Value of Communication: Data-Driven Topology Optimization for Distributed Linear Cyber-Physical Systems
Communication topology is a crucial part of a distributed control implementation for cyber-physical systems, yet is typically treated as a constraint within control design problems rather than a design variable. We propose a data-driven method for designing an optimal topology for the purpose of distributed control when a system model is unavailable or unaffordable, via a mixed-integer second-order conic program. The approach demonstrates improved control performance over random topologies in simulations and efficiently drops links which have a small effect on predictor accuracy, which we show correlates well with closed-loop control cost.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Optimal Network Topology of Multi-Agent Systems subject to Computation and Communication Latency (with proofs)
We study minimum-variance feedback-control design for a networked control system with retarded dynamics, where inter-agent communication is subject to latency. We prove that such a design can be solved efficiently for ci…
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology generation methods, however, typically learn communication topologies…
Causal InferenceDecentralized Deep Learning using Momentum-Accelerated Consensus
We consider the problem of decentralized deep learning where multiple agents collaborate to learn from a distributed dataset. While there exist several decentralized deep learning approaches, the majority consider a cent…
Deep LearningDynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
The efficiency of multi-agent systems driven by large language models (LLMs) largely hinges on their communication topology. However, designing an optimal topology is a non-trivial challenge, as it requires balancing com…
A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)
In this paper, a mechanistic data-driven approach is proposed to accelerate structural topology optimization, employing an in-house developed finite element convolutional neural network (FE-CNN). Our approach can be divi…