Optimal demand response programs selection using CNN‐LSTM algorithm with big data analysis of load curves

One of the problems in implementing DRPs is lack sufficient understanding consumers’ behaviour when DRPs. This paper compares load patterns annually by improved Weighted Fuzzy Average (WFA) K-means clustering method. According to collected data, are discussed using a combined Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). To make CNN-LSTM practical algorithm for executing DRPs, Time Series Prediction (TSP) operations must be performed, input data memorized. Finally, according TSP done obtained implementation practice facilitated. Then, executed with Deep Learning (DL) model power will prioritized Technique Order Preference Similarity Ideal Solution (TOPSIS) method, decision indicators determined weighted Shannon entropy The numerical studies section shows that able simulate Mean Absolute Percentage Error (MAPE) almost below 1% residential cluster highest MAPE commercial 15%. Nevertheless, this could easily give same answer as optimal selection programs.