> For the complete documentation index, see [llms.txt](https://docs.net2grid.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.net2grid.com/net2grid-energy-ai-edge-on-ami2/applications/ev/functionality-overview.md).
# Functionality Overview
NET2GRID EnergyAI® Edge EV application is engineered to enable real-time detection of EV charging events, entirely on the edge. The service leverages embedded deep learning models and advanced algorithms explicitly designed for low-resource environments, such as smart meters with constrained memory and processing capabilities. By moving intelligence to the edge, the solution ensures localized, secure, and efficient processing, eliminating the need for cloud infrastructure or high-frequency data transmission.
Our service operates out of the box, without requiring WiFi connection, prior knowledge of EV ownership or historical data from MDM systems. This makes deployment scalable, cost-effective, and agnostic to the end-user's energy profile.
The solution is based on a deep learning model that estimates the charging status of the EV every three minutes, comprising two core processes: a training period and real-time reporting.
Train and reporting periods
### Training period
When first deployed, the application enters an initial seven-day training phase, during which it analyzes household energy consumption patterns to determine whether an EV is present. Throughout this period, the application continuously monitors the incoming measurements and identifies potential EV charging events; however, no reports or events are generated.
At the end of the training phase, the application evaluates a set of detection criteria to determine whether the household is likely to own an EV. If the criteria are satisfied, the household is classified as an EV household, and the application transitions to the reporting phase, where EV-related insights are generated and communicated. If the criteria are not satisfied, the application continues monitoring the household without producing reports.
To account for scenarios where a user purchases a new EV or begins charging an EV at home after the initial deployment, the same criteria are re-evaluated daily over a rolling seven-day window. If EV presence is confirmed, the application shifts to real-time reporting.
In addition to the automatic detection process, the application supports manual retraining when required, for example following a change in household occupancy or other significant changes that may affect the learned consumption patterns.
### Real-time reporting
Once EV presence is confirmed, NET2GRID EnergyAI® Edge transitions to near real-time reporting of EV charging events. By default, the system reports an event 15 minutes after the actual charging start. This default reporting interval is designed to strike a balance between timeliness and detection accuracy, allowing the application to gather sufficient data to classify the event as EV charging confidently.
The reporting interval is configurable on a per-meter basis to suit different use cases. Available options include:
* 3, 5, and 10 minutes for applications requiring faster detection and more real-time responsiveness, and
* 30 minutes for scenarios where real-time insight is less critical and higher accuracy is preferred.
It is important to note that shorter intervals increase responsiveness but may reduce confidence, potentially leading to false positives. Conversely, longer intervals improve detection reliability by allowing more data to be accumulated, but at the cost of delayed reporting.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.net2grid.com/net2grid-energy-ai-edge-on-ami2/applications/ev/functionality-overview.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
