Predicting the Batteries' State of Health in Wireless Sensor Networks Applications

Abstract

The lifetime of wireless sensor networks deployments depends strongly on the nodes battery state of health. It is important to detect promptly those motes whose batteries are affected and degraded by ageing, environmental conditions, failures, etc. There are several parameters that can provide significant information of the battery state of health, such as: the number of charge/discharge cycles, the internal resistance, voltage, drained current, temperature, etc. The combination of these parameters can be used to generate analytical models capable of predicting the battery state of health. The generation of these models needs a previous process to collect dense data traces with sampled values of the battery parameters during a large number of discharge cycles under different operating conditions. The collected data allow the development of mathematical models that can predict the battery state of health. These models are required to be simple because they must be executed in motes with low computational capabilities. The article shows the complete process of acquiring the training data, the models generation and its experimental validation using rechargeable batteries connected to Telosb motes. The obtained results provide significant insight of the battery state of health at different temperatures and charge/discharge cycles.

Multi-Step Data Prediction in Wireless Sensor Networks Based on One-Dimensional CNN and Bidirectional LSTM

“…Rafael Lajara proposed a method for predicting battery health in wireless sensor networks [14]. The related parameters like The number of charge and discharge cycles, internal resistance of the node, voltage, output current, and temperature are considered to build an analytical model to predict the battery health.…”

Critical Review of Intelligent Battery Systems: Challenges, Implementation, and Potential for Electric Vehicles

“…With regard to cell individual SOH estimation, Lajara et al [232] focus on simple algorithms with low computational costs. They address the problem of wireless sensor networks, where multiple battery systems operate simultaneously with limited computing power.…”

“…Degradation of single cells is usually invisible in conventional battery systems. [226] x x x Haifeng et al [217] x x DKF Chiang et al [235] x x Adaptive O. Kim et al [19] x x x SMO Plett et al [236] x x WTLS Remmlinger et al [237] x x RLS Hu et al [174] x x DKF Rahimian et al [238] x LAM EKF/UKF Andre et al [192] x x x Feng et al [227] x x x Point Counting Kim et al [189] x x x Nuhic et al [239] x x x Prasad et al [222] x x Diffusion Time LS Remmlinger et al [240] x x KF Schwunk et al [241] x x PF Weng et al [242] x x x x Zheng et al [243] x x GA Eddahech et al [225] x CVCT Empirical Guo et al [223] x CCCT NLS Han et al [244] x x Calibrated O. Hu et al [245] x Sample Entropy Empirical Kim et al [80] x DWT Empirical Zou et al [185] x x DKF Berecibar et al [246] x x x Wu et al [247] x x x Zou et al [186] x x EKF Dubarry et al [248] x LAM, LLI Empirical Gong et al [233] x Gas Production Empirical Huhman et al [231] x x x Sanchez et al [249] Vessel Model x Fuzzy Cai et al [250] x DWT Empirical Chen et al [251] x x RF Lajara et al [232] x x x LS Li et al [228] x x x Li et al [252] x x EKF, PF Santos et al [253] x x x Shen et al [198] x x RLS Smiley et al [254] x x IMM KF Tang et al [255] x x...…”

Simple and Effective Secure Group Communications in Dynamic Wireless Sensor Networks

“…These devices and sensors aim to collect data to provide a numerous of valuable results. However, these low end devices come with very limited computation and processing capabilities [9,10,11]. Therefore, to overcome this issue, there is a need for a remote unit with computation capability to perform such a process.…”