The POWER Interview: Predictive Maintenance Key for Solid Solar Performance

Operators of utility-scale commercial solar farms know the importance of predictive maintenance for their installations. Being proactive when it comes to developing operations and maintenance (O&M) programs can help operators anticipate equipment failures, and also streamline repairs in the field, allowing O&M service providers to better manage and plan staff assignments, find spare parts, and schedule replacement procedures.

Increasing a facility’s availability and uptime, and optimizing its performance, are of greater importance in an era of extreme weather and other factors challenging the solar power sector, particularly as solar power becomes a greater part of the global energy mix.

Archie Roboostoff, vice president of software at Tigo Energy, a San Jose, California-based solar power solutions company, recently provided POWER with insight into what solar power operators need to know and practice to develop solid predictive maintenance programs. Tigo is a global leader in Flex MLPE (Module Level Power Electronics), designing programs to increase energy production, support safety, and decrease operating costs of solar installations.

POWER: How should a utility and/or solar farm operator develop a predictive maintenance program? Is it best to do it independently, bring in a third party, or use a combination of both?

Roboostoff: Predictive maintenance programs for a utility or commercial solar farms should anticipate and address equipment failures before they occur. The purpose of such programs, after all, is to maximize production, minimize downtime and maintenance costs, and reduce total cost of ownership.

The first steps toward predictive maintenance include an inventory of the assets, categorization, surface data collection, implementing sensors where collection isn’t taking place, and applying predictive modeling on these data. Next, one must implement a continuous improvement process to regularly check the system, swap out failed or degraded components, and maintain detailed maintenance logs with pictures and videos over time.

For more insight into predictive maintenance for solar power, read “Dialing in Data Key to Developing Successful Predictive Maintenance” in the January 2024 issue of POWER.

In predictive maintenance, emerging technologies like AI (artificial intelligence) and machine learning play the central role. Tigo Energy, for example, uses these technologies to forecast electricity generation and consumption automatically, providing accurate and scalable insights for energy producers. Such tools can augment smart meter data with external sources, enabling precise grid consumption forecasts.

An independent route allows operators to leverage in-house expertise and tailor the predictive maintenance program to their needs. This approach empowers them to align the program closely with their organizational goals and objectives. It requires a substantial investment in technology and talent but provides a high degree of control over the entire process.

Archie Roboostoff

Bringing in a third party can offer advantages such as specialized knowledge, experience, and access to cutting-edge technologies. Collaborating with experts in the field can accelerate the development of a robust predictive maintenance program. However, it’s crucial to ensure that the chosen third party supports the unique requirements and scale of the solar project.

A combination of independent development and third-party collaboration can also be a good choice. Operators may build a foundation in-house and then partner with external experts for specific components or enhancements. This hybrid model allows for flexibility, combining the strength of internal controls with the expertise of external specialists.

POWER: Why is operational data alone not enough to establish a strong predictive maintenance program? What is needed to allow asset managers and operators to anticipate O&M needs and maintain efficient system performance?

Roboostoff: Operational data serves as a valuable foundation for assessing the current performance of a solar system, ensuring that it operates within expected parameters. However, relying solely on operational data has limitations when establishing a robust predictive maintenance program.

The critical challenge lies in the potential oversight of issues concealed beneath the surface, escaping routine operational checks. This is where remote monitoring comes in.

For instance, the speed and efficiency of solar system installations can be significantly enhanced through advanced software and monitoring tools. These tools expedite the activation process and introduce a layer of proactive monitoring. With remote monitoring capabilities, the software empowers installers with automated alerts, enabling swift responses to deviations in system performance.

Consider a scenario where solar output falls below anticipated levels. Tigo installers can promptly detect, analyze, and diagnose issues remotely. This proactive approach allows for scheduling service calls before the system’s inefficiencies become apparent to the end user. Relying on operational data alone can obscure subtle anomalies that, if left unaddressed, could lead to performance degradation and even precipitate issues with performance-based contracts.

Integrating sophisticated software and active monitoring systems, complemented by optimizers, emerges as a robust approach. These tools extend beyond merely validating operational parameters; they actively contribute to anticipating O&M needs. By providing real-time insights and automating issue detection, they enhance solar panel installations’ safety, performance, and efficiency.

Crucially, this proactive approach further fortifies the safety of solar systems and enhances their reliability and cost-effectiveness. As such, users benefit by maximizing the returns on their solar investments and underscores the indispensable role of advanced software tools in augmenting the overall effectiveness of a predictive maintenance program.

POWER: What are the most common problems for solar arrays? What types of problems should anomaly detection systems be able to identify?

Roboostoff: Soiling, shading, inverter faults, connection issues, weather-related damage, and module performance degradation are the most common problems. A high-quality anomaly and predictive modeling system should be able to pick up the telltale signs related to most of these items. A good software monitoring and management platform, in turn, will be able to show any trends that run counter to the normal baseline.

Safety is also paramount in solar installations, which can be greatly enhanced through the use of Module Level Power Electronics devices that incorporate rapid shutdown functionality. This feature reduces module output voltage during power loss or roof access needs, aligning with global safety standards and electrical code requirements, including those in the U.S..

Modern MLPE devices provide module-level monitoring of power output and system health data. Residential and commercial solar users can access a monitoring platform to view real-time and historical energy output, battery levels, and other vital metrics. This granularity allows for remote issue identification and resolution, ensuring optimal system performance.

To address solar installation and maintenance challenges, homeowners and commercial users must prioritize high-quality system design and installation practices. Choosing a reputable solar installation company with trained, experienced teams familiar with specific equipment and holding industry certifications is crucial for success with solar.

POWER: What kinds of predictive maintenance capabilities is your company (if applicable) developing, and how are you bringing your system to the market?

Roboostoff: Tigo Energy has a leading solar monitoring and management platform that flags issues within a system to fleet operators. When combined with Tigo predictive modeling technologies, specifically through our EI Predict+ software, advanced AI and machine learning technologies  can flag many issues before they even happen. These capabilities are designed to forecast electricity generation and consumption at individual endpoints and aggregated energy portfolios automatically. The goal is to provide utilities, IPPs (independent power producers), and grid planners with accurate, scalable, and robust insights.

Through the Tigo platform, our customers can also predict what consumption vs. production patterns will take place in the near future, so operators can make better decisions on how to serve energy demand. Every day, we outline trending diagnostic information to our customers, along with the ability to anticipate and identify equipment failure before a piece of equipment fails. Tigo is currently working on next-generation technologies to help operators spend even less time fixing issues and more time maximizing power generation.

We are actively working to bring this product to market globally. Currently, we have Predict+ installations on three continents, forecasting more than 300 GWh of energy consumption daily.

POWER: How can predictive maintenance programs benefit workers in the field as they maintain and/or repair solar power equipment?

Roboostoff: Predictive maintenance programs empower field workers by providing them with timely and relevant information about the condition of solar power equipment and an ongoing log of preventative measures taken. The maintenance crews will be familiar with the equipment and understand what maintenance activities have been done. By doing this, each maintenance crew will be more efficient and safer, and activities that focus on maintenance ultimately benefit both the workers and the overall performance of the solar power system.

The cumulative effect is a workforce that operates with increased efficiency and safety. Armed with a thorough understanding of the equipment and a record of past maintenance activities, maintenance crews can approach their tasks precisely and confidently. Finally, with remote monitoring and deep, predictive analysis, maintenance crews can optimize tuck rolls and ensure they have any replacement components with them for site visits, both of which greatly reduce one-off service visits by bundling work tasks.

Darrell Proctor is a senior associate editor for POWER (@POWERmagazine).

SHARE this article