Artificial Intelligence for Smart Grids and Power Systems

Course info:

Semester: 7

Elective

ECTS: 6

Hours per week: 2

Professor: T.B.D.

Teaching style: Face to face, distance learning

Grading: Written exam (50%), Exercises (50%)

Activity Workload
Lectures 26
Tutorials
Laboratory work
Project development / exercises 56
Autonomous learning 68
Course total 150

Learning Results

Upon successful completion of the course, students will be able to:

  • Understand the basic principles of the design and operation of the power systems
  • Understand the applications of artificial intelligence in problems of power systems transforming them to smart grids,
  • Apply, design and implement tools for solving complex problems of power systems / smart grids, i.e. short term load forecasting, customers’ classification, fault detection, ground resistance, electromechanical equipment reliability etc.
  • Identify the capabilities and limitations of the artificial intelligence tools to the power systems problems
  • Identify the specialization of the artificial intelligence tools to the power systems problems, i.e. proper calibration of momentum term and training rate of neural networks for load forecasting
  • Expand the application of artificial intelligence tools to the power systems problems and smart grids, i.e. hybrid models with neural networks and fuzzy logic

Skills acquired

  • Work individually and in teams
  • Advance free, creative and causative thinking
  • Retrieve, analyse and synthesise data and information, with the use of necessary technologies
  • Work in interdisciplinary environment
  • Introduction on Power Systems
  • Design and operation problems on power systems, i.e. load forecasting, automatic generation control, optimal load flow, unit commitment, hydrothermal duel problem, hydrothermal interchange coordination, maintenance scheduling, generation planning, renewable energy sources / energy storage system / electric vehicles penetration, demand side management, etc.
  • Transition to smart grids
  • Long term and short term load forecasting in electric power systems with artificial neural networks/ fuzzy systems
  • Load time-series classification based on pattern recognition methods (for customers’ classification, load forecasting etc.)
  • Optimal operation of thermal electric power production system without transmission losses using Artificial Neural Networks based on external penalty functions
  • Strategic electricity market modeling
  • Fault detection based on artificial intelligence
  • Estimation of electromechanical equipment behavior based on artificial intelligence (i.e. prediction of distribution transformer no-load losses using decision trees, optimization of permanent magnet generators design using neural networks, ground resistance prediction by artificial neural network, estimation of the critical flashover voltage on insulators based on a fuzzy logic, etc.)
  • Control techniques for electromechanical equipment based on artificial intelligence (i.e. new techniques for MPPT control of PV system, power electronics on smart grids, Intelligent Home Energy Management, Smart monitoring & Optimization of Energy Consumption, etc.)
  • Cyber-attacks risk mitigation on the smart grid using Artificial Intelligence methods
  1. Theodore Wildi, Electrical machines, drives and power systems, Prentice Hall, 5th edition, 2002, ISBN 0-13-093083-0

  2. J. A. Momoh, Electric Power System Applications of Optimization, Marcel Dekker, 1st edition, ISBN 0-8247-9105-3

  3. N.M. Mastorakis, Aida Bulucea, G.J. Tsekouras. Computational Problems in Science and Enginnering, Springer, October 2015.

  4. Peng-Yeng Yin, Pattern Recognition; Techniques, Technology and Applications, I-Tech, Vienna, November 2008.

  5. Mehdi Rahmani Andebili, Applications of Artificial Intelligence in Planning and Operation of Smart Grids, Springer, 2022, ISBN 978-3-030-94521-3

  6. Marcelo Godoy Simões, Artificial Intelligence for Smarter Power Systems, Institution of Engineering & Technology, 2021, ISBN 978-1-83953-001-2

  7. Miltiadis D. Lytras, Kwok Tai Chui. Artificial Intelligence for Smart and Sustainable Energy Systems and Applications, Energies, 2022, ISBN 978-3-03928-890-8

– Related scientific journals:

  1. IEEE Transactions on Power Systems
  2. IEEE Transactions on Power Delivery

  3. IEEE Transactions on Smart Grids

  4. IEEE Transactions on Sustainable Energy

  5. IEEE Transactions on Energy Conversion

  6. IEEE Transactions on Industrial Informatics

  7. IEEE Intelligence Systems

  8. IEEE Open Access

  9. MDPI Energies

  10. International Transactions on Electrical Energy Systems

  11. Electrical Power Systems Research

  12. Transportation Research Part D: Transport and Environment

  13. International Journal of Energy Engineering (World Academic Publishing Company)

  14. European Transactions on Power Systems

  15. WSEAS Transactions on Power Systems

  16. WSEAS Transactions on Circuits & Systems

Learning Results - Skills acquired

Learning Results

Upon successful completion of the course, students will be able to:

  • Understand the basic principles of the design and operation of the power systems
  • Understand the applications of artificial intelligence in problems of power systems transforming them to smart grids,
  • Apply, design and implement tools for solving complex problems of power systems / smart grids, i.e. short term load forecasting, customers’ classification, fault detection, ground resistance, electromechanical equipment reliability etc.
  • Identify the capabilities and limitations of the artificial intelligence tools to the power systems problems
  • Identify the specialization of the artificial intelligence tools to the power systems problems, i.e. proper calibration of momentum term and training rate of neural networks for load forecasting
  • Expand the application of artificial intelligence tools to the power systems problems and smart grids, i.e. hybrid models with neural networks and fuzzy logic

Skills acquired

  • Work individually and in teams
  • Advance free, creative and causative thinking
  • Retrieve, analyse and synthesise data and information, with the use of necessary technologies
  • Work in interdisciplinary environment
Course content
  • Introduction on Power Systems
  • Design and operation problems on power systems, i.e. load forecasting, automatic generation control, optimal load flow, unit commitment, hydrothermal duel problem, hydrothermal interchange coordination, maintenance scheduling, generation planning, renewable energy sources / energy storage system / electric vehicles penetration, demand side management, etc.
  • Transition to smart grids
  • Long term and short term load forecasting in electric power systems with artificial neural networks/ fuzzy systems
  • Load time-series classification based on pattern recognition methods (for customers’ classification, load forecasting etc.)
  • Optimal operation of thermal electric power production system without transmission losses using Artificial Neural Networks based on external penalty functions
  • Strategic electricity market modeling
  • Fault detection based on artificial intelligence
  • Estimation of electromechanical equipment behavior based on artificial intelligence (i.e. prediction of distribution transformer no-load losses using decision trees, optimization of permanent magnet generators design using neural networks, ground resistance prediction by artificial neural network, estimation of the critical flashover voltage on insulators based on a fuzzy logic, etc.)
  • Control techniques for electromechanical equipment based on artificial intelligence (i.e. new techniques for MPPT control of PV system, power electronics on smart grids, Intelligent Home Energy Management, Smart monitoring & Optimization of Energy Consumption, etc.)
  • Cyber-attacks risk mitigation on the smart grid using Artificial Intelligence methods
Recommended bibliography
  1. Theodore Wildi, Electrical machines, drives and power systems, Prentice Hall, 5th edition, 2002, ISBN 0-13-093083-0

  2. J. A. Momoh, Electric Power System Applications of Optimization, Marcel Dekker, 1st edition, ISBN 0-8247-9105-3

  3. N.M. Mastorakis, Aida Bulucea, G.J. Tsekouras. Computational Problems in Science and Enginnering, Springer, October 2015.

  4. Peng-Yeng Yin, Pattern Recognition; Techniques, Technology and Applications, I-Tech, Vienna, November 2008.

  5. Mehdi Rahmani Andebili, Applications of Artificial Intelligence in Planning and Operation of Smart Grids, Springer, 2022, ISBN 978-3-030-94521-3

  6. Marcelo Godoy Simões, Artificial Intelligence for Smarter Power Systems, Institution of Engineering & Technology, 2021, ISBN 978-1-83953-001-2

  7. Miltiadis D. Lytras, Kwok Tai Chui. Artificial Intelligence for Smart and Sustainable Energy Systems and Applications, Energies, 2022, ISBN 978-3-03928-890-8

– Related scientific journals:

  1. IEEE Transactions on Power Systems
  2. IEEE Transactions on Power Delivery

  3. IEEE Transactions on Smart Grids

  4. IEEE Transactions on Sustainable Energy

  5. IEEE Transactions on Energy Conversion

  6. IEEE Transactions on Industrial Informatics

  7. IEEE Intelligence Systems

  8. IEEE Open Access

  9. MDPI Energies

  10. International Transactions on Electrical Energy Systems

  11. Electrical Power Systems Research

  12. Transportation Research Part D: Transport and Environment

  13. International Journal of Energy Engineering (World Academic Publishing Company)

  14. European Transactions on Power Systems

  15. WSEAS Transactions on Power Systems

  16. WSEAS Transactions on Circuits & Systems