Spatio-Temporal Generative Adversarial Network Based Power Distribution Network State Estimation With Multiple Time-Scale Measurements

The increasing penetration of distributed renewable generation has introduced significant uncertainties and randomness to the power distribution network operation. Accurate and timely awareness of the network operation is of paramount importance to ensure system safety and reliability and is considered nontrivial and costly as substantial network reinforcement with advanced measurement devices is generally required. Also, the existing state estimation methods, e.g., weighted least square, may not converge in the presence of incomplete and inaccurate measurements. This article proposes a spatio-temporal estimation generative adversarial network (ST-EGAN) consisting of feature extraction, information completion, data reconstruction, and fake data discrimination to generate high-resolution pseudo-measurements to promote the accuracy and robustness of state estimation. The task of high-resolution power distribution network state estimation is carried out based on the mixed dataset of multiple time-scale measurements obtained from supervisory control and data acquisition and phasor measurement units. The proposed solution is extensively assessed using the IEEE 33-bus test network compared with the existing solutions for a range of scenarios with different resolutions and noise intensities. The numerical results demonstrated that the proposed ST-EGAN can reduce the mean rmse by 4.78% compared to interpolation algorithms, and reduce the rmse by 0.14% and 0.21% compared with deep convolutional generative adversarial networks and super-resolution convolutional networks, respectively, in the presence of noises with different intensities. The proposed method can be generalized to cases with different topological structures and measurement assembly conditions.

I. Introduction

The increasing penetration of renewable distributed generation, e.g., micro wind turbines and solar photovoltaic, with the intermittent generation characteristics has brought significant challenges to the operation and control of power distribution networks [1]. The state estimation (SE) is considered critical for the timely awareness of distribution network operation through analyzing the measurement data and providing accurate real-time network states [2]. The advanced control and management functionalities of the distribution management system firmly rely on reliable and accurate state estimation, e.g., operation optimization, voltage stability analysis, dynamic security assessment, energy dispatch, etc. [3]. In the distribution network operation, many power system analysis tools require high-resolution SE to fulfill the functionality and prevent the system from operational risks, particularly in the presence of massive penetration of distributed renewable generation. However, the implementation of high-resolution SE in the power distribution system is considered a nontrivial task due to the following two reasons: 1) the accuracy and sampling frequency of supervisory control and data acquisition (SCADA) cannot meet the requirement of distribution network perception due to the highly uncertain operational conditions. The phasor measurement units (PMU) that can enhance the measurement capability with a much higher sampling rate compared with SCADA ([4], [5]) are generally only deployed in certain locations across the distribution network for economic reasons in practice [6]; 2) the measurement data faces the risk of being lost or tampered due to communication failure and network attacks, e.g., fake data injection attacks and network attacks; 3) the incompleteness and inaccuracy of measurements may directly degrade the performance, or even lead to nonconverge of SE [7].