Hierarchical Short Term Load Forecasting Considering Weighting by Meteorological Region

• Published in: Revista IEEE América Latina Vol. 21; no. 11; pp. 1191 - 1198
• Main Authors: Castro Figueiro, Iuri, Da Rosa Abaide, Alzenira, Knak Neto, Nelson, Nogueira Fontoura da Silva, Leonardo, Callai dos Santos, Laura
• Format: Journal Article
• Language: English; Portuguese; Spanish
• Published: Los Alamitos IEEE 01.11.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial Neural Network; Energy management; Forecasting; Hierarchical Short Term Load Forecasting; Horizon; IEEE transactions; Load forecasting; Load modeling; Mathematical models; Meteorological variables weighting; Multi Region Forecasting; Multilayer perceptrons; Multilayers; Power systems; Predictive models; RNA; Weather forecasting; Weather stations; Weighting
• ISSN: 1548-0992; 1548-0992
• DOI: 10.1109/TLA.2023.10268274

Activities related to the planning and operation of power systems use as premise the load forecasting, which is responsible to provide a load estimative for a given horizon that assists mainly in the electroenergetic operation of a power system. The hierarchical short-term load forecasting becomes an approach used for this purpose, where the overall forecast is performed through system partition in smaller macro regions, and soon after, is aggregated to compose a global forecast. Then, this paper presents a hierarchical short-term forecasting approach for macro-regions, with the main contribution being the proposal of an indicator that represents the Average Consumption per Meteorological Region (CERM), to be used as weighting of each Meteorological Station (EM) as their importance for the total demand of the macro-region. This indicator is used to weight the temperature variable and then, is incorporated into a Multi-layer perceptron ANN model for the load forecasting on the horizon of 7 days ahead with hourly and daily discretization. The results showed higher average performance of the variable CERM in relation to the other combination performed, and the best results were used to compose the prediction of the Multi-Region (MTR). Finally, the proposed model presented a superior performance compared to an basis aggregate model for MTR, which shows the efficiency of the proposed methodology.