Just as autonomous driving relies on data and simulation training, the intelligent advancement of energy storage systems likewise depends on data and algorithms.
In recent years, energy storage companies have become increasingly aware of the importance of big data, and operational data from energy storage systems has become a critical intangible asset.
Whether they are energy storage system integrators or manufacturers of core components such as energy storage PCS, companies are gradually moving away from the old practice of outsourcing equipment management to software firms or operators. Instead, they increasingly prefer to develop their own cloud platforms, retain control over equipment operation, and move data to the cloud. At present, most energy storage manufacturers have started to build their own databases.
The industry believes that, through big-data analysis and mining, equipment manufacturers and operators can uncover patterns hidden within massive datasets, feeding back into product iteration and service innovation, improving asset operation efficiency and safety, and maximizing asset returns.
However, a core problem faced by enterprises is how to make data truly deliver value, rather than leaving it as a mere “invisible asset” or “potential value” in theory.
On one hand, energy storage systems are highly complex. Components such as battery cells, PCS, BMS, and EMS typically come from different manufacturers, creating data silos within the system. Many issues—such as intelligent battery-fault early warning and smart O&M—cannot be solved by any single component alone.
On the other hand, the volume of data generated by energy storage systems keeps growing, and integrating massive, fragmented information is no easy task. It requires substantial experience and accumulation, and cannot simply adopt traditional big-data processing methods wholesale.
“We must ground ourselves in real data, develop advanced algorithms and applications based on user needs and actual operating conditions, and let data create real value.” Building on its deep expertise in power-battery BMS and the product-improvement demands of real application scenarios, LIGOO launched its new-energy big-data business in 2017.
To address the many pain points in data processing, LIGOO independently developed an energy storage big-data management platform, putting it at the forefront of the industry in unlocking big-data applications. The platform can be integrated at the design stage of a storage power station, and can also retrofit existing stations with low digitalization levels into intelligent operations.
LIGOO’s energy storage big-data management platform is not a simple data-aggregation tool, but a comprehensive data-management solution that systematically transforms data processing and truly allows energy storage systems to “grow” on the foundation of big data.
The Industry’s Urgency for Big Data Is Growing
An energy storage BMS primarily monitors, collects, and analyzes battery information to achieve safe, efficient, and stable battery operation. Consequently, the BMS involves numerous algorithms, including battery SOX estimation, charge/discharge control, health early-warning, balancing optimization, and data processing.
First, high-precision SOX estimation requires large volumes of real-world data for validation.
High-precision data acquisition and battery-state SOX (SOC, SOE, SOP, SOH) estimation are critical inputs for energy storage system operation decisions and are among the core functions of the BMS.
At present, high-precision detection is achievable both for battery voltage, current, and temperature and for various gas detections. However, different BMS manufacturers vary in the quality of their battery SOX algorithms.
Dr. Shen Yongbo, Dean of LIGOO’s Research Institute and a senior engineer, notes that even if an algorithm achieves high-precision estimation in the lab or under ideal conditions, various problems may arise in real-world applications, rendering the algorithm unusable.
In his view, whether the algorithm can truly run in real-world scenarios and maintain high precision across massive real-world datasets is a more important and more difficult challenge.
Second, intelligent balancing algorithms require training on more historical charge/discharge data.
In an energy storage system, all cells charge and discharge simultaneously. However, due to multiple factors—such as differences in manufacturing processes and temperature variations across locations within the battery container—the states of individual cells differ. As service life and cycle count increase, cell-to-cell inconsistency intensifies.
If metrics such as SOC and SOH diverge significantly between cells, the mild consequence is wasted system capacity, while the severe consequence is overcharge/discharge that shortens battery life—and may even trigger incidents such as cell fires. Under these circumstances, the BMS’s balancing-optimization technology is drawing increasing industry attention.
Cell balancing is achieved through both hardware architecture and software algorithms; the system must make intelligent decisions and issue balancing commands. This requires BMS manufacturers to possess more historical lithium-battery charge/discharge data, so that precise control of each charge/discharge cycle extends the service life of storage batteries.
Energy storage safety early-warning must be built on operational data from complex operating conditions.
In recent years, safety incidents at global energy storage stations have increased year by year. Confronted with the enormous latent safety risks in the energy storage industry, the state has also tightened its review and acceptance of energy storage safety. Owing to the intrinsic characteristics of lithium batteries, most energy storage safety incidents stem from battery thermal runaway.
However, there are many triggers for lithium-battery thermal runaway, and thermal runaway caused by different problems exhibits different early signs. Issues such as overcharge, impact, nail penetration, water ingress, and internal short circuit can all induce thermal runaway.
If an internal short circuit occurs in a storage battery, in the early stage of thermal runaway the temperature change is not pronounced, but the battery’s internal resistance may drop and voltage may fall, generating only small amounts of heat that the cooling system can handle in time.
The early stage of thermal runaway is the optimal window for early warning. Although the BMS and thermal management systems play important roles in battery safety, truly containing thermal runaway at its initial stage hinges on more precise and comprehensive monitoring and early-warning of the battery, capturing subtle changes in each cell’s data.
It is worth noting that thermal-runaway early-warning is not the same as safety early-warning. Dr. Shen explains that safety early-warning centers on precision (warning accuracy), minimizing false alarms, whereas thermal-runaway early-warning pursues recall—“better to over-warn than to miss any.”
How to miss no thermal-runaway-risk warning while minimizing false alarms has become a technical difficulty for battery safety early-warning systems.
Energy storage is an operations-heavy industry; the safe and efficient management of massive numbers of cells directly affects a storage station’s revenue. As stations grow larger and charge/discharge more frequently, traditional manual O&M is becoming less viable, and the industry’s call for AI-driven intelligent operation is growing louder.
Functions such as battery-state assessment, balancing optimization, and safety early-warning are all “intelligent” applications realized through big-data processing at storage stations.
Unlike conventional O&M platforms, LIGOO’s energy storage big-data management platform is a comprehensive solution for improving overall operational efficiency. Based on data processing and model computing, it integrates modules such as data visualization, safety early-warning, residual-value assessment, data analytics, data services, and project management.
From December 11 to 13, the 2024 GGII Energy Storage Annual Conference invited leading companies across the storage value chain to conduct in-depth discussions on key topics such as storage safety and intelligent O&M. LIGOO will further share insights on storage BMS, battery safety, and big-data intelligent operation.
Closing the Data Gap: Advancing Storage Safety and Intelligence
Although a growing number of energy storage companies recognize the importance of leveraging data to optimize products, a practical problem widely facing the industry is the huge gap in actual operational data from storage stations.
On one hand, the energy storage industry only truly began its leapfrog development in recent years; early commissioned stations were few demonstration projects, and domestically many stations were “built but not used.” On the other hand, energy storage systems serve diverse application scenarios, and battery operating conditions differ under different environmental conditions and charge/discharge strategies.
So how can the data gap in the energy storage industry be closed? One important approach is to make good use of operational data from power batteries.
The BMS for power and storage batteries differ little in charging strategy. However, because power and storage applications have different demands on battery systems, they differ considerably in discharge strategy. Power batteries face complex, random discharge-current profiles requiring instantaneous high-power output, whereas storage batteries have lower power demands and place greater emphasis on maintaining consistency and safety across massive numbers of cells.
As a leading domestic third-party BMS enterprise, LIGOO has amassed massive data in the power-battery field. Starting its new-energy big-data business in 2017, LIGOO now offers multiple big-data platform products spanning new-energy vehicles, new-energy forklifts, and energy storage systems.
Drawing on multi-application data accumulation and advanced algorithm models, LIGOO leads many industry peers in improving full-lifecycle battery safety and usage efficiency.
GGII believes that, given the energy storage industry’s higher safety requirements, storage BMS needs further technical advancement in battery safety—especially in safety early-warning, where the BMS has enormous room to contribute.
So how can storage safety early-warning be achieved? Dr. Shen notes that the industry currently mainly adopts three approaches. The first is threshold-based fault diagnosis—for example, setting voltage-difference alarm thresholds—but in practice this merely shifts and duplicates BMS functions.
The second is model-based fault early-warning, which warns based on statistical learning and algorithms. Its problem is strong correlation with the battery’s operating conditions, making warnings unstable and sharply reducing accuracy.
The third is to build a battery early-warning scoring system that, building on the second approach, further analyzes the root causes of problems and seeks intelligent maintenance solutions.
It is understood that LIGOO’s safety early-warning system adopts the third approach, and it is gradually building a correlated early-warning system to further reduce duplicated warnings.
At present, on the basis of its energy storage big-data management platform, LIGOO achieves a safety early-warning accuracy above 99% and a warning recall above 90%, and can issue consistency-related safety warnings more than 14 days in advance.
Benefiting from more than 40 data-quality rules, development of over 10 core-metric algorithms, and 50-plus advanced warning items, LIGOO has achieved high thermal-runaway-warning recall and high safety-warning precision.
Beyond safety early-warning, the functional modules of LIGOO’s energy storage big-data management platform also include residual-value assessment, equipment maintenance, smart dashboards, inspection work-orders, user management, degradation analysis, and task review.
It is understood that LIGOO’s energy storage big-data management platform has been maturely applied in projects such as Dongfang Xuneng, earning positive customer feedback.
