Iberdrola, machine learning and the future of offshore wind

Offshore wind turbines offer tremendous potential for renewable energy, but are still not as competitive as other low-carbon technologies. Iberdrola, global leader in power generation and one of the largest wind power producers, looks at machine learning solutions to decrease maintenance costs and make offshore wind more affordable.

Machine learning to tap into the potential of offshore wind power

In 1887, inventor Charles Brush built a wind turbine in the backyard of his mansion in Cleveland Ohio. After generations of improvement by talented engineers, wind power is today one of the fastest-growing renewable energy technologies, encouraged by policy support, technology advances and financial incentives [1,2,3]. Offshore turbines specifically offer tremendous potential because of more consistent and higher wind speeds (improving yield) and fewer restrictions on size. Offshore wind capacity is expected to almost triple to 52 GW by 2023, with half the growth driven by the European Union and the other half by Asia [5]. Under conservative scenarios, this capacity should reach 160 GW by 2030 and 350 GW by 2040 [6].

Iberdrola, global leader in power generation and one of the largest wind power producers, understands this potential. The group is investing heavily in renewables and in wind power specifically, to support the transition to low-carbon energy. In line with this strategy, its offshore wind capacity increased by 180% from 2016 to 2017 [7].

Figure 1 – Global levelized cost of electricity from utility-scale renewable power generation technologies, 2010-2017

However, competitiveness compared to other technologies remains a key obstacle for offshore wind to fulfill this potential [8,9, figure 1]. Operations and Maintenance (O&M) costs account for 15% to 30 % of the Levelized Cost of Electricity (LCoE) and can be a strong lever of optimization [10 – 13]. Traditionally reactive, static and labor-intensive, offshore O&M includes costly unplanned maintenance and inspections – often in harsh conditions – and is expected to represent a $4.9 billion market by 2026 [14].

This is where machine learning can improve the future of the industry. Using information generated by sensors in the turbines and learning from historical data, maintenance can become predictive. Anomalies and failure modes can be proactively and precisely identified to be addressed before causing any damage or service interruption [15 – 17]. Specific actions can be suggested to operators, switching from a calendar-based maintenance schedule to a much cheaper asset condition-based maintenance.

Looking forward: Iberdrola’s strategy to decrease offshore O&M costs

Iberdrola is leading the ROMEO project (“Reliable OM decision tools and strategies for high LCoE reduction on offshore wind”), working with 12 industrial partners including IBM, OEMs Adwen and Siemens [18,19]. The objective is to develop a platform to manage and analyze data collected from offshore wind turbines to:

  • Increase reliability and decrease downtime due to equipment failure,
  • Increase the lifespan of key turbine components,
  • Reduce O&M costs through a smarter use of resources and decreased need of foundations inspections.

The outcomes of the project will contribute to the improvement of health and safety, to the development of operational best practices in offshore wind, leading to increased competitivity and lower LCOE.

In the short-term (2020 horizon), four major offshore projects are underway in the U.K., Germany and France. East Anglia One (£2.5 billion CAPEX, 714MW) will be the largest offshore wind farm when it starts operations in 2020 and will serve as a pilot site for ROMEO [20].

In the medium term, Iberdrola plans to invest €9 billion to reach 3 GW of installed capacity in Europe and the U.S. by 2023 [21]. The group will also dedicate €4.8 billion in digital transformation by 2022 and will focus on improving O&M by using data analytics and artificial intelligence and increasing the availability across its generation plants.

Leveraging Machine Learning and AI beyond offshore wind

I believe that the ROMEO outcomes could easily be transferable to other technologies, chiefly onshore wind and photovoltaic. Additionally, forecasting production could also be facilitated by machine learning technology, based on weather data, asset-specific data and site information [22,23]. Accurate predictions would then allow to anticipate and quantify curtailment [24], to further optimize asset management.

But Iberdrola’s digital strategy should extend beyond asset management. For example, Iberdrola Ventures has recently invested in InnoWatts, a start-up working on smart metering and demand forecasting using machine learning. I would argue that further such acquisitions would strengthen the group’s position as a “utility of the future” and build a stronger capability to lead its digital transformation (including in consumer-facing applications).

As they implement their digital strategy, I would advise Iberdrola to preserve integration and the overall unity of their I.T. landscape. Tremendous amounts of data are measured and generated: coherence and smart management of this data will be key to maintain alignment and efficiency. The development of overarching cloud-based IoT platforms such as GE’s Predix [25] or Siemens’s Mindsphere [26] illustrate this trend.

As Iberdrola moves along their digital transformation journey, I see further outstanding issues around:

  • the role of engineering expertise and experience: how can analytics platforms complement technical competences and empower employees to improve performance?
  • Industry-wide collaboration on data platforms (including OEMs): are consortia such as ROMEO sustainable in a competitive industry?

 

(Wordcount: 791)

 

References:

[1] Advancing the Growth of the U.S. Wind Industry: Federal Incentives, Funding, and Partnership Opportunities, US Department of Energy (DoE), February 2017

[2] Innovation Outlook, Offshore Wind, International Renewable Energy Agency, 2016

[3] Global Landscape of Renewable Energy Finance, International Renewable Energy Agency, 2018

[4] Annual Market Update 2017, Global Wind Report, General Wind Energy Council

[5] Renewables 2018, Market analysis and forecast from 2018 to 2023, International Energy Agency

[6] Offshore Energy Outlook, International Energy Agency 2018

[7] Iberdrola Integrated Report, February 2018

[8] Renewable Power Generation Costs, International Renewable Energy Agency, 2018

[9] Offshore Energy Outlook, International Energy Agency, 2018

[10] Sensitivity analysis of offshore wind farm operation and maintenance cost and availability, R. Martin et al., Renewable Energy, 2015

[11] Levelized Cost and Levelized Avoided Cost of New Generation Resources in the Annual Energy Outlook 2018, U.S. Energy Information Administration, March 2018

[12] Levelized cost of energy for offshore floating wind turbines in a life cycle perspective, A. Myhr et al., Renewable Energy, 2014

[13] Lazard’s Levelized Cost of Energy Analysis, version 11.0, November 2017

[14] Europe Wind Power Outlook 2017, MAKE consulting, 2017

[15] Machine learning methods for wind turbine condition monitoring: A review, A. Stetco et al., Renewable Energy, 2018

[16] Deep Learning for fault detection in wind turbines, J. Helbing et al., Renewable and Sustainable Energy Reviews, 2018

[17] Failure rate, repair time and unscheduled O&M cost analysis of offshore wind turbines, J. Carroll et al., Wind Energy, June 2016

[18] ROMEO Seeks to Improve Wind Farms with Machine Learning and IoT at the Edge, IBM research blog, last accessed November 12th 2018

[19] ROMEO project website (https://www.romeoproject.eu/), last accessed November 12th 2018

[20] Iberdrola website (www.iberdrola.com) last accessed November 12th 2018

[21] Iberdrola press release, October 24th 2018

[22] Deep learning based ensemble approach for probabilistic wind power forecasting, H. Wang et al., Applied Energy, 2017

[23] Ensemble methods for wind and solar power forecasting—A state-of-the-art review, Y. Ren et al., Renewable and Sustainable Energy Review, 2015

[24] Wind and Solar Energy Curtailment: Experience and Practices in the United States, National Renewable Energy Laboratory, 2014

[25] Digital Wind Asset Performance Management from GE Renewable Energy, 2017

[26] The Predix platform, GE website (https://www.ge.com/digital/iiot-platform) last accessed November 12th 2018

[27] Siemens Mindsphere, Siemens website (https://www.siemens.com/global/en/home/products/software/mindsphere-iot.html) last accessed November 12th 2018

Previous:

Maison Me-chine

Next:

Open your open innovation to suppliers

5 thoughts on “Iberdrola, machine learning and the future of offshore wind

  1. That is fascinating! Thank you for sharing. It seems that (and I hope that) the use of machine learning may bring us closer to making wind and solar technologies profitable, even without subsidizing. I am wondering whether this opportunity may encourage governments to financially support also ML projects in this field, in addition to supporting energy projects directly. It sound like it could be a very reasonable long-term approach. Curious to see!

  2. Great article! I did not realize how large of a market there was for turbine maintenance. It is very interesting that predictive maintenance is going to be such a major effort across industrials in the coming future. I am excited to see how successful ML can be in building truly predictive failure models. I hope that ML is able to reach a stage where it can locate and combine all the data necessary to allow operators to generate predictive maintenance schedules.

  3. Interesting article. Thanks for sharing! On your question of industry-wide collaboration on data platforms, I would argue that it would be beneficial for areas that include new technology, large CAPEX, and high risk. The ROMEO is a perfect example since if you have a project with that size and risk for the offshore wind projects, it makes sense to have a consortium to diversify the risk. However, areas such as onshore wind and photovoltaic where the technology is mostly established and the industry is getting mature, I would argue the less benefit of industry-wide collaboration. Another point to think about is the country you are trying to operate. If the country has a less experience on onshore wind/photovoltaic, it could make sense to have partnerships vertically as the costs/risks could be substantial. Overall, I like the data sharing/industry collaboration to renewable energy space since it is still a risky emerging industry where lots of innovation, cost reduction and ultimately, environmental friendly solutions could occur.

  4. This is very interesting, thank you. I also believe that ML is transforming the energy industry, it is curious that it took this long to the sector to start leveraging the massive amount of data that they generate.
    Regarding your first question, I believe that the role of engineers will definitely change. The way I see it, ML will facilitate data analytics and will allow engineers and experts to spend more time thinking, rather than doing a manual job. However, I don’t believe that ML will totally replace human capabilities. In the end, human criteria is important, especially in risk issues related to context or to other aspects that ML cannot capture.

  5. Interesting article, thank you for sharing. As you mentioned, machine learning’s preventative maintenance application has high value for the offshore wind sector, especially given the high O&M costs in such rough, remote environments. Any innovation that allows these turbines to operate more efficiently with less human interface will help drive down costs across the industry. I agree with Daichi that sharing the risk with ROMEO consortium is beneficial as the industry comes up the curve on offshore technology. However, I do think that the data could provide Iberdrola valuable insights on asset management (costs, forecasts, curtailment, etc.), which could give them a competitive advantage as the lowest cost operator. Is there a trade-off between generating data from as many competitors’ turbines as possible and maintaining proprietary control over the insights?

Leave a comment