Feng Zhongkai

Knowledge rules dimensionality reduction method for multi-reservoir joint operation optimization

In general, reservoirs were used for many purposes, such as power generation, flood control, navigation, zoology and so on. During the process of modelling, we should consider the interest demand of relevant departments represented by water resources, electric power sector and environmental protection administration. Thus, there are numerous complex constraints with different forms in the operation model of multi-reservoir system. These constraints have such comprehensive effects as delivery, intertexture and coupling, which narrows the feasible region characterized by the complex spatiotemporal features and makes it hard for optimization method to enhance the quality of solution. Hence, based on the set operation theory, we proposed the knowledge rules dimensionality reduction method that combines multiple different operation constraints of multi-reservoir system. According to actual problems, the proposed method first identify the feasible region of single reservoir at one stage, two stages and multiple stages. Then, the feasible search space for multi-reservoir system can be identified by the dynamic coordination of various reservoirs. In this way, the infeasible state and decision variables can be removed during the calculation process of the optimization method. The results demonstrate that the proposed method can reduce the difficulty of the system modeling and calculation, and ensure the feasibility and availability of the scheduling process.