Short-term power grid load forecasting based on variable weight combination hybrid model

The power grid load exhibits non-linearity and volatility, posing challenges to power grid dispatching. To enhance the precision of power grid load forecasting, a variable weight combination forecasting model is suggested to address the issue of inadequate forecasting efficacy of individual algorithms. Considering the impact of various environmental factors on power grid load, a load influence feature dataset is formulated. Initially, support vector machines, genetic algorithm-optimized back propagation (BP) neural networks and radial basis neural networks are employed to forecast individual loads. Subsequently, a variance-covariance weight dynamic distribution method is utilized to merge the prediction results of the three individual algorithms, thereby establishing a short-term power grid load prediction model with variable weight combination. Taking a regional power grid as an example, the simulation results show that the prediction accuracy of the variable weight combination model is higher than that of the single algorithm. Taking the evaluation index MAPE as an example, compared with the three single algorithms, the prediction accuracy is improved by 42.31%, 48.56% and 65.33%. The practice proves that the proposed variable weight combination forecasting model greatly improves the accuracy of power network load forecasting.