Improving Energy Demand Prediction in IoT Based Smart Grids through Hybrid CNN-LSTM Modelling With Modified Sea Lion Algorithm

International Journal of Electrical and Electronics Engineering

© 2023 by SSRG - IJEEE Journal

Volume 10 Issue 9

Year of Publication : 2023

Authors : S. Sivarajan, S. D. Sundar Singh Jebaseelan

10.14445/23488379/IJEEE-V10I9P121

How to Cite?

S. Sivarajan, S. D. Sundar Singh Jebaseelan, "Improving Energy Demand Prediction in IoT Based Smart Grids through Hybrid CNN-LSTM Modelling With Modified Sea Lion Algorithm," SSRG International Journal of Electrical and Electronics Engineering, vol. 10,  no. 9, pp. 221-231, 2023. Crossref, https://doi.org/10.14445/23488379/IJEEE-V10I9P121

Abstract:

Efficient energy demand forecasting is pivotal for the reliable operation of modern IoT based smart grids, ensuring optimal resource allocation and grid stability. This study introduces a novel approach that combines Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) networks within a hybrid framework for accurate energy demand prediction. An innovative modification of the Sea Lion Algorithm (SLA) is proposed to enhance the model's performance for optimal hyperparameter tuning. The hybrid CNN-LSTM architecture leverages the strengths of CNNs in feature extraction from sequential data and LSTM's proficiency in capturing temporal dependencies. By synergizing these capabilities, the model offers improved accuracy in predicting energy demand patterns, which is critical for effective energy management and distribution. The Modified Sea Lion Algorithm (MSLA) is employed to fine-tune the hybrid CNN-LSTM model's hyperparameters effectively. Inspired by the behaviour of sea lions in balancing exploration and exploitation during foraging, MSLA ensures an optimal configuration of model parameters, leading to enhanced forecasting accuracy. Extensive experiments use real-world energy consumption datasets to assess the proposed methodology's efficacy. Comparative analyses are conducted against conventional CNN-LSTM models with default settings, highlighting the superiority of the hybrid approach. The results demonstrate that integrating CNNs and LSTMs yields more accurate predictions, while the modified Sea Lion Algorithm provides optimal parameter values, further enhancing prediction accuracy.

Keywords:

IoT, Hybrid CNN-LSTM, Modified Sea Lion Algorithm, Energy demand prediction, Smart grid.
 

References:

[1] Weixian Li et al., “A Novel Smart Energy Theft System (SETS) for IoT-Based Smart Home,” IEEE Internet of Things Journal, vol. 6, no. 3, pp. 5531-5539, 2019. 
[CrossRef] [Google Scholar] [Publisher Link]
[2] Shuoyao Wang, Suzhi Bi, and Ying-Jun Angela Zhang, “Locational Detection of the False Data Injection Attack in a Smart Grid: A Multilabel Classification Approach,” IEEE Internet of Things Journal, vol. 7, no. 9, pp. 8218-8227, 2020. 
[CrossRef] [Google Scholar] [Publisher Link]
[3] Mohammed J. Abdulaal et al., “Real-Time Detection of False Readings in Smart Grid AMI Using Deep and Ensemble Learning,” IEEE Access, vol. 10, pp. 47541-47556, 2022. 
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mahmoud M. Badr et al., “Detection of False-Reading Attacks in Smart Grid Net-Metering System,” IEEE Internet of Things Journal, vol. 9, no. 2, pp. 1386-1401, 2021. 
[CrossRef] [Google Scholar] [Publisher Link]
[5] Ilias Siniosoglou et al., “A Unified Deep Learning Anomaly Detection and Classification Approach for Smart Grid Environments,” IEEE Transactions on Network and Service Management, vol. 18, no. 2, pp. 1137-1151, 2021. 
[CrossRef] [Google Scholar] [Publisher Link]
[6] Michael A. Devlin, and Barry P. Hayes, “Non-Intrusive Load Monitoring and Classification of Activities of Daily Living Using Residential Smart Meter Data,” IEEE Transactions on Consumer Electronics, vol. 65, no. 3, pp. 339-348, 2019. 
[CrossRef] [Google Scholar] [Publisher Link]
[7] Kun Wang et al, “Green Energy Scheduling for Demand Side Management in the Smart Grid,” IEEE Transactions on Green Communications and Networking, vol. 2, no. 2, pp. 596-611, 2018. 
[CrossRef] [Google Scholar] [Publisher Link]
[8] Zhenyu Zhou et al., “Energy-Efficient Industrial Internet of UAVs for Power Line Inspection in Smart Grid,” IEEE Transactions on Industrial Informatics, vol. 14, no. 6, pp. 2705-2714, 2018. 
[CrossRef] [Google Scholar] [Publisher Link]
[9] Amrit Paudel et al., “Peer-to-Peer Energy Trading in Smart Grid Considering Power Losses and Network Fees,” IEEE Transactions on Smart Grid, vol. 11, no. 6, pp. 4727-4737, 2020. 
[CrossRef] [Google Scholar] [Publisher Link]
[10] Lipi Chhaya et al., “IoT-Based Implementation of Field Area Network Using Smart Grid Communication Infrastructure,” Smart Cities, vol. 1, no. 1, pp. 176-189, 2018. 
[CrossRef] [Google Scholar] [Publisher Link]
[11] Mamoun Alazab et al., “A Multidirectional LSTM Model for Predicting the Stability of a Smart Grid,” IEEE Access, vol. 8, pp. 85454-85463, 2020. 
[CrossRef] [Google Scholar] [Publisher Link]
[12] Fangyu Li et al., “Detection and Diagnosis of Data Integrity Attacks in Solar Farms Based on Multilayer Long Short-Term Memory Network,” IEEE Transactions on Power Electronics, vol. 36, no. 3, pp. 2495-2498, 2020. 
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zibin Zheng et al., “Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids,” IEEE Transactions on Industrial Informatics, vol. 14, no. 4, pp. 1606-1615, 2017. 
[CrossRef] [Google Scholar] [Publisher Link]
[14] Zhou Su et al., “Secure and Efficient Federated Learning for Smart Grid with Edge-Cloud Collaboration,” IEEE Transactions on Industrial Informatics, vol. 18, no. 2, pp. 1333-1344, 2021. 
[CrossRef] [Google Scholar] [Publisher Link]
[15] Madalina-Mihaela Buzau et al., “Hybrid Deep Neural Networks for Detection of Non-Technical Losses in Electricity Smart Meters,” IEEE Transactions on Power Systems, vol. 35, no. 2, pp. 1254-1263, 2019. 
[CrossRef] [Google Scholar] [Publisher Link]
[16] Muhammad Qamar Raza et al., “An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids,” IEEE Transactions on Industrial Informatics, vol. 15, no. 8, pp. 4624-4634, 2018. 
[CrossRef] [Google Scholar] [Publisher Link]
[17] Yang Li et al., “Detection of False Data Injection Attacks in Smart Grid: A Secure Federated Deep Learning Approach,” IEEE Transactions on Smart Grid, vol. 13, no. 6, pp. 4862-4872, 2022. 
[CrossRef] [Google Scholar] [Publisher Link]
[18] Tuong Le et al., “Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM,” Applied Sciences, vol. 9, no. 20, pp. 1-12, 2019. 
[CrossRef] [Google Scholar] [Publisher Link]
[19] S. Balaji, and S. Karthik, “Energy Prediction in IoT Systems Using Machine Learning Models,” CMC-Computers Materials and Continua, vol. 75, no. 1, pp. 443-459, 2023.
[CrossRef] [Google Scholar] [Publisher Link]