PENG9620 Smart cities for a Sustainable Energy Future - From Design to Practice Emneplan

This course covers contemporary topics in smart energy systems such as smart power grid, smart buildings, vehicle-to-grid (V2G) and communication technologies for and network security in smart energy systems, including emerging approaches towards energy intelligence such as machine learning and blockchain.

The course will be offered once a year, provided 5 or more students sign up for the course. If less than 5 students sign up for a course, the course will be cancelled for that year

All aids are permitted.

Each module will be taught in a series of lectures. At the end of each module, the students will be assigned a small project to be submitted within a given deadline.

Knowledge

On successful completion of the course, the student:

• is at the forefront of knowledge about smart energy systems, both at the system level and at the specific component/application level.
• understands what different technologies can be used at what level in energy generation, transmission, distribution and consumption networks.
• knows about communication technologies and their performance limits for enabling energy intelligence in smart energy systems.

Skills

On successful completion of the course, the student can:

• solve resource optimisation problems for the energy information network.
• apply optimisation techniques and machine learning-based approaches for residential demand response management and vehicle-to-grid.

General competence

On successful completion of the course, the student can:

• communicate and collaborate with experts from other disciplines on larger interdisciplinary and multidisciplinary research projects.
• Recognise and assess a project's potential and value
• participate in debates and communicate results through recognised international channels, such as academic conferences.
• can construct and develop relevant models and discuss the model's validity.
• Disseminate knowledge to broader audiences

Pass or fail.

Oral examination, individual.

The exam cannot be appealed.

None.

Students who complete the course are expected to have the following learning outcomes, defined in terms of knowledge, skills and general competence:

Knowledge:

On successful completion of the course, the student:

• is at the forefront of knowledge within the topic of his/her engineering project.
• has a profound understanding of the state-of-the-art and the latest developments in the professional engineering field relevant to his/her doctoral thesis.
• can apply the theories, methods and processes in scholarly projects as well as in professional engineering projects specific to his/her field of engineering.

Skills:

On successful completion of the course, the student can:

• apply theoretical knowledge, scientific methods and simulation tools suitable for solving complex civil engineering problems.
• deal with complex professional issues with an academic approach and reflect critically on established knowledge and practice within the research field of the project.
• plan and conduct scholarly work within the topic of his/her the engineering project.
• analyse existing theories, methods and standardised solutions on practical and theoretical engineering problems.

General competence:

On successful completion of the course, the student can:

• apply his/her knowledge and skills to carrying out advanced tasks and projects.
• communicate issues, analyses and solutions to both specialists and non-specialists.
• assess the need for, and initiate innovation in his/her field of expertise.

Two internal examiners. External examiner is used periodically.

Basic background in statistics or probability theory. Knowledge of a programming language.

The course is structured in five modules:

• Module 1: Unsupervised Data Mining
• Module 2: Supervised Machine Learning
• Module 3: Reinforcement Learning
• Module 4: Artificial Neural Network and Deep Learning
• Module 5: Major Concepts in Artificial Intelligence, including: complex systems (networks, cellular automata, and agent-based models) and evolutionary computing