> 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/pv/functionality-overview.md).
# Functionality Overview
The purpose of the NET2GRID EnergyAI® Edge PV application is to provide solar production estimation running fully on the edge without requiring any user input or prior knowledge of the presence of photovoltaic (PV) systems. The application utilizes lightweight deep learning models and algorithms 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, WiFi connection or high-frequency data transmission.
Our application operates out of the box, without requiring prior knowledge of PV ownership or historical data from MDM systems. This makes deployment scalable, cost-effective, and agnostic to the end-user's energy profile, delivering valuable insights on solar production within one week after deployment.
The solution is based on a deep learning model that estimates solar production and consists of two core processes: the training and the reporting periods.
### Training period
During the initial seven-day training period, the application focuses on the challenge of detecting the presence of PVs. Throughout this period, it continuously monitors household energy consumption patterns, identifying solar production activity without providing solar production estimations.
On the seventh day, the agent evaluates a set of criteria to determine whether a PV is likely present at the household. If the criteria are met, the household is flagged as having a PV, and the application transitions to the reporting phase. If the criteria are not met, meaning no PV is detected, the application continues with passive monitoring.
To account for scenarios where a user installs a PV system after the application deployment, the same criteria are re-evaluated daily over a rolling seven-day window.
### Reporting period
Once PV is detected, the application transitions to the reporting period. In this state, a deep learning model provides estimates of solar generation throughout the day, alongside a forecast for the subsequent hour. These insights are generated at 5-minute intervals and communicated on an hourly basis. Consequently, any previously forecasted figures are refined and updated using the most recent solar production estimations every hour.
---
# 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/pv/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.