Context
Battery storage plays a critical role in supporting system stability and enabling higher penetration of renewable energy as part of the Net Zero transition.
Challenge
Optimising how battery assets are used across different system conditions is complex, requiring coordination between system needs, renewable generation, and operational objectives.
AI Solution
The solution embeds AI-driven optimisation into the operational management of battery storage assets by incorporating both system-level and customer-level insights. It evaluates how battery capacity should be deployed to balance competing objectives such as security of supply and renewable energy integration, and operational efficiency. It generates near-real-time, constraint-aware battery trading recommendations for traders.
Impact & evidence
The solution delivers clear, data‑driven trading insights that turn complex, time‑intensive decisions into efficient, actionable strategies, enabling traders to maximise revenues within system constraints. It enhances decision-making through forward-looking analytics while integrating seamlessly into workflows, driving measurable efficiency gains and tangible value as storage portfolios scale and market volatility increases.
Implementation / Adoption
To implement this solution, other utilities would need access to battery, market and forecast data, along with optimisation models and machine-learning forecasts that generate recommendations within storage and market constraints. They would also require a governed data setup and dashboards integrated into trader workflows for near real-time use. In addition, the solution needs to align with market rules, support frequent updates, and be designed to onboard new assets over time.
Data
The solution requires battery data, market data and forecast inputs such as interconnector flows and System Non-Synchronous Penetration (SNSP) forecasts.
Future enhancements
Planned future enhancements include addition of new assets, historic battery trading analysis and optimisation of price forecast.
“The BESS Optimisation tool has enabled our traders to maximise ex-ante and DS3 revenues while ensuring all activity remains within storage constraints. It offers clear power cost insight and smart trade suggestions using Interconnector Flows and SNSP forecasts, boosting the SEM trading team’s efficiency.” – Stephen Piggot – Prompt Trading Manager
“The Battery Optimisation tool was designed to offer data led insight to the traders, turning a complex and time-consuming bidding process, into a clear and efficient solution. Adhering to the complex and ever changing ISEM market while ensuring that the tool was flexible enough to seamlessly onboard new assets, was central to its design.” – Vivion Grisewood – Senior Analyst
“From a trading perspective, this battery optimisation tool turns complexity into clarity it gives our traders forward-looking insight they can confidently act on. For the Trading Services team, it’s proof that energy analytics can be product-led, we can build ML/AI tools that scale, refresh in near real time, and fit directly into trading business processes. As ESB’s storage portfolio grows and volatility increases, this optimisation capability becomes essential to protecting value and capturing opportunity. This is our direction of travel; building ML/AI products that deliver real actionable insights, optimise assets for trading, and drive a very measurable impact on the bottom line.” – Daragh Noctor – Trading Services Manager