Load frequency control is among the most important control tasks in power systems operation. Many researchers have focused on tuning the load frequency controllers using single-objective evolutionary algorithms. To av...
详细信息
Load frequency control is among the most important control tasks in power systems operation. Many researchers have focused on tuning the load frequency controllers using single-objective evolutionary algorithms. To avoid the drawbacks of single-objective optimisation algorithms, in this paper, tuning the load frequency controllers is modelled as a many-objective (MO) minimization problem. This MO optimisation problem is solved using an MO optimisation algorithm with clustering-based selection. Considering the maximum value of each objective among the non-dominated solutions found by the MO optimisation algorithm, the worst solution is determined. To select one of the obtained non-dominated solutions as the controllers' parameters, a strategy based on the maximum distance from the worst solution is proposed. In order to measure the effectiveness of the proposed MO technique against several recently proposed single-objective optimisation algorithms, for tuning load frequency controllers, comparative simulation studies are carried out on two different test systems. Simulation results show that, in terms of different performance indices, the controllers designed by the proposed MO method are far superior to the controllers designed with the single-objective optimisation algorithms. Also, the presented results confirm the robustness of the controllers designed by the proposed method in case of power system parameters variations.
Consider optimization problems, where a target objective should be optimized. Some auxiliary objectives can be used to obtain the optimum of the target objective in less number of objective evaluations. We call such a...
详细信息
ISBN:
(纸本)9781479974153
Consider optimization problems, where a target objective should be optimized. Some auxiliary objectives can be used to obtain the optimum of the target objective in less number of objective evaluations. We call such auxiliary objective a supporting one. Usually there is no prior knowledge about properties of auxiliary objectives, some objectives can be obstructive as well. What is more, an auxiliary objective can be both supporting and obstructive at different stages of the target objective optimization. Thus, an adaptive online method of objective selection is needed. Earlier, we proposed a method for doing that, which is based on reinforcement learning. In this paper, a new algorithm for adaptive online selection of optimization objectives is proposed. The algorithm meets the interface of a reinforcement learning agent, so it can be fit into the previously proposed framework. The new algorithm is applied for solving some benchmark problems with single-objective evolutionary algorithms. Specifically, LEADINGONES with ONEMAX auxiliary objective is considered, as well as the MH-IFF problem. Experimental results are presented. The proposed algorithm outperforms Q-learning and random objective selection on the considered problems.
暂无评论