As renewable power and energy storage industries work to optimize utilization and lifecycle value of battery energy storage, life predictive modeling becomes increasingly important. Typically, end-of-life (EOL) is defined when the battery degrades to a point where only 70-80% of beginning-of-life (BOL) capacity is remaining under nameplate.
How to predict battery life of energy storage power plants?
To ensure the safety and economic viability of energy storage power plants, accurate and stable battery lifetime prediction has become a focal point of research. Predication methods can be divided into two categories: model-driven methods and data-driven methods.
What are the different methods of predicting energy storage batteries?
The main methods are divided into model-based methods [ 11, 12] and data-driven methods [ 13 ]. The data-driven model is currently the most popular method, because it has the advantage of being able to analyze the data to obtain the relationships between various parameters and forecast the RUL of energy storage batteries.
How is the energy storage battery forecasting model trained?
The forecasting model is trained by using the data of the first 1000 cycles in the data set to forecast the remaining capacity of 1500–2000 cycles. The forecasting result of the remaining useful life of the energy storage battery is obtained. Figure 4 shows the comparison between the forecasting value and the real value by different methods.
Why should energy storage batteries be forecasted?
Energy storage has a flexible regulatory effect, which is important for improving the consumption of new energy and sustainable development. The remaining useful life (RUL) forecasting of energy storage batteries is of significance for improving the economic benefit and safety of energy storage power stations.
How can battery management systems predict the state of charge?
The capacity to anticipate batteries for the purpose of maintaining a consistent supply of energy and the best possible use of that energy, remaining usable life (RUL), must be calculated beforehand. When it comes to accurately anticipating the battery management systems' state of charge, we decided to forecast RUL using a random forest model.
How to forecast energy storage batteries based on LSTM neural networks?
Firstly, the RUL forecasting model of energy storage batteries based on LSTM neural networks is constructed. The forecasting error of the LSTM model is obtained and compared with the real RUL. Secondly, the EMD method is used to decompose the forecasting error into many components.