QPSO-transformer-based power load forecasting model

With the gradual complexity of the power system, accurate and error-free grid load forecasting is now crucial for ensuring the stable operation of the power grid. Traditional forecasting methods struggle to address the challenges of nonlinearity and large-scale data in power load data. Therefore, this study proposes a QPSO-based Transformer model for power load forecasting. This method utilizes the quantum particle swarm optimization algorithm to optimize the hyperparameters of the transformer model, with the aim of further enhancing the stability and prediction accuracy of the model. Outperforming traditional methods such as LSTM and PSO-LSTM, the proposed method proved more effective across multiple performance metrics in the case study, showcasing its robust application prospects.