm for households equipped with residential photovoltaic power generation and energy storage systems publication-title: IEEE Trans. Sust. Ener. – volume: 6 start-page: 166 year: 2015 end-page: 177 ident: bib0059 article-title: Power system stability control for a wind farm based on adaptive dynamic programming publication-title: IEEE Trans. Smart Grid – reference: Francois-Lavet, V., Taralla, D., Ernst, D., and Fonteneau, R. (2016b). Deep reinforcement learning solutions for energy microgrids management. In European Workshop on Reinforcement Learning. – volume: 8 start-page: 359 year: 2015 end-page: 483 ident: bib0023 article-title: Bayesian reinforcement learning: A survey publication-title: Foundations and Trends@ in Machine Learning – year: 2015 ident: bib0031 publication-title: Deep reinforcement learning with double Q-learning – volume: 27 start-page: 373 year: 2012 end-page: 380 ident: bib0075 article-title: Multi-agent correlated equilibrium Q(\) learning for coordinated smart generation control of interconnected power grids publication-title: IEEE Trans. Power Syst – volume: 28 start-page: 599 year: 2006 end-page: 607 ident: bib0037 article-title: A comparison of nash equilibria analysis and agent-based modelling for power markets publication-title: Int. Journal Elec. Power and Ener. Syst. – volume: 62 start-page: 884 year: 1974 end-page: 891 ident: bib0011 article-title: Real-time computer control of power systems publication-title: Proc. IEEE – volume: 62 start-page: 6360 year: 2015 end-page: 6370 ident: bib0070 article-title: Reinforcement-learning-based intelligent maximum power point tracking control for wind energy conversion systems publication-title: IEEE Trans. Ind. Ecetr. – volume: 25 start-page: 2143 year: 2010 end-page: 2155 ident: bib0043 article-title: IEEE PSRC report on global industry experiences with system integrity protection schemes (SIPS) publication-title: IEEE Trans. Power Syst. – volume: 3 start-page: 493 year: 2015 end-page: 504 ident: bib0035 article-title: Intelligent control of grid-connected microgrids: An adaptive critic-based approach publication-title: IEEE Trans. Emer. Selec. Topics Power Electr. – volume: 63 start-page: 9 year: 2002 end-page: 26 ident: bib0002 article-title: A reinforcement learning approach to automatic generation control publication-title: Elec. Power Syst. Research – volume: 42 start-page: 1742 year: 2012 end-page: 1751 ident: bib0071 article-title: Multiagent-based reinforcement learning for optimal reactive power dispatch publication-title: IEEE Trans. Syst., Man, Cyber.: Part C – reference: US-DoE (2004). Final report on the august 14, 2003 blackout in the united states and canada: Causes and recommendations. Technical report, US Department of Energy, US-Canada Power System Outage Task Force. – reference: Dalal, G., Gilboa, E., and Mannor, S. (2016). Hierarchical decision making in electricity grid management. In Proceedings of The 33rd International Conference on Machine Learning, 2197-2206. – reference: Gemine, Q., Ernst, D., and Cornelusse, B. (2014). Active network management for electrical distribution systems: problem formulation, benchmark, and approximate solution. arXiv preprint arXiv:1405.2806. – volume: 4 start-page: 13 year: 2010 end-page: 26 ident: bib0009 article-title: Loadfrequency control: a GA-based multi-agent reinforcement learning publication-title: IET Gen., Transm., Dist. – volume: 3 start-page: 81 year: 2016 end-page: 88 ident: bib0038 article-title: Vehicle-solar-grid integration: Concept and construction publication-title: IEEE Power Ener. Tech. Syst. Journal – volume: 22 start-page: 85 year: 2007 end-page: 95 ident: bib0046 article-title: A reinforcement learning model to assess market power under auction-based energy pricing publication-title: IEEE Trans. Power Syst. – start-page: 2053 year: 2003 end-page: 2059 ident: bib0053 article-title: Transient stability emergency control combining open-loop and closed-loop techniques publication-title: IEEE PES General meeting – year: 2010 ident: bib0005 publication-title: Reinforcement learning and dynamic programming using function approximators – start-page: 1 year: 2016 end-page: 10 ident: bib0025 article-title: Potential, opportunities and benefits of electric vehicles as frequency regulation resources publication-title: Open Repository and Bibliography – volume: 40 start-page: 547 year: 2010 end-page: 556 ident: bib0050 article-title: An adaptive Q-learning algorithm developed for agent-based computational modeling of electricity market publication-title: IEEE Trans. Syst., Man, Cyber.: Part C – reference: Schaul, T., Quan, J., Antonoglou, I., and Silver, D. (2015). Prioritized experience replay. arXiv preprint arXiv:1511.05952. – volume: 7 start-page: 926 year: 2016 end-page: 936 ident: bib0047 article-title: Active management of low-voltage networks for mitigating overvoltages due to photovoltaic units publication-title: IEEE Transactions on Smart Grid – volume: 29 start-page: 2835 year: 2014 end-page: 2845 ident: bib0066 article-title: Trajectory-based supplementary damping control for power system electromechanical oscillations publication-title: IEEE Trans. Power Syst. – volume: 27 start-page: 373 year: 2012 end-page: 380 ident: bib0042 article-title: Comparing policy gradient and value function based reinforcement learning methods in simulated electrical power trade publication-title: IEEE Trans. Power Syst. – volume: 2 start-page: 1 year: 2009 end-page: 127 ident: bib0004 article-title: Learning deep architectures for AI publication-title: Foundations and trends@ in Machine Learning – volume: 20 start-page: 525 year: 2005 end-page: 526 ident: bib0026 article-title: Combining a stability and a performance-oriented control in power systems publication-title: IEEE Trans. Power Syst. – reference: Thomas, P.S. (2015). Safe Reinforcement Learning. PhD Dissertation, The University of Massachusetts Amherst, Amherst. – start-page: 1 year: 2015 end-page: 6 ident: bib0008 article-title: Reinforcement learning for the unit commitment problem publication-title: PowerTech – volume: 208 start-page: 383 year: 2013 end-page: 416 ident: bib0017 article-title: Batch mode reinforcement learning based on the synthesis of artificial trajectories publication-title: Annals of Operations Research – volume: 6 start-page: 577 year: 1999 end-page: 585 ident: bib0040 article-title: Learning coordinated fuzzy logic control of dynamic quadrature boosters in multimachine power systems publication-title: IEE Proc. Gen., Transm., Dist. – volume: 16 start-page: 1437 year: 2015 end-page: 1480 ident: bib0021 article-title: A comprehensive survey on safe reinforcement learning publication-title: Journal of Machine Learning Research – volume: 7 start-page: 2187 year: 2016 end-page: 2198 ident: bib0036 article-title: Dynamic pricing and energy consumption scheduling with reinforcement learning publication-title: IEEE Trans. Smart Grid – volume: 22 start-page: 2283 year: 2007 end-page: 2284 ident: bib0048 article-title: Distributed undervoltage load shedding publication-title: IEEE Trans. Power Syst. – start-page: 23 year: 2017 end-page: 60 ident: bib0015 article-title: On the dynamics of the deployment of renewable energy production capacities publication-title: Mathematical Advances Towards Sustainable Environmental Systems – volume: 26 start-page: 1272 year: 2011 end-page: 1282 ident: bib0077 article-title: Stochastic optimal relaxed automatic generation control in non-markov environment based on multi-step Q(λ) learning publication-title: IEEE Trans. Power Syst. – volume: 48 start-page: 2130 year: 2012 end-page: 2136 ident: bib0078 article-title: R(λ) imitation learning for automatic generation control of interconnected power grids publication-title: Automatica – volume: 518 start-page: 529 year: 2015 end-page: 533 ident: bib0044 article-title: Human-level control through deep reinforcement learning publication-title: Nature – volume: 6 start-page: 1795 year: 2015 end-page: 1805 ident: bib0063 article-title: Reinforcement learning of heuristic EV fleet charging in a day-ahead electricity market publication-title: IEEE Trans. Smart Grid – reference: Ruelens, F., Claessens, B.J., Vandael, S., Schutter, B.D., Babuska, R., and Belmans, R. (2016). Residential demand response of thermostatically controlled loads using batch reinforcement learning. IEEE Trans. Smart Grid, In Press, 1–11. – year: 1998 ident: bib0057 publication-title: Reinforcement Learning: An Introduction – volume: 11 start-page: e0157088 year: 2016 ident: bib0006 article-title: Benchmarking for bayesian reinforcement learning publication-title: PloS one – volume: 1 start-page: 990 year: 2003 end-page: 1029 ident: bib0051 article-title: Platform competition in two-sided markets publication-title: Journal of the European Economic Association – volume: 529 start-page: 484 year: 2016 end-page: 489 ident: bib0056 article-title: Mastering the game of Go with deep neural networks and tree search publication-title: Nature – volume: 33 start-page: 836 year: 2011 end-page: 845 ident: bib0033 article-title: Reinforcement learning approaches to economic dispatch problem publication-title: Int. Journal Elec. Power and Ener. Syst. – reference: Francois-Lavet, V., Gemine, Q., Ernst, D., and Fonteneau, R. (2016a). Towards the minimization of the levelized energy costs of microgrids using both long-term and short-term storage devices. Smart Grid: Networking, Data Management, and Business Models, 295–319. – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib0039 article-title: Deep learning publication-title: Nature – reference: Dubois, A., Wehenkel, A., Fonteneau, R., Olivier, F., and Ernst, D. (2017). An app-based algorithmic approach for harvesting local and renewable energy using electric vehicles. In Proceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017), 1-6. ICAART. – volume: 20 start-page: 53 year: 2000 end-page: 69 ident: bib0030 article-title: SEPIA: A simulator for electric power industry agents publication-title: IEEE Contr. Syst. Mag. – volume: 78 start-page: 1 year: 2016 end-page: 12 ident: bib0076 article-title: Hierarchical correlated Q-learning for multi-layer optimal generation command dispatch publication-title: Int. Journal Elec. Power and Ener. Syst – year: 2012 ident: bib0012 publication-title: Smart Grid: Technology and Applications – volume: 19 start-page: 1317 year: 2004 end-page: 1325 ident: bib0065 article-title: Reinforcement learning for reactive power control publication-title: IEEE Trans. Power Syst. – reference: Hasselt, H.V. (2010). Double Q-learning. In Advances in Neural Information Processing Systems, 2613-2621. – volume: 52 start-page: 395 year: 2016 end-page: 406 ident: bib0074 article-title: Design and real-time implementation of optimal power system wide-area system-centric controller based on temporal difference learning publication-title: IEEE Trans. Ind. App. – start-page: 2 year: 1997 ident: bib0058 article-title: Formalizing and securing relationships on public networks publication-title: Peer-Reviewed Journal on Internet – reference: Yan, J., He, H., Zhong, X., and Tang, Y. (2016). Q-learning based vulnerability analysis of smart grid against sequential topology attacks. IEEE Trans. Inf Forens. Secur., In Press, 1–11. – volume: 39 start-page: 517 year: 2009 end-page: 529 ident: bib0013 article-title: Reinforcement learning versus model predictive control: A comparison on a power system problem publication-title: IEEE Trans. Syst., Man, Cyber.: Part B – volume: 21 start-page: 1744 year: 2006 end-page: 1754 ident: bib0045 article-title: Adaptive critic design based neuro-fuzzy controller for a static compensator in a multimachine power system publication-title: IEEE Trans. Power Syst. – volume: 61 start-page: 85 year: 2015 end-page: 117 ident: bib0055 article-title: Deep learning in neural networks: An overview publication-title: Neural Networks – volume: 27 start-page: 1643 year: 2016 end-page: 1656 ident: bib0064 article-title: Dynamic energy management system for a smart microgrid publication-title: IEEE Trans. Neural Networks and Learning Systems – start-page: 1 year: 2006 end-page: 6 ident: bib0069 article-title: Automatic learning of sequential decision strategies for dynamic security assessment and control publication-title: IEEE PES General meeting – ident: 10.1016/j.ifacol.2017.08.1217_bib0018 doi: 10.1201/b19664-17 – volume: 27 start-page: 373 year: 2012 ident: 10.1016/j.ifacol.2017.08.1217_bib0042 article-title: Comparing policy gradient and value function based reinforcement learning methods in simulated electrical power trade publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2011.2166091 – volume: 52 start-page: 395 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0074 article-title: Design and real-time implementation of optimal power system wide-area system-centric controller based on temporal difference learning publication-title: IEEE Trans. Ind. App. doi: 10.1109/TIA.2015.2466622 – volume: 33 start-page: 836 year: 2011 ident: 10.1016/j.ifacol.2017.08.1217_bib0033 article-title: Reinforcement learning approaches to economic dispatch problem publication-title: Int. Journal Elec. Power and Ener. Syst. doi: 10.1016/j.ijepes.2010.12.008 – volume: 13 start-page: 81 year: 2005 ident: 10.1016/j.ifacol.2017.08.1217_bib0027 article-title: A reinforcement learning based discrete supplementary control for power system transient stability enhancement publication-title: Engineering Intelligent Systems for Electrical Engineering and Communications – volume: 86 start-page: 34 year: 2012 ident: 10.1016/j.ifacol.2017.08.1217_bib0001 article-title: Reinforcement learning tuned decentralized synergetic control of power systems publication-title: Elec. Power Syst. Research doi: 10.1016/j.epsr.2011.11.024 – start-page: 2053 year: 2003 ident: 10.1016/j.ifacol.2017.08.1217_bib0053 article-title: Transient stability emergency control combining open-loop and closed-loop techniques – ident: 10.1016/j.ifacol.2017.08.1217_bib0007 – ident: 10.1016/j.ifacol.2017.08.1217_bib0062 – volume: 48 start-page: 2130 year: 2012 ident: 10.1016/j.ifacol.2017.08.1217_bib0078 article-title: R(λ) imitation learning for automatic generation control of interconnected power grids publication-title: Automatica doi: 10.1016/j.automatica.2012.05.043 – volume: 8 start-page: 359 issue: 5-6 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0023 article-title: Bayesian reinforcement learning: A survey publication-title: Foundations and Trends@ in Machine Learning doi: 10.1561/2200000049 – volume: 4 start-page: 489 year: 2013 ident: 10.1016/j.ifacol.2017.08.1217_bib0029 article-title: Reinforcement learning based real-time wide-area stabilizing control agents to enhance power system stability publication-title: IEEE Trans. Smart Grid doi: 10.1109/TSG.2012.2235864 – volume: 20 start-page: 53 year: 2000 ident: 10.1016/j.ifacol.2017.08.1217_bib0030 article-title: SEPIA: A simulator for electric power industry agents publication-title: IEEE Contr. Syst. Mag. doi: 10.1109/37.856179 – volume: 11 start-page: e0157088 issue: 6 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0006 article-title: Benchmarking for bayesian reinforcement learning publication-title: PloS one doi: 10.1371/journal.pone.0157088 – volume: 63 start-page: 9 year: 2002 ident: 10.1016/j.ifacol.2017.08.1217_bib0002 article-title: A reinforcement learning approach to automatic generation control publication-title: Elec. Power Syst. Research doi: 10.1016/S0378-7796(02)00088-3 – volume: 16 start-page: 1437 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0021 article-title: A comprehensive survey on safe reinforcement learning publication-title: Journal of Machine Learning Research – volume: 7 start-page: 926 issue: 2 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0047 article-title: Active management of low-voltage networks for mitigating overvoltages due to photovoltaic units publication-title: IEEE Transactions on Smart Grid doi: 10.1109/TSG.2015.2410171 – volume: 27 start-page: 373 year: 2012 ident: 10.1016/j.ifacol.2017.08.1217_bib0075 article-title: Multi-agent correlated equilibrium Q(\) learning for coordinated smart generation control of interconnected power grids publication-title: IEEE Trans. Power Syst – volume: 7 start-page: 77 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0067 article-title: A near-optimal model-based control algorithm for households equipped with residential photovoltaic power generation and energy storage systems publication-title: IEEE Trans. Sust. Ener. doi: 10.1109/TSTE.2015.2467190 – year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0031 – volume: 19 start-page: 1317 year: 2004 ident: 10.1016/j.ifacol.2017.08.1217_bib0065 article-title: Reinforcement learning for reactive power control publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2004.831259 – volume: 78 start-page: 1 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0076 article-title: Hierarchical correlated Q-learning for multi-layer optimal generation command dispatch publication-title: Int. Journal Elec. Power and Ener. Syst doi: 10.1016/j.ijepes.2015.11.057 – volume: 2 start-page: 1 year: 2009 ident: 10.1016/j.ifacol.2017.08.1217_bib0004 article-title: Learning deep architectures for AI publication-title: Foundations and trends@ in Machine Learning doi: 10.1561/2200000006 – year: 2010 ident: 10.1016/j.ifacol.2017.08.1217_bib0005 – volume: 4 start-page: 13 year: 2010 ident: 10.1016/j.ifacol.2017.08.1217_bib0009 article-title: Loadfrequency control: a GA-based multi-agent reinforcement learning publication-title: IET Gen., Transm., Dist. doi: 10.1049/iet-gtd.2009.0168 – volume: 39 start-page: 517 year: 2009 ident: 10.1016/j.ifacol.2017.08.1217_bib0013 article-title: Reinforcement learning versus model predictive control: A comparison on a power system problem publication-title: IEEE Trans. Syst., Man, Cyber.: Part B doi: 10.1109/TSMCB.2008.2007630 – volume: 79 start-page: 1511 year: 2009 ident: 10.1016/j.ifacol.2017.08.1217_bib0034 article-title: Reinforcement learning based backstepping control of power system oscillations publication-title: Elec. Power Syst. Research doi: 10.1016/j.epsr.2009.05.005 – volume: 521 start-page: 436 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0039 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: 10.1016/j.ifacol.2017.08.1217_bib0028 doi: 10.1109/NAPS.2006.359598 – ident: 10.1016/j.ifacol.2017.08.1217_bib0061 – volume: 51 start-page: 743 year: 2012 ident: 10.1016/j.ifacol.2017.08.1217_bib0041 article-title: Optimal control in microgrid using multi-agent reinforcement learning publication-title: ISA Transactions doi: 10.1016/j.isatra.2012.06.010 – volume: 25 start-page: 2143 year: 2010 ident: 10.1016/j.ifacol.2017.08.1217_bib0043 article-title: IEEE PSRC report on global industry experiences with system integrity protection schemes (SIPS) publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRD.2010.2046917 – volume: 6 start-page: 1795 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0063 article-title: Reinforcement learning of heuristic EV fleet charging in a day-ahead electricity market publication-title: IEEE Trans. Smart Grid doi: 10.1109/TSG.2015.2393059 – start-page: 1 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0008 article-title: Reinforcement learning for the unit commitment problem – volume: 62 start-page: 884 year: 1974 ident: 10.1016/j.ifacol.2017.08.1217_bib0011 article-title: Real-time computer control of power systems publication-title: Proc. IEEE doi: 10.1109/PROC.1974.9541 – year: 1998 ident: 10.1016/j.ifacol.2017.08.1217_bib0057 – volume: 141 start-page: 179 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0079 article-title: Reinforcement learning approach for congestion management and cascading failure prevention with experimental application publication-title: Elec. Power Syst. Research doi: 10.1016/j.epsr.2016.06.041 – ident: 10.1016/j.ifacol.2017.08.1217_bib0010 doi: 10.5220/0006250803220327 – start-page: 23 year: 2017 ident: 10.1016/j.ifacol.2017.08.1217_bib0015 article-title: On the dynamics of the deployment of renewable energy production capacities – volume: 72 start-page: 37 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0020 article-title: Output-feedback adaptive optimal control of interconnected systems based on robust adaptive dynamic programming publication-title: Automatica doi: 10.1016/j.automatica.2016.05.008 – volume: 6 start-page: 166 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0059 article-title: Power system stability control for a wind farm based on adaptive dynamic programming publication-title: IEEE Trans. Smart Grid doi: 10.1109/TSG.2014.2346740 – volume: 40 start-page: 547 year: 2010 ident: 10.1016/j.ifacol.2017.08.1217_bib0050 article-title: An adaptive Q-learning algorithm developed for agent-based computational modeling of electricity market publication-title: IEEE Trans. Syst., Man, Cyber.: Part C doi: 10.1109/TSMCC.2010.2044174 – volume: 13 start-page: 743 year: 2005 ident: 10.1016/j.ifacol.2017.08.1217_bib0024 article-title: Design of a resistive brake controller for power system stability enhancement using reinforcement learning publication-title: IEEE Trans. Contr. Syst. Tech. doi: 10.1109/TCST.2005.847339 – start-page: 1 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0025 article-title: Potential, opportunities and benefits of electric vehicles as frequency regulation resources – ident: 10.1016/j.ifacol.2017.08.1217_bib0054 – ident: 10.1016/j.ifacol.2017.08.1217_bib0019 – start-page: 1 year: 2006 ident: 10.1016/j.ifacol.2017.08.1217_bib0069 article-title: Automatic learning of sequential decision strategies for dynamic security assessment and control – volume: 51 start-page: 3355 issue: 5 year: 2013 ident: 10.1016/j.ifacol.2017.08.1217_bib0016 article-title: Min max generalization for deterministic batch mode reinforcement learning: relaxation schemes publication-title: SIAM Journal on Control and Optimization doi: 10.1137/120867263 – volume: 529 start-page: 484 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0056 article-title: Mastering the game of Go with deep neural networks and tree search publication-title: Nature doi: 10.1038/nature16961 – volume: 29 start-page: 2835 year: 2014 ident: 10.1016/j.ifacol.2017.08.1217_bib0066 article-title: Trajectory-based supplementary damping control for power system electromechanical oscillations publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2014.2314359 – ident: 10.1016/j.ifacol.2017.08.1217_bib0022 – volume: 518 start-page: 529 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0044 article-title: Human-level control through deep reinforcement learning publication-title: Nature doi: 10.1038/nature14236 – ident: 10.1016/j.ifacol.2017.08.1217_bib0072 doi: 10.1109/TIFS.2016.2607701 – year: 2012 ident: 10.1016/j.ifacol.2017.08.1217_bib0012 – ident: 10.1016/j.ifacol.2017.08.1217_bib0052 doi: 10.1109/TSG.2016.2517211 – volume: 62 start-page: 6360 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0070 article-title: Reinforcement-learning-based intelligent maximum power point tracking control for wind energy conversion systems publication-title: IEEE Trans. Ind. Ecetr. doi: 10.1109/TIE.2015.2420792 – volume: 11 start-page: 3137 year: 2010 ident: 10.1016/j.ifacol.2017.08.1217_bib0060 article-title: A generalized path integral control approach to reinforcement learning publication-title: Journal of Machine Learning Research – volume: 1 start-page: 990 year: 2003 ident: 10.1016/j.ifacol.2017.08.1217_bib0051 article-title: Platform competition in two-sided markets publication-title: Journal of the European Economic Association doi: 10.1162/154247603322493212 – volume: 28 start-page: 599 year: 2006 ident: 10.1016/j.ifacol.2017.08.1217_bib0037 article-title: A comparison of nash equilibria analysis and agent-based modelling for power markets publication-title: Int. Journal Elec. Power and Ener. Syst. doi: 10.1016/j.ijepes.2006.03.002 – volume: 42 start-page: 1742 year: 2012 ident: 10.1016/j.ifacol.2017.08.1217_bib0071 article-title: Multiagent-based reinforcement learning for optimal reactive power dispatch publication-title: IEEE Trans. Syst., Man, Cyber.: Part C doi: 10.1109/TSMCC.2012.2218596 – volume: 27 start-page: 1643 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0064 article-title: Dynamic energy management system for a smart microgrid publication-title: IEEE Trans. Neural Networks and Learning Systems doi: 10.1109/TNNLS.2016.2514358 – volume: 26 start-page: 1272 year: 2011 ident: 10.1016/j.ifacol.2017.08.1217_bib0077 article-title: Stochastic optimal relaxed automatic generation control in non-markov environment based on multi-step Q(λ) learning publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2010.2102372 – ident: 10.1016/j.ifacol.2017.08.1217_bib0032 – volume: 19 start-page: 427 year: 2004 ident: 10.1016/j.ifacol.2017.08.1217_bib0014 article-title: Power systems stability control: Reinforcement learning framework publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2003.821457 – volume: 21 start-page: 1744 year: 2006 ident: 10.1016/j.ifacol.2017.08.1217_bib0045 article-title: Adaptive critic design based neuro-fuzzy controller for a static compensator in a multimachine power system publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2006.882467 – volume: 26 start-page: 2434 year: 2011 ident: 10.1016/j.ifacol.2017.08.1217_bib0073 article-title: A hybrid multiagent framework with Q-learning for power grid systems restoration publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2011.2157180 – start-page: 2 year: 1997 ident: 10.1016/j.ifacol.2017.08.1217_bib0058 article-title: Formalizing and securing relationships on public networks publication-title: Peer-Reviewed Journal on Internet – volume: 6 start-page: 577 year: 1999 ident: 10.1016/j.ifacol.2017.08.1217_bib0040 article-title: Learning coordinated fuzzy logic control of dynamic quadrature boosters in multimachine power systems publication-title: IEE Proc. Gen., Transm., Dist. doi: 10.1049/ip-gtd:19990426 – volume: 20 start-page: 525 year: 2005 ident: 10.1016/j.ifacol.2017.08.1217_bib0026 article-title: Combining a stability and a performance-oriented control in power systems publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2004.841146 – volume: 22 start-page: 85 year: 2007 ident: 10.1016/j.ifacol.2017.08.1217_bib0046 article-title: A reinforcement learning model to assess market power under auction-based energy pricing publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2006.888977 – volume: 8 start-page: 279 year: 1992 ident: 10.1016/j.ifacol.2017.08.1217_bib0068 article-title: Q-learning publication-title: Machine learning doi: 10.1007/BF00992698 – volume: 7 start-page: 2187 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0036 article-title: Dynamic pricing and energy consumption scheduling with reinforcement learning publication-title: IEEE Trans. Smart Grid doi: 10.1109/TSG.2015.2495145 – volume: 22 start-page: 2283 year: 2007 ident: 10.1016/j.ifacol.2017.08.1217_bib0048 article-title: Distributed undervoltage load shedding publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2007.907589 – volume: 3 start-page: 81 year: 2016 ident: 10.1016/j.ifacol.2017.08.1217_bib0038 article-title: Vehicle-solar-grid integration: Concept and construction publication-title: IEEE Power Ener. Tech. Syst. Journal doi: 10.1109/JPETS.2016.2558471 – year: 2008 ident: 10.1016/j.ifacol.2017.08.1217_bib0049 – start-page: 1 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0003 article-title: Imitative learning for online planning in microgrids – volume: 3 start-page: 493 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0035 article-title: Intelligent control of grid-connected microgrids: An adaptive critic-based approach publication-title: IEEE Trans. Emer. Selec. Topics Power Electr. doi: 10.1109/JESTPE.2014.2331188 – volume: 61 start-page: 85 year: 2015 ident: 10.1016/j.ifacol.2017.08.1217_bib0055 article-title: Deep learning in neural networks: An overview publication-title: Neural Networks doi: 10.1016/j.neunet.2014.09.003 – volume: 208 start-page: 383 issue: 1 year: 2013 ident: 10.1016/j.ifacol.2017.08.1217_bib0017 article-title: Batch mode reinforcement learning based on the synthesis of artificial trajectories publication-title: Annals of Operations Research doi: 10.1007/s10479-012-1248-5 |
| SSID | ssj0002964798 |
| Score | 2.2223146 |
| Snippet | In this paper, we review past (including very recent) research considerations in using reinforcement learning (RL) to solve electric power system decision and... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 6918 |
| SubjectTerms | control decision Electric power system reinforcement learning |
| Title | Reinforcement Learning for Electric Power System Decision and Control: Past Considerations and Perspectives |
| URI | https://dx.doi.org/10.1016/j.ifacol.2017.08.1217 |
| Volume | 50 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NU9swENUEeuHClGk7BVpGB64Ojm3Fdm80BCj9gHZghptHktdDIHUz4PTA_-D_sivJjkMzFLh4EiWSk-zLane1-5axbRAK9zlJbirkXqSE9hIIQq8IyL5NqA6WQgPff_QPz6Kjc3He6dy1spamlerq24V1JS-RKo6hXKlK9hmSbRbFAXyM8sUrShivT5LxLzC8p9qE-GqqVJsYOTTtbSjvndqgOWJy1C62o445MhjYLHWKCZzIm6rp3emS40wZwawU86Ztxn7Z3x14J3KCLx-X31pH8wdjiarHRFnh73iaj8rZNkfJ8iCnRqhyciHNGf3nJsNjeF3a-pM9-XvkCtRcOKIXN6mrTmuhhSC8JHVaCxaMObVr-Wbn4GV1aD91GhncU0se8I-ut2GHy-6oIIJvytKLiY21F9hi0Hlu7Qd7XpOJWCe5XWZ2mYyWyfwko2WW2KsAvQ_S919_Jk3ojk6qY9Nluflis9qwnYUfaLHV07JkTl-zVeeC8F2LpzXWgfINu5rDEq-xxHGI11jiBkvcYonXWOIIFO6w9IkTkvg8kswb2kh6y872h6eDQ8814vA0eu-VJ7SO0NWVGjf2GJQWuuijmyqElOhgp7jXhn5RaL9IlY7zfuznPZHnaSJlFEEYB-E7tlz-KeE941CkUR4AOv1EbOfr1FcgBURKBb7uhXKdRfUPlWnHUk_NUsbZo5JaZ91m2sTStPxvQlJLIXO2prUhM4TX41M3nnuvTbYy-6d8YMvV9RQ-oilbqS0DrHusJp9c |
| linkProvider | Colorado Alliance of Research Libraries |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Reinforcement+Learning+for+Electric+Power+System+Decision+and+Control%3A+Past+Considerations+and+Perspectives&rft.jtitle=IFAC-PapersOnLine&rft.au=Glavic%2C+Mevludin&rft.au=Fonteneau%2C+Rapha%C3%ABl&rft.au=Ernst%2C+Damien&rft.date=2017-07-01&rft.issn=2405-8963&rft.eissn=2405-8963&rft.volume=50&rft.issue=1&rft.spage=6918&rft.epage=6927&rft_id=info:doi/10.1016%2Fj.ifacol.2017.08.1217&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ifacol_2017_08_1217 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2405-8963&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2405-8963&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2405-8963&client=summon |