A Wasserstein Conditional Generative Adversarial Network Algorithm Model Applied to Data Analysis of Demand Response Systems

In this paper, an optimization algorithm model based on Wasserstein Conditional Generative Adversarial Networks (CGAN) is proposed. The Wasserstein distance is used instead of the loss function in the generative adversarial network to generate the adversarial network. The model not only has the ability of CGAN algorithm to classify and filter data according to the influencing factors, but also effectively avoids gradient disappearance and pattern collapse. Able to adapt to the data analysis needs of the Demand Response System (DRS) with large data volume and multiple influencing factors. In the data analysis application of demand response system, it has the advantages of strong data processing ability and accurate data analysis.