论文部分内容阅读
春节作为中国的传统节日,群众集中返乡造成部分配变台区发生重过载现象,严重影响供电可靠性。精准的负荷预测可以帮助公司高效地开展春节保供电工作,确保节日期间居民用电平稳有序。文章对青岛市某一配变春节期间负荷特性进行分析,通过应用平均影响值进行输入变量的筛选,运用遗传算法对Elman神经网络初始阈值和权重进行优化,结合配变的额定参数,预测春节期间是否重载或过载。算理分析表明,该方法预测精度高,在工程应用中具备可行性。
As a traditional festival in China, the Spring Festival reunification led to overloading of part of the distribution transformer substations and seriously affected the reliability of power supply. Accurate load forecasting can help companies effectively carry out the Spring Festival power supply and security work to ensure that residents during the holiday season, a stable and orderly. In this paper, the load characteristics of a distribution transformer during the Spring Festival in Qingdao are analyzed, and the input variables are selected by applying the average influence value. The initial thresholds and weights of the Elman neural network are optimized by using genetic algorithm. Based on the rated parameters of the distribution transformer, Whether overloaded or overloaded. Mathematical analysis shows that this method has high prediction accuracy and is feasible in engineering application.