A Federated Learning Approach to Anomaly Detection in Smart Buildings

TL;DR

This paper introduces a federated learning framework using stacked LSTM models for anomaly detection in smart buildings, significantly reducing training time while maintaining high prediction accuracy.

Contribution

It presents a novel privacy-preserving federated learning model with multi-task learning for efficient anomaly detection in IoT-enabled smart buildings.

Findings

Federated LSTM model trains over twice as fast as centralized models.

Achieves state-of-the-art performance on real-world datasets.

Reduces training cost without sacrificing accuracy.

Abstract

Internet of Things (IoT) sensors in smart buildings are becoming increasingly ubiquitous, making buildings more livable, energy efficient, and sustainable. These devices sense the environment and generate multivariate temporal data of paramount importance for detecting anomalies and improving the prediction of energy usage in smart buildings. However, detecting these anomalies in centralized systems is often plagued by a huge delay in response time. To overcome this issue, we formulate the anomaly detection problem in a federated learning setting by leveraging the multi-task learning paradigm, which aims at solving multiple tasks simultaneously while taking advantage of the similarities and differences across tasks. We propose a novel privacy-by-design federated learning model using a stacked long short-time memory (LSTM) model, and we demonstrate that it is more than twice as fast during training convergence compared to the centralized LSTM. The effectiveness of our federated learning approach is demonstrated on three real-world datasets generated by the IoT production system at General Electric Current smart building, achieving state-of-the-art performance compared to baseline methods in both classification and regression tasks. Our experimental results demonstrate the effectiveness of the proposed framework in reducing the overall training cost without compromising the prediction performance.