Research on Data Generation Model Based on Improved SeqGAN

With the demand of integrated energy metering business and the rise of artificial intelligence technology, the data generation model of digital equipment has become the focus of attention. As the most widely used method in the field of image generation, the implicit method based on GAN has great development potential and strong domain expansion ability. The addition of reinforcement learning method makes the GAN correlation algorithm suitable for data generation of discrete data. This paper proposes an improved SeqGAN model, reconstructs the original SeqGAN model, improves the roll-out module of the original model, uses model parameters lagging behind the generator, and increases the stability of long sequence reinforcement learning. Compared with some existing popular algorithms, the performance of the proposed model algorithm is significantly better than that of the comparison algorithm when the training times are enough (more than 150 times), which lays a foundation for its application in data generation of digital equipment.