This project will develop a simulation and decision-support platform that leverages machine learning (ML) and optimisation algorithms to maximise the value of household energy storage (batteries and EVs) in the Irish Single Electricity Market (SEM). Using historical SEMO and SEMOpx market data, combined with household electricity consumption and solar generation data, the platform will forecast PV energy generation and household demand, and generate optimal charging and discharging schedules for energy storage units. The core innovation lies in integrating forecasting ML models with multi-objective optimisation, balancing expected profits against battery degradation and user-defined constraints (e.g., minimum EV charge for mobility, household comfort). The platform can simulate different scenarios, such as adding extra batteries, integrating EV-to-grid, or adjusting household consumption patterns, to assess ROI and system flexibility. The primary use-case is as a decision-support tool for energy companies, aggregators, or researchers, enabling them to quantify the potential benefits of distributed storage and optimise arbitrage strategies without requiring live deployment. In the long term, the platform could be extended to: Support peer-to-peer energy sharing simulations. Incorporate reinforcement learning for real-time adaptive optimisation under price uncertainty. Serve as a planning tool for households considering hardware upgrades, showing expected returns from batteries or EV integration.