The Challenge: Electricity utilities are facing increasing challenges due to the rising share of distributed energy resources (DER), particularly photovoltaic (PV) installations. A significant problem is the lack of access to real-time generation data from many PV assets, making it difficult to balance the grid and manage flexibility. Current forecasting methods often lack the accuracy and granularity needed at the local grid level, especially for PV assets without readily available generation data. This can lead to inefficient grid operations, higher costs, and underutilization of local flexibility markets.
Project Vision: The "EO x Grid" project aims to develop an Earth Observation (EO)- and Artificial Intelligence (AI)-driven forecasting service to optimise electricity distribution grid operations and enable informed decisions related to local flexibility markets. The ultimate goal is to provide accurate and timely PV generation forecasts, leveraging space-based data, to enhance the integration of renewable energy sources and improve grid management.
Target Audience: The primary end-users of this project are electricity utilities. Key strategic partners include smart grid software providers (ADMS/DERMS). Secondary users include asset operators (PV, batteries) and power traders.
Funding: This project is a Feasibility Study proposed for funding under the European Space Agency's (ESA) ARTES 4.0 Downstream Applications program.
Project Goals & Objectives
Main Goals:
- To develop and validate a highly accurate and timely PV generation forecasting service that integrates Earth Observation data from Meteosat MTG and Artificial Intelligence.
- To assess the technical and commercial feasibility of this forecasting service for optimising electricity distribution grid operations and local flexibility management.
Specific Objectives / Key Performance Indicators (KPIs):
- Achieve a target Mean Absolute Percentage Error (MAPE) and Weighted MAPE (WMAPE) ranging from below 5% (nowcasting) to 20% (day ahead) in PV generation forecasts.
- Provide PV generation forecasts with a prediction horizon of up to 48 hours ahead.
- Develop the capability to forecast PV generation aggregated at the level of low- or mid-voltage transformers, including assets without historical or real-time data.
- Determine the minimal technical requirements and optimal number of reference points needed for the expected accuracy of forecasts across the grid.
- Validate the operational and financial value of the forecasting service with target customers.
Key Features/Activities:
- Utilisation of Meteosat MTG data: To achieve high accuracy and low latency in PV forecasting, which is a key differentiator from existing solutions.
- AI Framework for PV Forecasting: Employing advanced AI models to process and analyse satellite, weather, and energy data to generate accurate predictions.
- PV Forecasting for Reference Points: Establishing forecasts based on available data from satellites, NWP, and selected PV assets with IoT devices.
- PV Forecasting for All PV Assets on the Grid: Extrapolating forecasts from reference points to the entire grid using sensitivity analysis and available metadata.
- Validation on Different Scales: Ensuring the accuracy and reliability of forecasts at various aggregation levels.
- Assessment of Technical and Commercial Feasibility: Conducting a comprehensive study to determine the viability of the proposed service.
The core innovation lies in the use of Meteosat MTG data to achieve unprecedented performance and scalability in PV forecasting, particularly for localized forecasts at the transformer level and for PV assets without real-time data. The project aims for higher accuracy and lower latency than competing services, which currently do not leverage MTG data in this way. The focus on solving the specific problem of forecasting for PV assets lacking data is another key differentiator.
Connectivity Enhanced Grid Stability
Accurate PV forecasts improve prediction of grid imbalances.
Environment Environmental Gains
Maximizing PV usage reduces reliance on fossil fuels and lowers emissions.
Uporabniška izkušnja Greater Renewable Integration
Reliable forecasting allows more PV connections by mitigating intermittency issues.
Check Lower Operational Costs
Optimized operations and flexibility planning reduce balancing and procurement costs.
Impact & Benefits
Successful development and implementation of the "EO x Grid" service are expected to yield several significant benefits:
- Improved Grid Stability: More accurate PV generation forecasts will enable better anticipation of grid imbalances, leading to enhanced stability.
- Reduced Operational Costs: Utilities can optimise grid operations and better plan the use of local flexibility services, potentially reducing costs associated with balancing and energy procurement.
- Increased Renewable Energy Integration: Accurate forecasting can facilitate the connection of more PV power plants to the grid by mitigating concerns about intermittency.
- Better Local Flexibility Market Participation: Improved predictability of PV generation will allow for more effective utilization of local flexibility resources, fostering market growth and reducing prices.
- Minimised Investment in IoT Infrastructure: The space-based approach reduces the need for extensive and expensive IoT-based infrastructure for monitoring PV assets.
- Environmental Benefits: Maximising the use of PV power will reduce reliance on fossil fuels for grid balancing, contributing to lower greenhouse gas emissions.
The Feasibility Study is the first step towards developing a fully operational service. The goal is to progress to a demonstration project to validate the service in real-world conditions, followed by a commercial roll-out to electricity utilities and other relevant stakeholders. Partnerships with smart grid software providers are crucial for long-term market penetration and scalability.
Partners
The project team comprises experts from Abelium in AI-driven PV forecasting and project management, researchers from IRI UL with expertise in grid-level forecasting, and operational and technical experts from Elektro Primorska.
- Abelium d.o.o. (Lead Organisation), a high-tech company specializing in innovative digital solutions and research, with strong expertise in AI and data science.
- IRI UL (Institute for Innovation and Development of University of Ljubljana), a research and development institute with a focus on sustainable energy and smart energy networks.
- Elektro Primorska d.d., a Slovenian electricity distributor, providing real-world operational insights, data, and user requirements.
Similar projects
- Phot2Bin - Detection of multiple stellar systems from single-epoch photometry.
- Photo2Chem - Stellar chemistry from photometric narrow-band imaging