摘要
电力系统负荷预测的精度将直接影响电力系统的经济效益和用电的安全和稳定,短期电力负荷预测的重要组成部分。利用人工神经网络可以任意逼近非线性系统的特性,将其用于短期负荷预测。该文研究了在改进的BP网络中加入了动量项和构建输入网络时结合了同类型日思想的模糊映射,预测结果表明比标准BP算法具有更好的性能。同时,针对大量无法用精确数值来量化的信息,采用对输入数据进行分类和线性激活处理并映射到相对应的集合中,结果表明其精度比标准的人工神经网络更高。
The accuracy of the forecast of power system load, which is an important part of the tbrecast of short-term power systemiloan, will direcdy affect the economic of the power systems and its security and stability. The use of artificiaT neural network could get the similar feature like nonlinear system and use it on the short-term forecast, Researches add momentum into the improved BP network and combmate me same type of vague and mapping testilts when building input networks shows that it has better performance than standard BP algorithms. Meanwhile, after classification the input data categorize and dealing with the linear activate, put- ting these data to the corresponding sets, the result proved that its accuracy is higher than the standard of arti- ficial neuraI network.
出处
《杭州电子科技大学学报（自然科学版）》
2011年第4期173-176,共4页
Journal of Hangzhou Dianzi University：Natural Sciences
