电力系统保护与控制2012，Vol.40Issue(8)：116-120,5.
一种改进的多目标粒子群算法在购电风险评估中的应用研究
Application of an improved multi-objective particle swarm algorithm in power purchase risk assessment
摘要
Abstract
This paper proposes an improved multi-objective particle swarm optimization algorithm. The algorithm improves the local search ability by introducing the idea of local disturbance and variation operation, and maintains the external file with the idea of non-dominated sorting genetic algorithm. We have a detailed analysis of the risk of purchasing electricity of grid company, and establish a model of the risk to purchase electricity taking the minimum of Conditional Value-at-Risk (CVaR) and the maximum of the expected revenue as goals. This model makes up the flaw of Value at Risk (VaR) that it is not able to reflect the loss rear part information, guards against the small probability extreme risk, reduces the possibility of grid company to have the disastrous risk, and does not need the priori knowledge. We use the improved particle swarm algorithm to solve the model, each time a set of optimal solutions can be calculated, and the optimal solution evenly distributed in the optimal front end, which provides a reference of correct decisions for policy-makers. And the relative experiments prove that the algorithm and the model are feasible.关键词
CVaR/购电风险/粒子群算法Key words
CVaR/ power purchase risk/ particle swarm algorithm分类
信息技术与安全科学引用本文复制引用
张少敏,栗军,王保义..一种改进的多目标粒子群算法在购电风险评估中的应用研究[J].电力系统保护与控制,2012,40(8):116-120,5.基金项目
河北省科技项目资助(z2010290) （z2010290）
