In the Cloud

Intelligent Battery Management Systems

Battery Management Systems (BMS) are crucial for optimizing the operation of batteries by monitoring and controlling key parameters. Through real-time measurements of voltage, current, and temperature, BMSs can predict a battery’s performance, aiding in making informed decisions to enhance its lifespan and charging efficiency. The core functionalities include:

  • State-of-charge (SoC) – Determining the remaining charge in a battery by reading its voltage.
  • State-of-power (SoP) – Assessing the immediate power available in a battery for performance demands.
  • State-of-health (SoH) – Quantifying the degradation level to adapt the usage or decide on retirement by measuring capacity fade and resistance increases.
  • Remaining useful life (RuL) – Providing insights into the longevity of the battery, aiding in planning for replacements or other necessary actions.
  • Predictive cell diagnosis: Analyzing leading indicators for early diagnosis of battery cell issues.

These capabilities of a BMS not only ensure the safe operation of batteries but also optimize their performance, thereby extending their service life and reducing the total cost of ownership. For ‘Cloud BMS’ this involves a cloud-based digital twin tracking battery degradation. The data is relayed back to the ‘Local BMS’, allowing the BMS to adapt to the battery’s current health.

Vehicle control using cloud digital twin and embedded measurements [1]

Software vs Hardware

Local Battery Management Systems (BMS) and Cloud-based BMS serve the same fundamental purpose but differ in their operational models and capabilities. Here’s a comparison:

  1. Model Implementations:

Models are used to infer battery performance characteristics; these can range from simple/empirical to more complex/physical.

  • Local BMS: Generally employs simpler, empirical or equivalent circuit models due to computational limitations.
  • Cloud BMS: Leverages advanced physics-based models and machine learning algorithms. High-fidelity models like electrochemical models can be utilized here due to the abundance of computational resources.
  1. Data Processing and Storage:

Imporant for real-time monitoring, control, and analysis in battery management systems.

  • Local BMS: Processes and stores data on-premises. This model is suited for real-time monitoring and control but might lack in comprehensive analysis due to limited computational resources.
  • Cloud BMS: Processes and stores data in the cloud, providing virtually limitless computational resources for sophisticated data analysis, predictive modelling, and machine learning algorithms.
  1. Cost:

Including initial setup expenses and operational costs over time, significantly impacting the choice between local and cloud BMS. Initial setup costs refer to the initial expenses incurred when establishing a system, encompassing elements like hardware procurement, software licenses, installation, and configuration.

  • Local BMS: Lower initial setup cost but may incur higher operational costs over time due to manual maintenance and upgrades.
  • Cloud BMS: Higher initial setup cost but potentially lower operational costs due to automated maintenance and the ability to leverage shared resources in the cloud.
Design and functions of the cloud-based BMS [2]

It is Black and White!

The color-coded box models represent varying degrees of understanding and transparency concerning the internal dynamics of the system, and are crucial in the context of local and cloud BMS.

  • Local BMS often employs models leaning towards the black or grey box categorization, utilizing more empirical or simpler physics-based models due to computational limitations inherent in local setups.
  • Cloud BMS, on the other hand, has the luxury to delve into white box models, harnessing advanced physics-based or AI models, thanks to the abundant computational resources. This allows for a deeper understanding and predictive capabilities, making cloud BMS a powerful tool for comprehensive battery analysis and management.
Different types of models categorised based on empirical and physics-informed approaches [3]

Commercial Landscape

Several companies are deploying cloud-based BMS technologies, among them are Elysia, Twaice, Newten, and Eatron. They employ varying approaches, particularly in the use of Artificial Intelligence (AI) to enhance battery lifetime and performance.

Elysia (UK) offers a cloud-based platform deploying digital twin technology, enabling real-time analysis and forecasting to improve battery life and safety. Their Elysia Embedded suite houses robust BMS algorithms that are hardware-agnostic, facilitating seamless integration into existing software ecosystems.

Eatron Technologies (UK/Turkey) centrally features the BMSTAR Battery Management System, designed on a hardware-agnostic software platform grounded on physical models. It operates adeptly at the edge with a cloud counterpart for continuous, adaptive software improvements via over-the-air updates.

NEWTWEN (Italy) Creates high-fidelity digital replicas of physical systems integrated into real-time firmware, enhancing BMS efficacy. Their advanced BMS employs Battery Models to better estimate key battery parameters like SOC, SOH, aiding in life preservation.

Twaice (Germany) Provides a Battery Analytics Platform blending deep battery knowledge with AI and real-life data. Their digital twin concept creates a simulation model of the battery on their cloud platform, continually refining parameters to mirror the actual battery’s behaviour.

Predictive Maintenance

Predictive maintenance in Battery Management Systems (BMS) optimizes maintenance schedules, enhancing safety by addressing potential risks like overheating. This approach, utilized by cloud BMS systems like those from Elysia, Breathe, Eatron, Twaice, and Newtwen, improves energy efficiency in applications like electric vehicles and renewable energy storage, relying on data analysis and machine learning for insightful predictions on battery performance and health over time.

Predictive maintenance of battery systems using online state-of-charge and state-of-health estimation [4]

Silver Lining

Cloud BMS is critical for improving battery lifetime, charging, and safety. Despite next-generation battery chemistries emerging, current battery technology has room for growth. Intelligent software, advanced models, and better data analytics within cloud BMS can unlock potential performance gains. This technology is crucial for optimizing battery operations, ensuring safety, and advancing the field of battery management and electric mobility. Many other companies working in this domain including Rimac Energy, Battgenie, Breathe Battery Technologies, and Electra Vehicles.


  1. Billy Wu, Battery digital twins: Perspectives on the fusion of models, data and artificial intelligence for smart battery management systems
  2. Manh-Kien Tran, Concept Review of a Cloud-Based Smart Battery Management System for Lithium-Ion Batteries: Feasibility, Logistics, and Functionality
  3. Signe Schmidt, Model Identification Using Stochastic Differential Equation Grey-Box Models in Diabetes
  4. Weihan Li, Digital twin for battery systems: Cloud battery management system with online state-of-charge and state-of-health estimation


A data company that offers software to enhance battery performance throughout its lifetime. Its platform, “The Voltt”, reduces time and costs in developing new electric products for various industries. Utilizing advanced battery testing methods, this platform facilitates cell selection, benchmarking, and system design. Catering to anyone aiming to improve battery performance metrics, it efficiently trims down cell selection times from months to minutes through its comprehensive cell library. Users can leverage this resource to benchmark their emerging cell chemistries, maintaining a competitive edge by evaluating rival performance. Providing cloud-based tools and downloadable models, “The Voltt” aids in optimizing system designs by offering insights into battery pack behaviour

Leave a Comment