Grid-Scale BESS AI/ML Patent Landscape 2026
The grid-scale BESS AI/ML patent field is in a growth stage, with filings rising sharply on a multi-year basis and activity concentrated among a small set of industrial incumbents and research institutions. ABB leads the applicant ranking, but the top five filers account for only about a quarter of the hundred largest filers’ combined total, leaving meaningful room for challengers.
ABB leads a fragmented but fast-growing competitive field
ABB (Schweiz) AG holds the top position in the applicant ranking, followed by Honeywell International, King Fahd University of Petroleum and Minerals, LG Energy Solution, and FranklinWH Energy Storage. The field spans industrial automation majors, energy-storage specialists, and academic institutions — an unusually diverse mix that reflects the interdisciplinary nature of AI applied to grid storage.
The top five filers account for roughly 27% of the hundred largest filers’ combined patent records, indicating a moderately fragmented competitive structure with no single dominant incumbent. The gap between the leader and the fifth-ranked player is narrow, reinforcing the open character of the space.
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 1 | ABB (Schweiz) AG | 14 | |
| 2 | Honeywell International Inc | 11 | |
| 3 | King Fahd University of Petroleum and Minerals | 8 | |
| 4 | LG Energy Solution Ltd | 6 | |
| 5 | FranklinWH Energy Storage Inc | 5 | |
| 6 | Hitachi Ltd | 3 | |
| 7 | Octave | 3 | |
| 8 | Utopus Insights Inc | 3 | |
| 9 | Board of Regents, The University of Texas System | 3 | |
| 10 | French Alternative Energies and Atomic Energy Commission (CEA) | 3 |
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 11 | AES US Services LLC | 2 | |
| 12 | University of Ulsan Foundation for Industry Cooperation | 2 | |
| 13 | Kunyu Power Co Ltd | 2 | |
| 14 | Siemens Corporation | 2 | |
| 15 | Nyobolt Ltd | 2 | |
| 16 | Florida International University | 2 | |
| 17 | Tsinghua University | 2 | |
| 18 | Inventus Holdings LLC | 2 | |
| 19 | State Grid Corporation of China | 2 | |
| 20 | Electric Power Research Institute of Guangxi Power Grid Co Ltd | 2 |
ABB’s and Honeywell’s positions reflect their broader grid-automation portfolios being extended into ML-driven storage control, whereas King Fahd University’s strong showing signals active academic R&D feeding into the pipeline — a pattern that often precedes commercial filing acceleration.
Filings from approximately 2024 onward are subject to publication lag and likely understate actual activity; the true recent filing rate is higher than the raw counts suggest. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Filings have expanded sharply since 2021, anchored in grid-power and AI computing classes
Two charts together capture the pace and shape of innovation: the annual filing trend shows when activity accelerated, while the technology composition reveals which technical disciplines are driving it.
Annual filing trend
Annual filings were minimal through 2020, then accelerated from 2021 onward, reaching a visible high in 2024. The 350% multi-year growth rate reflects a genuine step-change in R&D focus. The 2025 and 2026 bars are understated due to publication lag and should not be read as a slowdown.
↗ Hover for values · click a bar to ask EurekaTechnology composition
H02J (power supply and grid systems) dominates the IPC mix, confirming that grid integration and dispatch control remain the primary application layer. G06N (AI/ML computing models) is the second-largest branch, directly representing the machine-learning methods being applied. G06Q (business and administrative data processing), G01R (electrical measurement), and G06F (digital data processing) form a secondary tier, pointing to energy-market optimization, battery diagnostics, and data-infrastructure concerns as adjacent application areas.
↗ Hover for values · click a bar to ask EurekaHighly cited patent families surfaced by the query
Citation-heavy patent families returned by the query. Use this section as citation context, not as a curated list of the most topic-specific patents.
Machine learning-based method for increasing lifet…
An apparatus for performing the following: the apparatus maintains, in a database, one or more trained machine learning algorithms for predicting an optimal charging strategy for a time interval based on one or more values of a set of prediction parameters relating to a point of common coupling and one or more electrical load devices and on a state of… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | Building and Building Cluster Energy Management an… | 83 |
| 2 | Battery energy storage control systems and methods | 64 |
| 3 | Building energy management and optimization | 38 |
| 4 | Dynamic non-linear optimization of a battery energ… | 23 |
| 5 | Machine Learning -Based Method For Increasing Life… | 14 |
| 6 | 光储电站的功率协调控制方法和装置、存储介质 | 14 |
| 7 | 一种稳定电网输电断面潮流的储能系统智能化控制方法 | 13 |
| 8 | Battery energy storage control systems and methods… | 11 |
Ranked by total forward citations. Citation counts favour older and broadly cited patent families, and broad or adjacent patents may appear when they match the search scope. Treat this section as citation context, not as a curated list of the most topic-specific patents. Some patent titles may be shown in their original, non-English language where an accurate translation could not be guaranteed.
What the competitive structure means for R&D investment decisions
Four structural observations — maturity, concentration, collaboration, and geography — help frame where the risks and openings lie for teams evaluating entry or expansion.
Growth stage with rising annual volume
The lifecycle evidence classifies this field as Growth, with annual filings still rising and recent years understated by publication lag. The 350% multi-year growth rate confirms this is not a mature, saturated space. Early movers who file now can still shape the prior-art landscape before consolidation.
Lifecycle: GrowthFragmented top tier — no entrenched monopolist
The top five filers hold roughly 27% of the hundred largest filers’ combined total, and the leader (ABB) holds only 14 patent records. This is a low-concentration field by industrial standards. A focused filing campaign of a dozen or more well-scoped patents could place a new entrant within the visible top tier.
HHI: LowNo co-applicant activity detected in the current dataset
The collaboration evidence is currently empty, meaning no co-filed or jointly assigned patent records were identified in this corpus. This absence may reflect the early-stage, proprietary nature of the technology or gaps in the dataset. Teams should monitor for future joint filings between utilities, AI vendors, and storage OEMs as the field matures.
Co-filing: Evidence pendingUS and China lead; India is a notable third jurisdiction
The United States is the leading filing jurisdiction, followed by China and India. Europe (EPO) and WIPO (PCT) filings are present but smaller, suggesting that international protection strategies are still developing. India’s third-place position is atypical for an energy-storage AI topic and may reflect active academic and startup filing activity there.
Lead office: USGo beyond the landscape: Eureka’s TRIZ Solution agent breaks down an R&D problem and returns patented concept solutions, each with a technical approach and cited patent & literature evidence.
Co-filing pairs, ranked by the number of jointly-filed patent families.
ABB and Honeywell anchor the industrial tier; academic filers add depth
The top two ranked applicants are established automation and controls companies extending grid-AI capabilities into storage dispatch. Both entered the corpus recently, consistent with the field’s Growth stage, and both show H02J grid-systems plus G06N AI-model co-tagging.
ABB (Schweiz) AG
ABB leads with 14 patent records, concentrated in H02J grid-power systems and G06N AI/ML models — a combination that points to ML-driven grid dispatch and storage-control algorithms. Their momentum is classified as a new entrant, meaning their presence in this specific corpus is recent, consistent with ABB extending its grid-automation IP into the BESS-AI niche rather than a legacy position.
Patent records: 14Honeywell International Inc
Honeywell ranks second with 11 patent records, with emphasis balanced across G06N AI-model methods, H02J grid systems, and H02J battery-charging management. Like ABB, Honeywell’s trajectory is classified as a new entrant to this topic, suggesting active build-out of an AI-for-storage portfolio. Their G06N-first emphasis distinguishes them from ABB’s H02J-first profile.
Patent records: 11| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| ABB (Schweiz) AG | 8 | ▲ new entrant |
| Honeywell International Inc | 5 | ▲ new entrant |
| King Fahd University of Petroleum and Minerals | 8 | ▲ new entrant |
| LG Energy Solution Ltd | 5 | ▲ new entrant |
| FranklinWH Energy Storage Inc | 4 | ▲ new entrant |
| Hitachi Ltd | 1 | ▲ new entrant |
| French Alternative Energies and Atomic Energy Commission (CEA) | 3 | ▲ new entrant |
| Utopus Insights Inc | 3 | ▲ new entrant |
Under-served technical branches adjacent to the dominant grid-AI core
Several IPC classes appear at relatively low shares of the overall corpus, suggesting areas where AI/ML methods have not yet been heavily applied to BESS — or where existing filings leave gaps a focused portfolio could address.
G01R · Electrical & Magnetic Measurement
With 25 patent records and an 8% share of the corpus, G01R — covering electrical measurement and diagnostic methods — is the largest under-served adjacent branch. Applying ML to real-time state-of-health and state-of-charge estimation for grid-scale cells is technically valuable and directly complements the dominant H02J dispatch layer. Entry paths include sensor-fusion algorithms and anomaly-detection models for cell-string monitoring.
Search this in Eureka →H01M · Batteries, Cells & Fuel Cells
H01M appears in only 19 patent records (6% share), meaning AI/ML methods applied at the electrochemical and cell-hardware level — such as ML-guided degradation modeling or formation-cycle optimization for grid cells — remain sparse relative to the grid-integration layer above them. Teams with materials or electrochemistry expertise alongside ML capability could stake out differentiated positions here.
Search this in Eureka →How top filers differ across technology routes
Route coverage across the main technology branches in the current evidence set.
| Player | H02J 3 · Power supply & grid systems | H02J 7 · Power supply & grid systems | G06N 3 · Computing based on AI models | G06N 20 · Computing based on AI models | G06Q 50 · Business, commerce & admin data processing |
|---|---|---|---|---|---|
| Honeywell International Inc | Strong · 6 | Strong · 5 | Strong · 6 | Strong · 4 | Moderate · 2 |
| ABB (Schweiz) AG | Strong · 11 | Strong · 6 | Emerging · 2 | Moderate · 3 | Absent |
| King Fahd University of Petroleum and Minerals | Absent | Strong · 8 | Absent | Strong · 8 | Absent |
| LG Energy Solution Ltd | Strong · 4 | Strong · 6 | Moderate · 2 | Absent | Absent |
| FranklinWH Energy Storage Inc | Strong · 5 | Strong · 3 | Absent | Absent | Absent |
| Octave | Strong · 3 | Strong · 3 | Absent | Absent | Absent |
| Board of Regents, The University of Texas System | Strong · 3 | Absent | Absent | Absent | Strong · 3 |
Frequently asked questions
The current dataset contains 129 patent families in scope. This is a relatively small but fast-growing corpus — the 350% multi-year growth rate indicates rapid acceleration from a low base.
ABB (Schweiz) AG is the top-ranked applicant with 14 patent records, focused on H02J grid-power systems and G06N AI/ML computing methods. Honeywell International is second with 11 patent records.
It is moderately fragmented. The top five filers account for approximately 27% of the hundred largest filers’ combined total, and no single applicant holds a dominant share. This structure is accessible to new entrants with focused filing strategies.
The United States is the leading jurisdiction, followed by China and India. Europe (EPO) and WIPO (PCT) filings are present at smaller volumes, suggesting that comprehensive international filing strategies are still developing in this field.
The evidence classifies this field as Growth. Annual filings are still rising on a multi-year basis, with a 350% growth rate. Recent filing years (2025–2026) are understated due to publication lag and should not be read as a slowdown.
G01R (electrical and magnetic measurement) and H01M (batteries and cells) are the two most notable under-served adjacent branches, each with relatively few patent records compared to the dominant H02J and G06N classes. AI/ML applied to cell-level diagnostics and electrochemical modeling remains sparse.
Map your own grid-storage AI patent landscape
Join 18,000+ innovators using PatSnap Eureka to map any technology landscape: search 2B+ patents and papers, surface key assignees, and generate a report like this in minutes.
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.