基于JADE平台的粒子群算法在经济调度中的应用  

The Particle Swarm Optimization Algorithm Basing on JADE Platform for the Economic Dispatch

作　　者：陈智慧[1] 

机构地区：[1]广东工业大学自动化学院自动化学院,广州510006

出　　处：《电气技术》2015年第1期32-35,共4页Electrical Engineering

摘　　要：针对标准粒子群算法容易出现"早熟"的问题,提出了基于JADE平台的改进粒子群算法。通过引入小概率变异和添加动态惯性权重,保持了种群的多样性,提高了算法的全局搜索能力。多智能体平台能大大增强了算法的并行性,能有效解决大规模复杂系统问题。通过对40机组经济调度模型进行测试,并与基于MATLAB平台的改进粒子群算法进行比较。测试结果表明所提出的改进算法具有更优的收敛精度,说明算法是可行的。Because the standard particle swarm algorithm is prone to ＂premature＂ problem, this paper puts forward the improved particle swarm algorithm based on JADE platform.By introducing a small probability variation and adding dynamic inertia weight method, the algorithm retains the diversity of population and improve the global search ability of the algorithm. Multi-agent platform can greatly enhance the algorithm＇s parallelism and can effectively solve the problem of large-scale complex system.Through testing on 40 units of economic operation model and to compare the improved particle swarm algorithm based on MATLAB platform.Test results show that the proposed algorithm has better convergence accuracy, algorithm is feasible.

关 键 词：JADE 经济调度 粒子群算法 多AGENT 

分 类 号：TM73[电气工程—电力系统及自动化]