SmartCer

SmartCer is a Gymnasium environment for Italian Renewable Energy Communities (CER, comunità energetiche rinnovabili). A community is a set of producers, consumers and prosumers, some of them with a battery. In every hour it earns an incentive on the shared energy (energia condivisa), the minimum between the energy its members feed into the grid and the energy they take from it. A reinforcement learning agent controls the batteries to maximise the social welfare of the community.

Beta

SmartCer 1.0.1 is a beta release: validation against a MILP reference trajectory is in progress. The MILP oracle file format and the forecast error presets are provisional.

pip install smartcer
Overview of SmartCer: a community of producers, consumers and prosumers, with batteries controlled by a reinforcement learning agent through a Gymnasium environment.

Overview of SmartCer.

Contents

  • Installation: requirements, pip, installation from source, building these docs.

  • Quickstart: a first simulation on synthetic example data.

  • Concepts: observation, action, reward, forecasts, MILP oracle and baselines.

  • Configuration: scenario format, CSV files, run arguments, outputs.

  • Formulation: the equations of the physics, economics and reward.

  • KPIs and outputs: the indicators and files the code produces.

  • API reference: the public modules.

  • Migrating from 0.x: what changed since 0.6.2.

  • Citing: how to cite SmartCer, license and acknowledgements.

Citing

If you use SmartCer in your research, please cite it: see Citing.