Short-Term Load Forecasting Model of Gray-Weighted Markov Chain Based on Particle Swarm Optimization

摘要

Traditional daily load forecasting has less effective data and has certain volatility. Emerging artificial intelligence forecasting algorithms have low prediction accuracy for too little data. In response to these problems, a particle swarm optimization-based gray-weighted Marx Short-term load forecasting model of Kuffan chain. The gray model solves the problem of insufficient prediction data. The optimization of the gray model parameters by the particle swarm optimization algorithm further improves the prediction accuracy. The addition of a weighted Markov chain reduces the impact of data volatility on the prediction. Through a case simulation of short-term load in Luoyang, the results show that the model has higher accuracy in the short-term load forecast with volatility.