Short-Term Load Forecasting based on ResNet and LSTM
The DOI matches its Crossref record; 18 of the 19 references it cites were found in a registry or an index.
Abstract
Recent development of artificial intelligence (AI) makes AI applicable to diverse fields, and the smart grid is not an exception. In particular, there have been extensive researches on load forecasting using deep learning. Most existing studies have been conducted on deep neural network (DNN) and recurrent neural network (RNN). Very recently, CNN with shallow network has been studied for short-term load forecasting (STLF). In this paper, we propose a novel framework based on ResNet/LSTM combined model. The proposed model has two steps. First, ResNet extracts latent features of daily and weekly load data. Then, LSTM is applied to train the encoded feature vector with dynamics, and make prediction suitable for volatile load data. By leveraging ResNet and LSTM, the proposed model has the advantage of forecasting load data that has both regularity and inconsistency. To demonstrate the performance, we compare the proposed model with other deep learning models: multi-layer perceptron (MLP), ResNet, LSTM and ResNet/MLP combined model. The results show that the proposed ResNet/LSTM combined model has 21.3% of MAPE improvement in overall, and 25.8% of MAPE improvement for the bottom 25% group in terms of MAPE compared to MLP.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Subsequently, the concept of identity mapping is introduced in [11]. A skip or residual connection of length 2 is proposed as shown in Fig. 13.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [11]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“ResNet resolves this degradation problem by introducing a residual learning framework [14].”
BackgroundHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“LSTM is designed to resolve these issues [15].”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“We adopt batch normalization (BN) right after each convolution and before activation, as in [19].”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Short-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 2×
“In [7], LSTM is used to forecast residential load and demonstrates why LSTM is suitable for predicting highly inconsistent residential load data.”
BackgroundMethodNeural 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×
“Load forecasting can be categorized based on the period of time to be predicted, (called forecasting horizon), and there are four types: very short-term load forecasting, short-term load forecasting (STLF), medium term load forecasting and long-term load forecasting [2].”
BackgroundBuilding 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
Deep Neural Network Based Demand Side Short Term Load Forecasting
Ryu, S., Noh, J., & Kim, H. (2016) · Energies · doi:10.3390/en10010003 · Cited by 409
Self-citation
Research works printed but not linked: 2
- goodfellow, 2016, Deep Learning
- maas, 2013, Rectifier nonlinearities improve neural network acoustic models, Proc Int’l Conf Machine Learning
Cited by
Object detection using YOLO: challenges, architectural successors, datasets and applications
Diwan, T., Anirudh, G., & Tembhurne, J. V. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13644-y · Cited by 1,549
“Subsequently, the concept of identity mapping is introduced in [11].”
BackgroundPrediction of solar energy guided by pearson correlation using machine learning
Jebli, I., Belouadha, F.-Z., Kabbaj, M. I., & Tilioua, A. (2021) · Energy · doi:10.1016/j.energy.2021.120109 · Cited by 556
Choi, Y., Ryu, S., Park, K., & Kim, H. (2019) · IEEE Access · doi:10.1109/access.2019.2920932 · Cited by 246
“The typical structure of CNN consists of convolution layer, pooling layer and fully-connected layer [25].”
BackgroundSelf-citationA Hybrid LSTM Neural Network for Energy Consumption Forecasting of Individual Households
Yan, K., Li, W., Ji, Z., Qi, M., & Du, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2949065 · Cited by 224
“Along with the fast development of artificial intelligence (AI) technology, the extended deep learning methods nowadays are capable of performing very short-term energy consumption forecasting results with spectacularly high prediction accuracy [7], [22], [29], [34].”
BackgroundDeep-learning-based short-term electricity load forecasting: A real case application
Yazıcı, İ., Beyca, Ö. F., & Delen, D. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104645 · Cited by 175
Karijadi, I., & Chou, S.-Y. (2022) · Energy and Buildings · doi:10.1016/j.enbuild.2022.111908 · Cited by 159
“Neural Network [22], Support Vector Regression (SVR) [23–25], and Deep Learning with Long Short-Term Memory (LSTM) [26–28] have also been widely used in the field of building energy prediction due to their capability to model nonlinear series in the data.”
Convolutional Autoencoder Based Feature Extraction and Clustering for Customer Load Analysis
Ryu, S., Choi, H., Lee, H., & Kim, H. (2019) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2019.2936293 · Cited by 157
“ing [28]–[30], system monitoring [31], clustering [15], battery management [32], and load control [33].”
BackgroundSelf-citationShort-Term Electricity-Load Forecasting by deep learning: A comprehensive survey
Dong, Q. R., Huang, R., Cui, C., Towey, D., Zhou, L., Tian, J., & Wang, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110980 · Cited by 161
“Our review of the literature from the past decade highlights that most load forecasting articles have focused on STELF [30, 57, 61, 76, 83, 138].”
BackgroundBai, P., Liu, X., & Xie, J. (2020) · Journal of Hydrology · doi:10.1016/j.jhydrol.2020.125779 · Cited by 131
Denoising Autoencoder-Based Missing Value Imputation for Smart Meters
Ryu, S., Kim, M., & Kim, H. (2020) · IEEE Access · doi:10.1109/access.2020.2976500 · Cited by 120
Self-citationPinheiro, M. G., Madeira, S. C., & Francisco, A. P. (2023) · Applied Energy · doi:10.1016/j.apenergy.2022.120493 · Cited by 119
Very short-term residential load forecasting based on deep-autoformer
Jiang, Y., Gao, T., Dai, Y., Si, R., Hao, J., Zhang, J., & Gao, W. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.120120 · Cited by 108
Multimodal Feature Extraction and Fusion Deep Neural Networks for Short-Term Load Forecasting
Kong, Z., Zhang, C., Lv, H., Xiong, F., & Fu, Z. (2020) · IEEE Access · doi:10.1109/access.2020.3029828 · Cited by 86
“In [33] and [34], a CNN-LSTM model combining residual network (ResNet, a typical improved CNN) with LSTM and a hybrid CNN-LSTM model based on CNN and LSTM were respectively proposed for the field of STLF.”
BackgroundMethodA Review on Digital Twins and Its Application in the Modeling of Photovoltaic Installations
Dimitrova-Angelova, D., Carmona-Fernández, D., Calderón, M., Moreno, J. A. Á., & González, J. F. G. (2024) · Energies · doi:10.3390/en17051227 · Cited by 71
A Deep Learning Approach for Multi-Depth Soil Water Content Prediction in Summer Maize Growth Period
Yu, J., Tang, S. Y., Zhangzhong, L., Zheng, W., Wang, L., Wong, A. K. C., & Xu, L. (2020) · IEEE Access · doi:10.1109/access.2020.3034984 · Cited by 67
“Choi et al. [32] and Guo and Chen [33] constructed a short-term load forecasting model and a facial expression recognition model based on ResNet and LSTM, respectively.”
MethodMasood, Z., Gantassi, R., Ardiansyah, A., & Choi, Y. (2022) · Energies · doi:10.3390/en15072623 · Cited by 61
A Transfer Learning Framework for Power System Event Identification
Li, H., Ma, Z., & Weng, Y. (2022) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2022.3153445 · Cited by 60
“The reason for using Resnet is that Resnet has excellent performances in various ML tasks [36]–[38].”
MethodThanh, P. N., Cho, M.-Y., Chang, C.-L., & Chen, M.-J. (2022) · IEEE Access · doi:10.1109/access.2022.3185747 · Cited by 61
“In addition, many researchers utilized the CNN-LSTM [35]–[40] for feature extraction in the sequential input data, which improved the accurate performance.”
MethodStochastic optimization of home energy management system using clustered quantile scenario reduction
Kim, M., Park, T., Jeong, J., & Kim, H. (2023) · Applied Energy · doi:10.1016/j.apenergy.2023.121555 · Cited by 58
Self-citationLee, E., & Rhee, W. (2021) · IEEE Access · doi:10.1109/access.2021.3053317 · Cited by 57
“These hyperparameters were set the same as the hyperparameters of [14] except for the number of epochs.”
BackgroundMethodInfluentialDa, T. N., Cho, M., & Thanh, P. N. (2024) · Expert Systems · doi:10.1111/exsy.13539 · Cited by 54
“…short-term load prediction, which could improve the forecasting accuracy compared with traditional neural networks dues to their higher accuracy and better capability of managing the non-linear relationship between input and target variables (Choi et al., 2018; Kim & Cho, 2019; Kong et al., 2017).”
BackgroundQuantile-Mixer: A Novel Deep Learning Approach for Probabilistic Short-Term Load Forecasting
Ryu, S., & Yu, Y. (2023) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2023.3290180 · Cited by 56
“LSTM models are further combined with various methods to improve the accuracy (e.g., CNN [16], [17], [18], [19]), and recent vein of them utilize the attention mechanism [20], [21], [22], [23], [24], [25].”
MethodSelf-citationArif, A., Javaid, N., Aldegheishem, A., & Alrajeh, N. (2021) · Concurrency and Computation · doi:10.1002/cpe.6316 · Cited by 31
Stacked ResNet-LSTM and CORAL model for multi-site air quality prediction
Cheng, X., Zhang, W., Wenzel, A., & Chen, J. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07175-8 · Cited by 45
“This study builds a basic model termed as ResNetLSTM [31], which uses a ResNet CNN to extract important information from the historical PM2.”
MethodThe Wind and Photovoltaic Power Forecasting Method Based on Digital Twins
Wang, Y., Qi, Y., Li, J., Huan, L., Li, Y., Xie, B., & Wang, Y. (2023) · Applied Sciences · doi:10.3390/app13148374 · Cited by 42
“Choi et al. [18] proposed a power load forecasting framework combining hybrid models of ResNet [19] and LSTM, which utilized ResNet to extract potential features of the data, and then used LSTM to predict the power load data.”
BackgroundMethodFelizardo, L., Paiva, F. C. L., Graves, C. D. V., Matsumoto, É. Y., Costa, A. H. R., Del-Moral-Hernandez, E., & Brandimarte, P. (2022) · Expert systems with applications · doi:10.1016/j.eswa.2022.117259 · Cited by 30
An ADMM-LSTM framework for short-term load forecasting
Liu, S., Kong, Z., Huang, T., Du, Y., & Xiang, W. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106150 · Cited by 46
Elahe, M. F., Jin, M., & Zeng, P. (2021) · International Journal of Energy Research · doi:10.1002/er.6745 · Cited by 44
“The deep architecture of the ResNet allows multiple layers of abstraction and can learn complex relationships between feature vector and output.(166) The powerful feature extraction ability of deep architecture has also been investigated in Ref.”
BackgroundImproving Load Forecasting of Electric Vehicle Charging Stations Through Missing Data Imputation
Lee, B.-S., Lee, H., & Ahn, H. (2020) · Energies · doi:10.3390/en13184893 · Cited by 35
“Hence, the LSTM model has been successfully used in various domains, including not only the power system [13,14], but also the business process [15] and economy areas [16].”
MethodDeep residual neural network-based classification of loaded and unloaded UAV images
Seidaliyeva, U., Alduraibi, M., Ilipbayeva, L., & Смайлов, Н. (2020) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc.2020.00088 · Cited by 34
“ResNet resolves this degradation problem by introducing a residual learning framework [15].”
BackgroundMissing-Insensitive Short-Term Load Forecasting Leveraging Autoencoder and LSTM
Park, K., Jeong, J., Kim, D., & Kim, H. (2020) · IEEE Access · doi:10.1109/access.2020.3036885 · Cited by 33
“…and outputs; multiple linear regression [1], exponential smoothing [2], autoregressive integrated moving The associate editor coordinating the review of this manuscript and approving it for publication was Thomas Canhao Xu . average (ARIMA) [3], and Kalman filtering [4] fall into this category.”
BackgroundSelf-citationGrAb: A Deep Learning-Based Data-Driven Analytics Scheme for Energy Theft Detection
Tanwar, S., Kumari, A., Vekaria, D., Raboacă, M. S., Alqahtani, F. H., Tolba, A. K. R., Neagu, B.-C., & Sharma, R. (2022) · Sensors · doi:10.3390/s22114048 · Cited by 32
CNN based 2D object detection techniques: a review
Lamichhane, B. R., Srijuntongsiri, G., & Horanont, T. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1437664 · Cited by 35
A novel time-delay neural grey model and its applications
Lei, D., Li, T., Zhang, L., Liu, Q., & Li, W. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121673 · Cited by 29
Áquila, G., Morais, L. B. S., Faria, V., Lima, J. W. M., Lima, L. M. M., & de Queiroz, A. R. (2023) · Energies · doi:10.3390/en16217444 · Cited by 31
“CNNs have seen a steady increase in STLF over time, as highlighted by numerous recent studies [38,43,44].”
BackgroundResultExplainable Artificial Intelligence for State of Charge Estimation of Lithium-Ion Batteries
Chan, H. T. J., Rubeša-Zrim, J., Pichler, F., Salihi, A., Mourad, A., Šimić, I., Časni, K., & Veas, E. E. (2025) · Applied Sciences · doi:10.3390/app15095078 · Cited by 29
Automatic detection of cancer metastasis in lymph node using deep learning
Bütün, E., Uçan, M., & Kaya, M. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104564 · Cited by 28
A Time Series Data Augmentation Method Based on Dynamic Time Warping
Yang, X., Zhang, Z., Cui, X., & Cui, R. (2021) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai50917.2021.9447507 · Cited by 24
“Common deep learning frameworks for time series analysis include LSTM (Long Short-Term Memory) [3], GRU (Gate Recurrent Unit) [4], CNN (Convolutional Neural Networks) [5], ResNet (Deep Residual Networks) [6].”
MethodAnan, M., Kanaan, K., Benhaddou, D., Nasser, N., Qolomany, B., Talei, H., & Sawalmeh, A. (2024) · Energies · doi:10.3390/en17246451 · Cited by 28
Practical Operation Strategies for Energy Storage System under Uncertainty
Kim, M., Kim, K., Choi, H., Lee, S., & Kim, H. (2019) · Energies · doi:10.3390/en12061098 · Cited by 21
“We leverage the deep learning-based short-term load-forecasting using ResNet and long short-term memory (LSTM) [18] and exploit the sub-sampled electricity consumption data at every minute instead of the typical time interval of 15 min.”
BackgroundMethodSelf-citationDangi, S., Mullapudi, S. K., Raghaw, C. S., Dar, S. S., Rehman, M. Z. U., & Kumar, N. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110895 · Cited by 22
“The models used for comparison include ResNet152 (He et al., 2016), DenseNet121 (Huang et al., 2017), BiLSTM (Ghasemlounia et al., 2021), StackedLSTM (Maaliw et al., 2021), ResNet-LSTM (Choi et al., 2018), CNN-LSTM (Islam et al., 2020), and CLIP (ViT-B/32) (Radford et al., 2021).”
Transmission Network Dynamic Planning Based on a Double Deep-Q Network With Deep ResNet
Wang, Y., Zhou, X., Zhou, H. Y., Chen, L., Zheng, Z., Zeng, Q., Cai, S., & Wang, Q. (2021) · IEEE Access · doi:10.1109/access.2021.3083266 · Cited by 21
“In the field of load forecasting, a more prominent method that combines ResNet with LSTM improves the accuracy of MAPE data by 21.3% [28].”
MethodInfluentialCloud Energy Storage System Operation with Capacity P2P Transaction
Sim, J., Kim, M., Kim, D., & Kim, H. (2021) · Energies · doi:10.3390/en14020339 · Cited by 19
“We assume that load prediction is reasonably accurate [16,17] and beyond the scope of this paper.”
MethodSelf-citationFahim, B. M., Akbar, M. K., & Amayri, M. (2025) · Building Simulation · doi:10.1007/s12273-025-1236-8 · Cited by 19
“A similar technique was proposed by Choi et al. (2018) where instead of CNN, a residual network combined with LSTM is used to forecast energy consumption.”
Short-Term Load Forecasting Utilizing a Combination Model: A Brief Review
Ahmad, F. A., Liu, J., Hashim, F., & Samsudin, K. B. (2024) · International Journal of Technology · doi:10.14716/ijtech.v15i1.5543 · Cited by 14
“…(Stratigakos et al ., 2021; Wei and Pan, 2021; Bedi and Toshniwal, 2019; Imani and Ghassemian, 2019; Wang et al ., 2019; Tang et al ., 2019; Choi, Ryu, and Kim, 2018; Kim, Kim, and Choi, 2018; Bouktif et al ., 2018; Zheng, Yuan, and Chen, 2017; Di Persio and Honchar, 2017; Sri et al .,…”
BackgroundSQL Injection Attack Detection using ResNet
Sangeeta, Nagasundari, S., & Honnavalli, P. B. (2019) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt45670.2019.8944874 · Cited by 14
“SQLIA can be categorized into following [4-19] Tautology, a union based SQLIA, error-based SQLIA, blind SQLIA, Boolean SQLIA; 1) Tautology: The attacker will modify SQL queries are in such a way that the conditions always return TRUE.”
BackgroundFault Diagnosis of Power IoT System Based on Improved Q-KPCA-RF Using Message Data
Jiang, H., Kai, C., Ge, Q., Wang, Y., Xu, J., & Li, C. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3058563 · Cited by 14
Forecast Energy Consumption Time-Series Dataset using Multistep LSTM Models
Nazir, S., Aziz, A. A., Hosen, J., Aziz, N. A. A., & Murthy, G. R. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1933/1/012054 · Cited by 13
“In recent studies, the deep neural network model, particularly the recurrent neural network RNN, primarily developed to predict sequence data, has received considerable attention to predicting short-term electricity load time-series data [8], [9].”
BackgroundMethodKumari, S., Kumar, N., & Rana, P. S. (2021) · Computing and Informatics · doi:10.31577/cai_2021_1_29 · Cited by 15
“In this approach, Residual Network (ResNet) and LSTM have been used to develop the forecasting approach [5].”
MethodMulti-Location Emulation of a Process-Based Salinity Model Using Machine Learning
Qi, S., He, M., Bai, Z., Ding, Z. J., Sandhu, P., Zhou, Y., Namadi, P., Tom, B., Hoang, R., & Anderson, J. (2022) · Water · doi:10.3390/w14132030 · Cited by 12
Li, J., Xu, X., Wang, Y., Chen, R., & Liu, C. (2023) · IEEE Access · doi:10.1109/access.2023.3264563 · Cited by 11
“memory forecasting techniques [41], [42], [43] are used for wind, PV and load power forecasting.”
MethodAn Image Processing-based and Deep Learning Model to Classify Brain Cancer
Alshahrani, A., Al-Amoudi, W., Bazaraah, R., Al-Sharief, A., & Farouquee, H. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.7803 · Cited by 11
“ResNet is a residual learning framework to address the degradation issue [12].”
BackgroundPower System Decision Making in the Age of Deep Learning: A Comprehensive Review
Lim, Y., Son, M., Park, K., Kim, M., Song, K., Lee, H., & Kim, H. (2025) · Energies · doi:10.3390/en18184867 · Cited by 10
Self-citationLiu, R., Lu, L., Ge, Y., Dong, L., & Zhou, J. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109038 · Cited by 10
Short-Term Power Load Forecasting Method Based on GRU-Transformer Combined Neural Network Model
Mao, W., Yu, S., & Chen, W. (2024) · Journal of Computing and Information Technology · doi:10.20532/cit.2024.1005783 · Cited by 10
“Power load forecasting is based on the changes of historical load data, time factors and meteorological factors, and the analysis of traditional or deep learning model methods is used to assess the demand load of the region [18].”
A PCA-based variable ranking and selection approach for electric energy load forecasting
Bezerra, F. E., Grassi, F., Dias, C. G., & Pereira, F. H. (2022) · International Journal of Energy Sector Management · doi:10.1108/ijesm-12-2019-0009 · Cited by 10
Short-term Load Forecasting with Deep Boosting Transfer Regression
Wu, D., Xu, Y., Jenkin, M. R. M., Wang, J., Li, H., Liu, X., & Dudek, G. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838983 · Cited by 10
“For example, methods based on feedforward neural networks (FNNs) for STLF are evaluated in [23], and a method based on convolutional neural networks (CNNs) for STLF is described in [24].”
MethodAnalysis of Predictive Models for Revealing Household Characteristics using Smart Grid Data
Aly, H., Al-Ali, A. K., Al-Ali, A. K., & Malluhi, Q. M. (2023) · IEEE PES Innovative Smart Grid Technologies Europe · doi:10.1109/isgteurope56780.2023.10407215 · Cited by 9
“2) ResNet: ResNet (Residual Neural Network) [13] is a deep learning model that not only achieved state-of-the-art performance in a wide range of computer vision tasks, but was also a high performer in various domains, including smart-grid related problems [14], [15].”
BackgroundSagheer, A. M., AlHamaydeh, M. H., Fayaz, J., & Al-Sadoon, Z. A. (2024) · Structures · doi:10.1016/j.istruc.2024.106484 · Cited by 9
Short-Term Load Forecasting Using Regularized Greedy Forest-Based Ensemble Model
Yiu, B. W.-K., Zhang, T., & Lee, C. W. (2024) · IEEE Access · doi:10.1109/access.2024.3441642 · Cited by 9
“In [24], a combined model based on ResNet and LSTM has been proposed.”
MethodXu, C., Inuiguchi, M., Hayashi, N., Raymond, W. J. K., Mokhlis, H., & Illias, H. A. (2025) · IEEE Access · doi:10.1109/access.2025.3548990 · Cited by 11
Urošević, V., & Dimitrijević, S. (2021) · Telecommunications Forum (TELFOR) · doi:10.1109/telfor52709.2021.9653206 · Cited by 9
Li, D., Yang, F., Miao, S., Gan, Y., Yang, B., & Zhang, Y. (2023) · Journal of Renewable and Sustainable Energy · doi:10.1063/5.0132544 · Cited by 9
A Missing Data Compensation Method Using LSTM Estimates and Weights in AMI System
Kwon, H.-R., & Kim, P. (2021) · Information · doi:10.3390/info12090341 · Cited by 9
Prediction of Weekly Load using Stacked Bidirectional LSTM and Stacked Unidirectional LSTM
Nam, Y.-J., & Jo, H.-H. (2020) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2020.18.9.9 · Cited by 9
Gu, X., Wang, M., Wang, Y., Zhou, G., & Ni, T. (2023) · Crop Protection · doi:10.1016/j.cropro.2023.106489 · Cited by 8
Optimizing Load Forecasting in Smart Grids with AI-Driven Solutions
Ahamed, A., Tarafder, M. T. R., Rimon, S. M. T. H., Hasan, E., & Amin, M. A. (2024) · IEEE International Conference on Data and Software Engineering (ICoDSE) · doi:10.1109/icodse63307.2024.10829903 · Cited by 8
“Techniques like Convolutional Neural networks and blending models like ResNet architecture with LSTM assist in better modeling of time series data [4].”
Deep Learning Models for Predicting COVID-19 Using Chest X-Ray Images
Muhammad, L. J., Algehyne, E. A., Usman, S. S., Mohammed, I. A., Abdulkadir, A., Jibrin, M. B., & Malgwi, Y. M. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-75945-2_6 · Cited by 12
Short-term load forecasting method of IES based on RLA neural network with dual signal processing
Lv, Y., Shi, Y., Li, Z., & Deng, D. (2024) · Energy and Buildings · doi:10.1016/j.enbuild.2024.114074 · Cited by 7
Short-term Solar Irradiance Forecasting Based on Multi-Branch Residual Network
Ziyabari, S., Du, L., & Biswas, S. (2020) · IEEE Energy Conversion Congress and Exposition (ECCE) · doi:10.1109/ecce44975.2020.9235930 · Cited by 7
“In [26], the author ensembles ResNet and LSTM.”
BackgroundBockrath, S., Wachtler, J., Wenger, M., Schwarz, R., Pruckner, M., & Lorentz, V. (2023) · IEEE Space Computing Conference (SCC) · doi:10.1109/scc57168.2023.00023 · Cited by 5
Energy Demand Forecasting Using Temporal Variational Residual Network
Ashebir, S., & Kim, S. (2025) · Forecasting · doi:10.3390/forecast7030042 · Cited by 4
“Our findings highlight the advantages of a hybrid dimension reduction-based deep learning framework over single deep learning models, emphasizing the importance of dimension reduction through multilevel feature extraction using ResNet, as described in reference [50].”
Kulkarni, S., Shenoy, P. D., & Venugopal, K. R. (2025) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200534 · Cited by 6
Short-term load forecasting based on DenseNet-LSTM fusion model
Liyun, P., Wenjun, Z., Wang, S., & Han, L. (2021) · IEEE International Conference on Energy Internet (ICEI) · doi:10.1109/icei52466.2021.00021 · Cited by 4
Research on Short-Term Electricity Load Forecasting Model Based on SWT-ResNet-LSTM
Wang, Y., Qian, Y., Zheng, J., Hu, Z., Chen, Q., Ding, K., & Tian, S. (2023) · doi:10.1109/epee59859.2023.10351934 · Cited by 4
“Therefore, [10] used Residual Network (ResNet) [11] to alleviate the problems of gradient disappearance and grid degradation in the network training process, and proposed a method based on ResNet-LSTM.”
MethodStatistical and Machine Learning Approaches for Electrical Energy Forecasting
Machado, S., & Xingquan Zhu, A. (2025) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70033 · Cited by 3
Kharisudin, I., Arissinta, I. O., Aulia, S. A., Dani, M. A. Q., & Wijaya, G. K. (2025) · BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN · doi:10.30598/barekengvol20iss1pp0105-0122 · Cited by 3
“Very Short-Term Load Forecasting (VSTLF) encompasses a period from several minutes up to an hour ahead [8], while Short-Term Load Forecasting (STLF) extends from one hour up to one week ahead.”
Enhanced Object Detection Based on YOLOv9 for Marine Life
Pawar, A., Handa, A., Pujari, M., & Hema, D. D. (2024) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn63059.2024.10847536 · Cited by 3
“[11, 12] A faster R-CNN was essential to achieving high detection precision and getting closer to real-time object detection capabilities.”
Monthly Load Forecasting Based on an ARIMA-BP Model: A Case Study on Shaoxing City
Wang, Y., Zhang, W., Li, X., Wang, A., Wu, T., & Bao, Y. (2020) · Asia-Pacific Power and Energy Engineering Conference (APPEEC) · doi:10.1109/appeec48164.2020.9220521 · Cited by 3
“[10] proposed a short-term load forecasting model based on residual network long short-term memory, which can This work is supported in part by National Natural Science Foundation of China (Project no.”
BackgroundShape-Aided Similar Day Selection Method for Short Term Load Forecasting
Shi, M., & He, X. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-6372-7_23 · Cited by 2
Federated Learning with LSTM Neural Network for Regional Load Forecasting
You, B., Xing, C., Yu, Q., Zhang, M., he, Z., Zeng, L., & Liu, C. (2024) · International Conference on Harmonics and Quality of Power · doi:10.1109/ichqp61174.2024.10768807 · Cited by 2
“[8] proposed a model combining ResNet and LSTM for short-term load forecasting.”
Research on Acoustic Scene Classification Based on Multiple Mixed Convolutional Neural Networks
Yang, L., Zhang, Z., & Hu, J. (2019) · IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · doi:10.1109/icsidp47821.2019.9172922 · Cited by 2
COMPARISON OF LINEAR REGRESSIONS AND NEURAL NETWORKS FOR FORECASTING COVID-19 RECOVERED CASES
Setiyorini, T., & Frieyadie, F. (2022) · Jurnal Riset Informatika · doi:10.34288/jri.v4i3.409 · Cited by 2
“The neural network is the deep learning method developed at this time to forecast energy consumption with very high predictive accuracy (Choi et al., 2018).”
MethodSmall Object Recognition Using a Spatio-Temporal Neural Network
Liang, Z., Liu, S., Shi, W., Wang, X., & Jiang, F. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428458 · Cited by 2
“Complying with some successful works[26, 25], we set two LSTM cells to form the LSTM state transfer subnet, and hidden units between LSTM cells as 1024.”
BackgroundTime Series Classification using Improved Deep Learning Approach for Agriculture Field Mapping
Sencaki, D. B., Putri, M. N., Sanjaya, H., Prayogi, H., Anatoly, N., Afifuddin, A., Putra, P. K., Grace, T., & Muhammad Luthfi, A. (2022) · IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS) · doi:10.1109/agers56232.2022.10093560 · Cited by 2
“Later on, we also compare the performance with one of the most renowned DL models of ResNet[14] which is commonly used in different applications such as image classification, segmentation[15] , and time-series dataset classification[16].”
ResultIncorporating Taylor Series and Recursive Structure in Neural Networks for Time Series PredictionPreprint
Mau, J., & Moon, K. R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.06441 · Cited by 2
“Alternatively ResNet (Residual Neural Network) can be used for time series analysis (Choi et al., 2018).”
BackgroundMethodEstimating Lithium-Ion Battery Health Parameters Using Deep Learning Techniques
Kakati, P., Dandotiya, D., Joshi, A. K., Singh, R. R., & Ramesh, C. S. (2024) · Lecture notes in mechanical engineering · doi:10.1007/978-981-97-3648-5_15 · Cited by 2
Multivariate Short-term Load Forecasting Using Deep Learning Algorithms
Altunkaya, D., & Yılmaz, B. (2020) · The Eurasia Proceedings of Science Technology Engineering and Mathematics · Cited by 1
A Study for Sign Language Detection Using Deep Learning Methods
Tewari, D., Mishra, S., Kumar, A., & Chaudhry, R. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-3148-2_41 · Cited by 1
Load2Load: Day-ahead load forecasting at aggregated level
Yılmaz, M. B. (2022) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.55730/1300-0632.3960 · Cited by 1
Intelligent Explosivity Prediction of Underground Coal Mines using a Deep Parametrised Residual RNN
Sharma, M., Maity, T., Vatsa, A., & Banerjee, S. (2022) · International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON) · doi:10.1109/smartgencon56628.2022.10083556 · Cited by 1
Short term load forecasting using LSTM ensembled network on utility scale load demandPreprint
Fattah, F. K., Mojumder, P., Fuad, A. A., Ahmad, M., & Hossain, E. (2022) · doi:10.36227/techrxiv.16807213.v3 · Cited by 1
Short term load forecasting using LSTM ensembled network on utility scale load demand.Preprint
Fattah, F. K., Mojumder, P., Fuad, A. A., Ahmad, M., & Hossain, E. (2021) · doi:10.36227/techrxiv.16807213.v2
“Some of those hybrid models include CNN-LSTM [34], [35], MLRLSTM [45], EMD-LSTM [46], and Resnet-LSTM [47], all of which have proven to significantly improve the error factor in the forecasts of standalone LSTM models.”
MethodShort term load forecasting using LSTM ensembled network on utility scale load demandPreprint
Fattah, F. K., Mojumder, P., Fuad, A. A., Ahmad, M., & Hossain, E. (2021) · doi:10.36227/techrxiv.16807213
“Some of those hybrid models include CNN-LSTM [46], [48], MLR-LSTM [61], EMD-LSTM [62], and Resnet-LSTM [63], all of which have proven to significantly improve the error factor in the forecasts of standalone LSTM models.”
MethodA Comparative Analysis Between LSTM and LSTM Ensembled Strategy for Short-term Load ForecastingPreprint
Fattah, F. K., Mojumder, P., Fuad, A. A., Ahmad, M., & Hossain, E. (2021) · doi:10.36227/techrxiv.16807213.v1
Constructing Renewable Energy Systems Using Big Data Applications
Sohaee, N. (2022) · Springer eBooks · doi:10.1007/978-3-030-72322-4_176-1
Das, S., Chowdhury, S., Chandra, J. K., & Sen, S. (2022) · IEEE Calcutta Conference (CALCON) · doi:10.1109/calcon56258.2022.10059693
“To eliminate this issue in [13] ResNet was used along with the long short term memory (LSTM) for short term load forecasting, where ResNet extracts the required feature while the LSTM holds the context of the data.”
MethodEvaluation of Deep Learning Approaches for Lung Pneumonia Classification
Asha, S., Usharani, S., & Ola, S. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-8136-4_31
Constructing Renewable Energy Systems Using Big Data Applications
Sohaee, N. (2023) · Springer eBooks · doi:10.1007/978-3-030-97940-9_176
ธาราวัชรศาสตร์, ก. (2022) · Chula Digiverse · doi:10.58837/chula.the.2022.846
Metadata
- Authors
- Choi, H., Ryu, S., & Kim, H.
- Affiliations
- Sogang University (KR)
- Venue
- 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)
- Publisher
- IEEE
- Published
- 2018-10
- Pages
- 1-6
- OpenAlex
- W2907277777
- Cited by
- 103
- References
- 19
- Citations by year
- 2026: 2 · 2025: 12 · 2024: 16 · 2023: 14 · 2022: 24 · 2021: 19 · 2020: 10 · 2019: 6
- FWCI
- 13.96
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) (publishedVersion)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Energy Load and Power Forecasting
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Keywords
- short-term load forecasting, ResNet, LSTM, CNN-LSTM hybrid model, smart grid, feature extraction, time series forecasting
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.