Resilient Voltage Estimation for Battery Packs Using Self-Learning Koopman Operator

TL;DR

This paper addresses secure voltage estimation for cloud-based BMSs during EV charging under sensor attacks. It introduces a self-learning Koopman operator framework with two-stage error compensation: Stage I corrects Koopman-approximation errors, and Stage II offers either a heuristic OCV-SOC mapping or Gaussian process regression to capture higher-order battery dynamics. The approach enables real-time,Attack-resilient voltage estimates across varied pack topologies and aging without reliance on sensor redundancy, demonstrated through extensive PyBaMM-liionpack simulations. The proposed method shows robust performance under DoS, data-swap, and FDI sensor-attacks and offers practical scalability for diverse battery configurations. The work provides a compelling route to maintain safe, coordinated bi-directional charging in V2G-enabled EV ecosystems under cyber-physical threats.

Abstract

Cloud-based battery management systems (BMSs) rely on real-time voltage measurement data to ensure coordinated bi-directional charging of electric vehicles (EVs) with vehicle-to-grid technology. Unfortunately, an adversary can corrupt the measurement data during transmission from the local-BMS to the cloud-BMS, leading to disrupted EV charging. Therefore, to ensure reliable voltage data under such sensor attacks, this paper proposes a two-stage error-corrected self-learning Koopman operator-based secure voltage estimation scheme for large-format battery packs. The first stage of correction compensates for the Koopman approximation error. The second stage aims to recover the error amassing from the lack of higher-order battery dynamics information in the self-learning feedback, using two alternative methods: an adaptable empirical strategy that uses cell-level knowledge of open circuit voltage to state-of-charge mapping for pack-level estimation, and a Gaussian process regression-based data-driven method that leverages minimal data-training. During our comprehensive case studies using the high-fidelity battery simulation package 'PyBaMM-liionpack', our proposed secure estimator reliably generated real-time voltage estimation with high accuracy under varying pack topologies, charging settings, battery age-levels, and attack policies. Thus, the scalable and adaptable algorithm can be easily employed to diverse battery configurations and operating conditions, without requiring significant modifications, excessive data or sensor redundancy, to ensure optimum charging of EVs under compromised sensing.

Figures (8)

• Figure 1: Block diagram shows the secure voltage estimation generation under sensor attack.
• Figure 2: Block diagram showing the components of the secure estimator along with the sensor attack-triggered self-learning feedback mechanism.
• Figure 3: For the LGM50 Lithium-ion battery, the figure exhibits OCV-SOC (top), $\frac{d\,OCV}{d\,SOC}$ (second), $\frac{d^2\,OCV}{d\,SOC^2}$ (third), and $\frac{d^3\,OCV}{d\,SOC^3}$ (bottom) graphs.
• Figure 4: Plot shows the distributions of voltage estimation error for heuristic and GPR correction at three different battery age-levels.
• Figure 5: DoS sensor attack: Each plot shows the true and compromised module voltage for the battery, the voltage estimation from self-learning Koopman-based estimation with only stage I correction, with stage II GPR correction, and with stage II heuristic correction.

Theorems & Definitions (1)

• Remark 1