Full Name
Hao Wang
Job title
Senior Lecturer
Organisation
Monash University
Speaker bio
Hao Wang is a Senior Lecturer in the Department of Data Science and AI and Monash Energy Institute at Monash University. He previously held the position of Research Scholar at Stanford University. Hao leads a dynamic research team dedicated to advancing optimisation and AI techniques for sustainable power and energy systems. He's been leading several government and industry funded projects, including Australian Research Council DECRA Fellowship and CSIRO's Next Generation Graduates Program 'AI for Clean Energy and Sustainability'.
Speaking At
Presentation title
Real-Time Bidding Strategies for Co-Located Renewable and Battery Energy Storage Systems
Presentation summary
As Australia advances toward a net-zero future, the rapid deployment of variable renewable energy such as wind and solar brings growing challenges in system operation and market integration. A key issue is generation curtailment, which leads to underutilisation of clean energy and revenue losses. Battery Energy Storage Systems (BESS) offer a promising solution by storing excess supply, providing grid services, and participating in multiple electricity markets.
Traditional approaches rely on forecasting prices and then optimising decisions based on those predictions. However, inaccurate forecasts often lead to suboptimal or even loss-incurring decisions, particularly when co-locating renewables and storage. Our research develops an advanced, real-time bidding strategy for co-located wind/solar and BESS assets that unlocks greater financial and operational value. By modelling the wind/solar farm and BESS as coordinated, decision agents, we deploy an AI based strategy tailored for the Australian National Electricity Market. Using real-world data from a Queensland wind farm and actual NEM price signals, our solution demonstrates clear improvements in both revenue performance and computation.
Traditional approaches rely on forecasting prices and then optimising decisions based on those predictions. However, inaccurate forecasts often lead to suboptimal or even loss-incurring decisions, particularly when co-locating renewables and storage. Our research develops an advanced, real-time bidding strategy for co-located wind/solar and BESS assets that unlocks greater financial and operational value. By modelling the wind/solar farm and BESS as coordinated, decision agents, we deploy an AI based strategy tailored for the Australian National Electricity Market. Using real-world data from a Queensland wind farm and actual NEM price signals, our solution demonstrates clear improvements in both revenue performance and computation.
