Real-time Power System State Estimation and Forecasting via Deep Neural Networks

Abstract

Contemporary power grids are being challenged by rapid voltage fluctuations that are caused by large-scale deployment of renewable generation, electric vehicles, and demand response programs. In this context, monitoring the grid's operating conditions in real time becomes increasingly critical. With the emergent large scale and nonconvexity however, the existing power system state estimation (PSSE) schemes become computationally expensive or yield suboptimal performance. To bypass these hurdles, this paper advocates deep neural networks (DNNs) for real-time power system monitoring. By unrolling an iterative physics-based prox-linear solver, a novel model-specific DNN is developed for real-time PSSE with affordable training and minimal tuning effort. To further enable system awareness even ahead of the time horizon, as well as to endow the DNN-based estimator with resilience, deep recurrent neural networks (RNNs) are also pursued for power system state forecasting. Deep RNNs leverage the long-term nonlinear dependencies present in the historical voltage time series to enable forecasting, and they are easy to implement. Numerical tests showcase improved performance of the proposed DNN-based estimation and forecasting approaches compared with existing alternatives. In real load data experiments on the IEEE 118-bus benchmark system, the novel model-specific DNN-based PSSE scheme outperforms nearly by an order-of-magnitude the competing alternatives, including the widely adopted Gauss-Newton PSSE solver.

References in corpus (11)

• Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
• A Survey on State Estimation Techniques and Challenges in Smart Distribution Systems
• Monitoring and Optimization for Power Grids: A Signal Processing Perspective
• Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
• ResNet with one-neuron hidden layers is a Universal Approximator
• Power System State Estimation via Feasible Point Pursuit: Algorithms and Cramer-Rao Bound
• PSSE Redux: Convex Relaxation, Decentralized, Robust, and Dynamic Approaches
• Moving-Horizon Dynamic Power System State Estimation Using Semidefinite Relaxation
• Learning Deep ${\ell }_0$ Encoders
• Robust and Scalable Power System State Estimation via Composite Optimization
• A Learning-to-Infer Method for Real-Time Power Grid Multi-Line Outage Identification

Cited by in corpus (27)

• Physics-Guided Deep Neural Networks for Power Flow Analysis
• Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
• Learning to Optimize: A Primer and A Benchmark
• Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising
• Reliably-stabilizing piecewise-affine neural network controllers
• Two-Timescale Voltage Control in Distribution Grids Using Deep Reinforcement Learning
• Deep Learning for Intelligent Demand Response and Smart Grids: A Comprehensive Survey
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning
• DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow
• State Estimation in Electric Power Systems Leveraging Graph Neural Networks
• Learning an Optimally Reduced Formulation of OPF through Meta-optimization
• Graph Neural Networks on Factor Graphs for Robust, Fast, and Scalable Linear State Estimation with PMUs
• Physics-Informed Neural Networks for Accelerating Power System State Estimation
• Two-Stage Stochastic Optimization via Primal-Dual Decomposition and Deep Unrolling
• Bayesian State Estimation for Unobservable Distribution Systems via Deep Learning
• Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids
• Sequence-to-Sequence Forecasting-aided State Estimation for Power Systems
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems
• Distributionally Robust Semi-Supervised Learning Over Graphs
• Robust stabilization of polytopic systems via fast and reliable neural network-based approximations
• Gauss-Newton Unrolled Neural Networks and Data-driven Priors for Regularized PSSE with Robustness
• Embedding Power Flow into Machine Learning for Parameter and State Estimation
• PIPO-Net: A Penalty-based Independent Parameters Optimization Deep Unfolding Network
• A Statistical Learning Approach to Reactive Power Control in Distribution Systems
• Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networks
• Real Time State Estimation of Power Grids Using Convolutional Neural Networks and State Forecasting Via Recurrent Neural Networks
• A Hybrid Deep Learning-Based State Forecasting Method for Smart Power Grids