A decentralized Artificial Immune System for solution selection in Cyber–Physical Systems

Semwal, Tushar; Nair, Shivashankar B.

doi:10.1016/j.asoc.2019.105920

Cited by 11 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such scenarios, some robots could be using one type of learning method while others could be using another, resulting in a heterogeneous federated learning environment. Eventually, the robots could choose the better performing models and use the same for exhibiting the associated behaviours in their respective environments, using decentralized algorithm selection methods [28]. The use of multiple mobile agents could facilitate the concurrent learning of more than one behaviour in a decentralized and federated manner.…”

Section: Discussionmentioning

confidence: 99%

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios

Nair¹,

Kulkarni²,

Joshi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Federated Learning (FL) allows for collaboratively aggregating learned information across several computing devices and sharing the same amongst them, thereby tackling issues of privacy and the need of huge bandwidth. FL techniques generally use a central server or cloud for aggregating the models received from the devices. Such centralized FL techniques suffer from inherent problems such as failure of the central node and bottlenecks in channel bandwidth. When FL is used in conjunction with connected robots serving as devices, a failure of the central controlling entity can lead to a chaotic situation. This paper describes a mobile agent based paradigm to decentralize FL in multi-robot scenarios. Using Webots, a popular free open-source robot simulator, and Tartarus, a mobile agent platform, we present a methodology to decentralize federated learning in a set of connected robots. With Webots running on different connected computing systems, we show how mobile agents can perform the task of Decentralized Federated Reinforcement Learning (dFRL). Results obtained from experiments carried out using Q-learning and SARSA by aggregating their corresponding Q-tables, show the viability of using decentralized FL in the domain of robotics. Since the proposed work can be used in conjunction with other learning algorithms and also real robots, it can act as a vital tool for the study of decentralized FL using heterogeneous learning algorithms concurrently in multi-robot scenarios.

show abstract

Section: Discussionmentioning

confidence: 99%

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios

Nair¹,

Kulkarni²,

Joshi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…AIS algorithm was then used to tackle the situations with highly variable conditions in the manufacturing process. Researchers in Semwal and Nair (2020) realized that the centralization approach for the implementation of networked environments in cyber-physical systems is expensive concerning the increasing number of devices and the flow of information. While decentralization and distribution of the architecture address this issue, it remains a challenge to find the best solutions for problems distributed across devices.…”

Section: Use Of Artificial Immune Systems In the Context Of Industry 40mentioning

confidence: 99%

Computational Intelligence in the Context of Industry 4.0

Hosŏvský

Piteľ

Trojanová

et al. 2021

Implementing Industry 4.0 in SMEs

View full text Add to dashboard Cite

Industry 4.0 is affecting almost every area of the industry, and as a result of its effects, systems, technologies, and the way information is processed are being transformed. Its typical feature is transmission of information in the system environment provided by the Internet of Things. All information should be stored and shared through cloud computing. As a result, access to information should be unrestricted. This chapter is focused on Computational Intelligence (CI) in the context of Industry 4.0. Each subchapter provides fundamentals of some paradigms, followed by the use of CI in the concrete paradigm. The ending part of the chapter is focused on connecting theory and practice in a case study, which lists industrial parts recognition by convolutional neural networks for assisted assembly.

show abstract

“…However, biological or ecological inspiration has remained a largely qualitative idea for resilience rather than a quantitative and practical framework for designing resilience in complex systems or SoS. A notable exception to this statement is the work on cyber-security algorithms inspired by the working of the biological immune system, 58 and embryonic cellular development. 59 While the success of these bio-inspired cyber-security approaches is encouraging, they are not generalizable to different types of complex systems or…”

Section: Resilience In Ecology and Relevance For Engineeringmentioning

confidence: 99%

Ecology‐inspired resilient and affordable system of systems using degree of system order

Chatterjee

Malak

Layton

2021

Systems Engineering

View full text Add to dashboard Cite

An optimal trade-off between resilience (the ability to survive and recover from disruptions) and affordability is highly desirable in System of Systems (SoS) architectures. However, it is difficult to design SoS architectures for these goals as existing resilience evaluation methods require detailed disruption models that are not readily available in the early stages of design. Biological ecosystems (nature's resilient SoS) achieve these goals through a unique balance of efficient and redundant interactions in their architectures-measured using the metric Degree of System Order (DoSO).This research tests if this ecological architecting principle and the DoSO metric are useful for designing resilient and affordable SoS. The resilience versus affordability tradespace of a large number of notional SoS architectures is investigated using the DoSO metric. Results indicate that the majority of Pareto optimal SoS architectures, under various disruptions, lie in the ecologically-identified favorable DoSO range. Further, SoS architectures within this DoSO range were found to have better resilience and affordability attributes, in general, than the architectures outside it. DoSO evaluation does not require knowledge of disruption scenarios and is the first network architecture metric to consider resilience versus affordability trade-offs, making it a valuable addition to the SoS engineering toolset.

show abstract

A decentralized Artificial Immune System for solution selection in Cyber–Physical Systems

Cited by 11 publications

References 18 publications

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios

Computational Intelligence in the Context of Industry 4.0

Ecology‐inspired resilient and affordable system of systems using degree of system order

Contact Info

Product

Resources

About