Minsait has a leading role in the ROMEO project (Work Package 5 “Data Acquisition and Analytics Ecosystem”)

Minsait, an Indra company, is a leading firm in Digital Transformation Consultancy and Information Technologies in Spain and Latin America. Minsait has a leading role in the ROMEO project (Work Package 5 “Data Acquisition and Analytics Ecosystem”). The team will enable the implementation of a novel IT Real Time Data Integration Platform for Wind Turbines (WT), aligned with the latest industrial Internet of Things initiatives, capable of boosting the real-time and preventive control and coordination capabilities of the future WT.

Besides, Minsait will also develop advanced predictive monitoring and performance monitoring analytic functions based on low level granular services hosted on edge devices.

Minsait has recently finished the definition of the Architecture and Data framework for the pilot tests included in the ROMEO project: the offshore wind farm of Wikinger (Germany), East Anglia ONE and Teesside (UK). This work, developed in collaboration with other partners (Iberdrola, EDF, IBM Research Zurich, Adwen, Uptime, Bachmann, Ramboll, Siemens Gamesa) sets the basis in order to succeed with the implementation of the ROMEO concepts and tools integrated in the O&M information management system that will be tested in the three multi-scale offshore pilots.

Recently the team have released the public report that define the arquitecture and the data framework for the pilot tests.

Catherine Murphy-O´Connor and Paloma Verdejo are part of the Minsait´s team involved in this challenge.

  • Could you explain into the specifics about how your team is contributing to the general goal of the ROMEO project to reduce the O&M cost of the offshore wind sector?

On the one hand, our team has expertise in leading ICT architecture definitions where a high number of heterogeneous devices, components, systems and algorithms from different partners need to be integrated. This background is brought on board to the project in order to face the ROMEO challenge where a flexible and interoperable Industrial IoT and Cloud platform will be built to provide an advanced analytics framework to better understand the real-time behaviour of the main components of Wind Turbine Generators under operational conditions.

On the other hand, Minsait has been pursuing in the last decade the concept of edge computing which means to push the frontier of computing applications from centralized nodes to the logical extremes of a network enabling analytics to occur at the source of the data. One of the challenges of the digital era is the transformation of the current monitor and control chart from a Centralized Control Centre into a management architecture consisting of a hybrid of both centralised and decentralised processing systems. The new distributed intelligent system should support the ability to quickly collect, organise, and analyse large volumes of data and help with processing, resolving, and delivering the large amount of actionable data needed to effectively manage and monitor the power system. With this purpose in mind, Minsait came to the project to provide this distributed architecture layer with 3 of its components that are part of Onesait Platform: i) Babel; a real-time power industry protocols manager that enables communication with multiple elements within a facility; ii) Industrial Node#1; a powerful Edge Computing node with processing capabilities to enable real-time devices management with embedded security. iii) iSPEED; a real-time Field Message Bus with the ability to handle large volumes of data in a secured, distributed and loosely-coupled way.

  • Your last report for the ROMEO project presents the overall system and communication architecture of the three demonstrators: Wikinger, East Anglia ONE and Teesside in order to know how the different components will interact. How difficult is the work developed and the coordination with the partners involved to put over the table all the necessary elements?

This work is always a challenge when you are facing the definition of a whole architecture where the first thing to tackle is to understand what each partner is bringing to the project that needs to be integrated. For a complete description of the architecture, a frame of collaboration was created. A process to fill out a component description template was defined from the very beginning of the project with the objective to identify all the systems and models to be developed by the partners in the different ROMEO work packages. This template includes among others the scope, data inputs and outputs of the component or dependencies with other components available in the architecture.

Once the template is filled out, one-to-one meetings were conducted to analyse in which architecture layer each component is placed and its best way of integration taking into account their real-time or historical data requirements. This is an iterative process where the architecture is being reviewed every time new partner inputs are incorporated. That is why it is very important to build a flexible architecture. Throughout the whole process of defining the global architecture, it has been very important to establish intermediate milestones as well as to monitor the risks and critical aspects. To reach this important milestone in the project, a close collaboration between partners has been crucial since the project kick-off.

  • The architectures defined must meet the requirements of the project: optimization of the maintenance of wind power facilities, extension in life of turbines and reduction of the cost of power generation. How are you going to reach this goal?

The architectures defined for Wikinger, East Anglia ONE and Teesside contain the different components that take part in each pilot which have been organized in layers. It starts from the offshore data acquisition layer which is connected to the onshore wind farm monitoring and maintenance layer. The real-time edge computing layer is integrated with the real-time operation systems whereas the IoT cloud analytics infrastructure collects data from the back-office systems and receives the outputs of the real-time layer. The IoT Cloud platform allows the data storage and the execution of the models and delivers the results and KPIs to the last O&M end-user layer.

This overall platform provides desirable mechanisms to improve O&M strategies increasing prospects for life extension and ultimately lower the levelized cost of energy of offshore wind. There will be different types of models and analytics running at different layers of the architecture such as diagnosis and prognosis for failure predictions of the main WT components or models which will provide damage and fatigue indicator values.

  • How are interacting the different components and which are the most critical points? Why is so important to define the frame of collaboration?

In order to establish the interactions of the different components through the architecture an analysis of the systems, models and algorithms participating in each pilot was conducted taking into account each system’s requirement, the already available integration mechanisms as well as the real-time or historical data needs.

All the architecture layers are crucial in order to meet the project objectives. From an ICT perspective the real-time integration layer with distributed processing capabilities provided by Minsait plays an important role bridging the gap between the real-time AS-IS wind farm monitoring infrastructure and the IBM Cloud IoT platform; which is also a key component of the project. The IoT platform is responsible for centrally managing all the interfaces within the ROMEO ecosystem and it is in charge of the data storage and the cloud analytics infrastructure. From the point of view of the O&M improvement of the offshore wind sector itself, the analytics and end-user layer will provide the innovative WT offline failure models and structural condition monitoring results as well as the KPIs of the project.

  • How does Minsait see the advances of the offshore wind energy with the fast development of the ICT sector: Big Data, the Artificial Intelligence or the blockchain?

Renewable energy sources (RES) are variable and depend on weather conditions, hence raise new challenges in management and operation of electricity systems, as more flexibility measures are required to ensure safe operation and stability. In addition, energy systems are growing to become more active, decentralised, complex and ‘multi-agent’. Local distributed control and management techniques are required to accommodate these decentralisation and digitalisation trends where blockchain could help addressing the challenges of building decentralised energy systems.

Moreover, predictability of individual turbine behaviour is key to operate offshore wind farms. In order to minimize the influence on the balance of the electricity grid it is necessary to have stable electricity production by each of the turbines. Hence all turbines should be available for operation when needed, which puts significant constraints on owner operators. Failure of turbine subcomponents should be avoided and this requires planning in advance of all necessary maintenance actions such that they can be performed during low wind and low electricity demand periods. In order to obtain the insights to predict component failure, it is necessary to have an integrated data set. A combination of Edge computing, Big Data technologies and Artificial Intelligence will be the solution to build the offshore wind farms monitoring platforms to tackle these challenges which increase the sophistication of decision-making processes.

  • Which are your expectations as a company involved in the ROMEO project?

ROMEO gives Minsait the opportunity to improve and test in a real environment the Edge Computing infrastructure that the company has been pursuing in the last years. Specifically, Minsait will be able to improve the above mentioned Onesait Platform components involved in the project. As a brief summary, Babel will improve the extended interoperability for WT protocols and will optimize performance and higher scalability. iSPEED will adapt its requirements to the needs of the WT domain, improving customized deployments, connectors, performance and security plugins. Finally, with Node#1 Minsait will demonstrate the edge computing architecture and governance with real pilots and tangible results. These innovations can be an opportunity for new use cases into the Industrial IoT market (deep learning and machine learning).