Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Control

04/28/2021
by   Fengjun Yang, et al.
8

When designing large-scale distributed controllers, the information-sharing constraints between sub-controllers, as defined by a communication topology interconnecting them, are as important as the controller itself. Controllers implemented using dense topologies typically outperform those implemented using sparse topologies, but it is also desirable to minimize the cost of controller deployment. Motivated by the above, we introduce a compact but expressive graph recurrent neural network (GRNN) parameterization of distributed controllers that is well suited for distributed controller and communication topology co-design. Our proposed parameterization enjoys a local and distributed architecture, similar to previous Graph Neural Network (GNN)-based parameterizations, while further naturally allowing for joint optimization of the distributed controller and communication topology needed to implement it. We show that the distributed controller/communication topology co-design task can be posed as an ℓ_1-regularized empirical risk minimization problem that can be efficiently solved using stochastic gradient methods. We run extensive simulations to study the performance of GRNN-based distributed controllers and show that (a) they achieve performance comparable to GNN-based controllers while having fewer free parameters, and (b) our method allows for performance/communication density tradeoff curves to be efficiently approximated.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/31/2022

Synthesis of Stabilizing Recurrent Equilibrium Network Controllers

We propose a parameterization of a nonlinear dynamic controller based on...
research
02/13/2023

Expediting Distributed DNN Training with Device Topology-Aware Graph Deployment

This paper presents TAG, an automatic system to derive optimized DNN tra...
research
03/25/2019

Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks

We consider the problem of finding distributed controllers for large net...
research
06/24/2021

Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks

In this paper, we present a perception-action-communication loop design ...
research
08/03/2021

Dynamic communication topologies for distributed heuristics in energy system optimization algorithms

The communication topology is an essential aspect in designing distribut...
research
09/11/2020

Graph Neural Network based Service Function Chaining for Automatic Network Control

Software-defined networking (SDN) and the network function virtualizatio...
research
12/29/2020

Decentralized Control with Graph Neural Networks

Dynamical systems consisting of a set of autonomous agents face the chal...

Please sign up or login with your details

Forgot password? Click here to reset