Influence Models on Layered Uncertain Networks: A Guaranteed-Cost Design Perspective

Alemzadeh, Siavash; Mesbahi, Mehran

doi:10.1109/cdc.2018.8619110

Cited by 8 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Suboptimal solutions to the controller design consistent with the graph structure has also been proposed. Nevertheless, in many real-world applications there is no a priori knowledge of the system's model due to either complexities or model uncertainties [12]. We introduce a model-free approach while considering the optimality criteria for each subsystem.…”

Section: A Distributed Lqr Problemmentioning

confidence: 99%

“…Graph-based structured controller design was further examined in works such as [9], [10]. The topic was also studied from a spatially distributed control viewpoint [11] or a layered control design approach [12]. However, all of these studies are based on the knowledge of the underlying dynamics; as the system grows in scale, modeling becomes prohibitively difficult and uncertain due to complexities or potential perturbations in high dimensions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distributed Q-Learning for Dynamically Decoupled Systems

Alemzadeh

Mesbahi

2019

2019 American Control Conference (ACC)

Self Cite

View full text Add to dashboard Cite

Control of large-scale networked systems often necessitates the availability of complex models for the interactions amongst the agents. However, in many applications building accurate models of these interactions might be prohibitive due to the curse of dimensionality or their inherent complexity. In the meantime, data-guided control methods can circumvent model complexity by directly synthesizing the controller from the observed data. In this paper, we propose a distributed Q-learning algorithm to design a feedback mechanism given an underlying graph structure parameterizing the agents' communication. We assume that the distributed nature of the system arises from a common cost and show that for the particular case of identical dynamically decoupled systems, the learned controller converges to the optimal Linear Quadratic Regulator controller for each subsystem. We provide a convergence analysis and verify the result with an example.

show abstract

Section: A Distributed Lqr Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Distributed Q-Learning for Dynamically Decoupled Systems

Alemzadeh

Mesbahi

2019

2019 American Control Conference (ACC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The results of this manuscript can be extended to study influence of agents in a network with higher-order dynamics or multi-layered structure [1]. We discuss the extension of the results to a class of networks with second-order dynamics which is a widely used model for studying platoon of cars [21,26,2].…”

Section: Network With Higher-order Dynamicsmentioning

confidence: 95%

Centrality in Time-Delay Consensus Networks with Structured Uncertainties

Ghaedsharaf¹,

Siami²,

Somarakis³

et al. 2019

Preprint

View full text Add to dashboard Cite

We investigate notions of network centrality in terms of the underlying coupling graph of the network, structure of exogenous uncertainties, and communication time-delay. Our focus is on time-delay linear consensus networks, where uncertainty is modeled by structured additive noise on the dynamics of agents. The centrality measures are defined using the H2-norm of the network. We quantify the centrality measures as functions of time-delay, the graph Laplacian, and the covariance matrix of the input noise. Several practically relevant uncertainty structures are considered, where we discuss two notions of centrality: one w.r.t intensity of the noise and the other one w.r.t coupling strength between the agents. Furthermore, explicit formulas for the centrality measures are obtained for all types of uncertainty structures. Lastly, we rank agents and communication links based on their centrality indices and highlight the role of time-delay and uncertainty structure in each scenario. Our counter intuitive grasp is that some of centrality measures are highly volatile with respect to time-delay.

show abstract

“…Fast forward a few decades, sufficient graph-theoretic conditions were provided for stability of formations comprised of identical vehicles [14] and, along the same lines, graph-based distributed controller synthesis was further examined independently in works such as [3,4,[15][16][17][18]. The topic was also studied from a spatially distributed control viewpoint [19,20] and a compositional layered design approach [21,22]. Moreover, from an agent-level perspective, the problem has been tackled for both homogeneous systems [3,15,17] and more recently heterogeneous ones [23].…”

Section: Related Workmentioning

confidence: 99%

D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems

Alemzadeh¹,

Talebi²,

Mesbahi³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Control of large-scale networked systems often necessitates the availability of complex models for the interactions amongst the agents. While building accurate models of these interactions could become prohibitive in many applications, data-driven control methods can circumvent model complexities by directly synthesizing a controller from the observed data. In this paper, we propose the Data-Driven Distributed Policy Iteration (D3PI) algorithm to design a feedback mechanism for a potentially large system that enjoys an underlying graph structure characterizing communications among the agents. Rather than having access to system parameters, our algorithm requires temporary "auxiliary" links to boost information exchange of a small portion of the graph during the learning phase. Therein, the costs are partitioned for learning and non-learning agents in order to ensure consistent control of the entire network. After the termination of the learning process, a distributed policy is proposed for the entire networked system by leveraging estimated components obtained in the learning phase. We provide extensive stability and convergence guarantees of the proposed distributed controller throughout the learning phase by exploiting the structure of the system parameters that occur due to the graph topology and existence of the temporary links. The practicality of our method is then illustrated with a simulation.

show abstract

Influence Models on Layered Uncertain Networks: A Guaranteed-Cost Design Perspective

Cited by 8 publications

References 20 publications

Distributed Q-Learning for Dynamically Decoupled Systems

Distributed Q-Learning for Dynamically Decoupled Systems

Centrality in Time-Delay Consensus Networks with Structured Uncertainties

D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems

Contact Info

Product

Resources

About