基于粒子群优化的支持向量机停电预测研究

Research on power outage prediction of support vector machine based on particle swarm optimization

停电预测可以为电力公司的停电决策提供参考,改善资源分配并尽可能缩短恢复时间,也可以给群众一定的反应时间。因此,针对停电预测精度不高的问题,该文采用粒子群优化的支持向量机模型预测停电问题。在已有的天气特征基础上通过对最大温度和最小温度作差来增加温差特征;采用随机森林方法提取与停电问题关联度较大的特征;利用支持向量机模型训练停电数据,并使用基于线性递减权重的粒子群优化算法搜索相对更优的支持向量机参数;利用训练的预测模型预测停电数据。基于真实数据集试验,并与其它算法进行比较,结果表明该文的预测模型对于停电数据的预测具有更好的效果。

Power outage prediction can provide a reference for power companies’outage decision-making,improve resource allocation and possibly shorten recovery time.In addition,it can also give the masses a certain reaction time.Therefore,in view of the problem of low prediction accuracy of power outage,this paper uses the support vector machine optimized by particle swarm optimization algorithm to predict the power outage problem.Firstly,based on the existing weather characteristics,the difference between the maximum temperature and the minimum temperature is made to increase the temperature difference characteristics.Secondly,the random forest method is used to extract features which are more related to the power outage problem.Then,the support vector machine model is used to train the power outage data,and the particle swarm optimization algorithm based on linear decreasing weight is used to search for the optimal parameters of support vector machine.Finally,the trained prediction model is used to predict the outage data.Based on experiments on real data sets and comparison with other algorithms,the results show that the prediction model in this paper has a better effect on the prediction of power outage data.