Ürünlerimiz ve çözümlerimiz hakkında daha fazla bilgi, çevrimiçi sunumlar, demolar ve PoC talepleri için bizimle iletişime geçin.

Contact us for more information about our products and solutions, online presentations, demos and PoC requests.


İletişim / Contact

İçerenköy Mah. Umut Sok. Quick Tower, Kozyatağı – İstanbul / Türkiye


+90 216 999 1394

Digital Transformation

How Asset Management Enabled by Artificial Intelligence and a Physics-Based Digital Twin Reduces the Cost of Renewable Energy

Renewables Dominate Electricity Generation Growth

The world is experiencing a revolution in how electricity is generated. As climate poses an existential threat to global ecologies and economies, the future belongs – and increasingly – to companies that can reliably and efficiently generate electricity from low- or zero-carbon sources.

The transition to wind, solar and hydropower, often backed by battery storage systems, presents both great opportunities and great challenges.

Challenges Facing Energy Producers Today

The challenges facing power producers today are many and varied. Managing and optimizing large data sets across different asset operations has never been easier, but now competition in the power generation market and threats from cybercriminals have increased the pressure to find scalable and profit-generating solutions.

Managing large amounts of data: Renewable energy assets generate enormous amounts of data. While this data contains valuable insights, managing it efficiently is a challenge. Manual and semi-automated methods used in the past are not scalable and are no longer cost-effective.

Getting rid of data silos: The size of data to manage is not only growing rapidly, it is also becoming increasingly diverse. Operations teams, asset managers and executives depend on data from multiple sources, including SCADA, incident, condition monitoring system (CMS), production, budget, maintenance, outage, revenue, weather and production forecasts, ES&G and market pricing tools (to name just a handful).

Managing these data sources in traditional ways requires using multiple tools, which reduces efficiency and increases costs. In traditional systems, these datasets exist in silos that do not talk to each other and cannot aggregate information from the data. An example of this is maintenance data, which can be stored in a computerized maintenance management system (CMMS) and typically contains information about part failures, spare parts and replacement. In some cases, this data is used for reliability-based maintenance and stand-alone spare parts forecasting. The same data combined with SCADA, event data and pricing data becomes much more powerful for predicting and planning maintenance activities to maximize operational profit.

Balancing a diverse asset mix: Renewable energy operators must efficiently manage multiple asset types within an asset class (e.g. wind, solar, storage, hydro, etc.) and multiple OEMs and equipment models. This diversity in operational assets will continue to grow, making fleet management more complex.

The addition of new technologies such as storage brings additional challenges that arise when different stakeholders have misaligned goals, and means that owners/operators cannot rely solely on OEMs. OEMs will want to accommodate performance that may not be optimal to reduce warranty risk and maximize asset profitability.

A competitive generation landscape: Competition is increasing as more players enter the renewable energy generation market. The most efficient operators will gain more of their market share, while less efficient operators will lose market share.

More complex power purchase agreements. The days of 10- to 20-year fixed power purchase agreements, the standard for renewable energy projects, are coming to an end. Variable pricing agreements, such as bank hedging or proxy revenue swaps, are becoming increasingly common. These variable pricing agreements require more complexity to properly assess, negotiate and manage risk.

While it is true that the cost of electricity from renewable sources ($/kWh) has fallen significantly thanks to the benefits of technological progress and economies of scale, a corresponding dramatic drop in the power purchase price (down to $0.03/kWh) and the phasing out of Policy support has put additional pressure on operators. Data-driven operational efficiency will play a leading role in helping power producers meet the challenges of lower PPAs.

Cybersecurity threats: While digital connectivity of renewable energy assets has many positive aspects, the proliferation of highly sophisticated digital hackers poses a serious threat that requires the deployment of cybersecurity solutions that work across OT and IT systems.

New skill sets required: Power plant operators have historically been experts in operating and maintaining generation equipment. However, skills such as data science, data engineering, software development and cybersecurity have not been core competencies. These skill sets are in high demand, hard to find and costly to add internally.

Moving beyond Alarm and Alert

Over the last 5 years, power plant operators have adopted a more proactive approach to managing their assets, even if the level at which data is effectively used varies from operator to operator.

Rules-based models and in some cases machine learning (ML) are being used more frequently to guide maintenance actions. This is undoubtedly a step up from the reactive approach of the 2000s, but each implementation will have its strengths and weaknesses.

Limitations of rule-based models: Rule-based models have serious limitations. They work well if an operator has many assets of the same type, but poorly if assets are few or different.

Rule-based models struggle to scale well and cannot be easily adapted to new assets. Also, it is quite rare for components such as gas turbines or power transformers to fail, making it difficult to build rules from historical data.

The power of machine learning models: Advanced ML models are better solutions for the above challenges. These models will include a combination of supervised (requiring historical data) and unsupervised models.

Unsupervised models are very powerful and have been used successfully in areas where true positive data is sparse, such as climate informatics. One example is predicting avalanches from images of snow-capped mountains.

Advanced machine learning models combined with the underlying physics of the assets are a powerful tool in developing an optimal operational strategy. Business decisions such as investing in software control or equipment upgrades cannot be made if operators cannot see the scope or root cause of the problem.

Therefore, a digital platform that provides an end-to-end solution from digitalization to prescriptive action is key. This will ensure smooth decision-making and efficiency.

How Power Producers Can Win the Renewable Energy Revolution

A holistic, scalable platform approach to address the various challenges facing energy producers today should include the following key elements.

Harness the power of cloud computing combined with advanced artificial intelligence. The platform should continuously monitor operating data and automatically alert operators to anomalies that need attention. This powerful automation of tedious tasks allows human operators to focus on higher value activities.

Consolidate multiple data streams into a single recording platform. The platform should reveal insights from all relevant project data, including SCADA, incident, maintenance, production, budget, weather, CMS and unstructured data sources (i.e. text) using natural language processing (NLP). Data and insights are easily accessible by all platform users from a single location.

Manage different asset types from a single platform. Wind, solar, hydro and storage assets should all be managed with a single, comprehensive platform. By reducing the number of tools required, operational efficiency and safety are greatly improved.

Increase energy production and reduce cost. Underperforming assets are quickly brought to the attention of platform users with a diagnosis of the most likely cause of the problem, along with recommended corrective actions enabled by prescriptive analytics. Advance notification of failures before they actually occur allows for better planning and reduces the impact of failures on project operation.

Forecasting and energy trading. The platform should provide accurate energy price forecasts, allowing operators to implement optimal operating strategies to maximize project revenue.

Provide zero-day threat protection for industrial assets. As nation-state actors and cybercriminals increasingly target critical infrastructure with next-generation malware (e.g. ransomware), energy operators should deploy next-generation cybersecurity tools to protect both OT and IT assets from zero-day attacks.

New classes of AI-based endpoint protection solutions can be integrated directly into the operator’s APM to provide the highest possible level of protection against cyber threats.

Find the right technology partners. Digital transformation never ends, and as adoption of advanced technologies such as machine learning and AI continues to grow, it is prudent for energy operators to choose the right technology partners to help them along their transformation journey, regardless of their current stage.

These partners can provide a full range of digital services to customers, including cloud migration, integration of applications, platform customization, and the development and integration of capabilities that are sure to come as major advances in data science and AI continue.

Electricity Generation Changes Rapidly, Leaving Old Paradigms Behind

History has shown that companies that are willing to rise to the challenges of the new paradigm will continue to grow and thrive, while those that cling to old ways of doing business are doomed to be displaced by their competitors.

The rapid growth of wind, solar and water generation, supported by energy storage, is creating new opportunities for innovative operators to grow their businesses and enter new markets. AI-powered asset management represents the new paradigm that some companies will embrace and others will resist for too long.

Advanced technologies such as cloud computing, machine learning and artificial intelligence are now market-ready. It will be exciting to watch which companies take advantage of early adoption strategies to increase the efficiency and production of renewable energy assets while reducing maintenance costs and operational risks.

Source: https://www.environmentalleader.com/2021/08/how-ai-enabled-asset-management-is-driving-down-the-cost-of-renewable-energy/

To get information about Cerrus Energy Analytics Platform and our other solutions: