AI in Energy 2026

Let's start by looking at what types of data are generated by different energy companies and how the underlying measurement architecture is built. We also highlight why data quality and validation is important and look at prioritisation: what information has real business relevance and what to focus on in a data-driven development. The aim is to present a framework that provides a clear answer to the question "what to measure and why?" for companies that want to invest in data-driven technologies.

What is the right approach to data?

Mapping energy data sources: production, consumption, grid and market data

Building metering architecture, data collection systems

Data prioritisation, data quality: which data have real business value?

What to measure and how?

Developing an energy data model and data warehouse strategy

How to turn data into value?

Predictive analytics: consumption forecasting, anomaly detection, maintenance optimisation

Driven investment decisions: CAPEX prioritisation based on metering data

Cybersecurity and systems integration challenges

This session will focus on how digitalisation, algorithms and artificial intelligence are being integrated into day-to-day business operations, and how energy management is increasingly becoming an IT issue. We will also look at the practical benefits of real-time monitoring and automated systems, including predictive consumption and production forecasting models.

There will be sessions on the proper optimisation of hybrid energy systems (e.g. solar PV and energy storage), AI-based scheduling, and the fine line that separates investments with real competitive advantage from low-return developments.

Digitalisation as an operational model shift: IT-driven decision support

The business impact of real-time monitoring systems

Automated control and optimization in an industrial environment

Predictive consumption and production forecasting

AI-based scheduling and portfolio optimisation in the electricity market

Optimisation of hybrid systems

Digital twin models in industrial power systems

Data-driven predictive maintenance

The third block asks: once the decision to invest has been made, where to take the idea from there. We put the financial reality behind the strategic intent: what are the sources of financing for energy digitisation, what is the cost structure and what are the conditions for making it a truly value-creating investment. We will review investment models such as classic CAPEX or SaaS schemes, and look at what external funding is available for energy digitisation.

By the end of the day, we will understand that data-driven investment and operating models are not a one-off technology development, but a long-term financial and strategic decision. With the right decisions, it can reduce energy costs, optimise production processes and lay the foundations for long-term market superiority.

CAPEX vs. OPEX models: own investment or SaaS/as-a-service

Bankability of software investments

Long-term competitive advantage: data assets as a strategic asset and market entry barrier

Monetising consumer flexibility: demand response business models

Participation in balancing and regulatory markets with data-driven optimization

Virtual power plant (VPP) models and industrial aggregation

AI-based portfolio management across multiple sites

Dynamic tariffs and real-time price signal-based operation

Selling surplus generation: when is it worth entering the market?

Energy sharing and peer-to-peer models in a corporate environment

Data as a service: externalisation of energy data

Szeretettel várjuk kedves vendégeinket a szakmai programot követő peszgős koccintásra!