Machine Learning Approaches for Optimising Battery Operations in Smart Grids

School of Engineering and Technology
Salahuddin Azad
Md Rahat Hossain


The project will investigate various machine learning approaches to optimise battery operations in the smart grid. Battery storage plays a vital role in smoothing out the fluctuations in energy demand and generation from distributed renewable sources. Machine learning can help predict the energy demand, and solar and wind power generation. Using reinforced learning, it is possible to make optimal battery charging and discharging decisions to flatten the demand curve. The project will involve extensive simulations and building machine learning models. The prospective students will need to have a strong background in programming, simulation and machine learning. The knowledge of renewable energy generation and battery storage is also essential.

Information and Computing Sciences| Engineering
Smart Grid, Machine Learning, Battery Storage


This project is associated with the International Engaged Research Scholarship, which offers a 20% reduction in tuition fees for eligible international students.

Other special notes

Funding is also provided by CQUniversity to support research higher degree student project costs, and to support national and international conference presentations. This includes:

For masters by research candidates:

  • up to $4,000 in Candidate Support Funds
  • up to $3,000 for Candidate Travel Support

For doctoral candidates:

  • up to $6,000 in Candidate Support Funds
  • up to $4,500 for Conference Travel Support

Project contacts