Renewable energy plants generate thousands of SCADA data points every second. Yet, every manufacturer names these signals differently. 'Power', 'AC Power', 'P', they may all mean the same thing, but inconsistent labels cripple automation and analytics.
Without a standardized renewable data taxonomy,digital tools and machine learning, attempting to provide portfolio-wide insights, simply cannot function. Standardization ensures clarity, automation, and reliable performance monitoring across renewable assets.
The solution: AI-powered Energy Data Tagger
Energy Data Tagger applies AI-driven SCADA signal mapping and renewable data taxonomy to eliminate inconsistencies.
By combining a robust, industry-aligned renewable data taxonomy with a powerful AI engine, Energy Data Tagger automatically performs AI-driven signal mapping, classifying and translating disorganized SCADA signals into standardized, taxonomy-compliant formats.
This AI-powered renewable data taxonomy tool enables automated tagging at scale, eliminating manual effort, reducing human error, and unlocking seamless integration of solar, wind, and battery storage data for analytics, compliance reporting, and operational efficiency across entire renewable portfolios.
Trained on over 1 million signals from renewable assets (solar, wind, battery)
Built on IEC 81346 and RDS-PS standards
Learns and improves using Natural Language Processing (NLP) for accurate signal mapping
Delivers standardized data for compliance, analytics, and reporting
Transform disorganized data into scalable renewable data intelligence
Energy Data Tagger is more than a tagging tool; it is the backbone for scalable, data-driven operations in renewables. Combining a robust taxonomy with AI-powered classification, it delivers fast, consistent integration across solar, wind, and battery assets, turning data chaos into clarity.
Built-in renewable data taxonomy
Ready-to-use and tested over 1 million data signals from renewable assets (wind, solar and battery)
Multi-asset coverage
Includes solar, wind, and battery storage portfolios.
API and web access
Choose how you want to integrate across your tools and workflows. More than 240 asset types and 1600 signals across solar, wind and battery storage.
Portfolio-wide data clarity
Enables cross-site analysis and insights.
AI-powered signal mapping
Uses Natural Language Processing (NLP) to automatically classify SCADA signals and asset names with minimal manual input.
Designed for data teams across renewable operations
Data analysts
Data engineers
Digital systems architect
Proven in practice, backed by industry standards
Real-world use case
Originally built to solve GreenPowerMonitor’s internal challenges with inconsistent SCADA signal naming across 7,000+ monitored assets, Energy Data Tagger has matured into a market-ready digital product.
What began as a tool to accelerate our own operations is now transforming how the renewable sector approaches signal standardization.
Energy Data Tagger is based on the globally recognized IEC 81346 and RDS-PS standards, extended to meet the complex realities of utility-scale solar, wind, battery energy storage systems (BESS) and hybrid energy systems.
The result is a reliable, field-tested taxonomy that enables consistent, machine-readable signal naming, critical for automation, integration, and analysis at scale.
We needed a better way to organize our SCADA data. We built it, and now, you can use it too. You just upload a spreadsheet, and the model gets to work, mapping, tagging, and learning."
Giuseppe Ferraro
Director of Innovation
GreenPowerMonitor, a DNV company
Flexible pricing and plans to match your renewable energy management needs
Energy Data Tagger subscription plans are built to scale with your needs - from a free trial to enterprise-level plans. Most importantly, if you subscribe before 31 December 2025, you will lock in our early-bird rates for the first year before standard pricing begins in 2026.
Features:
Graphical representation of asset models
5,000 input signals to Energy Data Tagger
14-day time limit
Export disabled
API disabled
Features included:
Graphical representation of asset models
5,000 input signals to Energy Data Tagger
Web and API access
Data export available
Features included:
Graphical representation of asset models
50,000 input signals to Energy Data Tagger
Web and API access
Data export available
Looking for a tailored renewable data solution? We may already have the right tool within our GPM product suite, or one currently in development.
If not, our experts can design a renewable energy asset management solution to fit your specific challenge.
Need help with your trial or subscription? Contact the service team.
Energy Data Tagger is a standardized taxonomy for SCADA data from solar, wind, and storage projects. It defines a consistent naming scheme for both physical assets and data signals, validated across multiple of utility-scale sites.
To simplify adoption, it is paired with a Natural Language Processing (NLP) tool that, for PV sites, automatically maps existing signal names to the taxonomy, eliminating a typically time-consuming task. Initially trained on our extensive site library, the tool continues to learn and adapt as you use it, ensuring accuracy for your systems.
The result is a clean, ready-to-use map file in CSV or JSON format, seamlessly integrable into your data handling workflows.
Answer
Answer
Without consistent signal naming, analytics platforms, digital twins, and AI models can’t operate effectively. Standardization enables portfolio-wide visibility, automation, and reliable performance monitoring.
Answer
Answer
The taxonomy was defined using the knowledge and experience of GPM and DNV’s engineers – human intelligence, not artificial. But it is accompanied by a mapping tool which uses AI and Natural Language Processing to map PV signal names from the ad hoc ones you have inherited on to the taxonomy, even when vendors have used varied or ambiguous naming conventions.
Answer
Answer
Before developing Energy Data Tagger, we evaluated existing standard taxonomies. While each offered useful elements, none provided complete coverage across the wide variety of utility-scale plants. Our approach was to build on the strengths of established standards where they work best and supplement them with our own definitions where needed.
PV and battery storage: RDS-PS for assets, combined with GPM definitions for signals
Wind: IEC 81346, combined with GPM definitions
Answer
Answer
Yes, it offers both a web interface and a flexible API that enables seamless integration with asset monitoring systems, analytics dashboards, and digital infrastructure.
Answer
Answer
Energy Data Tagger supports data from solar, wind, and battery energy storage systems, making it suitable for hybrid portfolios.
Answer
Answer
The model continuously learns from its outputs and corrections. With a training dataset drawn from 7,000+ real-world parks, its tagging accuracy improves as it processes more input.
Answer
Answer
An AI-powered tool automates the mapping of PV data signal tags from their existing names into the standard taxonomy. Future enhancements will extend this capability to cover PV asset names as well as storage and wind taxonomies.
While most signals are mapped automatically with high accuracy, some cases require manual review. When the tool is uncertain, it suggests the most likely matches, and the user selects the correct one. Each correction helps the Energy Data Tagger improve over time, continually refining its accuracy.
Answer
Answer
You can access it on the Veracity Store, with flexible pricing plans available depending on your needs.
Answer
Answer
It's designed for utilities, IPPs, O&M teams, data engineers, and digital system architects looking to scale operations, improve analytics, and ensure compliance across multiple assets or vendors.
Answer
Answer
Yes, access is available through a REST API. You can interrogate the taxonomy definition, and send tags for automatic mapping.
Answer
Answer
You will use Energy Data Tagger when you are setting up your data connections for a new site. It will help you establish your asset model, and to map your existing tags on to the taxonomy.
Once you have completed that set up work, you won’t need it again – until the next site joins your portfolio.
