基于Agent行为和范例学习的遗传算法在城网规划中的应用

A NEW GENETIC ALGORITHM BASED ON AGENT BEHAVIOR AND PARADIGM LEARNING WITH APPLICATION TO DISTRIBUTION SYSTEM OPTIMAL PLANNING

城市配电网优化规划 (简称城网规划 )目前还缺乏高效、实用的算法。传统遗传算法由于受确定编码形式的制约而缺乏对复杂问题的表述能力。文中通过吸收有关文献提出的“行为遗传”思想 ,进一步提出了一种基于 Agent行为和范例学习的新型遗传算法。该算法由 Agent基于知识的一系列决策行为 ,生成待优化问题的一个可行解的非编码方式 ,取代了传统遗传算法基于编码的可行解生成方式 ;用基于“范例学习”的进化寻优机制 ,取代了传统遗传算法基于模仿基因遗传和变异的进化寻优机制。最后 ,分别采用新型遗传算法和传统遗传算法对同一算例网络进行优化规划 ,对比的结果证明了新型遗传算法具有更好的复杂问题表述能力、计算效率、收敛稳定性以及可扩展性。

Distribution system optimal planning has vital significance, but there isn't efficient and practical algorithm at present. Traditional genetic algorithm has a poor expressive power for complicated problem because of the restriction of its certain encoding mode, which limits the application fields of genetic algorithm. This paper adapts the idea of 'Ethogenetics' in some reference, and presents a new type of genetic algorithm based on Agent behavior and paradigm learning. Unlike the encoding based creating mode of feasible solution in traditional genetic algorithm, a feasible solution is created by a series of intellective behaviors of Agent based on knowledge in the new genetic algorithm. To adapt the new creating mode of feasible solution, the traditional mechanism of evolution optimization based on Darwinism is abandoned and the mechanism of 'paradigm learning' is adopted to realize the evolution optimization. At last, an example distribution network is optimized by the new genetic algorithm and traditional genetic algorithm respectively. The comparative result proves the new genetic algorithm has higher expressive power, computing efficiency, convergent stability and extendable capability.