Inverter Based Resource Modelling Patents: Who Leads 2026
- Filing is concentrated in China. 11 of 12 receiving-office filings are Chinese, with a single Canadian filing from Quanta Technology representing the non-Chinese route into this space.
- 2025 is the peak year so far, at 6 filings. with 2017 through most prior years showing no activity in scope — this is a field that has only recently started accumulating patent claims.
- The leader holds only 2 records. against 17 ranked assignees total, so no single organisation has established a dominant claim position yet.
What this landscape covers
Inverter based resource modelling covers the methods used to represent grid-connected inverters, converters and the plants built around them — black-box models, parameter identification, and the electromagnetic transient simulations used to validate that a model’s transient response matches the physical device closely enough for interconnection studies. This is where the claims sit at the intersection of power systems engineering and computational modelling: a patent here typically covers a method for identifying model parameters, a validation or benchmark test procedure, or a way of exporting a trained model between simulation platforms.
The scope here is narrow and recent by design. With 12 published records in scope and filing concentrated in the past few years, this is a field still being staked out rather than one with settled prior art — publication lag means the most recent year understates actual filing activity.
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
Filing trend and technology composition
The numbers below come directly from the records in scope: a small, recent corpus concentrated around power system and computing classes rather than spread evenly across the taxonomy.
A field just starting to accumulate filings
Activity in scope was flat at zero for most of the tracked period, then reached a peak of 6 filings in 2025. With fewer than four complete years of meaningful activity once publication lag is accounted for, no growth rate can be reliably stated — but the shape shows a technology area that only recently became patent-active.
Power systems and digital processing dominate the classification mix
H02J (power supply and grid systems) appears on 66.7% of the 12 records in scope, followed by G06F (electric digital data processing) at 50.0% and G05B (control and regulating systems) at 33.3%. G06N (AI-based computing) reaches 25.0%, showing that a quarter of records already frame parameter identification or model validation as a machine-learning problem rather than a purely analytical one. F03D (wind motors) and G06Q (business data processing) each sit at 16.7%, and H02P (motor and generator control) at 8.3% — both signal adjacent claim territory rather than the core of the field.
Shares are the percentage of the 12 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Inverter Based Resource Modelling with Eureka
This page is one run against one query. Ask Eureka your own question about inverter based resource modelling and every answer comes back with the patent numbers behind it.
Try EurekaRepresentative and most-cited filings
Inverter-based resource or plant modeling (CA3230547A1)
Quanta Technology's filing discloses exporting a black-box model of an inverter-based resource or plant from one software platform for use by another. The method simulates instantaneous time-domain responses to conditions defined by a script, generates training data from those responses, and trains a machine learning model to reproduce the plant's behaviour for use in a second simulation environment.This is the only non-Chinese filing in the dataset's receiving-office mix and the clearest example of a cross-platform, ML-based black-box export method in scope.
View full filing| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | CN117526384A | 储能系统电磁暂态模型低电压穿越参数辨识方法及系统 | 12 |
| 2 | CN116470522A | 一种SVG通用电磁暂态模型的控制参数识别方法及装置 | 3 |
| 3 | CN118446087A | 一种基于自动编码器的电磁暂态模型参数辨识方法及系统 | 1 |
Citation counts favour older records within this searched corpus and should be read as a signal of influence, not of current commercial importance.
Patent titles are shown in the language they were filed in, not translated, so that each record stays verifiable against the original filing — a translated title will not match in Eureka or in any national register. Publication numbers are shown where the record carries one (3 of 3 rows); clicking a row searches Eureka by that number.
Put your own technology through the same analysis
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →What the filing pattern signals
Three findings stand out once the ranking, the trend and the classification mix are read together.
No dominant filer yet
The leading assignee holds only 2 of the records in the ranking, with fifth place already down to 1. Across 17 ranked assignees, that is a flat distribution rather than a concentrated one — there is no single portfolio a new entrant needs to design around wholesale.
A near-exclusively Chinese filing base, with one outside signal
Eleven of the twelve receiving-office filings are Chinese, dominated by grid-operator and research-institute assignees. The single Canadian filing, from Quanta Technology, is also the dataset's clearest black-box, ML-based modelling claim — worth watching as a marker of where non-Chinese activity may follow.
Parameter identification is drifting toward machine learning
A quarter of the 12 records in scope already classify under G06N, AI-based computing, alongside the more traditional H02J and G05B power-system classes. That overlap suggests newer filings are framing model validation and parameter identification as a learned-model problem rather than a purely deterministic one.
Filing partnerships exist but are shallow
Nine co-assignee pairs appear across the dataset, with the strongest pairing filing twice together and the rest only once. This points to occasional joint filing between grid operators and their research institutes rather than an established collaboration network.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to inverter based resource modelling, with the prior art for and against each one.
Who is filing, and where the activity has stalled
The assignee base is led by Chinese grid operators and their affiliated research institutes, but recent-year momentum has dropped to zero across every named organisation with a prior filing history.
A narrow lead, not a moat
The top-ranked assignee holds 2 of the 12 records — enough to lead the ranking, not enough to foreclose the field. Fifth and tenth place each sit at 1 record, showing how flat the distribution is beyond the top spot.
Every tracked assignee shows zero latest-year filings
Organisations including State Grid, China Southern Power Grid's research institute, Yunnan Power Grid's research institute, Southwest Jiaotong University, Shenyang Institute of Engineering and Zhuhai Power Supply Bureau all show 0 filings in the latest year, a -100% year-on-year drop for those with a prior filing to compare against.
Grid operators pair with their own research arms
The strongest co-assignee link in the dataset pairs China Southern Power Grid's research institute with Yunnan Power Grid's research institute, filing together twice. Other pairings, including State Grid with two of its provincial subsidiaries, appear only once each.
| Assignee | Recent year | YoY |
|---|---|---|
| State Grid Corporation of China | 0 | -100% |
| China Southern Power Grid Research Institute Co., Ltd. | 0 | -100% |
| Yunnan Power Grid Co., Ltd. Electric Power Research Institute | 0 | -100% |
| Southwest Jiaotong University | 0 | — |
| Shenyang Institute of Engineering | 0 | -100% |
| Zhuhai Power Supply Bureau, Guangdong Power Grid Co., Ltd. | 0 | -100% |
| Dalian University of Technology | 0 | — |
| State Grid Qinghai Electric Power Company Electric Power Research Institute | 0 | — |
Where to take this next
This landscape is a starting point for a freedom-to-operate check or a deeper technology scan, not a substitute for one.
Check claim scope against CA3230547A1
Anyone building cross-platform black-box export tools for inverter-based resources should read this filing's claims in full before committing to a similar architecture.
Explore in EurekaTrack the AI-modelling overlap
The G06N overlap with H02J and G05B is still small at 25.0% of records; a targeted search on machine-learning-based parameter identification may surface earlier or narrower prior art than this broad query returns.
Run a deeper search in EurekaWatch for non-Chinese filings
With 11 of 12 filings routed through China, a shift in receiving-office mix would be an early signal that the field is internationalising.
Set up monitoring in EurekaCommon questions on inverter based resource modelling patents
In this dataset, it refers to a mathematical or software representation of a grid-connected inverter, converter or plant, built for use in electromagnetic transient simulation or interconnection studies. Patents in this space typically claim a method for identifying the model's parameters, a way of validating that the model's transient response matches the physical device, or a technique for exporting a trained model between simulation platforms. The representative filing in this landscape, CA3230547A1, covers exactly this last case: exporting a black-box model trained with machine learning from one software platform to another.
The ranking includes 17 assignees, led by an organisation with 2 records, with fifth and tenth place each holding 1. That is a flat distribution rather than a concentrated one, so no single filer currently controls a broad claim position. Most of the ranked organisations are Chinese grid operators or their affiliated research institutes, reflecting the fact that 11 of the 12 filings in scope came through China's receiving office.
Yes, on receiving-office data: 11 of the 12 filings in scope were routed through China, against a single Canadian filing. That single non-Chinese filing, from Quanta Technology, is also the dataset's most detailed black-box modelling claim, which makes it worth tracking closely even though it is a minority of the filings by volume. This pattern may simply reflect where this specific query surfaces activity rather than the full global picture of inverter modelling research.
Based on IPC composition, branches touching wind-turbine-specific benchmark tests (F03D, 16.7% of records), motor and generator control parameter identification (H02P, 8.3%), and business-process framing of interconnection studies (G06Q, 16.7%) all show low record counts relative to the core H02J and G06F classes. These lower counts suggest claim space that is less occupied, though a low count in a narrow search does not guarantee the area is unclaimed elsewhere — it should be checked against a broader query before relying on it.
Not very, by filing history: the tracked period shows no activity in most years, then a peak of 6 filings in 2025, the most recent complete year in the dataset. Because publication typically lags filing by around 18 months, that 2025 figure is itself likely to be revised upward as later publications surface, and 2026 data is partial. With fewer than four complete years of real activity, no filing growth rate can be reliably calculated from this dataset.
Research Inverter Based Resource Modelling in depth with Eureka
Go past this page: query the whole inverter based resource modelling corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company’s registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.