A CNN-LSTM-Based Load Forecasting Method for Energy Storage Systems

The power system is becoming increasingly complex, and load volatility and uncertainty are also increasing. Energy storage systems are a key link in balancing energy supply and demand and improving grid stability. Accurate load forecasting can provide data support for the energy storage system's output plan and enhance the operational efficiency of the energy storage system. Based on this, this paper proposes an energy storage system load prediction method based on a CNN-LSTM model. Using CNN to extract temporal features from the original load data, and then undergo sequence modeling by Long Short-Time Memory Network (LSTM), which improves the feature extraction capability and stability of a single LSTM to achieve accurate prediction of the loads of the energy storage system. Experiments demonstrate that this model exhibits superior predictive accuracy compared to the sole forecasting model.