Header Information

NPRP10-0101-170082
NPRP 10
Texas A&M University at Qatar
Award Tech. Completed
01 May 2018
Prof. Haitham Abu-Rub
3 Year(s)
30 Sep 2021
New
Smart Grid Dynamic Control and Management with Big Data Process Platform

Project Summary
Gulf Cooperation Council (GCC) electricity markets have one of the fastest economic growth due to high population increase, economic growth, high level of income, manufacturing of goods, and low fixed electricity tariff [1]. The next ten years will require additional power generation capacity of 100 GW to meet the increase in energy demand [2]. For energy saving, environmental constraints, and energy security reasons those countries have put the mission of adopting various renewable energy sources (RES), particularly solar energy, and to transform their grids into Smart Grid (SG). Successful deployment and integration of such fluctuating renewable energy into the electricity grid and the transformation into SG will require the use of advanced technologies and management strategies [3]. Conventional power grids are facing many challenges to respond to the continues growing demand for energy and to deal with the increased penetration of intermittent renewable energies into the grid, as well as to provide a reliable, stable, and efficient electric grid. These diverse challenges are the forcing drivers to the transformation of current grid into SG [4]. Smart grid can be divided into two main parts, SG infrastructure and SG applications. SG infrastructure includes smart power system, information technology, and communication system, while SG applications are divided into fundamental applications and emerging applications. The fundamental applications refer to the energy management strategies, reliability models, security and privacy, in addition to promoting demand-side management while the emerging applications include the deployment of electric vehicles and mobile charging stations [5]. SGs are electrical power grids that use two-way flow of electricity and information. They are characterized with automated energy delivery, monitoring and consumption with players from utilities, market, and customers [6]. Microgrids play an important role in the effort to make the traditional electric grid smarter, more efficient, and resilient. The challenge is to manage the large system with high number of microgrids and distributed renewable energies and be able to maintain the supply-demand balance. The dynamic control and management in SG involves smart energy-efficient controllable equipment, smart distributed energy resources, advanced dynamic control architecture, distributed optimization architecture, and integrated communications architecture. SG is supported by large number of smart meters, sensors, detectors, measurement units, etc. Those elements provide a continuous stream of data to support SG performance. Huge amount of data in obtained from different SG sources satisfy all the Big Data characteristics [7]. The success of future SG depends mainly on the effective utilization of the huge amount of the big data flow. The proposed project is aimed to provide a smart management and dynamic control systems for SG while taking the advantages of the big data information flows. The project consists of four main components, each is with specific challenges, outputs, and expected outcomes, as described below: Big Data Platform, Big Data process is divided into data management and analytics. Data management contains Big Data storage, mining, and integration to prepare and retrieve for analysis. Data analytics include analyzing the managing data to be in a useful form for decision-making. This mass of information is essential to make SG more efficient, reliable, secure, independent, and supportive during normal conditions and contingencies. By using Big Data process platform, electricity suppliers and customers can reap significant benefits with successful implementation of Big Data analytics. The challenges in that stage are security and privacy of Big Data, quality and reliability of the diverse data sources, data complexity reduction, and online information extraction in a meaningful context [8]. In addition, the big data computational algorithms should be flexible to deal with the uncertainties and customers’ behavior [9]. Electric information management is an important issue raised for effective dynamic energy and control management. Energy Resources Platform, it generally refers to identifying, matching, allocating, scheduling, and monitoring energy resources over time, which is one of the challenges. It deals effectively with the coordinated sharing of resources, balancing the availability of these resources with varying levels of electricity demand, optimizes SG assets and makes them operate efficiently and reliably. A centralized big data process platform for the grid aims to act within seconds to achieve supervisory energy management of grid energy resources together with load forecasting and scheduling during the different operational scenarios Direct Load-management Platform, aims to control and manage the demand in order to shape the load profile. In the SG environment, loads include active and passive controllable loads. Those loads can communicate with the upper control system or electrical utility providers in real-time for optimal and planned energy consumption. A decentralized big data process platform for the grid aims to act within µ-seconds to m-seconds, which should be realized at the field level to achieve safe operation of the connected equipment in the network. Demand Response Platform, the demand response program is induced from load demand elasticity by reducing or shifting consumption in response to electric utilities signals such as prices or during peak demand periods to meet installed capacity requirements. Static and dynamic tariffs implementation are designed for load management, the real-time price increases with an increase in the demand, it is needed to limit tremendous growth in customers energy demands. The customers can help electricity providers to save energy consumption through reductions in peak demand.
Dynamic Energy Management; Big Data; Grid Control; Renewable Energy Sources Integration; Load management
Applied research
2. Engineering and Technology
2.02 Electrical, Electronic, and Information Engineering
Electrical and Electronic Engineering
Yes
No
2. Engineering and Technology
2.02 Electrical, Electronic, and Information Engineering
Communication Engineering and Systems
No
Yes

Institution
Texas A&M University at Qatar
Qatar
Submitting Institution
Texas A&M University - College Station
United States
Collaborative Institution
Iberdrola QSTP LLC
Qatar
Collaborative Institution

Personnel
Lead PI
Prof. Haitham Abu-Rub
Texas A&M University at Qatar
PI
Dr. Hussein Alnuweiri
Texas A&M University at Qatar
PI
Prof. Othmane Bouhali
Texas A&M University at Qatar
PI
Prof. Le Xie
Texas A&M University - College Station
PI
Dr. Shady Khalil
University of Hertfordshire
PI
Mr. Santiago Banales
Iberdrola QSTP LLC

Outputs/Outcomes
Online Paper
A Review on Big Data Management and Decision-Making in Smart Grid
Amira Mohamed-author-first, Shady S. Refaat-author-additional, Haitham Abu-Rub-author-additional
DOI:10.2478/pead-2019-0011
Conference Paper
Averaging Ensembles Model for Forecasting of Short-term Load in Smart Grids
Dabeeruddin Syed ; Shady S. Refaat ; Haitham Abu-Rub ; Othmane Bouhali ; Ameema Zainab ; Le Xie
DOI:10.1109/BigData47090.2019.9006183
Conference Paper
Faulted Line Identification and Localization in Power System using Machine Learning Techniques
Ameema Zainab ; Shady S. Refaat ; Dabeeruddin Syed ; Ali Ghrayeb ; Haitham Abu-Rub
DOI:10.1109/BigData47090.2019.9006377
Conference Paper
Performance Evaluation of Distributed Machine Learning for Load Forecasting in Smart Grids
Dabeeruddin Syed ; Shady S. Refaat ; Haitham Abu-Rub
DOI:10.1109/KI48306.2020.9039797
Conference Paper
Distributed Computing for Smart Meter Data Management for Electrical Utility Applications
Ameema Zainab ; Shady S. Refaat ; Haitham Abu-Rub ; Othmane Bouhali
DOI:10.1109/KI48306.2020.9039899
Conference Paper
Multivariate Features Extraction and Effective Decision Making Using Machine Learning Approaches
Sondes Gharsellaoui and Hassani Messaoud , Majdi Mansouri , Shady S. Refaat , Haitham Abu-Rub
DOI:10.3390/en13030609
Conference Paper
Performance Evaluation of Deep Recurrent Neural Networks Architectures : Application to PV Power Forecasting
Mohamed Massaoudi 1,2 , Ines Chihi , Lilia Sidhom , Mohamed Trabelsi , Shady S. Refaat , Fakhreddine S. Oueslati
DOI:10.1109/SGRE46976.2019.9020965
Journal Paper
Smart Grid Big Data Analytics: Survey of Technologies, Techniques, and Applications
D. Syed, A. Zainab, S. S. Refaat, H. Abu-Rub and O. Bouhali
ISSN:21693536
Conference Paper
Short-Term Electric Load Forecasting Based on Data-Driven Deep Learning Techniques
M. Massaoudi, S. S. Refaat, I. Chihi, M. Trabelsi, H. Abu-Rub and F. S. Oueslati
DOI:10.1109/IECON43393.2020.9255098
Conference Paper
A Hybrid Bayesian Ridge Regression-CWT-Catboost Model For PV Power Forecasting
M. Massaoudi, S. S. Refaat, H. Abu-Rub, I. Chihi and F. S. Wesleti
DOI:10.1109/KPEC47870.2020.9167596
Conference Paper
Short-term Power Forecasting Model Based on Dimensionality Reduction and Deep Learning Techniques for Smart Grid
D. Syed, S. S. Refaat, H. Abu-Rub and O. Bouhali
DOI:10.1109/KPEC47870.2020.9167560
Online Paper
Distributed Tree-Based Machine Learning for Short-Term Load Forecasting With Apache Spark
A. Zainab, A. Ghrayeb, H. Abu-Rub, S. S. Refaat and O. Bouhali
DOI:10.1109/ACCESS.2021.3072609
Online Paper
Deep Learning-Based Short-Term Load Forecasting Approach in Smart Grid With Clustering and Consumption Pattern Recognition
DABEERUDDIN SYED, HAITHAM ABU-RUB, ALI GHRAYEB, SHADY S. REFAAT, MAHDI HOUCHATI, OTHMANE BOUHALI, AND SANTIAGO BAÑALES,
DOI:10.1109/ACCESS.2021.3071654
Online Paper
Deep Learning in Smart Grid Technology: A Review of Recent Advancements and Future Prospects
M. Massaoudi, H. Abu-Rub, S. S. Refaat, I. Chihi and F. S. Oueslati,
DOI:10.1109/ACCESS.2021.3071269
Online Paper
An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
Mohamed Massaoudi; Ines Chihi; Lilia Sidhom; Mohamed Trabelsi; Shady S. Refaat; Haitham Abu-Rub; Fakhreddine S. Oueslati
DOI:10.1109/ACCESS.2021.3062776
Online Paper
Household-Level Energy Forecasting in Smart Buildings Using a Novel Hybrid Deep Learning Model
D. Syed, H. Abu-Rub, A. Ghrayeb and S. S. Refaat,
DOI:10.1109/ACCESS.2021.3061370
Online Paper
A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
Ameema Zainab; Dabeeruddin Syed; Ali Ghrayeb; Haitham Abu-Rub; Shady S. Refaat; Mahdi Houchati; Othmane Bouhali
DOI:10.1109/ACCESS.2021.3059730
Book
Smart Grid Enabling Technologies
Shady S. Refaat, Omar Ellabban, Sertac Bayhan, Haitham Abu-Rub, Frede Blaabjerg, Miroslav Begovic
ISBN:9781119422310
Book
Smart Grid and Enabling Technologies
Shady S. Refaat; Omar Ellabban; Sertac Bayhan; Haitham Abu-Rub; Frede Blaabjerg; Miroslav M. Begovic
ISBN:9781119422457
Book
Smart Grid and Enabling Technologies
Amira Mohammed; Dabeeruddin Syed
ISBN:9781119422457
Book
Smart Grid and Enabling Technologies
Mohamed Massaoudi; Shady S. Refaat; Haitham Abu‐Rub
ISBN:9781119422457
Journal Paper
Smart Grid Big Data Analytics: Survey of Technologies, Techniques, and Applications
Dabeeruddin Syed; Ameema Zainab; Ali Ghrayeb; Shady S. Refaat; Haitham Abu-Rub; Othmane Bouhali
ISSN:20985045
Journal Paper
A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
Ameema Zainab; Dabeeruddin Syed; Ali Ghrayeb; Haitham Abu-Rub; Shady S. Refaat; Mahdi Houchati; Othmane Bouhali; Santiago Bañales Lopez
ISSN:20375329
Journal Paper
Household-Level Energy Forecasting in Smart Buildings Using a Novel Hybrid Deep Learning Model
Dabeeruddin Syed; Haitham Abu-Rub; Ali Ghrayeb; Shady S. Refaat
ISSN:20399768
Journal Paper
Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
Dabeeruddin Syed, Shady S. Refaat, and Othmane Bouhali
ISSN:11070357
Journal Paper
Big Data Management in Smart Grids: Technologies and Challenges
Ameema Zainab; Ali Ghrayeb; Dabeeruddin Syed; Haitham Abu-Rub; Shady S. Refaat; Othmane Bouhali
ISSN:20986820
Journal Paper
Ensemble-Based Spam Detection in Smart Home IoT Devices Time Series Data Using Machine Learning Techniques
Ameema Zainab, Shady S. Refaat, and Othmane Bouhali.
ISSN:11070344
Journal Paper
An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
Mohamed Massaoudi; Ines Chihi; Lilia Sidhom; Mohamed Trabelsi; Shady S. Refaat; Haitham Abu-Rub; Fakhreddine S. Oueslati
ISSN:20380378
Journal Paper
Deep Learning-Based Short-Term Load Forecasting Approach in Smart Grid With Clustering and Consumption Pattern Recognition
Dabeeruddin Syed; Haitham Abu-Rub; Ali Ghrayeb; Shady S. Refaat; Mahdi Houchati; Othmane Bouhali; Santiago Bañales
ISSN:20966570
Journal Paper
A novel stacked generalization ensemble-based hybrid LGBM-XGB-MLP model for Short-Term Load Forecasting
Mohamed Massaoudi;Shady S.Refaat; InesChihi; Mohame Trabelsi; Fakhreddine S.Oueslati; HaithamAbu-Rub
ISSN:11887400
Journal Paper
Distributed Tree-Based Machine Learning for Short-Term Load Forecasting With Apache Spark
Ameema Zainab; Ali Ghrayeb; Haitham Abu-Rub; Shady S. Refaat; Othmane Bouhali
ISSN:20984790
Journal Paper
Deep Learning in Smart Grid Technology: A Review of Recent Advancements and Future Prospects
Mohamed Massaoudi; Haitham Abu-Rub; Shady S. Refaat; Ines Chihi; Fakhreddine S. Oueslati
ISSN:20966501
Journal Paper
PLS-CNN-BiLSTM: An End-to-End Algorithm-Based Savitzky–Golay Smoothing and Evolution Strategy for Load Forecasting
Mohamed Massaoudi, Shady S. Refaat , Haitham Abu-Rub, Ines Chihi, and Fakhreddine S. Oueslati
ISSN:13205464
Conference Paper
Investigation on Optimizing Cost Function to Penalize Underestimation of Load Demand through Deep Learning Modeling
Dabeeruddin Syed; Haitham Abu-Rub; Ameema Zainab; Mahdi Houchati; Othmane Bouhali; Ali Ghrayeb; Shady S. Refaat
DOI:10.1109/IECON48115.2021.9589229
Conference Paper
Detection of Energy Theft in Smart Grids using Electricity Consumption Patterns
Dabeeruddin Syed; Haitham Abu-Rub; Shady S. Refaat; Le Xie
DOI:10.1109/BigData50022.2020.9378190
Conference Paper
Accurate Smart-Grid Stability Forecasting Based on Deep Learning: Point and Interval Estimation Method
Mohamed Massaoudi; Haitham Abu-Rub; Shady S. Refaat; Ines Chihi; Fakhreddine S. Oueslati
DOI:10.1109/KPEC51835.2021.9446196
Journal Paper
Convergence of Photovoltaic Power Forecasting and Deep Learning: State-of-Art Review
MOHAMED MASSAOUDI 1,2, (Member, IEEE), INES CHIHI3,4,5 , HAITHAM ABU-RUB1 , (Fellow, IEEE), SHADY S. REFAAT1 , (Senior Member, IEEE), AND FAKHREDDINE S. OUESLATI6
ISSN:21693536
Conference Paper
Locational Marginal Electricity Price ForecastingBased Self-Attention Mechanism and Simulated Annealing Optimizer using Big Data
Mohamed Massaoudi1,2 , Haitham Abu-Rub1 , Shady S. Refaat1 , Ahmad Ali Al-Kuwari3 , and Tingwen Huang4
DOI:10.1109/ICRERA52334.2021.9598604