Published the 2 April 2024
The Di-Hydro project involves digitizing hydropower plants, to operate them as sustainably as possible and better plan maintenance. IMT, in particular Télécom SudParis, is contributing to the development of a federated platform designed to facilitate secure data-exchange and decision-making, both at the level of each individual plant and collectively.
The Ilarionas hydro power plant, located on Aliakmon basin in Central Macedonia, Greece, is one of the pilot sites for the management system developed during the Di-Hydro project. Credits: EUPCD.
Hydropower is the third biggest source of electricity in the world, behind coal and gas, and it is also the number-one source of renewable energy. But though it is renewable, it is not necessarily “green”. Hydropower plants use the kinetic energy of running water and convert it into mechanical energy, then electricity. These facilities – connected either to a direct water supply, such as a river, or to a water reservoir, such as a dam – have a significant impact on water quality and ecosystems: blocking the circulation of fish and sediment, increasing water temperature, increasing flooding risks downstream, and other issues besides.
Many European countries, particularly those with mountainous regions, have exploited their hydropower potential in a “wild” and opportunistic manner, without taking aquatic ecosystems into account. In a context of environmental transition, development of this renewable and competitive energy source therefore represents an opportunity to become more sustainable and eco-friendly.
The Di-Hydro project aims to respond to these challenges, with funding from the Horizon Europe program as part of the call for projects around the “digitalization” of power plants. The project is based on integrating digital technology to upgrade existing hydropower plants, in order to improve their energy and ecological performance. Two teams from Télécom SudParis are contributing their expertise in interoperability and cybersecurity.
The goal of the Di-Hydro project is to optimize the functioning of hydropower plants at seven pilot sites, located in Greece, Serbia and Italy. This optimization involves digitalizing ordinary operations and maintenance via the Internet of Things (IoT). Various sensors will be installed, to pilot infrastructure and machines as well as monitor biodiversity and water quality in surrounding ecosystems.
Some of these sensors will be provided directly by local energy providers that are partners of the project, while others will be developed by other members of the consortium. “We have planned around six months of installation and roll-out for the sensors, before being able to exploit and analyze the data,” says Georgios Bouloukakis, researcher at Télécom SudParis and Principal Instigator (PI) of the project.
This new data will make it possible to better monitor the energy efficiency of plants and their impact on the environment, so as to improve their functioning. It will also be used in conjunction with historic operational data to supply tools using Artificial Intelligence (AI) for predictive maintenance, or to better anticipate the energy demand and adapt production accordingly. All tools for data exploitation and decision-making will be grouped under a federated platform, developed by Télécom SudParis.
Hydropower plants are connected either to a direct water supply or to a water reservoir as shown here at Ovčar Banja, in Serbia. Credits : Elektroprivreda Srbije JSC.
The Télécom SudParis team was initially sought to respond to the platform’s cybersecurity needs, but it soon identified additional needs in terms of interoperability – in other words, the system’s functionality to exchange data and facilitate information-sharing. The subject emerged naturally when it became clear how many kinds of data would be needed to supply AI models and the wide range of actors involved – both in terms of their activity and their location – in the Di-Hydro project.
“As I was involved in the initial discussions and have significant experience in building IoT systems, I explained to the project coordinator the data exchange requirements in this domain,” says Georgios Bouloukakis. “Consequently, they suggested that I oversee this aspect of the project.” His work intersects with that of his colleague from Télécom SudParis, Joaquim Garcia Alfaro, cybersecurity researcher and co-PI of Di-Hydro, around the development of this federated platform in a secured IoT context. The latter had to facilitate decision-making and experience-sharing between the various actors – within a single country or between different countries, while guaranteeing the security and confidentiality of each one’s data and models.
The first stage in building this platform was integrating “Digital Twins” of hydropower plants. Each physical site will therefore be represented digitally “based both on static data (rooms, hallways, etc.) and dynamic data, like a person’s entry into a room, supplied by IoT devices,” says Georgios Bouloukakis.
As he highlights, the problem is that even if AI models are trained by a hydropower plant provider, “each sensor provides its own data structure and each provider will supply data in a different format.” It is therefore essential to define a standard, common format with which each partner must comply, in order to make collaboration possible.
This standard will apply to all data, whether collected by existing sensors or future sensors to be integrated into the system. The partners responsible for developing new sensors will have to ensure that the data collected “comes out” in a format defined by the project. “Some partners may encounter difficulties complying with the selected format. In this case, we will help them by creating connectors to ensure the ‘liaison’ of this non-standard data,” says Georgios Bouloukakis.
The aim of the platform is to offer new solutions through a distributed, non-centralized decision-making algorithm. At first, multiple AI models will be trained independently, using local data. To consolidate these advancements, IMT scientists will leverage their prior expertise in selective sharing mechanisms and ‘federated software architectures’.
This AI approach might involve developing a global model that consolidates multiple models trained on local data – in this case, data gathered at various plants. The ‘federated’ models can then be simulated for decision-making at multiple levels.
Sharing all this standardized data could also make it possible to complete missing data. “We anticipate a degree of variability in the data across different plants, with some able to provide certain data while others cannot. Thanks to this research and the tools under development, we aim to address these data gaps,” says Georgios Bouloukakis. The ultimate goal is to constantly gain greater understanding of these systems, for well-functioning, optimal and sustainable hydropower plants.
Di-Hydro is short for DIgital maintenance for sustainable and flexible operation of HYDROpower plant. The project has received €4 million of funding as part of the Sustainable, Secure and Competitive Energy Supply call for projects for the Horizon Europe program.
It mobilizes 13 public and private partners, across seven countries (Cyprus, France, Greece, Italy, Romania, Serbia, Spain). Among them, there is the CERTH (Centre for Research & Technology, Hellas), which is coordinating the project, and the main electricity suppliers for the countries where the hydropower plants under study are located: DEI (or Public Power Corporation, PPC) in Greece, EPS in Serbia, and A2A, the leading operator in the urban heating sector, in Italy.
The project was launched in October 2023 for a period of three years. The first in-person meeting has already taken place in Greece, and a second will soon follow in Romania on April 11. More information on the website: https://dihydro-project.eu
Stéphane Avril, the mechanics of human tissue