Olamide Jogunola
ABSTRACT
As energy forecasting is paramount to efficient grid planning, this work presents a comparative analysis of different hybrid deep learning frameworks for energy forecasting in applications such as energy consumption and trading. Specifically, we developed hybrid architectures comprising of Convolutional Neural Network (CNN), an Autoencoder (AE), Long Short-Term Memory (LSTM) and Bi-directional LSTM (BLSTM). We use the individual household electric power consumption dataset by University of California, Irvine to evaluate the proposed frameworks. We evaluated and compared the result of these frameworks using several error metrics. The results show an average MSE of ∼ 0.01 across all developed frameworks. In addition, the CNN-LSTM framework performed the least with a 20% and 10% higher RMSE and MAE to other frameworks respectively, while CNN-BiLSTM achieved the least computation time.
- Musaed Alhussein, Khursheed Aurangzeb, and Syed Irtaza Haider. 2020. Hybrid CNN-LSTM model for short-term individual household load forecasting. IEEE Access 8(2020), 180544–180557.Google Scholar
Cross Ref
- E Escobar Avalos, MA Rodríguez Licea, H Rostro González, A Espinoza Calderón, AI Barranco Gutiérrez, and FJ Pérez Pinal. 2020. Comparative Analysis of Multivariable Deep Learning Models for Forecasting in Smart Grids. In Intl. Autumn Meeting on Power, Electronics and Computing (ROPEC), Vol. 4. IEEE, Ixtapa, Guerrero, Mexico, 1–6.Google Scholar
- Mengmeng Cai, Manisa Pipattanasomporn, and Saifur Rahman. 2019. Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques. Applied energy 236(2019), 1078–1088.Google Scholar
- Zhaojing Cao, Can Wan, Zijun Zhang, Furong Li, and Yonghua Song. 2019. Hybrid ensemble deep learning for deterministic and probabilistic low-voltage load forecasting. IEEE Trans. Power Syst. 35, 3 (2019), 1881–1897.Google ScholarCross Ref
- Gopal Chitalia, Manisa Pipattanasomporn, Vishal Garg, and Saifur Rahman. 2020. Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks. Applied Energy 278(2020), 115410.Google ScholarCross Ref
- Google. 2021. Welcome to Colaboratory. Available at https://colab.research.google.com/, Accessed: 2021-10-16.Google Scholar
- G Hebrail and A Berard. 2021. Individual Household Electric Power Consumption Data Set. Available at https://archive.ics.uci.edu/ml/datasets/individual+household+electric+ power+consumption, Accessed: 2021-10-16.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.Google ScholarDigital Library
- Ying-Yi Hong and Rolando Pula. 2020. Comparative studies of different methods for short-term locational marginal price forecasting. In Intl. Conf. Green Tech. and Sust. Dev. (GTSD). IEEE, Ho Chi Minh City, Vietnam, 527–532.Google ScholarCross Ref
- Priyam Jain, Aman Gautam, Rahul Shukla, RK Porwal, Debasis De, SR Narasimhan, and KVS Baba. 2020. Planning and Operation of Indian Power System during the Pan India Lights Off Event. In 21st National Power Syst. Conf. (NPSC). IEEE, Gandhinagar, India, 1–6.Google ScholarCross Ref
- Olamide Jogunola, Bamidele Adebisi, Augustine Ikpehai, Segun I. Popoola, Guan Gui, Haris Gačanin, and Song Ci. 2021. Consensus Algorithms and Deep Reinforcement Learning in Energy Market: A Review. IEEE Internet of Things Journal 8, 6 (2021), 4211–4227. https://doi.org/10.1109/JIOT.2020.3032162Google ScholarCross Ref
- Olamide Jogunola, Yakubu Tsado, Bamidele Adebisi, and Mohammad Hammoudeh. 2021. VirtElect: A Peer-to-Peer Trading Platform for Local Energy Transactions. IEEE Internet of Things Journal(2021), 1.Google Scholar
- Zulfiqar Ahmad Khan, Tanveer Hussain, Amin Ullah, Seungmin Rho, Miyoung Lee, and Sung Wook Baik. 2020. Towards Efficient Electricity Forecasting in Residential and Commercial Buildings: A Novel Hybrid CNN with a LSTM-AE based Framework. Sensors 20, 5 (2020), 1399.Google ScholarCross Ref
- Tae-Young Kim and Sung-Bae Cho. 2019. Predicting residential energy consumption using CNN-LSTM neural networks. Energy 182(2019), 72–81.Google ScholarCross Ref
- Min-Seung Ko, Kwangsuk Lee, Jae-Kyeong Kim, Chang Woo Hong, Zhao Yang Dong, and Kyeon Hur. 2020. Deep Concatenated Residual Network With Bidirectional LSTM for One-Hour-Ahead Wind Power Forecasting. IEEE Trans. Sust. Energy 12, 2 (2020), 1321–1335.Google ScholarCross Ref
- Mohamed Massaoudi, Haitham Abu-Rub, Shady S Refaat, Ines Chihi, and Fakhreddine S Oueslati. 2021. Deep learning in smart grid technology: A review of recent advancements and future prospects. IEEE Access 9(2021), 54558–54578.Google ScholarCross Ref
- RC Ney, MR Ferreira, MP Vianna, RB Orling, MA Gama, and LN Canha. 2020. Planning Energy Distribution Systems in an Environment That Accelerates the Use of Distributed Energy Resources. In PES Trans. & Distr. Conf. and Exhibition-Latin America (T&D LA). IEEE, Montevideo, Uruguay, 1–6.Google ScholarCross Ref
- Vladimir Popov, Mykola Fedosenko, Vadim Tkachenko, and Dmytro Yatsenko. 2019. Forecasting consumption of electrical energy using time series comprised of uncertain data. In 6th Int. Conf. Energy Smart Syst. (ESS). IEEE, Kyiv, Ukraine, 201–204.Google ScholarCross Ref
- Rajat Sethi and Jan Kleissl. 2020. Comparison of Short-Term Load Forecasting Techniques. In Conf. Tech. for Sustainability (SusTech). IEEE, Santa Ana, CA, USA, 1–6.Google Scholar
- Dabeeruddin Syed, Haitham Abu-Rub, Ali Ghrayeb, and Shady S Refaat. 2021. Household-level energy forecasting in smart buildings using a novel hybrid deep learning model. IEEE Access 9(2021), 33498–33511.Google ScholarCross Ref
- Philipp A Trotter, Marcelle C McManus, and Roy Maconachie. 2017. Electricity planning and implementation in sub-Saharan Africa: A systematic review. Renewable and Sust. Energy Reviews 74 (2017), 1189–1209.Google ScholarCross Ref
- Fath U Min Ullah, Amin Ullah, Ijaz Ul Haq, Seungmin Rho, and Sung Wook Baik. 2019. Short-term prediction of residential power energy consumption via CNN and multi-layer bi-directional LSTM networks. IEEE Access 8(2019), 123369–123380.Google ScholarCross Ref
- Israr Ullah, Rashid Ahmad, and DoHyeun Kim. 2018. A prediction mechanism of energy consumption in residential buildings using hidden markov model. Energies 11, 2 (2018), 358.Google ScholarCross Ref
- United Nations. 2021. Sustainable development goals report 2021. Available at https://unstats.un.org/sdgs/report/2021/, Accessed: 2021-11-1.Google Scholar
- Gao Xiuyun, Wang Ying, Gao Yang, Sun Chengzhi, Xiang Wen, and Yue Yimiao. 2018. Short-term load forecasting model of gru network based on deep learning framework. In 2nd Conf. Energy Internet and Energy Syst. Integration (EI2). IEEE, Beijing, China, 1–4.Google ScholarCross Ref
- Yue Zhang, Chuan Qin, Anurag K Srivastava, Chenrui Jin, and Ratnesh K Sharma. 2020. Data-driven day-ahead PV estimation using autoencoder-LSTM and persistence model. IEEE Trans. Ind. Appl. 56, 6 (2020), 7185–7192.Google ScholarCross Ref
Index Terms
- Comparative Analysis of Hybrid Deep Learning Frameworks for Energy Forecasting
Index terms have been assigned to the content through auto-classification.
Recommendations
Comparative study of machine learning methods for COVID-19 transmission forecasting
Graphical abstractDisplay Omitted
AbstractWithin the recent pandemic, scientists and clinicians are engaged in seeking new technology to stop or slow down the COVID-19 pandemic. The benefit of machine learning, as an essential aspect of artificial intelligence, on past ...
Intelligent Solar Irradiance Forecasting Using Hybrid Deep Learning Model: A Meta-Heuristic-Based Prediction
AbstractSolar PhotoVoltaic is one among the majority of key techniques for moving away from fossil fuels and toward renewable energy. Solar prediction is an efficient approach for improving the process of an electrical method for combining a huge number ...
A short-term building energy consumption prediction and diagnosis using deep learning algorithms
Short-term energy consumption prediction of buildings is crucial for developing model-based predictive control, fault detection, and diagnosis methods. This study takes a university library in Xi’an as the research object. First, a time-by-time energy ...
Comments