EO x Grid: AI-Driven PV Forecasting for Grid Optimisation and Flexibility Management

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.

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

• Flare network - We are a core part of the Flare team, providing ongoing development of smart contracts for Flare Network for several decentralised on-chain mechanisms. We also provide the system's integrity and utility, leverage the distributed nature of the network, and enable its participants to act honestly while providing value and trust to the blockchain.
• INATrace in Rwanda - We developed a blockchain-based transparency and traceability technology, that makes coffee traceable from its production to the final package. The system confirms the coffee’s origin and quality, together with the fairness of its value chain, by tracking it all the way from the farmer to the end consumer.
• e-Su Register - We upgraded the e-Su Register information system by developing new functionalities, implementing EU standards and enabling parallelization to optimize the digital processes it supports
• One Stop Shop - SPOT - An all-in-one digital system that provides a supportive environment for entrepreneurs and easier access to all relevant information and funding. The platform was created and rolled out in cooperation with a public agency.
• GoOpti - A digital transformation of a transportation business into a cloud-based transportation marketplace, based on advanced algorithms. It’s a sustainable solution loved by end customers, as shown by the 93% satisfaction rate.
• 8ECM - We developed the congress’ website, digitalized processes, added analytics, and implemented its payment system.
• Multimedia portal SIO 2020 - We created a sustainable solution with three user-friendly, secure, and widely available platforms for video communication and management.
• ACE.Trade - We developed an entry-level app for crypto trading. It simplifies the first steps in the crypto world for initiatives and first time traders, while staying compliant with regulations.
• TAS - We actively participated in developing a Toronto Annotation Platform - a web-based application that allows for larger, more efficient, and more accurate data annotation projects.
• eSpis - Development and implementation of a digital system for reviewing court case files with support for search and filter functions to accelerate the process
• EO x Grid - Enhancing grid stability and renewable energy integration through accurate space-based PV forecasting. Funded under the European Space Agency's (ESA) ARTES 4.0 Downstream Applications program.
• EDISON WINCI - A project for developing the infrastructure, competencies, and elements of business models for logistical systems of contactless-charging electric vehicles.
• DIGITRUST - A digital transformation of a business with innovative digital solutions and a decentralized system
• Digital Solutions for Sustainable Cattle Farming - Developing advanced digital solutions that will help address the challenges of modern cattle farming. The main goal is to manage herds efficiently, improve animal welfare, and increase farm profitability by introducing advanced digital solutions.
• Di-Gozd - Development of an online and mobile application for a digital forest inventory
• ARRS J1-2481 - Mathematical and computational methods for polyhedral self-assembly.
• Phot2Bin - Detection of multiple stellar systems from single-epoch photometry.
• SOPOS - System for limiting the transmission of infections in buildings
• Photo2Chem - Stellar chemistry from photometric narrow-band imaging
• Infrastructure program I0-0047 - Upgrading services, providing support and maintaining scientific infrastructure
• Program group P1-0294 - Computationally intensive methods in theoretical computer science, discrete mathematics, combinatorial optimization, and numerical analysis and algebra with applications in natural and social sciences.
• KumuluzAPI - Establishing an API ecosystem of smart cities and communities
• PLASMA - A project for developing a banking and trading platform, upgraded with an innovative connection between the financial, fintech, and crypto worlds.
• SCI Journals - Managing, editing and hosting scientific and professional publications
• Kumuluz Crowdsensing - Researching new technologies for automatic data collection and the measurement of crowd data
• AI-FINREG - Regulation of modern FinTech services and protection of personal data
• Z7-7614 - Large networks in business systems analytics
• Z7-8271 - Improving the defibering process of mineral wool
• KKIPP - 4PR - A tool for creating intelligent digital technology platforms
• Da.Re. - The use of data science to restructure education