Load forecasting of electric vehicle charging station based on grey theory and neural network

Feng, Jiawei; Yang, Junyou; Li, Yunlu; Wang, Haixin; Ji, Huichao; Yang, Wanying; Wang, Kang

doi:10.1016/j.egyr.2021.08.015

Cited by 35 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our case, at least at this time, since we do not have sources that generate energy other than batteries, we do not predict the state of our system, but rather, given the system, we seek to obtain the consumption that the network will have to maintain flexibility, although, like them, we will use deep learning. In [19], the authors present the improvement the accuracy in predicting future loads, in this case of electric vehicle stations, through the combination of grey models and recurrent neural networks, Long Short-Term Memory (LSTM). As in the previous paper, we do not predict the consumption of these vehicles specifically but of the total smart grid, and, from this, we estimate the optimal actions, among which the parked electric car's batteries charging or discharging.…”

Section: Related Workmentioning

confidence: 99%

Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning

et al. 2023

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning

et al. 2023

View full text Add to dashboard Cite

“…To fully consider the environmental protection factors of EV charging statin planning, the driving carbon emissions between the EV load demand site to the charging station are used. The EVs' daily total carbon emission E CO2 for charging and swapping in the planning area is represented by (5).…”

Section: Driving Guide To Charging and Swappingmentioning

confidence: 99%

“…Some approaches aim at providing the medium-long-term forecasting of EV load, for example, the overall load change of PEVs in different years [1][2][3][4]. Deep learning method are used to obtain PEV load curves [5][6][7][8][9][10][11][12]. Some approaches propose a forecast of the PEV load curves based on the EVs travel chains analysis [13] or queu-ing theory [14].…”

Section: Introductionmentioning

confidence: 99%

Coordinated planning of charging swapping stations and active distribution network based on EV spatial‐temporal load forecasting

Zhu

Borghetti

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Electric vehicles (EVs) charging swapping stations (CSSs), as well as multi‐functional integrated charging and swapping facilities (CSFs), have become important to reduce the impact of e‐mobility on the electric power distribution system. This paper presents a coordinated planning optimization strategy for CSSs/CSFs and active distribution networks (AND) that includes distributed generation. The approach is based on the application of a specifically developed spatial‐temporal load forecasting method of both plug‐in EVs (PEVs) and swapping EVs (SEVs). The approach is formulated as a mathematical programming optimization model that provides the location and sizing of new CSSs, the best active distribution network topology, the required distributed generation, and substation capacities. The developed model is solved using CPLEX, and its characteristics and performances are evaluated through a realistic case study.

show abstract

“…The influence of factors is usually considered in power load forecasting, 28,29 so in order to further improve the forecasting accuracy, factors such as temperature, electricity price, and date type have also begun to be considered in the load forecasting of electric vehicle charging stations 30‐32 . Reference [30] used meteorological data and historical load as influencing factors to accurately predict the load, while 31 considered two related factors of electricity price and temperature, using a multivariable residual correction grey model (EMGM) to predict the charging load of electric vehicles, and using LSTM for error correction 32 .…”

Section: Introductionmentioning

confidence: 99%

“…27 The influence of factors is usually considered in power load forecasting, 28,29 so in order to further improve the forecasting accuracy, factors such as temperature, electricity price, and date type have also begun to be considered in the load forecasting of electric vehicle charging stations. [30][31][32] Reference [30] used meteorological data and historical load as influencing factors to accurately predict the load, while 31 considered two related factors of electricity price and temperature, using a multivariable residual correction grey model (EMGM) to predict the charging load of electric vehicles, and using LSTM for error correction. 32 used the multi-channel 1DCNN to extract the load characteristics of different time scales under the influence factors such as meteorological and date characteristics (seasonal type, week type), and input them into the temporal convolutional network (TCN) to establish a time-dependent relationship for each characteristic and improve the prediction accuracy.…”

Section: Introductionmentioning

confidence: 99%

Load prediction of multi‐type electric vehicle charging stations based on secondary decomposition and feature selection

Guo

Jia

Zhang

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary This study proposes a load prediction method for multi‐type electric vehicle charging stations based on secondary decomposition and feature selection. First, the original load sequence of an electric vehicle charging station is decomposed into relatively simple components using variational mode decomposition (VMD). The residual term after the decomposition carries rich information; therefore, this study introduces the idea of quadratic decomposition, where the residual term is decomposed by empirical mode decomposition (EMD). Second, an in‐depth investigation of the characteristics of ordinary, energy storage, and integrated charging stations for optical storage and charging establishes the corresponding influencing factor sets, and uses the maximum information coefficient to obtain the optimal feature set. Third, for the subsequent different frequencies, this study uses the long short‐term memory (LSTM) and back‐propagation neural network (BPNN) as basic learners to conduct the prediction. Finally, this study adopts the stacking ensemble learning strategy, takes the prediction result of the base learner and the optimal feature set as the input, and then obtains the final prediction result. Taking the real load data of three different types of charging stations in a city in Northwest China as an example, the model proposed in this study is evaluated and compared with other models. Meanwhile, the model's performance under the 2 to 6 h forecast periods was compared and analyzed. The results show that the model has good stability and representation, and can be used for load prediction of electric vehicle charging stations.

show abstract

Load forecasting of electric vehicle charging station based on grey theory and neural network

Cited by 35 publications

References 9 publications

Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning

Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning

Coordinated planning of charging swapping stations and active distribution network based on EV spatial‐temporal load forecasting

Load prediction of multi‐type electric vehicle charging stations based on secondary decomposition and feature selection

Contact Info

Product

Resources

About