Resource Optimized Federated Learning-Enabled Cognitive Internet of Things for Smart Industries

Abstract

Leveraging the cognitive Internet of things (C-IoT), emerging computing technologies, and machine learning schemes for industries can assist in streamlining manufacturing processes, revolutionizing operational analytics, and maintaining factory efficiency. However, further adoption of centralized machine learning in industries seems to be restricted due to data privacy issues. Federated learning has the potential to bring about predictive features in industrial systems without leaking private information. However, its implementation involves key challenges including resource optimization, robustness, and security. In this paper, we propose a novel dispersed federated learning (DFL) framework to provide resource optimization, whereby distributed fashion of learning offers robustness. We formulate an integer linear optimization problem to minimize the overall federated learning cost for the DFL framework. To solve the formulated problem, first, we decompose it into two sub-problems: association and resource allocation problem. Second, we relax the association and resource allocation sub-problems to make them convex optimization problems. Later, we use the rounding technique to obtain binary association and resource allocation variables. Our proposed algorithm works in an iterative manner by fixing one problem variable (for example, association) and compute the other (for example, resource allocation). The iterative algorithm continues until convergence of the formulated cost optimization problem. Furthermore, we compare the proposed DFL with two schemes; namely, random resource allocation and random association. Numerical results show the superiority of the proposed DFL scheme. INDEX TERMS Smart industry, cognitive Internet of Things, federated learning, convex optimization.

Research on Resource Allocation for Efficient Federated Learning

“…Therefore the proposed resource optimization schemes can not be directly applied to federated learning scenarios. The studies in [11], [22]- [26] considered resource optimization for federated learning, but they only considered one of the learning performance and energy consumption as optimization objectives, besides neither of them considered hierarchical network architecture. For those studies that considered hierarchical network architectures [27]- [30] , most of them focused on the design of federated learning architectures.…”

“…in the network. 2) A collaborative FL model for different participants must take into account the validity of the learning model parameters received from them [11]. Therefore, the transmission error in the process of model transmission is also an important factor affecting FL performance.…”

“…2)Research on Federated Learning: As a new technology, federated learning is becoming more and more widely studied [11], [22]- [30]. To minimize the loss function under a given resource budget, Wang et.…”

“…The joint optimization problem was then skillfully decomposed into two sub-problems: bandwidth allocation and device scheduling, and was solved effectively. Further adding the delay of federated learning into the optimization objective, a novel system model, namely, DFL was devised in [11] for the cognitive Internet of things (C-IoT). In this network scenario, an integer linear programming problem was constructed by the authors to minimize the global FL cost.…”

Spectrum Allocation and Device Association in Federated Learning-Enabled Industrial IoT via Hypergraph Matching

“…In [7], the authors studied the resource allocation problem for FL-enabled IIoT, and formulated a training latency minimization problem by jointly considering the active device selection and resource allocation. In [8], the authors explored the FL cost minimization problem in smart industries by capturing both the latency and packet error rate of FL. A communication-efficient FL framework in IIoT system was proposed in [9] for anomaly detection of IIoT devices.…”