论文部分内容阅读
季节型电力负荷同时具有增长性和波动性的二重趋势,使得负荷的变化呈现出复杂的非线性组合特征。对此,提出了一种综合最优灰色支持向量机预测模型,研究了同时考虑2种非线性趋势的复杂季节型负荷预测问题,说明了此优化模型分别优于2种单一负荷预测模型。在此基础上,对一般粒子群算法引入粒子速度自适应可调机制,并利用改进粒子群算法优化组合预测模型中的权值。对电力负荷预测应用实例的计算结果表明,该模型较大提高了季节型负荷预测的精度,具有较好的性能。
Seasonal power load at the same time with the dual trend of growth and volatility, making the load changes showed a complex combination of nonlinear characteristics. In view of this, a comprehensive optimal gray support vector machine prediction model is proposed. The complex seasonal load forecasting problem considering two kinds of nonlinear trends is also studied, which shows that the optimized model is superior to two kinds of single load forecasting models respectively. On this basis, the adaptive particle swarm optimization is introduced into the general PSO, and the improved particle swarm optimization algorithm is used to optimize the weight of the combined forecasting model. The calculation results of application examples of power load forecasting show that the model greatly improves the precision of seasonal load forecasting and has better performance.