ANALYSIS ON ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING APPROACHES BASED ON DEMAND-SIDE RESPONSE
Demand Response (DR) has gained popularity in recent years as a low-cost solution to increase the stability of energy networks by providing more leeway for consumers. However, Artificial Intelligence (AI) and Machine Learning (ML), a subset of AI, have recently emerged as key technologies for enabli...
Saved in:
Published in | NeuroQuantology Vol. 20; no. 10; p. 2615 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Bornova Izmir
NeuroQuantology
01.01.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Demand Response (DR) has gained popularity in recent years as a low-cost solution to increase the stability of energy networks by providing more leeway for consumers. However, Artificial Intelligence (AI) and Machine Learning (ML), a subset of AI, have recently emerged as key technologies for enabling demand-side response. This is largely attributable to the high complexity of tasks associated with DR, as well as their use of large-scale data and the frequent need for near real-time decisions. Algorithms trained by artificial intelligence (AI) can be utilised to select the most receptive audience and optimise rewards for DR scheme participants. Based on a thorough review of more than 160 articles, 40 companies and commercial initiatives, and 21 large-scale projects, this article presents an overview of AI techniques utilised for DR applications. Based on the AI/ML algorithm(s) used and the energy DR problem addressed, each study is assigned to one of several categories. In the next section, we will examine the commercial initiatives (from both new and established businesses) and large-scale innovation projects that have utilised AI technology for energy DR |
---|---|
ISSN: | 1303-5150 |
DOI: | 10.14704/nq.2022.20.10.NQ55224 |