(A) Study of Spatiotemporal Pattern Analysis Using Deep Hybrid Models for Power Forecasting = 전력 예측을 위한 심층 하이브리드 모델을 이용한 시공간적 패턴 분석 연구

다국어 초록 (Multilingual Abstract)

In recent years, the rapid integration of renewable energy sources, such as solar and wind power, into smart grids has led to a transformative shift toward decentralized, sustainable power systems. However, the intermittent and variable nature of renewable power generation, coupled with the complex and fluctuating patterns of power consumption, presents significant challenges for maintaining energy stability and optimizing power management. Accurate forecasting of both power generation and consumption is crucial for effective energy resource allocation, stability, and decision-making in smart grids. Existing forecasting models often struggle to capture the intricate spatial and temporal dependencies inherent in power data, facing limitations in scalability, adaptability, and generalization to diverse datasets and evolving energy patterns. These shortcomings hinder the potential of smart grid operations, necessitating innovative approaches to overcome the challenges in power forecasting.
This dissertation proposes comprehensive methodologies consisting of four advanced hybrid models to address these critical challenges in power forecasting. The proposed models are designed to enhance the accuracy and robustness of both power generation and consumption forecasting by leveraging state-of-the-art deep learning techniques and innovative attention mechanisms.
The first method introduced the Dual Stream Network (DSN), which is specifically designed for precise power generation and consumption forecasting. The DSN incorporates two parallel learning streams: a one-dimensional Convolutional Neural Network (CNN) for capturing spatial features and a sequential learning algorithm for temporal patterns. By integrating these spatial and temporal features, the DSN generates a comprehensive feature representation, which is further refined using a self-attention mechanism. This advanced feature selection process allows the model to focus on the most relevant and informative features, leading to more accurate predictions. The second method is the Dual Sequence Prediction Model (DSPM), provides a holistic approach to forecasting both power generation and consumption. Built on a Spatiotemporal CNN (STCNN) architecture, the DSPM efficiently extracts spatial and temporal information, enabling it to predict power generation and consumption simultaneously. This dual sequence prediction capability is critical for smart grids, where balancing power supply and demand is essential for stable operations. To enhance spatial feature extraction, the DSPM incorporates a 1D spatial attention module, which captures crucial dependencies in historical data, and leverages shared weather information to streamline the learning process. By applying the Kullback–Leibler Divergence (KLD) algorithm, the DSPM ensures efficient power distribution within smart and microgrids, offering significant improvements over baseline models. The third approach introduces the Trapezoidal Attention Mechanism (TAM) within a two-stream architecture for both power generation and consumption forecasting. The first stream employs dilated causal convolutional layers to capture intricate spatial patterns, while the second stream focuses on extracting temporal information. The novel trapezoidal attention module plays a central role in refining the feature representation by applying spatial, temporal, and spatiotemporal attention. Unlike traditional attention mechanisms, TAM enhances feature maps through a unique trapezoidal structure, which incorporates skip connections from pre-TAM features to enrich the final output. By intelligently combining the outputs from both streams and attention module, TAM significantly improves the model ability to capture complex dependencies. The final and most advanced model presented is the Dual-stream Site Incremental Network (DSI-Net), developed to address the challenges of power forecasting in dynamic environments. DSI-Net is also based on a two-stream architecture that combines one-dimensional CNN for spatial feature extraction and a Graph Neural Network-based Spatial Attention Module (GNN-SA) to model complex spatial relationships across different sites. The GNN-SA module allows the network to capture interdependencies between multiple spatial locations, which is crucial for power forecasting across various geographic regions. The second stream of DSI-Net utilizes ConvLSTM layers followed by a Self-Attention Memory Module (SAMM) to capture both global and local dependencies in the temporal domain. The SAMM module employs a pairwise similarity score to aggregate temporal features, further improving the DSI-Net learning capabilities. Additionally, DSI-Net incorporates an incremental learning procedure, allowing the model to adapt dynamically to new datasets and evolving patterns, making it highly generalizable across different power systems and weather conditions.
Collectively, the proposed models—DSN, DSPM, TAM, and DSI-Net—offer a comprehensive solution to the challenges of power forecasting in modern smart grids. These models are thoroughly evaluated on diverse power datasets, including solar and wind power generation datasets, appliances, residential, regional, and industrial power consumption datasets, and PowerGrid dataset including power generation, consumption, and weather data. The dissertation presents compelling evidence that these models surpass the performance of state-of-the-art approaches, particularly in terms of error rates reduction, adaptability, and generalization to evolving patterns. By addressing key limitations in existing methods, this research contributes to advancing smart grid technologies, ensuring more reliable and efficient energy management in the face of growing renewable energy integration.

목차 (Table of Contents)

• ABSTRACT i
• LIST OF FIGURES ix
• LIST OF TABLES xi
• CHAPTER 1 Introduction 1
• 1.1 Overview 1
• 1.2 Motivation and Problem Definition 6
• 1.3 Problem Statement and Proposed Solutions 8
• 1.4 Thesis Organization 10
• CHAPTER 2 Literature Review 13
• 2.1 Overview 13
• 2.2 Statistical Methods 14
• 2.3 Machine Learning based Methods 15
• 2.4 Deep Learning based Models 16
• 2.5 Hybrid Models 17
• CHAPTER 3 Advanced Deep Learning Models for Power Generation and
• Consumption Forecasting 20
• 3.1 Overview 20
• 3.2 Data Preprocessing 21
• 3.3 Dual Stream Network for Power Generation and Consumption Forecasting
• 22
• 3.3.1 DSN Modules 23
• 3.3.2 DSN Architecture: 27
• 3.4 Dual Sequence Prediction Model for Power Generation and Consumption
• Forecasting 29
• architecture, learning procedure, PG & PC matching procedure and finally, the
• advantages of the DSPM. 30
• 3.4.1 Theoretical Background of DSPM 30
• 3.4.2 Core Block 32
• 3.4.3 DSPM Model Architecture: 33
• 3.4.4 Learning Procedure 36
• 3.4.5 Electricity Generation and Consumption Equilibrium: 39
• 3.4.6 Advantages of the DSPM 41
• 3.5 Trapezoid Attention Mechanism for Power Generation and Consumption
• Forecasting 42
• 3.5.1 TAM Learning of Spatiotemporal Features 44
• 3.5.2 Trapezoid Attention Module 49
• 3.6 Dual-stream Site Incremental Network for Power Generation and
• Consumption Forecasting 59
• 3.6.1 Spatial Stream 59
• 3.6.2 Temporal Stream 62
• 3.6.3 DSI-Net Network Architecture 66
• CHAPTER 4 Experimental Results and Discussion 69
• 4.1 Overview 69
• 4.2 Power Consumption and Generation Datasets 69
• 4.2.1 Solar Power Generation Dataset 71
• 4.2.2 Wind Power Generation Dataset 72
• 4.2.3 Building Power Consumption Dataset 72
• 4.2.4 Regional Power Consumption Dataset 73
• 4.2.5 Appliances Energy Consumption 74
• 4.2.6 Industrial Power Consumption Dataset 75
• 4.2.7 PowerGrid Dataset for Power Generation and Consumption 76
• 4.3 Experimental Setup 77
• 4.4 Evaluation Metrics 77
• 4.5 Dual Stream Network Experimental Results 79
• 4.5.1 Ablation Study 79
• 4.5.2 Performance Assessment of the DSN with State-of-the-art Methods 83
• 4.5.3 Performance Assessment of DSN over Power Consumption Datasets: . 87
• 4.6 DSPM Experimental Results 89
• 4.6.1 Single Sequence Prediction 90
• 4.6.2 Dual Sequence Prediction 93
• 4.6.3 Ablation Study 97
• 4.6.4 Visual Analysis 99
• 4.6.5 Time Complexity Analysis 100
• 4.7 TAM Experimental Results 102
• 4.7.1 Comparative Analysis 102
• 4.7.2 Ablation Study 111
• 4.7.3 Visual Analysis 114
• 4.7.4 Time Complexity Analysis 115
• viii
• 4.8 DSI-Net Experimental Results 117
• 4.8.1 Comparative Analysis 117
• 4.8.2 Visual Analysis 127
• 4.8.3 DSI-Net Generalization Test 129
• 4.8.4 Discussion and Implications of Findings of DSI-Net 132
• 4.9 Summary of the Proposed Methods 134
• CHAPTER 5 Conclusions and Future Directions 138
• 5.1 Conclusion 138
• 5.2 Future Direction 140
• BIBLIOGRAPHY 142
• 국문초록 151
• DEDICATION 157
• ACKNOWLEDGMENTS 158

참고문헌 (Reference)

1. Attention Is All You Need., A. Vaswani, Advances in neural information processing systems, vol. 30, , 2017

2. Anomaly detection: A survey, V. Kumar, V. Chandola, A. Banerjee, ACM computing surveys (CSUR), vol. 41, no. 3, pp. 1-58, , 2009

3. Self-attention convlstm for spatiotemporal prediction,, Y. Cheng, Z. Zheng, Z. Lin, M. Li, C. Yuan, vol. 34, 07 ed., pp. 11531-11538, , 2020

4. Deep learning for estimating building energy consumption, E. Mocanu, M. Gibescu, P. H. Nguyen, W. L. Kling, Sustainable Energy, Grids and Networks, vol. 6, pp. 91-99, , 2016

5. Individual household electric power consumption Data Set, A. B. Georges Hebrail, https://archive. ics. uci. edu/ml/datasets/individual+household+electric+power+consumptionOnline Available https://archive. ics. uci. edu/ml/datasets/individual+household+electric+power+consumption, , 2012

6. Building energy load forecasting using deep neural networks, K. Amarasinghe, D. L. Marino, M. Manic, in IECON 2016-42nd Annual Conference of the IEEE Industrial Electronics Society, IEEE, pp. 7046-7051, , 2016

7. CTNet: Context-based tandem network for semantic segmentation, Y. Sun, L. Zhang, J. Tang, Z. Li, IEEE Transactions on Pattern Analysis and Machine Intelligence, , 2021

8. Photovoltaic power forecasting based LSTM-Convolutional Network, X. Qi, K. Wang, H. Liu, Energy, vol. 189, p. 116225, , 2019

9. Electrical Energy Prediction with Regression-Oriented Models, in, F. Zou, T. Zhang, H. Lai, Q. Cai, L. Liao, J. Liu, The Euro-China Conference on Intelligent Data Analysis and Applications, Springer, pp. 146-154, , 2018

10. A hybrid deep learning model for short-term PV power forecasting,, K. Zhou, X. Lu, S. Yang, P. Li, vol. 259, p. 114216, , 2020

11. On post-processing day-ahead NWP forecasts using Kalman filtering, D. Yang, Solar Energy, vol. 182, pp. 179-181, , 2019

12. SpringNet: Transformer and Spring DTW for time series forecasting, Y. Lin, M. Rana, I. Koprinska, Springer, pp. 616-628, , 2020

13. Analysis of the value for unit commitment of improved load forecasts, B. F. Hobbs, S. Jitprapaikulsarn, K. A. Loparo, D. J. Maratukulam, V. Chankong, S. Konda, IEEE Transactions on Power Systems, vol. 14, no. 4, pp. 1342-1348, , 1999

14. A Hybrid Deep Learning-Based Network for Photovoltaic Power Forecasting, S. W. Baik, F. U. M. Ullah, S. Rho, Z. A. Khan, T. Hussain, A. Hussain, Complexity, vol. 2022, , 2022

15. Gated recurrent unit network-based short-term photovoltaic forecasting,, Y. Wang, Y. Chang, W. Liao, vol. 11, no. 8, p. 2163, , 2018

16. Improving electric energy consumption prediction using CNN and Bi-LSTM,, B. Vo, T. Le, S. W. Baik, E. Hwang, S. Rho, M. T. Vo, Applied Sciences, vol. 9, no. 20, p. 4237, , 2019

17. RTFN: A robust temporal feature network for time series classification,, H. Xing, Z. Xiao, S. Luo, D. Zhan, X. Xu, P. Dai, vol. 571, pp. 65-86, , 2021

18. A novel photovoltaic power forecasting model based on echo state network, Z. Wang, X. Yao, H. Zhang, Neurocomputing, vol. 325, pp. 182-189, , 2019

19. Efficientnet: Rethinking model scaling for convolutional neural networks, M. Tan, Q. Le, PMLR, pp. 6105-6114, , 2019

20. Predicting residential energy consumption using CNN-LSTM neural networks, S.-B. Cho, T.-Y. Kim, Energy, vol. 182, pp. 72-81, , 2019

21. Recurrent neural networks based photovoltaic power forecasting approach,, H. Liu, S. Zhang, H. Wang, G. Li, J. Xin, vol. 12, no. 13, p. 2538, , 2019

22. Kullback-leibler distance-based enhanced detection of incipient anomalies,, M. Madakyaru, F. Harrou, Y. Sun, vol. 44, pp. 73-87, , 2016

23. Recursive wind speed forecasting based on Hammerstein Auto-Regressive model,, O. A. Maatallah, P. Marzocca, A. Achuthan, K. Janoyan, vol. 145, pp. 191-197, , 2015

24. Bayesian optimized echo state network applied to short-term load forecasting,, L. dos Santos Coelho, V. Cocco Mariani, G. Trierweiler Ribeiro, N. Fraccanabbia, J. Guilherme Sauer, vol. 13, no. 9, p. 2390, , 2020

25. Towards efficient and effective renewable energy prediction via deep learning,, F. U. M. Ullah, T. Hussain, I. U. Haq, Z. A. Khan, S. W. Baik, vol. 8, pp. 10230-10243, , 2022

26. Deep learning based ensemble approach for probabilistic wind power forecasting,, J.-c. Peng, G.-q. Li, H.-z. Wang, G.-b. Wang, H. Jiang, Y.-t. Liu, Applied energy, vol. 188, pp. 56-70, , 2017

27. Divergence measures for statistical data processing—An annotated bibliography, M. Basseville, Signal Processing, vol. 93, no. 4, pp. 621-633, , 2013

28. The relationship between summer weather and summer loads-a regression analysis,, D. Nordmian, G. Heinemann, E. Plant, IEEE Transactions on Power Apparatus and Systems, no. 11, pp. 1144-1154, , 1966

29. A Kalman filter-based bottom-up approach for household short-term load forecast,, X. Luo, Z. Zheng, H. Chen, vol. 250, pp. 882-894, , 2019

30. A trapezoid attention mechanism for power generation and consumption forecasting, S. W. Baik, Z. A. Khan, W. Ullah, T. Hussain, IEEE Transactions on Industrial Informatics, 2023, , 2023

31. A novel CNN-GRU-based hybrid approach for short-term residential load forecasting, M. Sajjad, IEEE Access, vol. 8, pp. 143759-143768, , 2020

32. Efficient short-term electricity load forecasting for effective energy management, Z. A. Khan, Sustainable Energy Technologies and Assessments, vol. 53, p. 102337, , 2022

33. A review of combined approaches for prediction of short-term wind speed and power,, A. Tascikaraoglu, M. Uzunoglu, vol. 34, pp. 243-254, , 2014

34. Recovering missing data via matrix completion in electricity distribution systems,, I. Esnaola, L. F. Ochoa, C. Genes, D. Coca, S. M. Perlaza, 2016 IEEE 17th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2016: IEEE, pp. 1-6, , 2016

35. Regularization methods for the short-term forecasting of the Italian electric load, A. Incremona, G. De Nicolao, Sustainable Energy Technologies and Assessments, vol. 51, p. 101960, , 2022

36. DSPM: Dual sequence prediction model for efficient energy management in micro-grid,, S. W. Baik, T. Hussain, S. A. Khan, Z. A. Khan, Applied Energy, vol. 356, p. 122339, 2024, , 2024

37. Electricity demand loads modeling using AutoRegressive Moving Average (ARMA) models, D. C. Karamousantas, S. S. Pappas, P. Liatsis, L. Ekonomou, S. K. Katsikas, G. E. Chatzarakis, Energy, vol. 33, no. 9, pp. 1353-1360, , 2008

38. Multi-meteorological-factor-based Graph Modeling for Photovoltaic Power Forecasting, G. Sun, Z. Wei, T. Ding, L. Cheng, H. Zang, IEEE Transactions on Sustainable Energy, , 2021

39. Deep-based conditional probability density function forecasting of residential loads, M. Khazaei, M. Afrasiabi, M. Mohammadi, L. Stankovic, S. Afrasiabi, M. Rastegar, IEEE Transactions on Smart Grid, vol. 11, no. 4, pp. 3646-3657, , 2020

40. Different states of multi-block based forecast engine for price and load prediction,, M. Toghani, O. Abedinia, M. Mohammadi, N. Ghadimi, A. Darvishan, W. Gao, International Journal of Electrical Power & Energy Systems, vol. 104, pp. 423-435, , 2019

41. Recurrent inception convolution neural network for multi short-term load forecasting, E. Hwang, J. Kim, P. Kang, J. Moon, Energy and buildings, vol. 194, pp. 328-341, , 2019

42. Predicting wind turbine power and load outputs by multi-task convolutional LSTM model, J. Park, S. Woo, J. Park, IEEE, pp. 1-5, , 2018

43. Deep Learning Based Forecasting of Individual Residential Loads Using Recurrence Plots, A. Estebsari, R. Rajabi, in 2019 IEEE Milan PowerTech, 2019: IEEE, pp. 1-5, , 2019

44. An efficient deep learning framework for intelligent energy management in IoT networks,, T. Hussain, T. Han, J. Lloret, S. W. Baik, K. Muhammad, IEEE Internet of Things Journal, vol. 8, no. 5, pp. 3170-3179, , 2020

45. Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting, A. Mohapatra, S. N. Singh, vol. 136, pp. 758-768, , 2019

46. An Efficient Deep Learning Framework for Intelligent Energy Management in Dependable IoT, Sung Wook Baik, Tanveer Hussain, K. M. Tao Han, Jaime Lloret, , 2020

47. Forecasting the load of electrical power systems in mid-and long-term horizons: a review, S. R. Khuntia, M. A. van der Meijden, J. L. Rueda, IET Generation, Transmission & Distribution, vol. 10, no. 16, pp. 3971-3977, , 2016

48. A high precision artificial neural networks model for short-term energy load forecasting,, P.-H. Kuo, C.-J. Huang, vol. 11, no. 1, p. 213, , 2018

49. Boosting energy harvesting via deep learning-based renewable power generation prediction,, Z. A. Khan, T. Hussain, S. W. Baik, Journal of King Saud University-Science, vol. 34, no. 3, p. 101815, , 2022

50. Forecasting uncertainty parameters of virtual power plants using decision tree algorithm,, H. Sathish, R. Krishna, N. Zhou, Electric Power Components and Systems, vol. 51, no. 16, pp. 1756-1769, 2023, , 2023

51. Privacy-Preserving Collaborative Split Learning Framework for Smart Grid Load Forecasting, A. Iqbal, B. Sikdar, P. Gope, arXiv preprint arXiv:2403.01438, 2024, , 2024

52. A novel fuzzy-based ensemble model for load forecasting using hybrid deep neural networks,, A. Ikonomopoulos, N. D. Hatziargyriou, G. Sideratos, Electric Power Systems Research, vol. 178, p. 106025, , 2020

53. Deep semantic multimodal hashing network for scalable image-text and video-text retrievals, L. Jin, J. Tang, Z. Li, IEEE Transactions on Neural Networks and Learning Systems, , 2020

54. STLF-Net: Two-stream deep network for short-term load forecasting in residential buildings, H. Hawash, M. Abdel-Basset, K. Sallam, S. S. Askar, M. Abouhawwash, Journal of King Saud University-Computer and Information Sciences, , 2022

55. Deep learning methods and applications for electrical power systems: A comprehensive review, A. K. Ozcanli, M. Baysal, F. Yaprakdal, International Journal of Energy Research, vol. 44, no. 9, pp. 7136-7157, , 2020

56. Electric energy consumption prediction by deep learning with state explainable autoencoder,, S.-B. Cho, J.-Y. Kim, Energies, vol. 12, no. 4, p. 739, , 2019

57. An efficient and scalable simulation model for autonomous vehicles with economical hardware,, M. Sajjad, IEEE transactions on intelligent transportation systems, vol. 22, no. 3, pp. 1718-1732, , 2020

58. AB-Net: A Novel Deep Learning Assisted Framework for Renewable Energy Generation Forecasting,, S. W. Baik, S. U. Khan, I. U. Haq, M. Y. Lee, F. U. M. Ullah, N. Khan, Mathematics, vol. 9, no. 19, p. 2456,, , 2021

59. An efficient federated distillation learning system for multitask time series classification,, H. Xing, R. Qu, Z. Zhu, B. Zhao, Z. Xiao, IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-12, , 2022

60. Renewable energy prediction: A novel short-term prediction model of photovoltaic output power,, L.-L. Li, C.-S. Wang, S.-Y. Wen, M.-L. Tseng, Journal of Cleaner Production vol. 228, pp. 359-375, , 2019

61. Short-term load forecasting with multi-source data using gated recurrent unit neural networks,, S. Zhang, M. Liu, Y. Wang, Z. Bao, Energies, vol. 11, no. 5, p. 1138, , 2018

62. Long-term electricity consumption forecasting based on expert prediction and fuzzy Bayesian theory, S. Liu, L. Tang, C. Shao, X. Wang, S. Tian, X. Wang, vol. 167, pp. 1144-1154, , 2019

63. ESAENARX and DE-RELM: Novel schemes for big data predictive analytics of electricity load and price, N. Javaid, S. Mujeeb, Sustainable Cities and Society, vol. 51, p. 101642, , 2019

64. Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm, M.-L. Tseng, X. Zhao, L.-L. Li, R. R. Tan, vol. 242, p. 118447, , 2020

65. A novel evolutionary-based deep convolutional neural network model for intelligent load forecasting,, S. M. J. Jalali, J. P. S. Catalão, S. Nahavandi, A. Khosravi, S. Ahmadian, M. Shafie-khah, IEEE Transactions on Industrial Informatics, vol. 17, no. 12, pp. 8243-8253, 2021., , 2021

66. A novel system based on neural networks with linear combination framework for wind speed forecasting, H. Lu, N. Zhang, J. Wang, Energy Conversion and Management, vol. 181, pp. 425-442, , 2019

67. An end-to-end adaptive input selection with dynamic weights for forecasting multivariate time series, L. Munkhdalai, vol. 7, pp. 99099-99114, , 2019

68. Diving Deep into Short-Term Electricity Load Forecasting: Comparative Analysis and a Novel Framework,, S. W. Baik, T. Hussain, N. Khan, M. Y. Lee, F. U. M. Ullah, Mathematics vol. 9, no. 6, p. 611, , 2021

69. Sequential learning-based energy consumption prediction model for residential and commercial sectors,, I. U. Haq, Mathematics, vol. 9, no. 6, p. 605, , 2021

70. A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network,, K. Wang, H. Liu, X. Qi, vol. 251, p. 113315, , 2019

71. Photovoltaic power forecasting: A hybrid deep learning model incorporating transfer learning strategy,, S. Zhang, Z. Zhang, K. Yang, Y. Tang, vol. 162, p. 112473, , 2022

72. CL-Net: ConvLSTM- ased brid rchitecture for atteries’ tate of ealth and Power Consumption Forecasting,, F. U. M. Ullah, I. U. Haq, M. Y. Lee, N. Khan, S. U. Khan, Mathematics, vol. 9, no. 24, p. 3326,, , 2021

73. Deep dive into hybrid networks: A comparative study and novel architecture for efficient power prediction,, N. Khan, S. W. Baik, S. U. Khan, vol. 182, p. 113364, 2023, , 2023

74. Time series forecasting with multi-headed attention-based deep learning for residential energy consumption,, S.-J. Bu, S.-B. Cho, Energies, vol. 13, no. 18, p. 4722, , 2020

75. An improved temporal convolutional network with attention mechanism for photovoltaic generation forecasting,, Y. Xia, Z. Zhang, J. Wang, D. Wei, Engineering Applications of Artificial Intelligence, vol. 123, p. 106273, 2023, , 2023

76. Datasets on South Korean manufacturing factories’ electricit consumption and demand response participation,, E. Lee, J. Kim, K. Baek, Scientific Data, vol. 9, no. 1, pp. 1-11, , 2022

77. Modelling Electricity Consumption During the COVID19 Pandemic: Datasets, Models, Results and a Research Agenda, Z. A. Khan, p. 113204, 2023, , 2023

78. A stacked GRU-RNN-based approach for predicting renewable energy and electricity load for smart grid operation,, M. Xia, C. W. de Silva, X. Ma, H. Shao, IEEE Transactions on Industrial Informatics, vol. 17, no. 10, pp. 7050-7059, , 2021

79. Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning,, H. Zang, L. Cheng, Z. Wei, T. Ding, G. Sun, K. W. Cheung, International Journal of Electrical Power & Energy Systems, vol. 118, p. 105790, , 2020

80. Short-term photovoltaic power forecasting based on long short term memory neural network and attention mechanism, Q. Liu, L. Yang, Y. Du, H. Zhou, Y. Zhang, K. Yan, IEEE Access, vol. 7, pp. 78063-78074, , 2019

81. Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks,, V. Srikumar, A. D. Smith, A. Rahman, Applied energy, vol. 212, pp. 372-385, , 2018

82. Electrical energy prediction in residential buildings for short-term horizons using hybrid deep learning strategy,, A. Ullah, S. Rho, M. Lee, Z. A. Khan, W. Ullah, S. W. Baik, Applied Sciences, vol. 10, no. 23, p. 8634, , 2020

83. LEAP simulated economic evaluation of sustainable scenarios to fulfill the regional electricity demand in Pakistan, K. Imran, M. Shahid, K. Ullah, A. Mahmood, M. Arentsen, Sustainable Energy Technologies and Assessments, vol. 46, p. 101292, , 2021

84. Short-term prediction of residential power energy consumption via CNN and multi-layer bi-directional LSTM networks, I. U. Haq, S. Rho, F. U. M. Ullah, S. W. Baik, A. Ullah, IEEE Access, , 2019

85. Smart and intelligent energy monitoring systems: A comprehensive literature survey and future research guidelines,, T. Hussain, International Journal of Energy Research, vol. 45, no. 3, pp. 3590-3614, , 2021

86. An accurate gru-based power time-series prediction approach with selective state updating and stochastic optimization, G. Chen, W. Zheng, IEEE Transactions on Cybernetics, , 2021

87. Multistep energy consumption forecasting by metaheuristic optimi ation of time‐series anal sis and machine learning, J. S. Chou, D. N. Truong, vol. 45, no. 3, pp. 4581-4612, , 2021

88. Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine,, M. Jiang, Y. Zhou, L. Gong, N. Zhou, vol. 204, p. 117894, , 2020

89. Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks,, G. Chitalia, S. Rahman, V. Garg, M. Pipattanasomporn, vol. 278, p. 115410, , 2020

90. Probabilistic load forecasting using an improved wavelet neural network trained by generalized extreme learning machine, M. Rafiei, J. Aghaei, J. P. S. Catalão, T. Niknam, M. Shafie-Khah, IEEE Transactions on Smart Grid, vol. 9, no. 6, pp. 6961-6971, , 2018

91. DB-Net: A novel dilated CNN based multi-step forecasting model for power consumption in integrated local energy systems,, N. Khan, S. Rho, S. W. Baik, M. Y. Lee, I. U. Haq, S. U. Khan, International Journal of Electrical Power & Energy Systems, vol. 133, p. 107023, , 2021

92. CT-NET: A Novel Convolutional Transformer-Based Network for Short-Term Solar Energy Forecasting Using Climatic Information, M. Ullah, S. U. Khan, M. Munsif, N. Khan, U. Fath, S. W. Baik, Computer Systems Science & Engineering, vol. 47, no. 2, 2023, , 2023

93. Wavelet decomposition and convolutional LSTM networks based improved deep learning model for solar irradiance forecasting,, Z. Zhen, K. Li, Y. Yu, Z. Zhang, F. Wang, J. Li, vol. 8, no. 8, p. 1286, , 2018

94. Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting,, S. Wang, S. Wang, D. Wang, X. Wang, International Journal of Electrical Power & Energy Systems, vol. 109, pp. 470-479, , 2019

95. A deep learning-based forecasting model for renewable energy scenarios to guide sustainable energy policy: A case study of Korea,, C. Yoo, K. Nam, S. Hwangbo, vol. 122, p. 109725, , 2020

96. Towards efficient electricity forecasting in residential and commercial buildings: A novel hybrid CNN with a LSTM-AE based framework,, M. Lee, T. Hussain, S. W. Baik, A. Ullah, Z. A. Khan, S. Rho, Sensors, vol. 20, no. 5, p. 1399, , 2020

97. A CNN-Assisted deep echo state network using multiple Time-Scale dynamic learning reservoirs for generating Short-Term solar energy forecasting, S. Kwon, M. Ishaq, Sustainable Energy Technologies and Assessments, vol. 52, p. 102275,, , 2022

98. Significant wave height forecasting via an extreme learning machine model integrated with improved complete ensemble empirical mode decomposition, M. Ali, R. Prasad, vol. 104, pp. 281-295, , 2019

99. SolarNet: A hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting,, D. Korkmaz, vol. 300, p. 117410, , 2021

100. Very-short-term power prediction for PV power plants using a simple and effective RCC-LSTM model based on short term multivariate historical datasets,, B. Chen, Z. Chen, S. Cheng, P. Lin, Y. Lai, L. Wu, Electronics, vol. 9, no. 2, p. 289, , 2020

101. Combined electricity-heat-cooling-gas load forecasting model for integrated energy system based on multi-task learning and least square support vector machine,, Z. Tan, vol. 248, p. 119252, , 2020