基于GIS-MCDM-GRU的舟山市波浪能电站选址决策研究

Research on Site Selection Methodology of Wave Power Plant for Zhoushan Based on GIS-MCDM-GRU

选址决策是开发利用波浪能资源的重要前提。为实现波浪能电站选址决策,本文基于地理信息系统(Geographic information system,GIS)、多准则决策(Multi-criteria decision making,MCDM)方法和门控循环单元(Gated recurrent unit,GRU)神经网络建立波浪能选址决策方法框架。在决策过程中,为降低主观偏差,提出基于云-层次分析法(Analytic hierarchy process,AHP)和熵值法的组合赋权方法进行权重求解;为更加准确地描述实际情况,应用基于区间数的简单加权法进行方案排序;为提高电站后期实施运行的可预测性和可控性,采用GRU神经网络对最优场址波功率密度进行短期预测。最后,以舟山市波浪能电站选址为例验证了该方法的鲁棒性和可靠性。本文为中国波浪能电站建设提供了重要的理论依据。

Site selection is a necessary prerequisite for the development and utilization of wave energy resources.In order to realize the site selection decision of wave power plant,a decision framework is proposed based on geographic information system(GIS),multi criteria decision-making(MCDM)method and gated recurrent unit(Gru)neural network.In the decision-making process,to reduce the subjective deviation,a combined weighting method based on cloud-analytic hierarchy process(AHP)and entropy method is proposed as a criteria weighting algorithm;to describe the actual situation more accurately,simple additive weighting method based on interval number is established as an alternative ranking algorithm;to improve the predictability and controllability of the later implementation and operation for wave power plant,Gru neural network is used for short-term forecasting of wave power density at the optimal site.Finally,the robustness and reliability of this method is verified by a case study of wave power plant site selection in Zhoushan.This paper provides an important theoretical foundation for the construction of wave power plant in China.