The goal of the course is to raise student competencies for the development of smart cities and smart energy systems, especially related to a real-time grid optimization. The course includes a team work on a project concerning the use of advanced control and artificial intelligence for the demand side participation on smart grids. The project uses the living laboratory for smart buildings in the collaboration with the Technical school Ruđera Boškovića. The laboratory is equipped with the most advanced technologies for heating, cooling, ventilation, measurement and advanced control. As such, it is a unique opportunity for students to develop an algorithm for advanced control of an energy system and test it in a realistic environment.

Student responsibilities:

Regular attendance to lectures and workshops. Continuous adoption of theoretical knowledge and active participation on practical assignments and discussions.

Grading and evaluation of student work over the course of instruction and at a final exam:

Project 50%, practical work 40%, lecture attendance 10%.

Upon successful completion of the course, students will be able to (learning outcomes):

1 . Identify the objectives for making an energy system intelligent.

2 . Develop critical thinking to evaluate an artificial intelligence (AI) potential in energy systems, in terms of efficiency, feasibility, effort and impact.

3 . Identify the perceptional gap between what AI in energy systems is doing and what it could do.

4 . Develop a simple computer algorithm for the advanced control of energy system and the demand side participation on an energy market.

5 . Perform a real-time optimization of an energy system.

6 . Anticipate challenges and risks brought about by advanced energy technologies.

Lectures

1. Potential for the digitalization of the energy sector aiming at the increase in grid flexibility and stability as well as the reduction of carbon footprint.

2. Introduction and a visit to the living laboratory for smart buildings.

3. Methods for an energy system optimization using advanced technologies (artificial intelligence, machine learning, digital twin, predictive control).

4. Practical aspects of a real-time optimization of energy systems (definition of the objective function, optimization parameters and boundary conditions).

5. Practical aspects of a real-time optimization of energy systems (definition of the objective function, optimization parameters and boundary conditions).

6. Artificial intelligence and machine learning basics.

7. Artificial intelligence and machine learning basics.

8. Enabling technologies (IoT, smart sensors, cloud computing).

9. Collection, processing, and interpretation of data.

10. Specifics of interaction between buildings, electric vehicles and grid based on the objective function (minimization of energy consumption, minimization of cost, increase in grid flexibility).

11. Specifics of interaction between buildings, electric vehicles and grid based on the objective function (minimization of energy consumption, minimization of cost, increase in grid flexibility).

12. User-centric control.

13. Characteristics of national and international energy markets.

14. Mechanisms for demand side participation on energy markets.

15. Challenges and risks brought about by advanced energy technologies.

Exercises

1. Case study presentation.

2. Case study - development of a simulation model for the basecase (without the advanced control).

3. Case study - proposal of a conceptual solution aiming to increase an energy system intelligence.

4. Case study - proposal of a conceptual solution aiming to increase an energy system intelligence.

5. Case study - definition of key elements of an optimization algorithm (objective function, optimization parameters and boundary conditions).

6. Case study - definition of key elements of an optimization algorithm (objective function, optimization parameters and boundary conditions).

7. Case study - analysis and the selection of an optimization method.

8. Case study - development of a computer algorithm for a real-time optimization.

9. Case study - development of a computer algorithm for a real-time optimization.

10. Case study - development of a computer algorithm for a real-time optimization.

11. Case study - a real-time optimization of an energy system.

12. Case study - analysis of the results.

13. Case study - the quantification of benefits of the proposed solution.

14. Case study - final presentation.

15. Discussion about lessons learned and the proposal of a case study for the next academic year.

Compulsory literature:

1. Energy Performance of Buildings Directive (EPBD), European Commission, Directorate-General for Energy, Arbon, J., Allington, M., Lonsdale, J., et al., European Commission, Publications Office, 0000, p. 0-0

2. Final report on the technical support to the development of a smart readiness indicator for buildings, European Commission, Directorate-General for Energy, Verbeke, S., Aerts, D., Reynders, G., et al., European Commission, Publications Office, 0000, p. 0-0

3. Lecture notes, Žakula, T., Bađun., N., Interno u Laboratoriju za energetsku učinkovitost, 0000, p. 0-0

Recommended literature: