Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,51 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: SARIMAX Model for Energy Consumption Prediction
|
| 3 |
+
description: >-
|
| 4 |
+
This model predicts energy consumption based on meteorological data and
|
| 5 |
+
historical usage.
|
| 6 |
+
license: gpl
|
| 7 |
+
---
|
| 8 |
+
# SARIMAX Model for Energy Consumption Prediction
|
| 9 |
+
|
| 10 |
+
## Description
|
| 11 |
+
This SARIMAX model predicts energy consumption over a 48-hour period based on meteorological data and historical energy usage from 2021 to 2023. It utilizes time series data from a transformer station and incorporates both time-based and weather-related variables to enhance prediction accuracy.
|
| 12 |
+
|
| 13 |
+
## Model Details
|
| 14 |
+
**Model Type:** SARIMAX (Seasonal ARIMA with exogenous variables)
|
| 15 |
+
**Data Period:** 2021-2023
|
| 16 |
+
**Variables Used:**
|
| 17 |
+
- `Lastgang`: Energy consumption data
|
| 18 |
+
- `StundenwertStrahlung`: Hourly radiation
|
| 19 |
+
- `Globalstrahlung_15Min`: Global radiation every 15 minutes
|
| 20 |
+
- `StrahlungGeneigteFläche`: Radiation on inclined surfaces
|
| 21 |
+
- `TheorPVProd`: Theoretical photovoltaic production
|
| 22 |
+
- `Direktnormalstrahlung`: Direct normal radiation
|
| 23 |
+
- `Schönwetterstrahlung`: Clear sky radiation
|
| 24 |
+
- `Lufttemperatur`: Air temperature
|
| 25 |
+
- `Lastgang_Moving_Average`: Moving average of energy consumption
|
| 26 |
+
- `Lastgang_First_Difference`: First difference of energy consumption
|
| 27 |
+
|
| 28 |
+
## Features
|
| 29 |
+
The model splits the data into training and testing sets, with the last 192 data points (equivalent to 48 hours at 15-minute intervals) designated as the test dataset. It defines target variables (`Lastgang`) and explanatory variables including hourly and daily patterns as well as derived features from the consumption data. The dataset includes preprocessed features such as scaled energy consumption (`Lastgang`), and weather-related features.
|
| 30 |
+
|
| 31 |
+
## Installation and Execution
|
| 32 |
+
To run this model, you need Python along with the following libraries:
|
| 33 |
+
- `pandas`
|
| 34 |
+
- `numpy`
|
| 35 |
+
- `matplotlib`
|
| 36 |
+
- `statsmodels`
|
| 37 |
+
- `scikit-learn`
|
| 38 |
+
- `pmdarima`
|
| 39 |
+
- `psutil`
|
| 40 |
+
|
| 41 |
+
### Steps to Execute the Model:
|
| 42 |
+
1. **Install Required Packages**
|
| 43 |
+
conda install pandas numpy matplotlib scikit-learn statsmodels pmdarima psutil
|
| 44 |
+
or
|
| 45 |
+
pip install pandas numpy matplotlib scikit-learn statsmodels pmdarima psutil
|
| 46 |
+
|
| 47 |
+
2. **Load your Data**
|
| 48 |
+
|
| 49 |
+
3. **Preprocess the data according to the specifications**
|
| 50 |
+
|
| 51 |
+
4. **Run the Script**
|