In recent years, with the development of societies and economies, the demand for social electricity has further increased. The efficiency and accuracy of electric-load forecasting is an important guarantee for the safety and reliability of power system operation. With the sparrow search algorithm (SSA), long short-term memory (LSTM), and random forest (RF), this research proposes an SSA-LSTM-RF daily peak-valley forecasting model. First, this research uses the Pearson correlation coefficient and the random forest model to select features. Second, the forecasting model takes the target value, climate characteristics, time series characteristics, and historical trend characteristics as input to the LSTM network to obtain the daily-load peak and valley values. Third, the super parameters of the LSTM network are optimized by the SSA algorithm and the global optimal solution is obtained. Finally, the forecasted peak and valley values are input into the random forest as features to obtain the output of the peak-valley time. The forest value of the SSA-LSTM-RF model is good, and the fitting ability is also good. Through experimental comparison, it can be seen that the electric-load forecasting algorithm based on the SSA-LSTM-RF model has higher forecasting accuracy and provides ideal performance for electric-load forecasting with different time steps.

This paper proposes a new method for short-term electric load forecasting using a Ridgelet Neural Network (RNN) combined with a wavelet transform and optimized by a Self-Adapted (SA) Kho-Kho algorithm (SAKhoKho). The aim of this method is to improve the accuracy and reliability of electric load forecasting, which is essential for the planning and operation of competitive electrical networks. The proposed method uses the Wavelet Transform (WT) to decompose the load data into different frequency components and applies the RNN to each component separately. The RNN is, then, optimized by the SAKhoKho algorithm, which is an improved version of the KhoKho algorithm that can adapt the search parameters dynamically. The proposed method is trained and tested on the Zone Preliminary Billing Data from the PJM regulatory area, which is updated every two weeks based on the Intercontinental Exchange (ICE) figures. The proposed method is compared with six other cutting-edge methods from the literature, including SVM/SA, hybrid, ARIMA, MLP/PSO, CNN, and RNN/KhoKho/WT. The results show that the proposed method achieves the lowest Mean Absolute Error (MAE) of 7.7704 and Root Mean Square Error (RMSE) of 17.4132 among all the methods, indicating its superior performance. The proposed method can capture the temporal dependencies in the load data and optimize the RNN's weights to minimize the error function. The proposed method is a promising technique for electric load forecasting, as it can provide accurate and reliable predictions for the next hour based on the previous 24 h of data.

The ability of electric load forecasting become the key to measuring electric planning and dispatching, and improving the accuracy of electric load forecasting has become one hot spot topic of scholars in recent years. The traditional electric load forecasting algorithm mainly include statistical learning algorithm. The electric load forecasting algorithm based on traditional forecasting algorithm, machine learning algorithm and neural network algorithm greatly improve the convergence approximation effect and accuracy. In recent years, the electric load forecasting algorithms based on the deep learning algorithm has greatly reduced the error and improved the measurement accuracy and robustness, such as RNN, GRU, LSTM, DBN, TCN, and so on, as well as the combination algorithm based on deep learning. This paper introduces the classical algorithm of deep learning in electric load forecasting. The main purpose is to explore the error and fitting degree of algorithms established by different algorithms, and provide reference for the selection of forecasting algorithms for various types of electric load forecasting.