| WP2 | Data layer design and development |
This activity aimed to develop the data layer of the SMART-LEM platform, focusing on the efficient integration and processing of data from various sources to support business models in Local Energy Markets (LEM). Requirements for data collection and integration were defined, utilizing IoT devices, sensors, and other sources, with an emphasis on personalizing consumer comfort and optimizing energy resources. The proposed architecture includes two processing layers: a local layer, based on edge computing, for initial data collection, and a cloud layer for aggregation and integration, with data managed in a “data lake” connected to multiple sources.
The Big Data storage solution enables real-time and batch data ingestion and distillation, preparing it for complex analyses. Business process models were developed using BPMN diagrams for prosumers, storage systems, EV charging stations, aggregators, and local markets, optimizing transactions and resource usage.
| WP3 | Business Models (BM) development |
T3.1 Develop BM for con-/prosumers:
This activity focused on developing innovative business models for participants in Local Energy Markets, including consumers, prosumers, aggregators, and EV charging stations. For prosumers, a monitoring and control module was proposed to optimize consumption and the utilization of renewable energy through predictions, recommendations, and optimizations. The models for charging stations targeted energy flexibility and smart charging, also addressing the use of batteries in a Vehicle-to-Grid context. Aggregators were positioned as intermediaries that consolidate multiple resources, acting as virtual power plants to provide flexibility services and mitigate price fluctuation risks.
The business models for local markets provide a decentralized framework for trading renewable energy, reducing dependence on the main grid and maximizing resource efficiency. An innovative component was proposed in the form of a virtual assistant which uses Artificial Intelligence (AI)-based algorithms to optimize consumption, transactions, and cost reduction. Simulations demonstrated significant improvements in energy self-sufficiency and financial savings for users.