Big Data-driven Sensor Placement Optimization Method for Distribution Network: IEEE ITAIC(ISSN:2693-2865)

Under the background of big data in power system, it is urgent for large power grid to effectively configure sensors at key nodes to support the state perception of distribution network. A method to determine the sensor placement of distribution network from the global perspective by mining the variation characteristics of operating data is proposed. Firstly, a high-dimensional data matrix representing the real-time operation state of the distribution network is constructed by using the operation data of each node of the distribution network. Then, from the perspective of data-driven, the state of power grid is mapped to the change of operating data, and a random matrix index system representing the change of real-time data of power grid is proposed, and its reliability supporting the state perception of power grid is analyzed. Finally, the key nodes in the example are determined through the simulation example and the proposed index, and the optimization scheme of sensor placement in the distribution network is finally determined.