Residential Energy Consumption Prediction Based on Regional Power Supply Side and Demand Side Management
With the dynamic and seasonal changes in energy supply and demand,residential building energy consumption prediction plays an important role in energy management and control systems. The monthly electricity consumption of more than 16000 residential buildings is accurately classified,and data mining techniques are used to discover and summarize the electricity consumption patterns hidden in the data. The particle swarm optimization-K-means algorithm is applied to the cluster analysis to classify the level of electricity consumption through the cluster centers. An efficient classification model using the support vector machine as the basic optimization framework is proposed and verified to be feasible. The results show that the accuracy and F-measure of the new model reach 96.8％ and 97.4％ respectively,which are significantly better than the traditional methods. The method proposed in this paper will help the power sector to grasp the dynamic behavior of residential electricity consumption,provide decision-making reference for the formulation of reasonable supply and demand management strategies,and be of great value for improving the overall quality of the power grid.
万方数据
维普
