Data-centric technology

Wind turbines and solar panels are equipped with a wide array of sensors and detectors that generate millions of invaluable data points. However, the absence of a common standard for structuring and labeling the outputs has hindered the industry’s ability to derive results. Many existing solutions employ rudimentary data models or rely on manual processing to prepare data, leading to inefficient analysis, potential errors in the resulting insights or both.

At Clir, our technology stack is built to extract the maximum possible value from wind and solar data and deliver quantifiable results. Using data-centric artificial intelligence, we programmatically structure and label the data points generated by renewable energy assets. This approach ensures faster insights, enhanced accuracy and greater confidence, transforming the way we leverage renewable energy data.

A higher standard of data quality

As a foundation for insights that could make a difference of millions of dollars, data integrity is critical. Clir’s data model automates the cleansing, labeling and structuring of data. The result is better quality data and more valuable insight.

A graph of Clir's power curve showing the average wind speed

Reduced uncertainty

Using a data-centric approach to machine learning improves the accuracy of Clir’s models and the insights they drive. For example, Clir’s power curve model uses an iterative approach to model accurate power curves, requiring fewer data points. This allows for quicker change detection, efficient identification of underperformance and greater confidence in downstream insights.

Smart labelling of status codes

Clir employs smart logic to automatically label and categorize missing data periods. Using supplementary information from the vast pool of ingested data points, lost energy detectors categorize missing data including soiling, icing, curtailment and derating. Algorithms that detect component breakdown or partial performance enable improved transparency into losses and allow for a detailed analysis of asset underperformance.

A graph of single year production p value verse farm age with industry comparsions

Informed decisions across the project lifecycle

By leveraging enriched project and industry data, and understanding areas of loss and risk, we provide deeper insights into technical and financial inputs. Our AI-powered analytics support clients across the project lifecycle, providing data for strategic decision-making, risk mitigation, service provider oversight, and OPEX and revenue optimization. This helps to minimize costs, maximize revenue and mitigate risk.

Oversight you can rely on

Insights derived from clean and enhanced data are surfaced through the Clir app, improving asset oversight, analytics and reporting. With high quality performance, risk and technical insights, Clir’s app provides a roadmap to make smarter financial decisions through portfolio- and asset-level optimization and risk mitigation strategies.

Learn more

A graph of energy output over the year with the context of the budget

Technology features

Data lake integrations

Data lake integrations seamlessly synchronize both raw and Clir-enriched data with your internally- or cloud-hosted data lake infrastructure, enabling improved data strategies.

Learn about integrations

Volume modelling

Machine learning-powered volume modelling enables owners to reduce uncertainty regarding hourly production shape and volume.

Learn about volume modelling

Energy yield assessments

Clir uses industry data from peer projects across the globe to develop more robust and defensible energy yield assumptions, ultimately improving certainty on projects.

Improve energy yield assessments

Book a demo

Leverage data, AI and technical expertise to maximize financial returns.

Leverage market intelligence.
Increase production.
Minimize operational costs.