Optimizing Power Systems through Tariff Design and Regional Trade Networks

power transfer station in the foreground with the sun rising behind it
The complexity of energy grids cannot be overstated. In order to be reliable and sustainable, power systems must be robust enough to operate seamlessly when there are unpredicted surges in demand, but also must run more efficiently and incorporate a greater variety of energy sources in order to meet sustainability goals. In this research project we apply deep learning to the study of a national and regional power system in order to develop simulation and modeling tools that help energy providers and regulators to pursue new strategies to positively affect performance and sustainability. By simulating the effects that tariffs and trade has on the cost of generating and delivering electricity to consumers, utility companies and government agencies can make better decisions about investments in electrical power capacity expansion and how using new sources of renewable energy affects the performance and cost of the system over time. The kinds of insights derived from our methods can also help regulators design tariffs in a manner that incentivizes consumers to more efficiently use the power network.
Logo for MIT's Center for Complex Engineering Systems (CCES)

Info & Decision

Systems & Networking




Visit the CCES site to learn more.