Connected Intelligence

Master 2 - Interoperable Coordination and Regulation Schemes in Multi-Agent based Energy Management Systems
Keywords: Multi-Agent Systems, SemanticWeb Technology, Smart Energy Management

Summary

The global context of this research concerns the changes taking place in the global energy market introduced by the evolution of digital technologies. This global market is transforming into a decentralized eco-system of several local and agile energy markets where prosumers trade the energy they produce as well as the one they consume. In this context, Multi-Agent System (MAS) technologies are proving to be promising solutions [6, 8]. Since the preliminary works with the ARCHON system[5], several proposals have been done in relation to energy eco-system simulation [11], energy allocation optimisation [1, 3], energy trading management on behalf of human users (individuals or energy stakeholders), virtual plant formation[7], etc.

This research project is mainly concerned with the integration of several management units, each dedicated to individual energy management models, and their cooperation and coordination in a virtual power plant [4, 12]; or several. Beyond the definition of coordination and optimisation algorithms, a key issue in such approaches concerns the inter-operability of the various agent knowledge models. To this aim, several domain ontologies are proposed: Smart Energy Aware Systems, [9], Electricity Markets Ontology (EMO), ontology for electricity and natural gas energy markets [2, 13].

Since electricity markets are becoming extremely complex and dynamic, enlarging at regional and continental scale and integrating several energy sources, it is of first importance to go one step further in the study of interoperability. The research objective of this project is to study and propose models for building interoperable multi-agent based energy management systems. Basing the approach on existing ontologies and platforms (e.g. [10]), and on standards (https://sites.ieee.org/pes-mas/), the aim is to develop models integrating various market models and platforms addressing:

  1. interaction capabilities among heterogeneous autonomous agents (agent communication languages, actions on resources);
  2. coordination capabilities among the heterogeneous decision capabilities (e.g. Call for Proposals (CFP) ontology, Electricity Markets Results (EMR) ontology);
  3. regulation and organisation capabilities among the heterogeneous normative and coordination structures ruling the cooperation within the various virtual power plants, energy markets, etc (e.g. [14]).

Expected results

Theoretical

Models and ontologies for the interoperability among Multi-Agent based Energy Management Systems at the coordination and organisational levels

Practical

Proof of concepts demonstrating the interoperability between an Energy Management System developed at GECAD Laboratory in Porto, an Energy Management System developed at Connected Intelligence in Saint-Etienne, and an existing platform in use at ENGIE.

References