中长期电力负荷预测的改进免疫粒子群算法

Improved Particle Swarm Optimization with Immunity Algorithms for Medium and Long Term Load Forecasting

针对免疫粒子群算法收敛速度慢,精确度相对较低的缺点,采用平衡理论和自适应调整两项策略加以改进,提出改进的免疫粒子群算法。一方面在新的粒子种群产生过程中引入扰动变量,使粒子群在遵守秩序和随机行为之间达到平衡;另一方面在粒子搜索复杂解空间过程中,通过计算个体适应值划分粒子的优劣等级,提出粒子速度自适应可调机制。实例证明,将改进的免疫粒子算法应用到中长期电力负荷组合预测是可行的,具有较高的精度及收敛速度。

An improved particle swarm optimization with immunity algorithms（IA PSO）based on equity theory and adaptive adjustment is proposed to solve the shortcomings of IA-PSO for slow convergence rate and rela-tively low accuracy. On the one hand,through leading pertubation variables into the generation process of particle population,a balance is reached between the order and the random behaviors. On the other hand,and adjust able mechanism of the adaptive particle velocity is proposed through the division of particle levels,which is ob tained by computing adaptive value. Examples show that it is feasible to apply the improved IA-PSO to the combination forecast of medium and long term load,with better accuracy and convergence speed.