Engineering Innovation in
Smart Energy & Utilities
Up to a million predictions in 60 minutes: with our holistic approach we use Artificial Intelligence to predict energy production from renewable sources.
Approach & Solution
Approach
The steady increase in the number of non-programmable Renewable Energy Sources plants has obvious advantages from the point of view of environmental impact, but it poses major new challenges to the traditional model of electricity grid management: we are moving from a hierarchical model in which a few large power stations generate energy by planning it to a grid model in which many non-programmable sources contribute to energy production. This poses problems in guaranteeing the continuity of the service.
It is therefore necessary to transform the current electricity grid into an active and intelligent organisation that monitors all energy sources and regulates itself to avoid overloads or blackouts.
Our client, among the leaders of energy distribution, has initiated this transformation process by selecting Engineering as its partner to manage this revolution in the energy world.
It is therefore necessary to transform the current electricity grid into an active and intelligent organisation that monitors all energy sources and regulates itself to avoid overloads or blackouts.
Our client, among the leaders of energy distribution, has initiated this transformation process by selecting Engineering as its partner to manage this revolution in the energy world.
Solution
The project was carried out according to our holistic and multidisciplinary approach, which allows us to achieve our goals by integrating a variety of techniques, ranging from engineering, mathematics, statistics, machine/deep learning and artificial intelligence.
We used a Grey Box approach, combining models of electrical systems with predictive ones, exploiting Machine Learning and Deep Learning. We also developed algorithms capable of making accurate predictions, able to adapt themselves both to the changes in the structure of the national electricity system and to the variations in production and load detected in the data.
We have therefore evolved the model by adding associative algorithms to relate different plants to each other, optimisation algorithms to identify the actual load state of the electricity grid, simulation algorithms to assess performance trends and the number and optimal position of sentinel plants from which is possible to extract real data to optimise grid load forecasting.
We used a Grey Box approach, combining models of electrical systems with predictive ones, exploiting Machine Learning and Deep Learning. We also developed algorithms capable of making accurate predictions, able to adapt themselves both to the changes in the structure of the national electricity system and to the variations in production and load detected in the data.
We have therefore evolved the model by adding associative algorithms to relate different plants to each other, optimisation algorithms to identify the actual load state of the electricity grid, simulation algorithms to assess performance trends and the number and optimal position of sentinel plants from which is possible to extract real data to optimise grid load forecasting.
Results
Predictive, Associative, Optimization, Simulation Algorithms
Real-time Estimates
1 Mil previsions / 60 mins
Improved Grid Stability and Energy transportation
Project value
Process performance
Innovation
Enabling Technologies
AI & Advanced Analytics
Project Team
Data & Analytics