A Heat Load Forecasting Method Based on Genetic Algorithm and Neural Network

• Main Authors: WANG ZIFENG, FANG ZHOU, LUO JINWEN, JIE PENGFEI, ZHANG XINNAN, YAN FUCHUN
• Format: Patent
• Language: Chinese; English
• Published: 25.12.2018
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a Heat Load Forecasting Method Based on a Genetic Algorithm and Neural Network. Firstly, four eigenvectors and one tag to be forecasted are obtained by simulation for a periodof time. The simulation data are divided into training set data and prediction set data according to the time. The z-scroe algorithm is used for normalizing the eigenvectors of the two data sets and the labels to be predicted, and then the dimensions of each data set are unified; setting and initializing the parameters of genetic algorithm and BP neural network are performed; a BP neural network is established based on initialization parameters; a fitness value of an individual is calculated; the optimal BP neural network is obtained by optimizing the parameters of genetic algorithm, and the heat load of forecasting set data is forecasted. The method can overcome the shortcomings of the traditional artificial neural network which is easy to fall into the local minimum value, and effectively predict the heat load t