News archive

The second CRETE VALLEY review meeting brought project partners together in Crete to assess progress achieved across the project and discuss the next steps towards the Renewable Energy Valley Living Lab (REV-Lab). The meeting combined technical discussions on implementation, citizen engagement and replication with site visits to Arvi and Arkalochori.

This new study investigates how topology optimization and additive manufacturing can create lighter and high-performance automotive components, achieving up to 30% weight reduction while maintaining structural integrity.

CRETE VALLEY marked a major milestone with the inauguration of the construction of its district heating system in Arkalochori, followed by the first Energy Communities Day celebration in Greece.

This study presents a new modular framework for estimating electricity demand in distribution networks with limited monitoring data. Validated on a real network in Crete, it enables accurate load and voltage estimation even where smart meters are not widely available.

The paper presents an enhanced Measure–Correlate–Predict (MCP) approach to evaluate long-term wind potential and energy production in complex terrain in Greece.

New study introduces a modular framework to design and scale Renewable Energy Valleys, combining renewable generation, storage solutions, and sector-specific demand to support flexible and transferable energy systems.

Accurate wind power forecasting represents a challenge in integrating renewable energy into modern power. This paper presents a new meta-learning framework combining machine learning models and multi-source data to significantly improve the accuracy and reliability of short-term wind power forecasting.

Samsø Energy Academy represented CRETE VALLEY at the annual meeting of the European island community.

This paper presents SARGON2, an updated ontology that improves semantic data sharing in the energy sector. By integrating renewable energy, weather, and grid data, SARGON2 enhances interoperability and supports smarter energy systems.

A new study shows that short-window machine learning (7–90 days) improves electricity price forecasting in changing markets. LightGBM outperforms deep learning, offering higher accuracy and better detection of seasonal trends and price spikes.

This study explores how the design of traditional Lasithi Plateau windmills can inspire resilient, small-scale wind energy systems for electricity production.

This publication shows how transfer learning and advanced AI models significantly improve short-term building load forecasting, even when historical data are scarce.