The energy storage system (ESS) plays a crucial role in electric vehicles (EVs), impacting their performance and efficiency. While batteries are the standard choice for energy storage, they come with drawbacks like low power density and limited life cycles, which can hinder pure battery electric vehicles (PBEVs). To address these issues, a hybrid energy storage system (HESS) that combines a battery with a supercapacitor provides a more effective solution. The battery delivers consistent power, while the supercapacitor manages peak power demands and regenerative braking energy. This study proposes a new energy management strategy for the HESS, an advanced adaptive rule-based algorithm. The results of the standard rule-based and adaptive rule-based algorithms are used to verify the proposed control algorithm. The system was modeled in MATLAB/Simulink and evaluated across three driving cycles—UDDS, NYCC, and Japan1015—while varying states of charge for the supercapacitors. The findings indicate that the HESS significantly alleviates battery stress compared to a pure battery system, enhancing both efficiency and lifespan. Among the algorithms tested, the advanced adaptive rule-based algorithm yielded the best results, increasing the number of viable drive cycles.
Commercial and industrial customers are subject to monthly maximum demand charges, which can be as high as 30% of the total electricity bill. A battery-based energy storage system (BESS) can be used to reduce the monthly maximum demand charges. A number of control strategies have been developed for the BESS to reduce the daily peak demands. However, the existing control strategies may fail to reduce the peaks on some occasions because the energy of the BESS runs out during the process of peak reduction. Therefore, a new active control strategy for the BESS is developed and presented in this paper. This strategy is able to reduce the peaks even though the peaks are different from the forecasted ones. This strategy is able to reduce the monthly maximum demands by 9% when the BESS capacity is reduced to 37% of the full capacity due to financial constraints. Hence, the customers can achieve the payback period of 11 years over the project lifespan of 21 years with the reduced capacity of the BESS.
Battery-based energy storage systems (BESS) can be installed and controlled by a control strategy to reduce daily peak demands. Majority of the existing controllers for BESS is developed and studied on a simulation platform. Hence, an innovative adaptive threshold-based controller is developed and implemented on a real 200 kWh BESS installed on a university campus in Malaysia to reduce daily peak demands. This controller is developed on the free, open-source Node-RED platform using a deep learning-based one-dimensional convolution neural network (1D-CNN) to forecast the load profile for one day ahead. The controller uses the forecasted load profile to define a threshold or specific power demand level above which the BESS will start discharging power to meet the demand. The threshold is actively adjusted according to the actual and forecasted power demand of the customer as well as preceding peak of the grid power. The performance of the controller is initially assessed through six months of comprehensive simulations, where its daily peak reduction factor (Kpdr) and monthly peak reduction failure rate (ηfailure) are compared with that of two fixed-threshold controllers, namely forecasted threshold and historical threshold-based controllers, and another two advanced controllers, namely active and fuzzy controllers. The adaptive threshold-based controller achieves an average Kpdr of 41.62% and ηfailure of just 16.55%, which are better than that of other four controllers. The controller is implemented to BESS in a university building to evaluate its practical performance over 21 days under a real operating condition. The controller achieves an average Kpdr of 49.45% with a ηfailure of just 4.76%, which are better than the simulation results.
This paper presents a long short-term memory (LSTM) network for battery state-of-charge (SoC) estimation. At present, there is limited research on machine learning techniques for the SoC estimation of batteries in grid applications. Therefore, this paper studies the use of the LSTM network for battery SoC estimation during peak demand reduction. The LSTM network is compared with other existing SoC estimation methods such as empirical method, coulomb counting, extended Kalman filter, and unscented Kalman filter, along with another machine learning algorithm, namely the feedforward neural network. The LSTM network achieves an average mean absolute error of 0.10 and a root mean square error of 0.12.