Federated Anomaly Detection With Sparse Attentive Aggregation for Energy Consumption in Buildings
Yuan Shi, Bo Gao, Fengqiu Xu, Xianze Xu, Yufei Jiang · IEEE Internet of Things Journal · 2023
Anomaly detection (AD) in energy consumption for buildings plays a critical role in improving energy efficiency. In distributed systems, federated learning (FL) has gained widespread adoption due to its ability to train robust models while preserving privacy. However, most FL algorithms face challenges in handling heterogeneous data across different buildings, where distribution gaps exist. Moreover, addressing the heterogeneity in data necessitates additional efforts in model personalization, resulting in significant computational overhead, especially in large-scale FL settings. To address these challenges, we propose a sparse attentive aggregation-based federated AD (SAA-FAD) approach. SAA-FAD comprises an extraction network and a lightweight recognition network. The extraction network employs a variational Bayes scheme to extract statistical characteristics from the raw data for computing similarities between clients while preserving privacy. Then, the recognition network is trained with the extracted statistical features. The model is trained in an SAA manner, which leads to superior AD performance on heterogeneous data. Additionally, SAA-FAD achieves a time and memory complexity of$\mathcal {O}(N\cdot {\mathrm {log}}N)$for computing similarity. Simulation results demonstrate that SAA-FAD outperforms other baseline models, particularly in scenarios with heterogeneous data, while offering a significant advantage in terms of computation time.