TY - GEN
T1 - A Simulation Environment of Solar-Wind Powered Electric Vehicle Car Park for Reinforcement Learning and Optimization
AU - Li, Handong
AU - Dai, Xuewui
AU - Kotter, Richard
AU - Aslam, Nauman
AU - Cao, Yue
N1 - Funding information: This work is supported in partial by the EPSRC project Electric Fleets with On-site Renewable Energy Sources (EFORES) under grant EP/W028727/1, the Wuhan Knowledge Innovation Program (2022010801010117), and the EU Interreg North Sea Region programme’s SEEV4-City (Smart, clean Energy and Electric Vehicles for the City) project (J-No.: 38-2-23-15). The authors would acknowledge Adrian McLoughlin at Newcastle City Council and Prof. James Yu at Scottish Power for their support on application and technical discussions.
PY - 2023/3/10
Y1 - 2023/3/10
N2 - In accordance with the United Kingdom's goal to reach net zero by 2050, electric vehicles (EVs) play a crucial role in transportation. However, if the electricity used to charge EVs is derived from fossil fuels, this does not necessarily imply a reduction of overall emissions nationally or globally. To achieve optimal EV charging, a deeper comprehension of the unpredictability of on-site renewable energy sources (ORES) energy output is required. In this paper, the predicted renewable energy generated is used as the actual value for the reinforcement learning algorithm simulation environment. Such a model can represent the relationship between the power generation and the wind speed as well as solar irradiation, which are characterized by significant uncertainties. The uncertainty analysis shows that the wind speed at Newcastle upon Tyne can be modelled as a Weibull distribution with parameters A = 19.98 and B = 1.91. As for energy demand, this paper integrates information from an Oslo (Norway) car parking garage-based set of EV charging stations with EVs' demand statistics. The charging habits of EV users range from 800 min to 1,000 min of parking time, and from 5 kWh to 20 kWh in terms of charging energy. The maximum connection frequency for EV charging is 20 min. In addition, this paper develops methods for stochastic EV charging and parking space occupancy employing actual data. Based on the aforesaid renewable energy generation and the EV charging status, it is possible to develop a decision algorithm to optimal renewable energy efficiency.
AB - In accordance with the United Kingdom's goal to reach net zero by 2050, electric vehicles (EVs) play a crucial role in transportation. However, if the electricity used to charge EVs is derived from fossil fuels, this does not necessarily imply a reduction of overall emissions nationally or globally. To achieve optimal EV charging, a deeper comprehension of the unpredictability of on-site renewable energy sources (ORES) energy output is required. In this paper, the predicted renewable energy generated is used as the actual value for the reinforcement learning algorithm simulation environment. Such a model can represent the relationship between the power generation and the wind speed as well as solar irradiation, which are characterized by significant uncertainties. The uncertainty analysis shows that the wind speed at Newcastle upon Tyne can be modelled as a Weibull distribution with parameters A = 19.98 and B = 1.91. As for energy demand, this paper integrates information from an Oslo (Norway) car parking garage-based set of EV charging stations with EVs' demand statistics. The charging habits of EV users range from 800 min to 1,000 min of parking time, and from 5 kWh to 20 kWh in terms of charging energy. The maximum connection frequency for EV charging is 20 min. In addition, this paper develops methods for stochastic EV charging and parking space occupancy employing actual data. Based on the aforesaid renewable energy generation and the EV charging status, it is possible to develop a decision algorithm to optimal renewable energy efficiency.
KW - ORES
KW - Reinforcement learning
KW - Wind power
KW - Renewable energy
KW - EV
UR - http://www.scopus.com/inward/record.url?scp=85151157332&partnerID=8YFLogxK
U2 - 10.1007/978-981-99-0553-9_102
DO - 10.1007/978-981-99-0553-9_102
M3 - Conference contribution
SN - 9789819905522
SN - 9789819905553
VL - 1017
T3 - Lecture Notes in Electrical Engineering
SP - 979
EP - 991
BT - Proceedings of the 3rd International Symposium on New Energy and Electrical Technology
A2 - Cao, Wenping
A2 - Hu, Cungang
A2 - Chen, Xiangping
PB - Springer
CY - Singapore
ER -
