基于边缘计算的虚拟电厂架构及光伏出力预测算法研究

Research on Virtual Power Plant Architecture and Photovoltaic Output Prediction Algorithm Based on Edge Computing

随着大规模智能终端的异构连接,海量数据的接入,传统虚拟电厂的运行管理需求仅仅依靠云计算技术已不能满足。边缘计算技术拥有的将计算量下移到网络边缘侧的特点,既可以改善传统虚拟电厂实时性不足缺陷,也能促进网络边缘处的协同性能。通过分析边缘计算在行业中的应用,将边缘计算技术首次用于虚拟电厂运行,以此设计了基于边缘计算的虚拟电厂架构且对其智能终端进行简单设计,有效提高虚拟电厂运行控制的实时性。同时鉴于传统灰色系统模型GM(1,1)存在准确性不高等问题,将灰色GM(1,2)-马尔可夫模型用于边缘侧光伏出力预测并进行了算例分析,为边缘计算技术在能源管理领域的应用提供了新思路。

With the heterogeneous connection of large-scale intelligent terminal and the access of mass data,the operation and management requirements of traditional virtual power plant can no longer be satisfied by relying on cloud computing technology alone.Edge computing technology has the characteristics of moving the computing amount down to the edge side of the network,which can not only improve the deficiency of real-time performance of traditional virtual power plants,but also promote the synergy performance at the edge of the network.This paper first analyzes the application of edge computing in the industry,and then applies edge computing technology to the virtual power plant operation for the first time,on the basis of which a virtual power plant architecture based on edge computing is designedand its intelligent terminal is also designed simply,thus effectively improving the realtime performance of virtual power plant operation control.At the same time,considering that the traditional gray system model GM(1,1)has problems such as low accuracy,etc.,the paper applies the gray GM(1,2)-Markov model to the marginal PV output prediction,and alsomakes analyses onthe numerical examples,providing a new idea for the application of edge computing technology in the field of energy management.