GEORGES HEBRAIL (EDF R&D)
Control of Future Smart Grids Using Big Data Analytics
In this talk, we will present a new framework called the Smart-Energy Operating-Systems (SE-OS) for controlling the electricity load in future smart grids. This framework, which is based on big data analytics, provides an optimal setting for intelligent demand response solutions for future intelligent and integrated energy systems.
The SE-OS concept contains classical market-based solutions using bidding and clearing on the higher levels, but on lower levels, ie. higher temporal or spatial resolutions, the concept takes advantage of a hierarchy of nested control technologies.
On a medium level, reference-based controllers are used for dealing with eg ancillary services problems, while model predictive control technologies are used on the end-user level. Examples from real life applications will be given. (presentation)
Digital Transformation @Enedis:
How Big Data Brings Value
In today’s context of the energy transition, important changes are undergoing in the energy sector. As a Distribution System Operators (DSO), Enedis operates its network in a context where more decentralized renewables are connected to its grid and new ways of electricity consumption are emerging. Given the increasing development of information technology, such as the Internet of things, so called artificial intelligence… digital transformation, and in particular data-driven approaches, brings data at the heart of energy transition.
Enedis is committed to an ambitious data strategy. Linky, Enedis’s smart meter currently in deployment, provides a large set of data that helps to improve electricity distribution quality and performance (better grid supervision in context of increasing decentralized renewables, power failures anticipation, asset management, predictive maintenance). In addition, Enedis, as a neutral market enabler, is committed to administrate the exchange of energy market data neutrally. Enedis is the first DSO in Europe that launched an open data platform where aggregated data of public interest are released to local authorities and to customers in order to support local innovation and new services to enable the energy transition.
This is, for now, and more will come soon, how big data brings value for Enedis.
How (Big) Data is Transforming the Commercial Context for an Energy Supplier
This presentation will give insights related to the following questions:
What are the opportunities for an energy supplier in exploiting the full potential of the available data?
How is big data changing the customer relationship at EDF Luminus today and what is to be expected in the future?
What applications / new services/ process optimizations / … have a proven track record in value creation and which domains seem promising for future development? (presentation)
Digital Transformation in Enel Thermal Generation
The impact of Big Data technologies in the energy domain is increasing due to the digitalization of all the processes in the generation value chain. Through the application of integrated sensors and predictive algorithms developed with the latest cloud-based computing techniques and machine-learning algorithm, it is possible to maximize the efficiency of maintenance tasks by reducing power plant outage and transforming the operation data into smart actions.
Enel is investing in the development of a specific application of Big Data Predictive Analytics for industrial plant machinery fault and anomaly detection, with the objective to reduce unavailability and maintenance costs and at the same time improve plant flexibility and reliability. The applications are focused on the development of machine learning failure prediction models and anomalous operating condition scoring on a subset of the main types of machinery in the power plant.
The outcomes of the models are important information to be adopted for optimizing plant operation, in order to maximize revenues and minimizing maintenance and operation costs. One of the most critical and complex failures that Enel addressed with big data techniques is the disruptive thermo-acoustic instabilities, also known as humming, in natural gas turbines. Example of this application will be given.