FInal Project for AA 203: Optimal and Learning-Based Control: Real-Time, Multi-Service Operation of Grid-Scale Energy Storage using Model Predictive Control

Project: QLX is the open-source foundation for the QLX EON Nexus—a vision to create a decentralized, asset-backed infrastructure that transforms globally stranded or underutilized green energy into the most scarce asset of the AI era: verifiable green compute.

Maximizing the energy arbitrage revenue of a PV-BESS system under day-ahead electricity prices using linear programing

DQN-based battery dispatch with exact rainflow degradation tracking, cyclic time encodings, and observation stacking for superior energy arbitrage and load-following performance

Rainflow‑aware DQN for battery dispatch (arbitrage + FR/reserves): Gymnasium env with safety layer, exact cycle‑based degradation, time features & stacked observations; SB3 training.

Co-optimization framework for Battery Energy Storage Systems between day-ahead energy arbitrage and balancing reserves. Builds a unified optimization model and evaluates revenue of multiple strategies using French market data (RTE/Ember).

🔋 Optimize battery dispatch using a rainflow-aware DQN that tracks degradation and enhances performance with advanced features for reliable results.