Prediction of the Electrical Load for Egyptian Energy Management Systems: Deep Learning Approach

In the era of the Internet of Things (IoT) and machine learning, energy utilities have now the possibility of providing many benefits to the customers. Using advanced metering infrastructure is an important step to optimize and manage energy consumption. Smart meters are deployed in millions of households worldwide, representing an opportunity for monitoring systems and data analytics. Egypt has started its path into smart metering and needs to use big data analytics to endow the Egyptian grid with intelligence. In this paper, we investigate the role of big data analytics and available machine learning technologies that mine the data to generate insights into smart grid management process. We investigate a deep learning-based methodology such as long short-term memory (LSTM) network model to perform prediction of the electrical load for energy management systems. The LSTM model presents a decrease of 14% in forecasting error compared to deep forward neural networks.

[1]  Clark W. Gellings,et al.  Demand-Side Management , 2015 .

[2]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[3]  Gonzalo Joya,et al.  Global model for short-term load forecasting using artificial neural networks , 2002 .

[4]  Jian Ma,et al.  A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network , 2018, Energies.

[5]  Mohammed Guller.  Big Data Analytics with Spark , 2015, Apress.

[6]  Mohammed E. El-Telbany,et al.  Short-term forecasting of Jordanian electricity demand using particle swarm optimization , 2008 .

[7]  Lothar Richter.  Jure Leskovec, Anand Rajaraman, and Jeffrey D. Ullman. Mining of Massive Datasets. Cambridge, Cambridge University Press. , 2018 .

[8]  Chang-Tien Lu,et al.  Activity analysis based on low sample rate smart meters , 2011, KDD.

[9]  George K. Karagiannidis,et al.  Big Data Analytics for Dynamic Energy Management in Smart Grids , 2015, Big Data Res..

[10]  Emmanuel Müller,et al.  Data Analysis Challenges in the Future Energy Domain , 2013, IDA 2013.

[11]  Alvaro A. Cárdenas,et al.  Evaluating Electricity Theft Detectors in Smart Grid Networks , 2012, RAID.

[12]  Ian Beausoleil-Morrison,et al.  Disaggregating categories of electrical energy end-use from whole-house hourly data , 2012 .

[13]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[14]  Karl Aberer,et al.  Consumer Segmentation and Knowledge Extraction from Smart Meter and Survey Data , 2014, SDM.

[15]  Carlos Cardeira,et al.  The Daily and Hourly Energy Consumption and Load Forecasting Using Artificial Neural Network Method: A Case Study Using a Set of 93 Households in Portugal☆ , 2014 .

[16]  Sandy Ryza.  Advanced Analytics with Spark , 2015 .

[17]  Athanasios V. Vasilakos,et al.  Big data analytics: a survey , 2015, Journal of Big Data.

[18]  Sisil Kumarawadu,et al.  Smart Metering Design and Applications , 2013 .

[19]  Gianfranco Chicco,et al.  Overview and performance assessment of the clustering methods for electrical load pattern grouping , 2012 .

[20]  Moon-Hee Park,et al.  Short-term Load Forecasting Using Artificial Neural Network , 1992 .

[21]  Wenye Tian,et al.  Numerical research of the effect of surface biomimetic features on the efficiency of tidal turbine blades , 2018 .

[22]  Wan He.  Deep neural network based load forecast , 2014 .

[23]  Kostas S. Metaxiotis,et al.  Artificial intelligence in short term electric load forecasting: a state-of-the-art survey for the researcher , 2003 .

[24]  Vladimir Ceperic,et al.  A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines , 2013, IEEE Transactions on Power Systems.

[25]  Zhiyu Sun,et al.  Modeling and Forecasting Short-Term Power Load With Copula Model and Deep Belief Network , 2019, IEEE Transactions on Emerging Topics in Computational Intelligence.

[26]  Xinghuo Yu,et al.  Smart Electricity Meter Data Intelligence for Future Energy Systems: A Survey , 2016, IEEE Transactions on Industrial Informatics.

[27]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[28]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  Rayman Preet Singh,et al.  Computing Electricity Consumption Profiles from Household Smart Meter Data , 2014, EDBT/ICDT Workshops.

[30]  Itziar Angulo,et al.  State of the Art and Trends Review of Smart Metering in Electricity Grids , 2016 .