Study Shows Nextracker's Machine Learning Software Improves Solar Plant Production

Study Shows Nextracker’s Machine Learning Software Improves Solar Plant Production

The software’s algorithms have been found to increase production by taking advantage of Nextracker’s independent line tracking system.

Next tracker LLC, a specialist in smart solar trackers, has released a white paper based on third-party analysis showing how Nextracker’s machine learning software improves the performance of utility-scale solar power plants. In a series of tests conducted at operational sites in three states, TrueCapture was found to increase annual energy production by hundreds of thousands of megawatt hours per year.

“TrueCapture earnings are predictable and bankable, providing asset owners gigawatt hours of additional production and millions of dollars in additional revenue,” said Dan Shugar, Founder and CEO of Nextracker. “Our trackers have built-in communication and control capabilities, so we can provide our TrueCapture and NX Navigator control software to both our customers’ existing installed fleet as well as their new projects. Split-boost, added last year, has further improved TrueCapture’s performance.

What sets Nextracker’s decentralized architecture apart from linked row tracker designs is how it allows for very granular row-level control and optimization. Each row in a Nextracker system is powered by its own solar module, battery, actuator and controller, enabling intelligent operation of independent rows. Additionally, at the control level, the network components needed to monitor, control and optimize each row of single-axis trackers are all located at the project site. Nextracker’s hardware is wirelessly controlled by the NX Data Hub, a Linux-based industrial computer. And because it’s locally powered and controlled, hardware and software are protected against AC power failures and loss of external communications. The way the tracker works is that TrueCapture adjusts the position of each individual Nextracker line by sending real-time tracking parameters in response to site-specific conditions. Informed by sensor data and machine learning technologies, this allows TrueCapture to precisely orient tracking lines to account for terrain variance, building tolerance, cellular technology and weather conditions. .

Three case studies

The paper examined longitudinal data from three operating projects in California, Georgia, and New Mexico with average production exceeding 2% of production benefit. At these sites, the performance of trackers equipped with TrueCapture was tested against a set of control blocks using standard rollback.

The 40 MWac California site, located in the Mojave Desert, is one of five power plants that make up the largest portfolio of 250 MWac Beacon solar projects. Commissioned in 2017, the Beacon 5 solar power plant incorporates full-cell crystalline silicon photovoltaic modules and Nextracker’s flagship NX Horizon single-axis trackers. The site has a ground coverage rate of 50.5% and an average diffuse illumination percentage of 26.4%. Beacon 5 has significant shading while working with standard backtracking algorithms. To mitigate the impacts of terrain shading, Nextracker proposed to implement TrueCapture’s performance-enhancing algorithms. Black & Veatch’s independent performance engineers validated the performance gains of TrueCapture, noting in its follow-up engineering report, a 2.2% increase in power efficiency for the TrueCapture group compared to the control group.

The 120 MWac facility in New Mexico is located on 840 acres. Called the Bluemex Solar Project, it integrates full-cell crystalline silicon photovoltaic modules onto NX Horizon single-axis trackers. Unlike the California site, the New Mexico site is relatively flat, but experiences extreme humidity on a seasonal basis. Nextracker estimated that the site would see a 0.64% increase by implementing TrueCapture, with gains of 0.3% coming from Nextracker’s Diffuse Boost and 0.34% from Shade Avoid. At the end of the test period, performance engineers found that the Diffuse Boost module provided measured gains of 0.31% and Shade Avoid mode resulted in an average gain of 0.32% for test blocks that best matched the average slope number of the site. Overall, TrueCapture provided measured gains of 0.63%.

The 102.5 MWac site in southwest Georgia, called Bancroft Station, supplies 100% renewable energy to Facebook’s Newton Data Center. This dual-use site co-locates solar production with regenerative farming practices, which is why Silicon Ranch performed minimal grading to minimize negative impacts on topsoil. In addition to using single-axis trackers controlled by TrueCapture, the Bancroft station site incorporates half-cell crystalline silicon photovoltaic modules that Silicon Ranch sourced locally from a Hanwha Q Cells factory in Belton, Georgia. . In a Split Boost test conducted in June 2021, performance engineers calculated that the half-cell optimization algorithm improved performance by 1.7% over standard rollback on a median tilted test block on a period of 12 months.

By examining empirical gains from three real-world projects, independent engineers validated TrueCapture’s project performance improvements and factored those gains into an independent, bankable energy performance assessment.

More details on the tests are available in the white paper, Enhancing Energy Yields with TrueCapture Using Nextracker’s Proven Intelligent Control Capabilities to Optimize Solar Project Financing and Plant Performance.

This content is copyrighted and may not be reused. If you wish to cooperate with us and wish to reuse some of our content, please contact: editors@pv-magazine.com.

#Study #Shows #Nextrackers #Machine #Learning #Software #Improves #Solar #Plant #Production

Leave a Comment

Your email address will not be published. Required fields are marked *