Dataset of Noise Signals Generated by Smart Attackers for Disrupting State of Health and State of Charge Estimations in Battery Energy Storage Systems

This dataset is derived from real-time MATLAB/Simscape simulations, focusing on the impact of subtle noise signals on battery energy storage systems. Using Proximal Policy Optimization (PPO), noise signals in millivolt and milliampere ranges are generated to stealthily disrupt the State of Charge (SoC) and State of Health (SoH) estimations within Unscented Kalman Filters (UKF). Designed to evade detection while causing estimation errors, this dataset is a valuable resource for studying and mitigating smart cyber-physical attacks. It can be reused in research to enhance the resilience of SoC and SoH estimation methods and develop robust defensive strategies.本数据集源自实时MATLAB/Simscape仿真，聚焦微弱噪声信号对电池储能系统的影响。该数据集通过近端策略优化算法（Proximal Policy Optimization, PPO）生成毫伏级与毫安级噪声信号，以隐蔽方式干扰无迹卡尔曼滤波器（Unscented Kalman Filters, UKF）中的荷电状态（State of Charge, SoC）与健康状态（State of Health, SoH）估计结果。其设计目标为规避检测的同时引发估计偏差，是研究与缓解智能信息物理攻击的宝贵资源。该数据集可复用于相关研究，以提升荷电状态与健康状态估计方法的鲁棒性，并开发可靠的防御策略。