Advanced Load Cycle Generation for Electrical Energy Storage Systems Using Gradient Random Pulse Method and Information Maximising-Recurrent Conditional Generative Adversarial Networks

The paper presents two approaches to generating load cycles for electrical energy storage systems. A load cycle is described as the operation of an energy storage system. The cycles can include different metrics depending on the storage application. Load cycle analysis using the rainflow counting method is employed to understand and validate the metrics of the load cycles generated. Current load cycle generation can involve clustering methods, random microtrip methods, and machine learning techniques. The study includes a random microtrip method that utilises the Random Pulse Method (RPM) and enhances it to develop an improved version called the Gradient Random Pulse Method (gradRPM), which includes the control of stress factors such as the gradient of the state of charge (SOC). This method is relatively simple but, in many cases, it fulfills its purpose. Another more sophisticated method to control stress factors has been proposed, namely the Information Maximising-Recurrent Conditional Generative Adversarial Network (Info-RCGAN). It uses a deep learning algorithm to follow a machine learning-based, data-driven load cycle generation approach. Both approaches use the measurement dataset of a BMW i3 over multiple years to generate new synthetic load cycles. After generating the load cycles using both approaches, they are applied in a laboratory environment to evaluate the stress factors and validate how similar the synthetic data are to a real measurement. The results provide insights into generating simulation or testing data for electrical energy storage applications.