Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting

Power grids are transforming into flexible, smart, and cooperative systems with greater dissemination of distributed energy resources, advanced metering infrastructure, and advanced communication technologies. Short-term electric load forecasting for individual residential customers plays a progressively crucial role in the operation and planning of future grids. Compared to the aggregated electrical load at the community level, the prediction of individual household electric loads is legitimately challenging because of the high uncertainty and volatility involved. Results from previous studies show that prediction using machine learning and deep learning models is far from accurate, and there is still room for improvement. We herein propose a deep learning framework based on a combination of a convolutional neural network (CNN) and long short-term memory (LSTM). The proposed hybrid CNN-LSTM model uses CNN layers for feature extraction from the input data with LSTM layers for sequence learning. The performance of our developed framework is comprehensively compared to state-of-the-art systems currently in use for short-term individual household electric load forecasting. The proposed model achieved significantly better results compared to other competing techniques. We evaluated our proposed model with the recently explored LSTM-based deep learning model on a publicly available electrical load data of individual household customers from the Smart Grid Smart City (SGSC) project. We obtained an average mean absolute percentage error (MAPE) of 40.38% for individual household electric load forecasts in comparison with the LSTM-based model that obtained an average MAPE of 44.06%. Furthermore, we evaluated the effectiveness of the proposed model on different time horizons (up to 3 h ahead). Compared to the recently developed LSTM-based model tested on the same dataset, we obtained 4.01%, 4.76%, and 5.98% improvement for one, two, and six look-forward time steps, respectively (with 2 lookback time steps). Additionally, we have performed clustering analysis based on the power consumption behavior of the energy users, which indicate that prediction accuracy could be improved by grouping and training the representative model using large amount of data. The results indicated that the proposed model outperforms the LSTM-based model for both 1 h ahead and 3 h ahead in forecasting individual household electric loads.

[1]  Vincent W. S. Wong,et al.  Autonomous Demand-Side Management Based on Game-Theoretic Energy Consumption Scheduling for the Future Smart Grid , 2010, IEEE Transactions on Smart Grid.

[2]  Daniel Hsu,et al.  Time Series Forecasting Based on Augmented Long Short-Term Memory , 2017, ArXiv.

[3]  B. B. V. L. Deepak,et al.  Multi-objective optimization of ethanol fuelled HCCI engine performance using hybrid GRNN–PSO , 2017 .

[4]  Michael Beigl,et al.  Sequential pattern mining — A study to understand daily activity patterns for load forecasting enhancement , 2015, 2015 IEEE First International Smart Cities Conference (ISC2).

[5]  Cyril Voyant,et al.  Solar Radiation Forecasting Using Ad-Hoc Time Series Preprocessing and Neural Networks , 2009, ICIC.

[6]  Fahad H. Al-Qahtani,et al.  Multivariate k-nearest neighbour regression for time series data — A novel algorithm for forecasting UK electricity demand , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[7]  A. Arabali,et al.  A hybrid short-term load forecasting with a new input selection framework , 2015 .

[8]  Pang Qingle,et al.  Very Short-Term Load Forecasting Based on Neural Network and Rough Set , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[9]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[10]  Nadeem Javaid,et al.  Towards Efficient Energy Management of Smart Buildings Exploiting Heuristic Optimization with Real Time and Critical Peak Pricing Schemes , 2017 .

[11]  F. Muñoz,et al.  Hopfield K-Means clustering algorithm: A proposal for the segmentation of electricity customers , 2011 .

[12]  Xia Liu,et al.  Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part I) , 2015, IEEE Trans. Neural Networks Learn. Syst..

[13]  Mahesh Panchal,et al.  A Review on Support Vector Machine for Data Classification , 2012 .

[14]  Rui Zhang,et al.  Short-term load forecasting of Australian National Electricity Market by an ensemble model of extreme learning machine , 2013 .

[15]  Nadeem Javaid,et al.  Game Theoretical Energy Management with Storage Capacity Optimization and Photo-Voltaic Cell Generated Power Forecasting in Micro Grid , 2019, Sustainability.

[16]  L. Zarzalejo,et al.  Prediction of global solar irradiance based on time series analysis: Application to solar thermal power plants energy production planning , 2010 .

[17]  Nadeem Javaid,et al.  Electricity Load and Price Forecasting Using Jaya-Long Short Term Memory (JLSTM) in Smart Grids , 2019, Entropy.

[18]  Mohamed Chaouch,et al.  Clustering-Based Improvement of Nonparametric Functional Time Series Forecasting: Application to Intra-Day Household-Level Load Curves , 2014, IEEE Transactions on Smart Grid.

[19]  Hany M. Hasanien,et al.  Short term load forecasting using ANN technique , 2017, 2017 Nineteenth International Middle East Power Systems Conference (MEPCON).

[20]  Saad Mekhilef,et al.  Application of extreme learning machine for short term output power forecasting of three grid-connected PV systems , 2017 .

[21]  Joaquim Melendez,et al.  Short-term load forecasting in a non-residential building contrasting models and attributes , 2015 .

[22]  Xiaohua Li,et al.  Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network , 2017, 2017 51st Annual Conference on Information Sciences and Systems (CISS).

[23]  Wei-Peng Chen,et al.  Neural network model ensembles for building-level electricity load forecasts , 2014 .

[24]  Zongben Xu,et al.  Is Extreme Learning Machine feasible ? A Theoretical Assessment ∗ , 2013 .

[25]  M. Etezadi-Amoli,et al.  Smart meter based short-term load forecasting for residential customers , 2011, 2011 North American Power Symposium.

[26]  Rayman Preet Singh,et al.  On hourly home peak load prediction , 2012, 2012 IEEE Third International Conference on Smart Grid Communications (SmartGridComm).

[27]  Hans-Arno Jacobsen,et al.  Household electricity demand forecasting: benchmarking state-of-the-art methods , 2014, e-Energy.

[28]  Nadeem Javaid,et al.  An Efficient Energy Management Approach Using Fog-as-a-Service for Sharing Economy in a Smart Grid , 2018, Energies.

[29]  Ronald R. Yager,et al.  OWA filters and forecasting models applied to electric power load time series , 2014, Evol. Syst..

[30]  Weicong Kong,et al.  A composite k-nearest neighbor model for day-ahead load forecasting with limited temperature forecasts , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[31]  Ali Ouni,et al.  Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † , 2018, Energies.

[32]  Yinan Jing,et al.  A Data-Driven Hybrid Optimization Model for Short-Term Residential Load Forecasting , 2015, 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing.

[33]  Holger Ziekow,et al.  The potential of smart home sensors in forecasting household electricity demand , 2013, 2013 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[34]  Xia Liu,et al.  Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part I) , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[35]  Xiao Lu,et al.  Machine-to-machine communications for home energy management system in smart grid , 2011, IEEE Communications Magazine.

[36]  Zhou Quan,et al.  RBF Neural Network and ANFIS-Based Short-Term Load Forecasting Approach in Real-Time Price Environment , 2008, IEEE Transactions on Power Systems.

[37]  Mikko Kolehmainen,et al.  Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data , 2010 .

[38]  Bruce Stephen,et al.  Incorporating Practice Theory in Sub-Profile Models for Short Term Aggregated Residential Load Forecasting , 2017, IEEE Transactions on Smart Grid.

[39]  Ihsan Ullah,et al.  An Automated System for Epilepsy Detection using EEG Brain Signals based on Deep Learning Approach , 2018, Expert Syst. Appl..

[40]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[41]  Ram Rajagopal,et al.  Household Energy Consumption Segmentation Using Hourly Data , 2014, IEEE Transactions on Smart Grid.

[42]  Khursheed Aurangzeb,et al.  Short Term Power Load Forecasting using Machine Learning Models for energy management in a smart community , 2019, 2019 International Conference on Computer and Information Sciences (ICCIS).

[43]  Hong Li,et al.  Short-term load forecasting based on the grid method and the time series fuzzy load forecasting method , 2015 .

[44]  Musaed Alhussein,et al.  Microgrid-Level Energy Management Approach Based on Short-Term Forecasting of Wind Speed and Solar Irradiance , 2019, Energies.

[45]  Athula D. Rajapakse,et al.  Microgrids research: A review of experimental microgrids and test systems , 2011 .

[46]  Mareček Jan Usage of Generalized Regression Neural Networks in Determination of the Enterprise’s Future Sales Plan , 2016 .

[47]  X. Wen,et al.  A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset , 2016 .