Section: Application Domains

Energy Management

Energy management, our prioritary application field, involves sequential decision making with:

• Stochastic uncertainties (typically weather);

• Both high scale combinatorial problems (as induced by nuclear power plants) and non-linear effects;

• High dimension (including hundreds of hydroelectric stocks);

• Multiple time scales:

  • Minutes (dispatching, ensuring the stability of the grid), essentially beyond the scope of our work, but introducing constraints for our time scales;

  • Days (unit commitment, taking care of compromises between various power plants);

  • Years, for evaluating marginal costs of long term stocks (typically hydroelectric stocks);

  • Tenths of years, for investments.

Nice challenges also include:

• Spatial distribution of problems; due to capacity limits we cannot consider a power grid like Europe + North Africa as a single “production = demand” constraint; with extra connections we can balance excess production by renewables for remote areas, although to a limited extent.

• Other uncertainties, which might be modeled by adversarial or stochastic frameworks (e.g., technological breakthroughs, decisions about ecological penalization).

We have several related projects (Citines, a European (FP7) project; in the near future we should start the Post project (ADEME); IOMCA, a ANR project), and POST, a ADEME project about investments in power systems. We have a collaboration with the SME Artelys, that works on optimization in general, and on energy management in particular.

Technical challenges: Our work focuses on the combination of reinforcement learning tools, with their anytime behavior and asymptotic guarantees, with existing fast approximate algorithms; see 6.2 . Our goal is to extend the state of the art by taking into account non-linearities which are often neglected in power systems due to the huge computational cost.

Related Activities:

• We are in the process of creating a Franco-Taiwanese company (maybe a Taiwanese company using French software) for energy optimization in Taiwan.

• We have a joint team with Taiwan, namely the Indema associate team (see Section 8.4.1.1 ).

• We have an I-lab in progress with Artelys (see Section 5.1 ) in order to ensure the transfer of our work.

• We have organized various forums and meetings around Energy Management.