Based on the predictions of fossil fuels depletion in the following years, as well as their negative impact due to generated exhaust fumes, eco-friendly generators, and more specifically wind generators, have arisen as a so-lution for the electric demand challenge. Wind energy consists in extracting energy from wind speed, and because of the uncertain and intermittent behaviour of this meteorological parameter, wind turbines output power cannot be optimally exploited. Although the vast majority of the research in wind speed forecasting field has consisted in the purpose of novel algorithms, these studies have not made a pre-processing step of the data in order to try to extract the maximum information from databases. Therefore, the goal of this paper consists in analysing whether the combination of time-frequency decomposition of wind speed data with different machine learning algorithms can increase the accuracy of current wind speed predictions for 10 min ahead. Obtained error metrics demonstrated that the deviation of developed wind speed forecaster was lower than 0.1% in 62% of the validation database. In addition, the root mean square error of the final forecaster was 0.34 m/s. This means an accuracy increase of 51.5% if the result is compared with benchmark model's results.

The aeronautical industry is one of the last groups which has decided to join the distributed architecture trend in order to increase both the safety and efficiency of future aircraft. However, the actual power system used in aircrafts has certain limitations that makes it difficult to achieve this objective due to its high centralisation. This paper proposes a novel methodology for the design of a new modular power electronic device that is based on semiconductor technology, which provides the equipment and functionality that makes the full decentralisation of the aircraft DC power system possible in the near future. The proposed and developed device can be adapted to the requirements of the system where it is going to be implanted, as it is possible to add as many devices as the system needs and have as many modules as needed. All the modules are bidirectional, which makes the system more redundant and fault tolerant, as the number of possible paths to feed the loads is increased. Tests were carried out with 5 devices (4 modules per device), 3 power supplies and 2 loads, where the correct operation of the system (path search, load feed and failure management) was proved.