EVOLVE: a Value-Added Services Platform for Electric Vehicle Charging Stations

A notable challenge in Electric Vehicle (EV) charging is the time required to fully charge the battery, which can range from 15 minutes to 2-3 hours. This idle period, however, presents an opportunity to offer time-consuming or data-intensive services such as vehicular software updates. ISO 15118 referred to the concept of Value-Added Services (VAS) in the charging scenario, but it remained underexplored in the literature. Our paper addresses this gap by proposing \acronym, the first EV charger compute architecture that supports secure on-charger universal applications with upstream and downstream communication. The architecture covers the end-to-end hardware/software stack, including standard API for vehicles and IT infrastructure. We demonstrate the feasibility and advantages of \acronym by employing and evaluating three suggested value-added services: vehicular software updates, security information and event management (SIEM), and secure payments. The results demonstrate significant reductions in bandwidth utilization and latency, as well as high throughput, which supports this novel concept and suggests a promising business model for Electric Vehicle charging station operation.

💡 Research Summary

The paper introduces EVOLVE, a novel edge‑computing platform that transforms electric vehicle (EV) charging stations from pure power dispensers into secure, data‑centric hubs capable of delivering value‑added services (VAS) during the vehicle’s idle charging time. Recognizing that the 15‑minute to several‑hour charging window is underutilized, the authors build on ISO 15118 – the standard governing vehicle‑to‑charger communication – and extend it to support universal applications with both upstream (vehicle‑to‑cloud) and downstream (cloud‑to‑vehicle) data flows.

EVOLVE’s architecture is organized into three software layers plus an event bus that interconnects them. Layer 1 hosts low‑level firmware, hardware accelerators (e.g., GPUs, FPGAs, TEEs) and the EV Edge Server, providing flexible data handling and secure key management. Layer 2 consists of a suite of micro‑services: a Security service (cryptographic libraries, TPM/TEE drivers), a Charging Stack (high‑availability power control), AI/ML libraries (for inference and analytics), Cache Storage, Telemetry & Communication, and Resilience (monitoring, redundancy, fault handling). Layer 3 implements the actual VAS – over‑the‑air (OTA) vehicle software updates, Security Information and Event Management (SIEM), and Secure Payments – each leveraging the lower layers for compute, storage, and security. The event bus enforces access‑control lists (ACLs) to isolate services while maintaining low‑latency messaging.

The platform exposes two standardized APIs. The vehicle‑side API follows the ISO 15118 discovery (SDP) and service negotiation (SNP) procedures, establishing a TLS session with Ephemeral Diffie‑Hellman (EDH) key exchange over either the charging cable or a wired Power Line Communication (PLC) link. This API is mapped to the AUTOSAR application layer, ensuring minimal impact on vehicle real‑time functions. The cloud‑side API uses HTTPS and MQTTS to securely off‑load heavy computation, synchronize logs, and exchange data with third‑party services. By adhering to ISO 15118 while adding these extensions, EVOLVE remains interoperable with existing chargers and vehicles.

Evaluation comprises a requirements‑compliance analysis and an empirical performance study on a prototype charger built on a Raspberry‑Pi‑class SECC. Memory footprint and CPU usage are measured to confirm that the platform can run on modest hardware. Three VAS use cases are exercised: (1) OTA updates involving a 500 MB firmware image, where PLC communication achieves an average latency 3.8× lower than 4G/5G and a 99.9 % success rate; (2) SIEM, which pushes 200 MB of log data and pulls 2 KB federated‑learning parameters, reducing network load by over 70 % compared to cloud‑only processing; (3) Secure Payments, generating up to 350 transactions per second with sub‑15 ms response times, representing a seven‑fold throughput improvement over 5G‑based solutions. These results demonstrate that embedding edge compute in chargers can dramatically cut bandwidth consumption, lower latency, and enable high‑frequency, security‑critical transactions.

The authors argue that EVOLVE opens new business models for charging‑station operators: they can act as distribution points for OEM software updates, provide real‑time security monitoring for fleets, and host micro‑payment ecosystems without relying on costly cellular links. The modular micro‑service design and standardized APIs also simplify integration of future services and third‑party applications. Limitations include the added hardware cost, power consumption of edge modules, and the need for robust operational management in large‑scale deployments. The paper concludes by positioning EVOLVE as the first comprehensive, standards‑compliant VAS platform for EV charging, and outlines future work such as multi‑station collaborative edge computing, AI‑driven grid load balancing, and contributions to standardization bodies.