Artificial intelligence and machine learning are key factors for energy transition. Not only do they help in the decarbonisation of energy generation sources, but they also provide the means by which electricity is produced and distributed more intelligently. In today’s world, renewable energy sources cause unique challenges due to their variable nature. Because of this, energy prediction is crucial for stable work in the utilities sector.

In his presentation, Giuseppe Amoroso will discuss Enel’s AI program with a detailed look at three major case studies.

Artificial intelligence and communications technology present an opportunity for substantial change in the utilities sector. Mark Dillon will present on bringing practical experience to information security and the complexities of the utilities industry.

In his speech, Mark will present case studies of working with IoT as well as the automation of electric grids.

Leroy will present a case study on how NeedEnergy has used

• Weather variables in training its models to predict and forecast energy generation for microgrids in remote areas.
• Load Demand to train its Solar PV sizing tools, which bring insights and advice to utilities to respond to this demand with a combination of Solar PV and Battery Storage.
• Power trading data and volumes to predict day-ahead prices that will encourage energy developers to trade in these platforms especially in developing regions.
• Has been able to go beyond typical kWh/m² benchmarks and provide two linear models that can estimate residential electricity demand given a household’s monthly income and access to water.

In her presentation, Hajer Ben Charrada will discuss some of the AI platforms designed to make AI algorithms accessible to anyone in the industry, even those without prior knowledge of Machine Learning techniques and programming skills. During the presentation she will:

• Explain the modeling approach for forecasting different values such as electricity demand, power prices, renewable generation, and more

• Discuss case studies that have helped utilities companies produce better forecasts through deep learning techniques

• Introduce AI platforms through which end-users from the utilities and power industry can create and train their own AI models, using them for forecasting various time series

• The speaker will talk about the recently developed solutions designed to continually collect and analyze high-frequency data signatures across hundreds of asset types. 
• He will present some of the advanced AI tools and algorithms to identify the warning signs/precursors of an imminent failure in near real-time, allowing proactive replacement of key infrastructure assets before they fail. 
• He will also present case studies of how the applications of machine learning and intelligence can dramatically reduce unplanned power outages. The results of these applications are improved customer satisfaction, reduction of maintenance costs, and increased safety rates.