Short-term Load Forecasting of Power User Based on EWA Algorithm

作者：Li ZaiZhong, Xing Fu, Lei Wang, Yang Li, Haixia Li, You Shanshan, Huang Lei, Dai Biyan · 发表于：2021 6th International Conference on Power and Renewable Energy (ICPRE) · 年份：2021 · DOI：10.1109/icpre52634.2021.9635335 · 被引用次数：1 · 研究领域：Energy Load and Power Forecasting

Precisely forecasting the load of power users is of great significance for power sales companies to reasonably declare power demand curves in spot transactions and to promote retail market reform under the electricity spot market model. Based on the actual power load data design model of a power sales company in Shandong, the exponential weighted average algorithm is used to predict the short-term load of the next 1-7 days through the analysis of the load data of the power users in the previous 60 days. For the user's 24-hour load time-sharing forecast, the average absolute percentage error of the load forecast value and the actual value is used to analyze the accuracy of the algorithm forecast. The experimental results show that the prediction error is within a relatively small range, which verifies the accuracy and effectiveness of the model, and provides a powerful aid for the retail power company's spot transaction decision-making.