Electric Vehicle Charging Load Forecasting: A Comparative Study of Deep Learning Approaches
Open accessThe DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
Load forecasting is one of the major challenges of power system operation and is crucial to the effective scheduling for economic dispatch at multiple time scales. Numerous load forecasting methods have been proposed for household and commercial demand, as well as for loads at various nodes in a power grid. However, compared with conventional loads, the uncoordinated charging of the large penetration of plug-in electric vehicles is different in terms of periodicity and fluctuation, which renders current load forecasting techniques ineffective. Deep learning methods, empowered by unprecedented learning ability from extensive data, provide novel approaches for solving challenging forecasting tasks. This research proposes a comparative study of deep learning approaches to forecast the super-short-term stochastic charging load of plug-in electric vehicles. Several popular and novel deep-learning based methods have been utilized in establishing the forecasting models using minute-level real-world data of a plug-in electric vehicle charging station to compare the forecasting performance. Numerical results of twelve cases on various time steps show that deep learning methods obtain high accuracy in super-short-term plug-in electric load forecasting. Among the various deep learning approaches, the long-short-term memory method performs the best by reducing over 30% forecasting error compared with the conventional artificial neural network model.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“[31] and aimed to relief the gradient vanish problem of original RNN.”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014) · Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · doi:10.3115/v1/w14-4012 · Cited by 7,099 · cited 7×
“In Table 2, we can find that the LSTM proves to be more accurate than the ANN, RNN, GRU, SAE, Bi-LSTM models for the minute-level load forecasting.”
MethodInfluentialFramewise phoneme classification with bidirectional LSTM and other neural network architectures
Graves, A., & Schmidhuber, J. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.06.042 · Cited by 5,839
Backpropagation through time: what it does and how to do it
Werbos, P. J. (1990) · Proceedings of the IEEE · doi:10.1109/5.58337 · Cited by 4,879 · cited 2×
“The model training method for LSTM is the well adopted back-propagation through time (BPTT) [45].”
MethodGreedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 1×
“In this case study, six featured and popular models are selected for performance comparison including ANN, RNN [49], canonical LSTM, gated recurrent units (GRU) [50], stacked auto-encoders (SAEs) [51] and the bi-directional long short-term memory (Bi-LSTM) [52].”
Method(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · cited 2×
“Featured deep learning based network include convolutional neural network (CNN), recurrent neural network (RNN), Deep Boltzmann Machines [29], Stacked AutoEncoder [30], etc. Long short-term memory is an improved RNN, which was first introduced by Hochreiter et al. [31] and aimed to relief the gradient vanish problem o…”
BackgroundShort-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network
Kong, W., Dong, Z. Y., Jia, Y., Hill, D. J., Xu, Y., & Zhang, Y. (2019) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2017.2753802 · Cited by 2,645 · cited 1×
“[33] applied LSTM to the residential load forecasting, and LSTM showed the best performance compared to other counterparts.”
MethodNeural networks for short-term load forecasting: a review and evaluation
Hippert, H. S., Pedreira, C. E., & Souza, R. C. (2001) · IEEE Transactions on Power Systems · doi:10.1109/59.910780 · Cited by 2,221 · cited 1×
“Due to the strong adaptive learning and generalization ability, artificial neural network (ANN) has become successful in delivering load forecasting tasks [11].”
BackgroundDommel, H., & Tinney, W. (1968) · IEEE Transactions on Power Apparatus and Systems · doi:10.1109/tpas.1968.292150 · Cited by 1,664 · cited 1×
“The minute-level extra-short-term model plays a crucial role in the operation and maintenance of the EV charging aggregators as well as in the power flow analysis and control [17].”
BackgroundElectric load forecasting using an artificial neural network
Park, D.-C., El-Sharkawi, M. A., Marks, R. J., Atlas, L., & Damborg, M. J. (1991) · IEEE Transactions on Power Systems · doi:10.1109/59.76685 · Cited by 1,440 · cited 1×
“Model based load forecasting techniques include statistical models using recursive and traditional mathematical tools [5–8], and artificial intelligence models involving various state-of-the-art machine learning approaches [9,10].”
MethodModeling of Load Demand Due to EV Battery Charging in Distribution Systems
Qian, K., Zhou, C., Allan, M., & Yuan, Y. (2011) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2010.2057456 · Cited by 1,268 · cited 1×
“[39] proposed a methodology for modeling and analyzing the load in a distribution system considering PEV battery charging, and adopted Monte Carlo simulation in scenario generations.”
MethodRaza, M. Q., & Khosravi, A. (2015) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2015.04.065 · Cited by 1,021 · cited 1×
“Load forecasting can be categorized into short-, medium- and long-term depending on the time span or resolution [1].”
BackgroundBouktif, S., Fiaz, A., Ouni, A., & Serhani, M. (2018) · Energies · doi:10.3390/en11071636 · Cited by 915 · cited 1×
“[35] proposed an optimal LSTM model for electric load forecasting using feature selection and genetic algorithm.”
MethodLoad Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001
Chen, B.-J., Chang, M.-W., & Lin, C.-J. (2004) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2004.835679 · Cited by 841 · cited 1×
“Model based load forecasting techniques include statistical models using recursive and traditional mathematical tools [5–8], and artificial intelligence models involving various state-of-the-art machine learning approaches [9,10].”
MethodA review of data-driven approaches for prediction and classification of building energy consumption
Wei, Y., Zhang, X., Shi, Y., Xia, L., Pan, S., Wu, J., Han, M., & Zhao, X. (2018) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2017.09.108 · Cited by 803 · cited 1×
“In dealing with the load forecasting and energy prediction tasks, data-driven approaches have achieved good results compared to other analytical models [48].”
ResultSelf-citationZheng, H., Yuan, J., & Chen, L. (2017) · Energies · doi:10.3390/en10081168 · Cited by 635 · cited 1×
“[34] presented a hybrid LSTM model for short-term load forecasting and obtained comparatively good results compared with other counterparts.”
ResultThe Time Series Approach to Short Term Load Forecasting
Hagan, M. T., & Behr, S. M. (1987) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.1987.4335210 · Cited by 546 · cited 1×
“[19] proposed an autoregressive moving average model (ARMA) model prediction method, and Juberias et al.”
MethodYu, F., & Xu, X. (2014) · Applied Energy · doi:10.1016/j.apenergy.2014.07.104 · Cited by 536
Building energy load forecasting using Deep Neural Networks
Marino, D. L., Amarasinghe, K., & Manic, M. (2016) · IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2016.7793413 · Cited by 522 · cited 1×
“[32] used long-short-term memory (LSTM) for building energy load forecasting and discussed the effect of neuron nodes numbers on the forecasting error.”
MethodA spatial–temporal model for grid impact analysis of plug-in electric vehicles
Mu, Y., Wu, J., Jenkins, N., Jia, H., & Wang, C. (2014) · Applied Energy · doi:10.1016/j.apenergy.2013.10.006 · Cited by 424
Day-ahead load forecast using random forest and expert input selection
Lahouar, A., & Slama, J. B. H. (2015) · Energy Conversion and Management · doi:10.1016/j.enconman.2015.07.041 · Cited by 390 · cited 1×
“The authors in [24] used a random forest approach to build a load forecasting model and the inputs are refined by expert feature selection using fuzzy rules.”
MethodSupport vector machines with simulated annealing algorithms in electricity load forecasting
Pai, P.-F., & Hong, W.-C. (2005) · Energy Conversion and Management · doi:10.1016/j.enconman.2005.02.004 · Cited by 388 · cited 1×
“Pai and Hong [22] applied support vector machine (SVM) to load forecasting and used the simulated annealing algorithm to select the kernel parameters.”
MethodRegression based peak load forecasting using a transformation technique
Haida, T., & Muto, S. (1994) · IEEE Transactions on Power Systems · doi:10.1109/59.331433 · Cited by 350
Yang, Z., Li, K., & Foley, A. (2015) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2015.06.007 · Cited by 228 · cited 1×
“Other environmental concerns such as urban air quality and related health impacts have also prompted policy makers and stakeholders to opt for the popularization of electric vehicles (EVs) [3] in replacing traditional internal combustion engine (ICE)”
BackgroundSelf-citationRecurrent neural networks for short-term load forecasting
Vermaak, J., & Botha, E. C. (1998) · IEEE Transactions on Power Systems · doi:10.1109/59.651623 · Cited by 227
Short-Term Load Forecasting for Electric Vehicle Charging Stations Based on Deep Learning Approaches
Zhu, J., Yang, Z., Guo, Y., Zhang, J., & Yang, H. (2019) · Applied Sciences · doi:10.3390/app9091723 · Cited by 184 · cited 1×
“In our previous study [43], the deep learning method is used for hourly level PEV load forecasting and obtained well performance.”
MethodSelf-citationLu, Y., Li, Y., Xie, D. G., Wei, E., Bao, X., Chen, H., & Zhong, X. (2018) · Energies · doi:10.3390/en11113207 · Cited by 155 · cited 1×
“[42] utilized a random forest to forecast the 15 min level EV charging data.”
MethodA Scalable Stochastic Model for the Electricity Demand of Electric and Plug-In Hybrid Vehicles
Alizadeh, M., Scaglione, A., Davies, J., & Kurani, K. S. (2013) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2013.2275988 · Cited by 144 · cited 1×
“[40] proposed a stochastic model based on queuing theory for PEV charging load.”
MethodUtilization of Electric Vehicles and Their Used Batteries for Peak-Load Shifting
Aziz, M., Oda, T., Mitani, T., Watanabe, Y., & Kashiwagi, T. (2015) · Energies · doi:10.3390/en8053720 · Cited by 140 · cited 1×
“Accurate and efficient load forecasting for PEV charging is critical for the maintenance and operation of charging stations [36,37].”
BackgroundA new ARIMA model for hourly load forecasting
Juberías, G., Yunta, R., Moreno, J. G., & Mendivil, C. (1999) · IEEE PES Transmission and Distribution Conference and Exhibition · doi:10.1109/tdc.1999.755371 · Cited by 106 · cited 1×
“[20] established the autoregressive integral moving average model (ARIMA) model to achieve load forecasting.”
MethodGuo, Y., Nazarian, E., Ko, J., & Rajurkar, K. P. (2014) · Energy Conversion and Management · doi:10.1016/j.enconman.2013.12.060 · Cited by 95 · cited 1×
“[23] utilized time-indexed autoregressive with exogenous terms (ARX) models with two-stage weighted least squares regression for modeling hourly cooling load.”
MethodSelf-citationFault Diagnosis for Energy Internet Using Correlation Processing-Based Convolutional Neural Networks
Yang, D., Pang, Y., Zhou, B., & Li, K. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2919940 · Cited by 94 · cited 1×
“Deep learning methods have been on the spotlight and seen remarkable success in image semantic segmentation and feature classification [12–14], natural language processing [15] and various computational extensive science and engineering fields [16].”
BackgroundForecasting charging load of plug-in electric vehicles in China
Luo, Z., Song, Y., Hu, Z., Xu, Z., Yang, X., & Zhan, K. (2011) · IEEE Power Engineering Society General Meeting · doi:10.1109/pes.2011.6039317 · Cited by 80 · cited 1×
“[41] proposed a Monte Carlo simulation based model to forecast the charging load of the PEVs in China.”
BackgroundModeling and Forecasting Electric Vehicle Consumption Profiles
Gérossier, A., Girard, R., & Kariniotakis, G. (2019) · Energies · doi:10.3390/en12071341 · Cited by 79 · cited 1×
“Accurate and efficient load forecasting for PEV charging is critical for the maintenance and operation of charging stations [36,37].”
BackgroundMahmoud, T. S., Habibi, D., Hassan, M. Y., & Bass, O. (2015) · Energy Conversion and Management · doi:10.1016/j.enconman.2015.10.066 · Cited by 44 · cited 1×
“[27] utilized a tuning fuzzy system and ANN method for modeling the medium voltage load.”
MethodShankar, R., Chatterjee, K., & Chatterjee, T. K. (2012) · Journal of Engineering Science and Technology Review · doi:10.25103/jestr.051.17 · Cited by 35
Modeling of Electric Vehicle batteries using RBF neural networks
Zhang, C., Yang, Z., & Li, K. (2014) · International Conference on Computing, Management and Telecommunications · doi:10.1109/commantel.2014.6825590 · Cited by 14 · cited 1×
“However, the rapid development of the EV industry is introducing new challenges to the existing power system structure owing to their large battery capacity [4] and highly stochastic individual charging behavior.”
BackgroundSelf-citation
Cited by
Sadeghian, O., Oshnoei, A., Mohammadi-ivatloo, B., Vahidinasab, V., & Anvari-Moghaddam, A. (2022) · Journal of Energy Storage · doi:10.1016/j.est.2022.105241 · Cited by 424
Machine Learning Approaches for EV Charging Behavior: A Review
Shahriar, S., Al-Ali, A. R., Osman, A. H., Dhou, S., & Nijim, M. (2020) · IEEE Access · doi:10.1109/access.2020.3023388 · Cited by 280
Daily electric vehicle charging load profiles considering demographics of vehicle users
Zhang, J., Yan, J., Liu, Y., Zhang, H., & Lv, G. (2020) · Applied Energy · doi:10.1016/j.apenergy.2020.115063 · Cited by 259
Li, Y., He, S., Li, Y., Ge, L., Lou, S., & Zeng, Z. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3168577 · Cited by 132
“The above algorithms rely on the structured input data with a specific human-defined feature, which requires cumbersome engineering-based efforts [12].”
BackgroundEnsemble Learning for Charging Load Forecasting of Electric Vehicle Charging Stations
Huang, X., Wu, D., & Boulet, B. (2020) · 2020 IEEE Electric Power and Energy Conference (EPEC) · doi:10.1109/epec48502.2020.9319916 · Cited by 76
“…showed its impressive potential in many research area such as natural language processing [12], computer vision [13], etc., some researchers adopted the Long Short-Term Memory (LSTM) [14], an improved Recurrent Neural Network (RNN) algorithm, to solve load forecasting issues [15] [16] [17] [18].”
Method
Metadata
- Authors
- Zhu, J., Yang, Z., Mourshed, M., Guo, Y., Zhou, Y., Chang, Y., Wei, Y., & Feng, S.
- Venue
- Energies
- Publisher
- MDPI AG
- Published
- 2019-07-13
- Volume
- 12
- Issue
- 14
- Pages
- 2692
- ISSN
- 1996-1073 (ISSN-L)
- OpenAlex
- W2962444989
- Cited by
- 242
- References
- 42
- FWCI
- 6.26
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.