SSRScientific and Social Research2661-43322981-9946Bio-Byword Scientific Publishing Pty. Ltd.10.26689/ssr.v8i3.14462ArticleApplication and Performance Comparison of a CNN–LSTM Hybrid Neural Network for Power Load Forecastinghttps://artdesignp.com/journal/SSR/8/3/10.26689/ssr.v8i3.14462WangWenwen,ZhangHui2026832026-04-15Accurate and stable power load forecasting is essential for power system operation and planning. However, traditional single prediction models often exhibit limited performance when modeling complex load data characterized by strong nonlinearity and non-stationarity. To address this issue, this paper proposes a hybrid neural network model that combines a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network for short-term power load forecasting. First, considering the temporal dependency and nonlinear characteristics of power load time-series data, both LSTM and CNN–LSTM forecasting models are constructed. Then, the hybrid model is systematically optimized by adjusting the number of convolutional layers, the structure of LSTM hidden layers, and different activation function configurations. Finally, the forecasting performance of the proposed model is evaluated and compared with that of the single LSTM model using root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The experimental results indicate that the CNN–LSTM model achieves higher forecasting accuracy and better generalization performance, and its predicted load curves show greater consistency with actual load variations. The proposed approach provides an effective solution for power load forecasting and offers valuable support for power system dispatching and planning.

Han Y, Hou ZM, 2026, BO-CNN BiLSTM Attention Analysis and Peak Scenario Simulation of Carbon Emissions in Resource-based Cities in China Based on RF-RFECV Feature Selection. Environmental Science, 47(3): 1433–1448. https://doi.org/10.13227/j.hjkx.202501278

Tan Z, Zhang WM, Yin ZL, et al., 2025, Short Term Power Load Forecasting Model Based on Deep Learning and Optimization Algorithms. Microcomputer Applications, 41(12): 28–31 + 35.

Qiao YH, Lin X, Cao DY, et al., 2025, Ship Power Load Forecasting Method Based on Variational Mode Decomposition and Hybrid Neural Network. Ship and Sea Engineering, 54(6): 127–133.

Zhao RX, Gu H, and Meng QY, 2026, Short-Term Power Load Forecasting Based on CNN-LSTM and Dual Attention Mechanism. Information & Computer, 38(1): 29–32.

Qi XF, 2025, Research on Energy Saving and Loss Reduction Technology of Power Transmission and Distribution Lines Based on Deep Learning. Electrical Technology & Economy, 2025(12): 57–60.

Cao T, 2025, Research on Power System Load Forecasting Models Based on Deep Learning. Electrical Technology & Economy, 2025(12): 18–20 + 23.

Chen YT, Chen JJ, Lv HX, et al., 2025, The Current Application Status of Artificial Intelligence Technology in Power System Load Forecasting. Energy Conservation, 44 (11): 157–160.

Hou PP, Liu B, Xie J, et al., 2025, Research on Intelligent Algorithm-based Power Load Forecasting and Optimization Method. Electrical Era, 2025(11): 80–82.

Ding WF, Zhou ZZ, Xie ZH, et al., 2025, Low Voltage Substation Load Forecasting Based on Temporal Convolutional Neural Network and Cross Algorithm. Power System Protection and Control, 53(21): 156–165.

Qi SJ, Li RH, Duan MH, 2025, Research on Power Load Forecasting Based on Backpropagation Neural Network Algorithm. Shanxi Electric Power, 2025(5): 9–14.

Li HT, 2025, Research on Power Load Forecasting Considering New Energy and Joint Scenarios, thesis, Shijiazhuang Railway University.

Geng JT, 2025, Research on Intelligent Power Load Forecasting Based on Deep Learning. Automation Application, 66(20): 34–36. DOI: 10.19769/j.zdhy.2025.20.009.

Suo Zhigang. “Research on Data Analysis and Forecasting Technologies in Intelligent Photovoltaic Power Generation Systems.” Science & Technology Information, vol. 23, no. 20, 2025, pp. 208–210. https://doi.org/10.16661/j.cnki.1672-3791.2412-5042-0597

Zhang Q, Li ZH, Fan YP, et al., 2025, A Tilted Sample Prediction Algorithm Based on LSTM and CNN in a Novel Power System. Telecommunications Science, 41(10): 211–221

Rui LX, 2024, Research on Residential Load Forecasting Based on Spatiotemporal Graph Neural Networks, thesis, Nanjing University of Posts and Telecommunications.