One of the Sustainable Development Goals of the United Nations is affordable and clean energy. True utilization of renewable energy is only possible via battery-based energy storage systems. Overseeing the operation of battery-based energy storage systems and diagnosing abnormal batteries are of the utmost importance for their durability and stability. Because of inadequate anomalous samples and privacy considerations, we jointly train a global autoencoder on various battery-based energy storage systems to detect anomalous batteries. Due to potentially unstable network connectivity in energy storage systems, a chunk of model parameters may be lost during model transmission, leading to dramatic performance deterioration. The trained model tends to classify all measurements as anomalies. To solve this problem, we propose a robust federated learning scheme to mitigate negative impact caused by packet loss during model transmission. By permuting and unpermuting model parameters before and after model transmission, we are able to distribute the lost parameters across the entire model. Such a loss can no longer have a significant negative impact on anomalous battery detection. Experimental results illustrate that the proposed algorithm is robust against packet loss during the model exchange between the cloud server and battery-based energy storage systems.

We have aspired as a green and intelligent future, where humans, the built environment, and the nature are interconnected as a cyber-physical system. To such an Internet of Things, the sustainability and robustness of the power system is crucial, and the reliable operation of the battery-backed energy storage systems is key because of their abilities in power smoothing and shifting. However, detecting battery failures at the early-deployment stage is challenging due to the unavailability of anomalous measurement data and privacy concerns. In this paper, we propose an anomaly detection scheme for the energy storage systems without using prior information. We train autoencoders on the normal measurement data. Instead of training autoencoders in a centralized way, we train a global autoencoder over many energy storage systems in a federated manner without compromising privacy. Experimental results show that the proposed algorithm effectively detects anomalous batteries instantly after the system is set up without sharing sensitive data.

Receiver sensitivity is one of the most important performance metrics in communication systems. Industry has been using exhaustive search in a specified range to identify the sensitivity of a receiver. However, such an exhaustive search is neither efficient in terms of measurement time, nor accurate due to the fixed step-size. In this paper, a data-driven approach is proposed to measure the receiver sensitivity based on a dynamic linearization representation of a time-varying pseudo-gradient parameter estimation procedure. Unlike the model-based approach, the proposed data-driven approach is dependent only on the input and output measurement data. In addition, we derive the minimum number of test packets needed to satisfy the desired confidence level for packet error rate estimation. By adapting the number of test packets, we are able to further reduce the measurement time. Numerical analyses and experimental results show that the proposed data-driven sensitivity measurement can achieve good estimation performance as well as reduce measurement time.

Receiver sensitivity is one of the most important parameters in determining the overall performance of a radio frequency communication system. The traditional receiver sensitivity measurement is to use exhaustive search in a specified range to identify the receiver's sensitivity. However, such an exhaustive search is neither efficient in terms of measurement time, nor accurate due to the fixed step-size. In this paper, a data-driven approach is proposed to measure the receiver sensitivity based on a dynamic linearization representation of a time-varying pseudo-gradient parameter estimation procedure. Unlike the model-based approach, the proposed data-driven approach is dependent only on the input and output measurement data. Furthermore, an analytical approach is presented to derive the minimum number of test packets needed to satisfy the desired confidence level for packet error rate estimation. By adapting the number of test packets, the proposed approach can converge to the exact receiver sensitivity with less time. A theoretical analysis of the proposed approach is provided and further validated by numerical analyses and real-world experimental verification. These analyses show that the proposed data-driven sensitivity measurement can a achieve good estimation performance within a few iterations as well as reduce measurement time.