DATASET
Open Source Community
Photovoltaic fault dataset
This dataset contains 16 days of operational data from a grid‑connected photovoltaic power plant, covering both normal and fault conditions. It consists of two .mat files that can be loaded with MATLAB and includes voltage, current, temperature, irradiance, and fault‑type labels.
Updated 3/7/2024
github
Description
Dataset Overview
Dataset Name
- Photovoltaic fault dataset
Dataset Content
- Contains 16 days of grid‑connected photovoltaic power plant operational data, covering normal and fault states.
Dataset Files
dataset_elec.mat: DC electrical data (voltage and current for two strings)dataset_amb.mat: Temperature, irradiance, and fault‑type labels
Variable Description
| Variable | Description |
|---|---|
| vdc1 | Voltage – String 1 |
| vdc2 | Voltage – String 2 |
| idc1 | Current – String 1 |
| idc2 | Current – String 2 |
| irr | Irradiance |
| pvt | Photovoltaic module temperature |
| f_nv | Fault label |
Fault Labels (f_nv)
| Value | Description |
|---|---|
| 0 | Normal operation (no fault) |
| 1 | Short circuit (short between two modules in a string) |
| 2 | Degradation (resistance between two modules in a string) |
| 3 | Open circuit (a string disconnected from the inverter) |
| 4 | Shadow (one or more modules covered by shadow) |
Fault Introduction Methods
- Degradation: introduced by inserting a resistive load bank between two modules.
- Short circuit: introduced by connecting a cable between the positive and negative terminals of the modules.
- Open circuit: introduced by opening the main breaker of the string.
- Shadow: occurs naturally, caused by nearby buildings.
AI studio
Generate PPTs instantly with Nano Banana Pro.
Generate PPT NowAccess Dataset
Login to Access
Please login to view download links and access full dataset details.
Topics
Photovoltaic Systems
Fault Analysis
Source
Organization: github
Created: 6/4/2020
Power Your Data Analysis with Premium AI Models
Supporting GPT-5, Claude-4, DeepSeek v3, Gemini and more.
Enjoy a free trial and save 20%+ compared to official pricing.