基于改进MOEA/D的钢铁多介质能源计划优化

Multi-media Energy Planning Optimization of Steel Based on Improved MOEA/D

针对多介质钢铁能源计划模型存在变量较多、约束复杂和模型求解难度高等问题,提出基于自适应邻域的改进MOEA/D(decomposition-based multi-objective evolutionary algorithm)实现多介质能源计划优化。考虑分时电价特性和煤气柜的缓冲作用,构建以最小化运行成本和总能耗的目标函数,设计能源介质供需和工序饱和度等模型约束;基于能源产耗规则的解码方法确定目标值,定义归一化的切比雪夫聚合函数和种群进化程度的自适应邻域更新,设计改进MOEA/D的能源计划优化算法。仿真对比实验验证了改进MOEA/D有效实现能源计划优化,提高解的收敛性,降低运行成本1.3%和能耗1.2%。

To address the problems of multi-media iron and steel energy planning model with more variables,complex constraints and high difficulty in model solving,an improved MOEA/D(decomposition-based multi-objective evolutionary algorithm)based on adaptive neighborhood is proposed to realize multi-media energy planning optimization.Considering the characteristics of TOU price and the buffer effect of gas holder,the objective function to minimize operation cost and total energy consumption is constructed.And the model constraints are designed such as energy supply and demand balance.The decoding method based on energy production and consumption rules is designed to determine the target value.The normalized Chebyshev aggregation function and the adaptive neighborhood update of population evolution degree are used to improve the design of MOEA/D energy planning optimization algorithm.Through simulation and comparison experiments,it is verified that the improved MOEA/D can effectively realize energy planning optimization and improve the convergence of the solution.The optimized scheme reduces the operation cost by 1.3%and energy consumption by 1.2%.