I have deep knowledge and experience in the two utmost important fields: AI (Machine Learning) and Energy (Renewables). Led an AI-project for Dell Inc, where a framework for detecting and quantifying AI opportunities was developed and a taxonomy for the different technologies was created to classify the established and the rising options. Wrote my thesis ("Artificial Intelligence Opportunities and an End-To-End Data Driven Solution for Predicting Hardware Failures") as part of this project to develop a new approach "to detect and prevent hardware failure" by using different Machine Learning platforms (ie. Amazon ML, Microsoft Azure, IBM Watson, DataRobot, Eureqa Nutonian, etc.) and algorithms. On the other hand, I have been involved in the energy (including renewable) businesses through directly having worked for companies in this area (Bain & Company, Grupo Alfa, Kiin Energy) and focused on business (commercial and operational) analysis and business development.

1) I have good experience for Setting up wind turbines i.e. projects commissioning and thereafter O&M so complete knowhow to setup wind farm 2) Worked on different make of with turbines

I have 7 years of experience in Business Analysis and Data Science applied to the Energy Sector. I started in university, doing a Master thesis with an O&G industrial sponsor on novel approaches to seismic data processing for Oil exploration, then as a R&D geophysicist in a geophysical service company, working on new algorithms for magnetotelluric and controlled source electromagnetics data processing, and finally moving to a leading european gas company to work as a Technical-Scientific software manager. My focus now is on simulation and optimization algorithms and systems applied to Gas Storage and Transportation processes; I have leaded projects ranging from an automated surveillance system that helps reservoir engineers to have complete control over more than 300 operative wells throuhg the seamless integration of a Production Data Management system, Reservoir simulation system, Well simulation system and IIOT data coming from the field, to a global optimizer of the operative condition (e.g. fuel gas consumption, emissions) of gas transport and gas storage plants through the combination of simulation and IIOT data. My role has been extended last at the end of 2016, and now I cover also the IT Innovation area, scouting solutions and delivering PoC on business-oriented applications of the current most promising technologies in the IT field (e.g. AI, ML, IIoT, Blockchain, RPA, etc)

Almost for 10 years I have been involved in the wind energy industry with different roles. The wind industry is changing, wind farms have to be more reliable and cost effective for the asset owners to have decent revenues. From the competitiveness point of view technology and machine learning are gonna help to improve wind turbine´s performance. Still, there is a big challenge to integrate technology in real wind farms. As a technical operator and analyst I have seen that the main turbine issues might be prevented with proper technology solutions and consecuently minimizing down time. Another interesting point is how to integrate machine learning to maximize financial turnover on the energy markets. I have concrete knowledge on how to trade energy from a renewable energy producer´s view. Finally, I have been project manager for a project integrating an ERPS system, a top level SCADA and wind turbine manufacturers mfor AREVA, Vestas, Enercon and Nordex. It would be a pleasure to participate within this team.

I have a good understanding of machine learning and wind energy systems. I placed in the top 25% of the Kaggle machine learning Two Sigma Financial Modeling Challenge and have worked for the National Renewable Energy Laboratory researching wind energy systems engineering as an intern for two years. I am an author of three scientific publications: “Optimization Under Uncertainty of Site-Specific Turbine Configurations,” “Wind Farm Turbine Type and Placement Optimization,” and “Optimization Under Uncertainty for Wake Steering Strategies.” I think that there are several great ways to apply machine learning in the wind energy industry: data validation is a time-consuming task that could be automated, model errors can predicted in a sophisticated manner, and component damage can be detected before it’s too late.