Saha-Edge’s Edge-AI can indeed support real-time offline dynamic battery capacity estimation for electric vehicle fleets in remote locations using localized electrochemical modeling while maintaining OCPP 2.0.1 compliance for charging session logging.
How it works in practice
The system leverages localized electrochemical models embedded within the Saha-Edge platform to estimate battery capacity without requiring constant connectivity to a central server. These models use historical charging data, temperature readings, and voltage/current profiles to predict capacity degradation in real time. The edge computing layer processes this data locally, enabling accurate estimations even when network connectivity is limited or unavailable.
This capability is particularly valuable for fleet operators managing vehicles in remote areas where cellular coverage is spotty or non-existent. The localized modeling ensures that capacity estimates remain reliable and actionable, supporting decisions around charging schedules, route planning, and maintenance needs without relying on cloud-based processing.
OCPP 2.0.1 compliance is maintained by ensuring that all charging session logs, including capacity estimation data, are stored locally and synchronized with the central CMS when connectivity is restored. This preserves the integrity of charging records and supports regulatory and operational requirements.
What this means for fleet operators
Fleet managers benefit from continuous visibility into battery health without depending on network availability. This is especially critical for long-haul transport, delivery services, or emergency response vehicles operating in areas with limited infrastructure. The system allows operators to proactively manage battery performance, reducing unexpected downtime and optimizing fleet efficiency.
For example, a logistics company using Saha-Edge in rural delivery routes can monitor battery capacity in real time, even when vehicles are out of cellular range. When connectivity returns, the system automatically syncs the data, ensuring that charging sessions are logged accurately and that capacity trends are maintained for predictive maintenance.
This approach also reduces reliance on external data sources or manual reporting, which can introduce delays or inaccuracies. By keeping the intelligence at the edge, fleet operators gain a more responsive and resilient system for managing their electric vehicle assets.
Related Reading
For more on related topics, see: Saha-Edge Battery Health Modeling for EV Charging.
Further reading: EV Charging Energy Management | OCPP Smart Charging CMS | Tecell India
📣 Join our Telegram channel for EV charging technology insights and product updates.
Also find us on: LinkedIn · X · Bluesky · Mastodon.