The transition of energy systems towards decentralisation and decarbonisation creates novel challenges to energy system management, which necessitates a shift to more intelligent control of the whole energy system. Machine learning is a powerful means of digitalisation that can be used to leverage the huge amount of data in energy systems to efficiently evaluate and coordinate various system components. This short course will provide with essential machine learning methods and tools to tackle the real-world energy system problems in facilitating the transition towards net zero.

Machine learning is a powerful means of digitalisation that can be used to leverage the huge amount of data in energy systems to efficiently evaluate and coordinate various system components. This short course will provide with essential machine learning methods and tools to tackle the real-world energy system problems in facilitating the transition towards net zero.

At a glance

  • Dates
    • Please enquire for course dates
  • DurationThree days
  • LocationCranfield campus
  • Cost£1020

Course structure

The total length of course is three days and consists of several theoretical lectures, practical case study sessions with software training.

What you will learn

On successful completion of this course you will be able to:

  • Identify the key research questions of energy systems,
  • Develop machine learning models to resolve them,
  • Evaluate their performance in a simulation environment and assess their effectiveness for realistic case studies,
  • Identify and assess the requirements of machine learning methods, and their contributions to facilitate the transition of energy system towards net-zero.

Core content

  • Introduction of challenges and problems of energy systems transition towards net-zero,
  • Fundamentals and process of implementing machine learning methods,
  • Concepts and tools of supervised learning and unsupervised learning techniques,
  • Machine learning frameworks in Python,
  • Practical case study session on energy usage pattern recognition (user profile) applying unsupervised learning,
  • Practical case study session on supervised learning – detection of electricity usage anomalies.

Who should attend

This course is suitable for engineers, IT professionals, consultant and managers working towards net zero and who want to obtain knowledge on applied machine learning techniques.

Speakers

Dr Da Huo
Dr Ali Alderete Peralta 
Dr Enze Lu

Accommodation options and prices

This is a non-residential course. If you would like to book accommodation on campus, please contact Mitchell Hall or Cranfield Management Development Centre directly. Further information regarding our accommodation on campus can be .

Alternatively you may wish to make your own arrangements at a nearby hotel.

Location and travel

SWAG合集 is situated in Bedfordshire close to the border with Buckinghamshire. The University is located almost midway between the towns of Bedford and Milton Keynes and is conveniently situated between junctions 13 and 14 of the M1.

London Luton, Stansted and Heathrow airports are 30, 90 and 90 minutes respectively by car, offering superb connections to and from just about anywhere in the world. 

For further location and travel details

Location address

SWAG合集
College Road
Cranfield
Bedford
MK43 0AL

Read our Professional development (CPD) booking conditions.