Short-term load forecasting based on conditional generating adversarial networks

With the promotion of power market reform, accurate short-term load forecasting is of great significance for power systems to formulate reasonable production plans and ensure safe operation of the power grid. At present, the power grids have brought great challenges to load forecasting, and due to the need of production, a large number of nonlinear, asymmetric, and impact loads are connected to the power grid, so it is difficult for traditional power load forecasting methods to fully and accurately characterize the load characteristics. In order to learn the complex hidden deep relationship in nonlinear load data and improve the prediction accuracy, this paper proposed a method based on conditional generative adversarial networks (CGANs). This method used a convolutional neural network to construct a generative model and a discriminant model, took the load influencing factor as a condition. Through the game training of the confrontation network, the generation model can learn the mapping relationship between the noise and the real load data, to perform short-term load forecasting. The validation was conducted using a dataset from a certain power plant, and the experimental results showed that the trained CGAN has strong ability to learn load temporal features and has high prediction accuracy in different scenarios. The subsequent work will analyze the characteristics of different types of load data and consider the impact of real-time electricity prices and other factors on load prediction, so as to further improve the prediction accuracy and universality of the model.