Multi-Agent Systems SemantiC Interoperability for simulation and dEcision supporT in
complex energY systems

MAS-Society focuses on providing effective solutions to enable the widespread of Distributed Energy Resources (DER), namely Renewable-Based Generation (RBG), Demand Response (DR), Energy Storage Systems (ESS) and Electric Vehicles (EVs), enabling to catch their potential to increase the overall energy efficiency and economic and energetic sustainability. This is targeted through the implementation of a complete simulation infrastructure that combines several distinct simulators and systems directed to the study of specific problems in Power and Energy Systems (PES). The goal is to enable the joint simulation of multiple problems, enabling studying the problem as a whole in a realistic way. In this way allowing to assess the impact of different business, market and players? models in the scope of Electricity Markets (EM) and Smart Grids (SG), as well as analyzing the outcome from alternative
decision support approaches.MAS-Society conceives and develops an ontology based knowledge model that represents the domain concepts, accounting for the considered business, market and players? models. The ontology enables automatic reasoning to extract new knowledge. It also supports the communication between the considered systems and applications.

Understanding the same language will enable those tools to register in a registration platform that will be developed in the project, and therefore communicate and interact with distinct agents, systems and applications. The resulting society of Multi-Agent Systems (MAS) will also incorporate a set of advanced context-aware decision support models and methods that are developed in the scope of this project. This decision support is based on a strong artificial intelligence approach to enhance players? outcomes from their participation. A context analysis and definition methodology is developed, and a portfolio optimization model will support players in their decisions on which market opportunities to participate in each moment and context. The actual negotiation between players in a market environment is addressed by a machine learning approach to identify the best negotiation approaches to undertake
against each opponent.

The setup of MAS-Society simulations, through the specification and control of the multiple systems, applications and algorithms that will compose the simulation platform, will be enabled through a simulations control center. This control center will include a mechanism to manage the balance between simulations efficiency/effectiveness.
The ontology-based knowledge model will also be used to represent the concepts related to the different considered devices (e.g. energy related devices in buildings and SG), which will enable the models and methods developed by MAS-Society to be validated through the integration in a GECAD/ISEP laboratorial platform, which will combine the simulation capabilities of the MAS society resulting from this project, with physical control of energy resources.

 

Workpackages of the project

WP1 Organization and management: WP1 will ensure the effective coordination of the project, ensuring that the project objectives are achieved within the budget and the time schedule using the available resources effectively. Zita Vale, the PI, will ensure proper communication and coordination among the involved researchers and facilitate the project activities. She will coordinate periodical meetings and ensure compliance with legal, ethical, and privacy concerns.

WP2 Players, business and market models and specifications: WP2 defines the required business, players and market models and establishes the specifications to enable the implementation of the envisaged simulation environment.

WP3 Decision support for smart grid and electricity market participation: This WP will conceive and develop ontologies to represent the knowledge model to support the MAS society and simulation/emulation infrastructure to be developed in WP5 and WP6. The objectives are: to represent the domain concepts, relations and properties; and to support the communications between the involved systems, applications, services, players and devices. The domain knowledge is essential to enable a common understanding of the environment, and communications are critical to enable a common language for communication between all components that will be registered in the registration platform (WP5).

WP4 Decision support for smart grid and electricity market participation: This WP conceives and develops the required decision support models and methods to address the gaps identified in the SotA, namely the decision support contextualization; the optimization of players’ participation in multiple alternative/complementary market opportunities; the analysis of competitor players’ negotiation profiles; and the intelligent adaptation of market negotiation strategies. These methods will be developed according to the specifications of T2.4, so that the ontologies developed in WP3 can be used to integrate them in the MAS society of WP5.

WP5 Multi-agent systems society: WP5 develops a MAS society, enabling the interaction between distinct systems, through their inclusion in a registration platform that will make use of the ontologies developed in WP3 to facilitate the communications.

WP6 Laboratorial simulation and result analysis: This WP undertakes intensive and realistic simulation studies to test and validate, in laboratorial environment (TRL4), the multi-agent simulation platform that includes the models and methods resulting from the project.

WP7 Communication and Dissemination: WP7 is devoted to the project communication and dissemination activities creating visibility of the project objectives and of the achieved results. WP7 will ensure that the knowledge and results created in the project are disseminated to the appropriate target audiences at a national and international level (scientific community, industry, the general public, and other relevant stakeholders).

 

 

Start Date: 1st June 2018

Duration: 36 Months