Particle Swarm Optimized Federated Learning For Industrial IoT and Smart City Services

TL;DR

This paper introduces a PSO-based method to optimize local ML model hyperparameters in federated learning, significantly reducing training rounds while maintaining accuracy, demonstrated through smart city and IIoT case studies.

Contribution

It presents a novel PSO-based hyperparameter tuning approach for FL that enhances training efficiency without sacrificing model performance.

Findings

PSO reduces hyperparameter tuning rounds by approximately 98% compared to grid search.

The proposed method maintains comparable accuracy to traditional approaches.

Efficient hyperparameter optimization accelerates FL deployment in IoT applications.

Abstract

Most of the research on Federated Learning (FL) has focused on analyzing global optimization, privacy, and communication, with limited attention focusing on analyzing the critical matter of performing efficient local training and inference at the edge devices. One of the main challenges for successful and efficient training and inference on edge devices is the careful selection of parameters to build local Machine Learning (ML) models. To this aim, we propose a Particle Swarm Optimization (PSO)-based technique to optimize the hyperparameter settings for the local ML models in an FL environment. We evaluate the performance of our proposed technique using two case studies. First, we consider smart city services and use an experimental transportation dataset for traffic prediction as a proxy for this setting. Second, we consider Industrial IoT (IIoT) services and use the real-time telemetry dataset to predict the probability that a machine will fail shortly due to component failures. Our experiments indicate that PSO provides an efficient approach for tuning the hyperparameters of deep Long short-term memory (LSTM) models when compared to the grid search method. Our experiments illustrate that the number of clients-server communication rounds to explore the landscape of configurations to find the near-optimal parameters are greatly reduced (roughly by two orders of magnitude needing only 2%--4% of the rounds compared to state of the art non-PSO-based approaches). We also demonstrate that utilizing the proposed PSO-based technique to find the near-optimal configurations for FL and centralized learning models does not adversely affect the accuracy of the models.