Graph Neural Networks for Distributed Linear-Quadratic Control
arXiv:2011.05360
Abstract
The linear-quadratic controller is one of the fundamental problems in control theory. The optimal solution is a linear controller that requires access to the state of the entire system at any given time. When considering a network system, this renders the optimal controller a centralized one. The interconnected nature of a network system often demands a distributed controller, where different components of the system are controlled based only on local information. Unlike the classical centralized case, obtaining the optimal distributed controller is usually an intractable problem. Thus, we adopt a graph neural network (GNN) as a parametrization of distributed controllers. GNNs are naturally local and have distributed architectures, making them well suited for learning nonlinear distributed controllers. By casting the linear-quadratic problem as a self-supervised learning problem, we are able to find the best GNN-based distributed controller. We also derive sufficient conditions for the resulting closed-loop system to be stable. We run extensive simulations to study the performance of GNN-based distributed controllers and showcase that they are a computationally efficient parametrization with scalability and transferability capabilities.
arXiv commentSubmitted to 3rd Annual Learning for Dynamics and Control Conference (L4DC 2021)
References in corpus (11)
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Geometric deep learning: going beyond Euclidean data
- Discrete Signal Processing on Graphs
- Convolutional Neural Network Architectures for Signals Supported on Graphs
- Stability Properties of Graph Neural Networks
- Gated Graph Recurrent Neural Networks
- Forecasting Time Series with VARMA Recursions on Graphs
- Graphon Neural Networks and the Transferability of Graph Neural Networks
- Controllability of Bandlimited Graph Processes Over Random Time Varying Graphs
- Ergodicity in Stationary Graph Processes: A Weak Law of Large Numbers
- Efficient Learning of Distributed Linear-Quadratic Controllers