Data-driven modelling for grid-Integrated renewable energy distribution: Demand side forecasting and grid optimisation 

Supervisors 

Prof. Taufiq Asyhari (Monash University Indonesia) 

A/Prof. Markus Wagner (Monash University)

The project 

As cities move toward cleaner and more sustainable energy systems, integrating renewable sources like solar, wind, and biomass into existing power grids presents new challenges. These energy sources are variable, and urban electricity demand patterns are complex and ever-changing. 

This project develops a data-driven modelling framework to support reliable, efficient, and clean energy distribution in urban grids. Using advanced machine learning and probabilistic modelling, the research will deliver accurate, high-resolution forecasts of electricity demand – drawing on data such as energy consumption trends, weather conditions, and socio-economic factors. 

These forecasts will guide grid optimisation, helping balance supply and demand, reduce energy waste, and enhance grid resilience. By simulating different grid scenarios, the framework identifies strategies to improve how renewable energy is distributed across urban systems. 

The outcome will be a scalable, adaptable platform that gives energy planners and policymakers powerful insights into electricity demand and grid performance – supporting smarter, more sustainable energy systems for the future.