为了准确、快速、高效地预测电网短期负荷，提出了改进的粒子群–径向基神经网络算法。用改进的粒子群算法训练径向基神经网络，实现了径向基函数神经网络的参数优化。建立了短期电力负荷预测模型，综合考虑气象、天气、日期类型等影响负荷的因素进行短期负荷预测。算例结果表明，该算法优于径向基神经网络法和粒子群–径向基网络算法，克服了径向基网络和粒子群优化方法的缺点，改善了径向基神经网络的泛化能力，输出稳定，预测精度高，收敛速度快，平均百分比误差可控制在1.2%以内。

To forecast short-term power load fast, accurately and efficiently, the features and defects of particle swarm optimization (PSO) algorithm are analyzed and an modified PSO- radial basis function neural network (RBFNN) algorithm is proposed, in which the RBFNN is trained by improved PSO to implement the optimization of RBFNN parameters and a short-term load forecasting model is built. In load forecasting such factors impacting loads as meteorology, weather and date types are comprehensively considered. Calculation example results show that the forecasting results by the proposed mehtod are better than those by RBFNN method and PSO- radial basis function network (RBFN) method, the defects of the latters are remedied and the generalization ability of RBFN is improved. The proposed method possesses following advantages: stable output, high precision of forecasting, fast convergence and its average percentage error is within the range of 1.2%, thus the proposed forecasting method is available to short-term load forecasting.

基金项目：国家火炬计划创新基金(07C26213711606)；陕西省自然科学基础研究计划基金(SJ08E220)；山东省软科学基金(2007RKB188)。

[1] 雷绍兰，孙才新，周湶，等．基于径向基神经网络和自适应神经模糊系统的电力短期负荷预测方法[J]．中国电机工程学报，2005，25(22)：78-82． Lei Shaolan，Sun Caixin，Zhou Quan，et al．Short-term load forecasting method based on RBF neural network and ANFIS system [J]．Proceedings of the CSEE，2005，25(22)：78-82(in Chinese)． [2] 黎灿兵，刘梅，单业才，等．基于解耦机制的小地区短期负荷预测方法[J]．电网技术，2008，32(5)：87-92． Li Canbing，Liu Mei，Shan Yecai，et al．Short-term load forecasting method of small region based on decoupling mechanism[J]．Power System Technology，2008，32(5)：87-92(in Chinese)． [3] 栗然，郭朝云，韦仲康．京津唐电网电力日峰荷与气象指数的关联性分析[J]．电网技术，2008，32(6)：87-93． Li Ran，Guo Chaoyun，Wei Zhongkang．Relevance analysis of meteorological index and peak load in Tianjin-Beijing-Tangshan power grid[J]．Power System Technology，2008，32(6)：87-93(in Chinese)． [4] 王德意，杨卓，杨国清．基于负荷混沌特性和最小二乘支持向量机的短期负荷预测[J]．电网技术，2008，32(7)：66-72． Wang Deyi，Yang Zhuo，Yang Guoqing．Short-term load forecasting based on chaotic characteristic of loads and least squares support vector machines[J]．Power System Technology，2008，32(7)：66-72(in Chinese)． [5] 李媛媛，牛东晓，乞建勋，等．基于因散经验模式分解的电力负荷混合预测方法[J]．电网技术，2008，32(8)：58-62． Li Yuanyuan，Niu Dongxiao，Qi Jianxun，et al．A novel hybrid power load forecasting method based on ensemble empirical mode decomposition[J]．Power System Technology，2008，32(8)：58-62(in Chinese)． [6] 周春明，江辉，何禹清，等．可中断负荷参与阻塞管理的多目标模糊优化[J]．电网技术，2008，32(9)：27-32． Zhou Chunming，Jiang Hui，He Yuqing，et al．A multi-objective fuzzy optimization of congestion management with participation of interruptible loads[J]．Power System Technology，2008，32(9)：27-32(in Chinese)． [7] 张思远，何光宇，梅生伟，等．基于相似时间序列检索的超短期负荷预测[J]．电网技术，2008，32(12)：56-59． Zhang Siyuan，He Guangyu，Mei Shengwei，et al．Ultra-short term load forecasting based on similarity search in time-series[J]．Power System Technology，2008，32(12)：56-59(in Chinese)． [8] 罗玮，严正．基于广义学习矢量量化和支持向量机的混合短期负荷预测方法[J]．电网技术，2008，32(13)：62-68． Luo Wei，Yan Zheng．A hybrid approach of short-term load forecasting based on generalized learning vector quantity and support machine vector[J]．Power System Technology，2008，32(13)：62-68(in Chinese)． [9] 毛李帆，江岳春，龙瑞华，等．基于偏最小二乘回归分析的中长期电力负荷预测[J]．电网技术，2008，32(19)：71-77． Mao Lifan，Jiang Yuechun，Long Ruihua，et al．Medium and long term load forecasting based on partial least squares regression analysis [J]．Power System Technology，2008，32(19)：71-77(in Chinese)． [10] 郝文波，于继来．基于负荷受电路径电气剖分信息的配电网重构算法[J]．中国电机工程学报，2008，28(19)：42-48． HaoWenbo，Yu Jilai．Distribution network reconfiguration algorithm basing on electrical dissection information of load path [J]．Proceedings of the CSEE，2008，28(19)：42-48(in Chinese)． [11] 顾丹珍，艾芊，陈陈，等．自适应神经网络在负荷动态建模中的应用[J]．中国电机工程学报，2007，27(16)：31-36． Gu Danzhen，Ai Qian，Chen Chen，et al．Application of adaptive neural network in dynamic load modeling[J]．Proceedings of the CSEE，2007，27(16)：31-36(in Chinese)． [12] 陈昊．基于不对称自回归条件异方差模型的短期负荷预测[J]．电网技术，2008，32(15)：84-89． Chen Hao．Short-term load forecasting based on asymmetric autoregressive conditional heteroscedasticity models[J]．Power System Technology，2008，32(15)：84-89(in Chinese)． [13] 王波，王灿林，梁国强．基于粒子群寻优的D-S算法[J]．传感器与微系统，2007，26(1)：84-86． Wang Bo，Wang Chanlin，Liang Guoqiang．D-S algorithm based on particle swarm optimizer[J]．Transducer and Microsystem Technologies，2007，26(1)：84-86(in Chinese)． [14] 方仍存，周建中，张勇传，等．基于粒子群优化的非线性灰色Bernoulli模型在中长期负荷预测中的应用[J]．电网技术，2008，32(12)：60-64． Fang Rengcun，Zhou Jianzhong，Zhang Yongchuan，et al．Application of particle swarm optimization based nonlinear grey Bernoulli model in medium-and long-term load forecasting[J]．Power System Technology，2008，32(12)：60-64(in Chinese)． [15] 石红瑞，刘勇，刘宝坤，等．基于混合递阶遗传算法的径向基神经网络学习算法及其应用[J]．控制理论与应用，2002，19(4)：627-630． Shi Hongrui，LiuYong，Liu Baokun，et al．RBFNN algorithm based on hybrid hierarchy genetic algorithm and its application[J]．Control Theory and Application，2002，19(4)：627-630(in Chinese)．