Search

Abstract Incorporating Battery Battery Energy Storage System (BESS) with wind farm to build up Wind-Storage Combined Generation System is a promising solution to improve the dependability of wind power. BESS sizing and generation scheduling optimization are the key points of this process to improve the economy and efficiency of the integrated combined system. In this paper, based on Quantization Index (QI) clustering, the fluctuation feature of real-time wind power output is studied to obtain the most economic capacity as well as maximum charging/discharging power of BESS in every scheduling circle (15min). Thus, this size of BESS is taken as parameters and constraints for MPC simulation process to minimize the deviation between generation scheduling plan and actual integrated power of Combined Generation System. The optimization results of case study shows that both economic size and ordinary size performs well for generation scheduling optimization, while the proposed BESS sizing method can reduce invest cost to a large extent. [ABSTRACT FROM AUTHOR]

Energy management strategy is vital for a plug-in hybrid electric vehicle and in this paper, a strategy based on stochastic model predictive control is proposed. Firstly, Markov Chain Monte Carlo Simulation is used to predict velocity sequences in the 10-second horizon followed by post-processing like average filtering, quadratic fitting, etc. which is meant to moderate fluctuations of the results. The RMSE is controlled around 2.4357 Km/h. Moreover, dynamic programming is adopted to construct a benchmark strategy and also to act as the rolling optimization part of SMPC-based strategy. The results show that the fuel economy of the strategy based on SMPC is around 13 percent worse than that on DP. However, with 14.7 L/100 km as fuel consumption, it is still within reasonable ranges. [ABSTRACT FROM AUTHOR]

Energy management strategy (EMS) for plug-in hybrid electric vehicle (PHEV) is the key to improve the energy utilization efficiency and vehicle fuel economy. In this paper, a model predictive control (MPC) based on EMS coupled with double Q-learning (DQL) is presented to allocate the power between multiple power sources for PHEV. Firstly, the powertrain framework of the PHEV and its mathematical models were analyzed in detail. Then, based on the required power and speed, an effective convergent offline learning controller was established based on DQL algorithm. Subsequently, the multi-feature input Elman neural network was implemented to predict vehicle speed in MPC, and the trained DQL controller was applied to solve the rolling optimization process in MPC to find the optimal battery output in the prediction horizon. Finally, the proposed strategy was verified in Autonomie software, and the simulation results show that the proposed strategy can achieve a superior fuel economy close to that of the offline stochastic dynamic planning strategy, meanwhile with a perfect adaptability for different state of charge (SOC) reference trajectories. [Display omitted] • An online EMS based on DQL-MPC is proposed for PHEV to improve fuel economy. • The multi-feature input Elman NN is applied to predict vehicle speed in MPC. • The proposed EMS has a perfect adaptability for different SOC reference trajectories. [ABSTRACT FROM AUTHOR]