Short-term electric load forecasting using particle swarm optimization-based convolutional neural network

Short-term electric load forecasting is essential for the operation of power systems and the power market, including economic dispatch, unit commitment, peak load shaving, load management and bidding strategy development. This paper presents a novel method that uses a hybrid convolutional neural network (CNN) that is cascaded with a fully-connected network, to conduct 24h-ahead electric load forecasting in power systems. Spearman's rank-order correlation, which serves as input size information for the CNN, was used to measure the cross-correlation between two sets of observations (chronological loads) of time shifts or lags. Both max and average pooling operations were utilized to extract data features in concatenation while spatial and conventional dropouts were employed to avoid overfitting in the hybrid CNN. The proposed method used two loops to yield the optimal CNN. The outer loop optimizes the structure and hyperparameters (such as kernel size) of the hybrid CNN by a proposed method of enhanced elite-based particle swarm optimization (EEPSO) while the inner loop optimizes the parameters (such as values of a kernel) and weights in neural networks using the Adam optimizer. The EEPSO is based on the mean search and chaotic descending inertia weight. The proposed method was used to study the 2018 and 2019 hourly load data in Taiwan Power Company. Simulation results show that the proposed method outperforms the well-known ARIMA, Radial Basis Function Network, Support Vector Regression, Long Short-term Memory and their hybrid variants.

Automated summary

This paper proposes a novel method that combines a hybrid convolutional neural network (CNN) with a fully-connected network for 24h-ahead electric load forecasting in power systems. The method utilizes Spearman's rank-order correlation for input size information and employs max and average pooling operations, as well as spatial and conventional dropouts, to extract data features and avoid overfitting. The proposed method optimizes the CNN structure and hyperparameters using enhanced elite-based particle swarm optimization (EEPSO) and optimizes the neural network parameters and weights using the Adam optimizer. Simulation results show that the proposed method outperforms various existing forecasting methods.