The solar workforce of 2030 will operate at a scale that is tenfold today’s activity. With this tremendous projected growth rate, Developers, EPCs, O&Ms, Asset Managers, IEs, and Financiers need to operate more efficiently and make faster, better-informed decisions. The workforce of 2030 must leverage technology to scale successfully. And they must start now.
Denowatts developed the technology needed to help these teams achieve massive growth. Our technology focuses on three areas:
Denowatts’ technology quickly and efficiently places accurate data at the fingertips of decision-makers from O&M technicians to CEOs, Designers to financiers. Cross-functional teams working in concert with transparent and reliable data are productive, engaged, and effective.
A benchmark is a standard by which things are measured or compared. Historically, the solar industry benchmarks performance using energy models and weather stations. Weather stations typically include pyranometers, temperature sensors, anemometers, and other meteorological sensing equipment to measure local conditions. Measured condition inputs are then used in the energy model to calculate the weather-adjusted energy benchmark, defined in IEC 61724-1 as “Expected Energy.” The process that calculates Expected Energy can be thought of as creating a “digital twin” that will accurately simulate the power output of a solar asset under a given set of weather conditions.
Not all digital twins are created equal. Digital twins can take many forms and provide a range of results based on the quality of the input data, the adherence to the energy model parameters, and the resolution of processing.
Denowatts developed the Deno Digital Twin Benchmark (DTB) by reimaging the weather station, restructuring the data processing architecture, and employing the Internet of Things (IoT) practices to achieve advanced capabilities not yet seen in the solar industry, including:
Deno DTB is the foundation of Denowatts’ analytics and business intelligence systems. Denowatts delivers Deno DTB as a service to actively manage data quality and minimize measurement uncertainty. Denowatts is an ISO/IEC 17025 Accredited Calibration and Testing Laboratory, and Deno DTB sensors have a typical calibration uncertainty of 1.0%
Cleaning, organizing, and managing a firehose of data is very labor-intensive. The solar workforce has spent much time cleaning and analyzing data in spreadsheets, manually uploading and downloading datasets, and managing a siloed database that becomes too daunting to move. In addition to monitoring services, many fleet operators utilize portfolio reporting software or develop internal ERP integrations.
Denowatts approaches this problem with two principles: 1) Leverage machines to learn mundane tasks whenever possible to free up human time to focus on decisions and action, and 2) Operate an open data exchange for 2-way connection with other asset management tools which are critical to the team.
Artificial Intelligence (AI) means using machines and processes to mimic human behavior. For Denowatts, machine learning is utilized to carefully understand the operating profile of each solar asset. While the Expected benchmark represents modeled output, Denowatts created the Learned benchmark to describe a solar asset’s observed operating characteristics. Learned Energy is developed from machine learning processes to help performance managers hone performance expectations.
Denowatts utilizes Learned Energy to develop an “as-built” shading model and perform energy accounting leveraging machine learning tools. Energy accounting reconciles the production and losses of each solar asset. While local metering readily determines production, quantifying and qualifying losses is historically a labor-intensive task. Denowatts completes energy accounting efficiently using a combination of machine learning and human supervision. The result is clean and reconciled performance data, saving substantial time for the solar workforce.
Interoperability refers to the basic ability of computerized systems to connect and communicate with one another readily. Denowatts technology is built on the premise that solar asset management tools need to talk to each other to deliver the best results for the solar workforce. Data is securely transferred across common systems to save time, reduce errors, and provide real-time results.
Examples of Denowatts interoperability include:
These are examples of manual tasks that historically consume substantial time and focus by the workforce. The Denowatts technology platform is built on the premise that the workforce of 2030 must leverage AI and Interoperability so it can shift focus from mundane tasks to performance optimization action.
Business Intelligence (BI) is the process of transforming data into actionable insight to allow organizations to make informed decisions. Behind the BI process is numerous layers of cleaning, analyzing, filtering, and organizing data. An effective BI interface is a chart that answers a question that can lead to action.
For various reasons, many stated above, BI is underutilized by today’s workforce. As the industry matures and becomes increasingly competitive, the workforce of 2030 must have BI tools readily available at all levels of operations.
Denowatts is a BI company that started with a fundamental question: “Is my solar array performing as it should?”. After years of developing benchmarking and machine learning technologies, Denowatts continues to expand the BI capability and answer more questions.
Denowatts utilizes Tableau Server, a best-in-class BI visualization suite. Denowatts clean and reconciled data is connected to Tableau, allowing clients to easily and instantly access visualizations that present clear answers to performance questions, whether for an entire portfolio or any subset of parameters. Examples of the most popular visualizations include:
The possibilities for performance questions and visualizations are limitless. Creating and refining visualizations is scalable and straightforward, with the critical work completed at the underlying data quality, processing, and organizing levels.