I-NERGY is an EU-funded H2020 innovation project around Artificial Intelligence (AI) for Next Generation Energy aiming at reshaping the energy sector value chain towards better business and operational performance, increased environmental sustainability, and the creation of a stronger social fabric propagating high social value among citizens.
I-NERGY will run for 3 years has an overall budget of approximately €5m and will distribute around €2m among its selected open call beneficiaries.
The project will launch 2 open calls to select 10 and 15 Bottom-up Projects. The 1st Open Call was targeted to SMEs and Startups developing building blocks for new AI algorithms/services and small-scale experiments with an expected outcome of fully functional prototypes. The 2nd Open Call was targeted to consortiums made up of Start-up / SME (service developer / provider), plus 1 EPES stakeholder to develop MVPs.
In both cases, the selection process prioritised projects maximising the impact of the platform and demonstrating the benefit of AI in products, processes, or services.
Following a careful review and assessment of 80 applications from 26 European Union and Associated Countries member states, the I-NERGY initiative selected the 15 winning proposals who have embarked on a nine-month-long Technical Transfer Programme (TTP) in March 2023.
Each beneficiary will receive a financial grant of up to 100,000 Euros and invaluable mentorship services.
The selected beneficiaries have the goal to develop new services on top of existing technologies (Minimum Viable Products) addressing specific cross-sectorial challenges within the Energy sector or an energy-related domain. The services are being developed and tested within a pilot setting in order to get to a fully functional stage with produced assets being published on Europe’s AI on-demand platform.
All selected proposals were submitted by consortia of 2 members (mandatory), made up of a technology service provider/developer (SME) and an infrastructure provider/data owner willing to implement an energetic solution (any entity) with the selected third parties representing a total of 12 European Countries.
For further details, access the comprehensive Evaluation Report here.
Additional information on the I-NERGY Open Call is available here.
Meet the winners here.
I-NERGY 1st Open Call
After the assessment and evaluation of 126 submitted applications from 27 European Union and Associated Countries, the I-NERGY project has selected the 10 winning proposals to join its first 6-month long Technical Transfer Programme, starting at the end of April 2022, which includes up to 50,000 Euros funding per beneficiary and mentoring services.
Meet the winners here.
This dataset contains data of electricity generation of Montenegro and several neighboring countries between 2019 and mid 2023. Data was gathered from the ENTSOE transparency platform.
A dataset of the Montenegro electricity generation by generation unit for the whole year 2022, in an hourly basis.
To provide accurate measures of Cross Zonal Capacity, a key parameter is Net Position (the difference between generation and load of a zone). Here we describe our supervised model to predict net position for the next 48h that achieve an MAE of 75.8 and a...
In the context of AI4CZC project, this model forecasts the Montenegro net position (difference between generation and load) for the next 48h. The model was trained with data from 2019 to 2021 and tested on 2022 data. It performs with a MAE of 75.8 and a R...
This dataset presents an estimation of the emissions by kWh of CO2 equivalent of the generation types of Montenegro, Serbia, Bosnia, Italy Center-South and Kosovo
We present here three scenarios of 24h that we used to test the AI4CZC model. These scenarios include an usual day scenario, a scenario where the Montenegro thermal plant is down, and a scenario were the cable between Montenegro and Italy is down.
After obtaining new meteorological data, we try to improve the results of session 1. The objective is to build a model to forecast Montenegro Cross Zonal Capacity 48h in advance. In this session, we achieved a model with a R2 of 0.7167 and a MAE of 67.0...
In the energy landscape that DSOs find themselves in today, predicting demand and the generation capacity of the systems to which they distribute becomes essential. This is mainly due to the injection of renewable energy among the consumers of the network...
LexaTexer provides an Enterprise AI platform to support the energy value chain with prebuilt, configurable AI applications addressing CAPEX intense hydro assets like Pelton and Francis turbines and pumps. In this project we combine our Enterprise AI platf...
SPIRE client provides multiple helper functions to allow communication with the SPIRE server and manipulation of ROS bagfiles and topics
Jupyter Notebook providing the execution of a simulation of a given Grid2Op agent using the PowSyBl backend.
Docker image containing the script to execute a Grid2Op agent training while using the PowSyBl Backend on a dataset.
A machine learning operations (MLOps) framework for time series forecasting
The service provides the total PV production per year for a defined site and parametrised fields, with comparative graphs between current production (based on historical weather data) and the future (short-term) production considering climate change scena...
The service contains three tools: EPC and Estimated Energy Demand Viewer, Asturias Cadastre data analysis and Asturias Energy Performance Certificates data analysis; and is available both in English and Spanish, as it is developed for the region of Asturi...
Service Docker deployment accompanied by a Postgresql/PostGIS database.
A Dataset with Energy Efficiency Measures available for renovations provided by REA (Riga Energy Agency)
FlexDR, an AI-based web application for Flexibility Forecasting and Demand Response
Databroker service used for feeding timeseries data to electrical load profiling service.
An electrical load clustering service for identifying the load profile for prosumers in city of Terni, Italy.
A global forecasting service for predicting the aggregated hourly net electrical load of 20 European transmission system operators (Belgium, Czech Republic, Denmark, Estonia, Estonia, Finland, France, Greece, Hungary, Italy, Latvia, Lithuania, the Netherl...
A forecasting service for predicting the positive active energy (in kWh) consumption of prosumers in the Italian city of Terni. The dataset was provided by ASM and the service makes use of a LightGBM model. (AIExperiments Asset)
AI Model based on LSTM forecasting the Utilization and Energy Consumption of Charging Stations. We forecast the future activity/consumption/utilization/Customer-experience on EV Charging stations using LSTM timeseries forecasting yielding highly accurate ...
The service supports users in the definition of the Measurement and Verification Plan following the instructions provided in the International Performance Measurement and Verification Protocol (IPMVP). It is divided into two parts, one to define the prope...
The service is based on the Energy Performance Certificates XML database from Asturias region (in the North of Spain), and it checks data from different parameters in the XML (either an uploaded file or selecting one from the database) according to differ...
A physics-informed deep neural network developed to predict the energy consumption of a buildings.
An easy to use tool to manage B2B Cross-stakeholder Trusted Off-chain Data Sharing
