基于PSO-BP神经网络的热电厂负荷预测策略研究OA

At present,the efficient use of energy and green development have attracted widespread attention from scholars.Based on a large amount of historical data generated by the energy management system of a thermal power plant,this paper uses big data analysis method to calculate the correlation coefficient between the data to judge the correlation status between the data.A PSO-BP neural network model is established to predict the heat load of a thermal power plant in the next 24 hours,in order to better provide production,operation,management and decision-making services for the thermal power plant.The PSO-BP neural network model is produced by fusing particle swarm algorithm and BP algorithm.It not only improves the prediction accuracy of BP neural network,but also effectively solves the problem of slow learning speed of BP neural network algorithm,easy to fall into local minima,poor stability,etc.