Traditional federated learning (FL) adopts a client-server architecture where FL clients (e.g., IoT edge devices) train a common global model with the help of a centralized orchestrator (cloud server). However, current approaches are moving away from centralized orchestration toward a decentralized one in order to fully adapt FL for a cross-silo configuration with multiple organizations acting as clients. State-of-the-art decentralized FL mechanisms make at least one of the following assumptions: 1) clients are trusted organizations and cannot inject low-quality model updates for aggregation and 2) client local models can be shared with other clients or a third party for verification of low-quality updates. This article proposes a Blockchain-based decentralized framework for scenarios where participatory organizations are believed to be fully capable of injecting low-quality model updates as they are not willing to expose their local models to any other entity for verification purpose. The proposed decentralized FL framework adopts a novel hierarchical network of aggregators with the ability to punish/reward organizations in proportion to their local model quality updates. The framework is flexible and unlike state-of-the-art solutions, prevents a single entity from possessing the aggregated model in any FL round of training. The proposed framework is tested with respect to off-chain and on-chain performance in two Industry 4.0 use cases: 1) predictive maintenance and 2) product visual inspection. A comparative evaluation against the state-of-the-art reveals the proposed framework’s utility in terms of minimizing model convergence time and latency while maximizing accuracy and throughput.

The proliferation of Industry 4.0 has made modern industrial assets a rich source of data that can be leveraged to optimise operations, ensure efficiency, and minimise maintenance costs. The availability of data is advantageous for asset management, however, attempts to maximise the value of this data often fall short due to additional constraints, such as privacy concerns and data stored in distributed silos that is difficult to access and share. Federated Learning (FL) has been explored to address these challenges and has been demonstrated to provide a mechanism that allows highly distributed data to be mined in a privacy-preserving manner and offering new opportunities for a collaborative approach to asset management. Despite the benefits, FL has some challenges that need to be overcome to make it fully compatible for asset management or more specifically predictive maintenance applications. FL requires a set of clients that participate in the model training process, however, orchestration, device heterogeneity and scalability can hinder the speed and accuracy in the context of collaborative predictive maintenance. To address this challenge, this work proposes a split-learning-based framework (SplitPred) that enables FL clients to maximise available resources within their local network without compromising the benefits of a FL approach (i.e., privacy and shared learning). Experiments performed on the benchmark C-MAPSS data-set demonstrate the advantage of applying SplitPred in the FL process in terms of efficient use of resources, i.e., model convergence time, accuracy, and network load.

The complex nature of wireless local area networks (WLAN) design has led many of the deployments being done in an ad-hoc fashion without efficient design methodologies. Although this approach may work for a small environment with a small number of access points, it is infeasible to use such a process when designing a larger wireless infrastructure. Due to the low cost that is indicative of WLAN deployments, many practitioners view formal optimization techniques as being too complex and costly to implement. There have been a number of research works that investigate the use of formal optimization techniques for the accurate design of a WLAN. Unfortunately, the approaches taken do not address one major issue when designing a complex and demanding wireless network infrastructure, namely scalability. An optimization algorithm must consider a multitude of design criteria and therefore needs to be scalable to be successfully applied to large scenarios. The main contribution of the work presented in this paper is the development of a scalable optimization algorithm based on the tools of distributed artificial intelligence, which overcomes the failings of current approaches and can be utilized for WLAN design regardless of size or complexity of site specific requirements.

Collaborative robots (cobots) are becoming more prominent in the manufacturing industry due to their ability to operate outside safety zones and work in tandem with humans to perform precise and repetitive tasks, such as visual inspection, product categorization, quality control, etc. Cobots generally have limited computational resources that limit their ability to perform complex machine learning (ML) tasks and as such, various cloud- and fog-based computational task offloading mechanisms have been proposed. However, a growing reluctance to share manufacturing data on the cloud, cybersecurity concerns, and demand of agile decision making is encouraging researchers to design resource-sharing frameworks for on-floor cobots where they can share the execution of complex ML tasks. However, agile on-floor environments and the potential presence of malicious elements make reliable task offloading a significant challenge. This article investigates reliability issues and their effects on executing complex ML task executed by participating on-floor cobots. Specifically, this article aims to answer whom to offload? with the objective of ensuring reliability, security, and data protection when offloading computation tasks. To this end, a reputation-based collaborative robotic learning (CoRoL) framework is proposed with the ability to isolate and/or minimize the impact of malicious or poor-performing cobots on computation task execution. In addition, CoRoL is supported by split learning for privacy-preserving task offloading with minimum data exchange. Simulation results and comparative analysis will demonstrate CoRoL’s efficiency in terms of percentage of completed tasks, achieved accuracy, and impact on energy consumption.

The Edge-Cloud Continuum refers to the dynamic provisioning of distributed computing and network resources that can be scaled to support the creation of secure, resource-efficient, and decentralised digital ecosystems, which also support federated topologies for collaborating and sharing resources. Trusted interaction and orchestration of distributed edge-cloud resources are the fundamental principles of distributed network infrastructure and service provisioning. The zero trust architecture (ZTA) paradigm is gaining momentum based on being able to ensure trusted and secure interaction for edge-cloud networks. However, ZTA’s strict authentication policy mandates devices to be authenticated for every session, leading to significant overhead for resource-constrained devices engaged in multiple sessions. To address this challenge, this paper proposes a ZTA that integrates a performance-based trust assessment mechanism, allowing a higher number of consecutive sessions without the need for costly authentication/authorisation while preserving system integrity. Reputation, viewed through the performance lens, is a metric to gauge a node’s trustworthiness, considering its past behaviour and interactions. The proposed trust assessment mechanism is evaluated for its feasibility within our conceptualised ZTA for edge computing environments with limited resources, and simulation results demonstrate the practicality of utilising this technique in zero trust environments.