energy2050: Here are the winners of the VERBUND Innovation Challenge 2017

Digitalisation makes new approaches possible for the wide variety of challenges in the energy sector. "With the Innovation Challenge 2017, over the course of the summer VERBUND sought out innovative solutions for three different energy-related tasks", says CEO Wolfgang Anzengruber. "Our teams in the areas of electricity generation, transmission and consumer solutions identified relevant questions, genuine 'needs', and called on the international research community to find solutions for them." More than 50 start-ups, research teams, university institutes and SMEs took part in preliminary talks with the supporting VERBUND teams. 26 candidates from 12 different countries then submitted their applications. These supporting documents were evaluated by a jury according to uniform criteria. Three finalists per challenge had the opportunity to present their ideas at a Pitching Day the end of July in Vienna.

Three challenges, three winners

As part of the VERBUND energy conference, the three winners from Spain, England and Austria were each awarded EUR 8,000 in prize money and presented themselves and their solutions to the energy sector audience at the energy2050 conference.

CIMNE: Neural networks for predicting dam performance

VERBUND's dams and retaining walls are some of the most thoroughly monitored constructions in Austria. Highly sensitive measuring equipment discerns even the smallest of changes and communicates the measurement values in real time. In addition, there are regular inspections by trained personnel who carry out visual checks and further measurements, and record and evaluate the measurement data.

The question in Challenge Number 1 was whether this could be supplemented by neural networks, linking the multitude of data in such a way that the performance of power plant dams could be analysed and predicted. The Spanish research centre CIMNE (International Center for Numerical Methods in Engineering, Barcelona) convincingly demonstrated its numerical research methods for neural networks. "Effective dam monitoring systems provide a multitude of reliable technical data. While conventional statistical methods analyse these data, neural networks capable of learning have the additional ability to interpret the data and to predict future dam performance", states Fernando Salazar from CIMNE. "The ultimate goal in practice is to recognise possible anomalies so early on that errors do not even have a chance to occur."

This increase in the existing data, using all effective analysis tools that offer advantages compared to conventional statistical methods, offers more precision, flexibility, or the capability of predicting dam performance. The ultimate goal in practice is that the anomalies which lead to errors are recognised early on.

Efficient Energy Technology (E2T): Energy optimisation for prosumers

The third challenge has to do with the topic of decentralised optimisation for private or business consumers who have their own production facilities. How can internal consumption be maximised and interruption-free electricity supply be ensured? The winner is the start-up Efficient Energy Technology (E2T) from Graz, which constructs a combi-system for PV generation and electricity storage and upgrades it into an intuitive plug-and-play mini-power plant through intelligent energy measuring technology. "We have developed an innovative measuring technique which is capable of determining the electricity demand of a phase of the household from a power outlet. On the basis of this technology, for the first time ever household power stores are possible which can simply be connected to a normal power outlet", relates Christoph Grimmer, CEO and co-founder of E2T. Based on this technology with the working title NetDetection, 100% internal consumption of the decentrally produced green electricity can be ensured for the smallest unit, a household.

Leeds Becket University: Sonification of large quantities of data

The second challenge related to the field of high voltage grids: The sought-after solution was sonification of large quantities of data, particularly operating data such as load data for power lines, transformers or other network elements. These data are usually presented in a visual form. Sonification makes use of a second sensory dimension, and depending on its usage, it can offer more security from the grid operator's perspective or more emotion, for example during training or tours. The winning team from the English Leeds Beckett University collaborated for this task with Echochroma New Music Research Group, which furthers the development of compositional language. "Together with our colleagues at Echochroma, we transformed the APG energy generation data into music and created individual sounds for each kind of energy. For example, renewable energy sources such as hydropower or wind power are depicted by natural sounds, while energy from fossil sources is represented by rhythmic and machine-like sounds. And the relative volume makes perceptible the amount of energy generated by this energy source at every point in time during the year", explains Kingsley Ash from Leeds Becket University. Sonification is still in an early stage of development. With our system it is possible to experience energy data in a completely new, intuitive way."

More about the energy conference in Fuschl: www.energy2050.at