Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,38 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: TBATS 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 |
+
|
9 |
+
# TBATS Model for Energy Consumption Prediction
|
10 |
+
|
11 |
+
## Description
|
12 |
+
This TBATS model predicts energy consumption over a 48-hour period based on historical energy usage from 2021 to 2023. It utilizes time series data from a transformer station to forecast future energy demands.
|
13 |
+
|
14 |
+
## Model Details
|
15 |
+
**Model Type:** TBATS (Exponential smoothing state space model with Box-Cox transformation, ARMA errors, Trend and Seasonal components)
|
16 |
+
**Data Period:** 2021-2023
|
17 |
+
**Variables Used:**
|
18 |
+
- `Lastgang`: Energy consumption data
|
19 |
+
|
20 |
+
## Features
|
21 |
+
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. The dataset includes preprocessed features such as interpolated and aggregated energy consumption data (`Lastgang`).
|
22 |
+
|
23 |
+
## Installation and Execution
|
24 |
+
To run this model, you need Python along with the following libraries:
|
25 |
+
- `pandas`
|
26 |
+
- `tbats`
|
27 |
+
- `numpy`
|
28 |
+
- `matplotlib`
|
29 |
+
- `scikit-learn`
|
30 |
+
|
31 |
+
### Steps to Execute the Model:
|
32 |
+
1. **Install Required Packages**
|
33 |
+
|
34 |
+
2. **Load your Data**
|
35 |
+
|
36 |
+
3. **Preprocess the data according to the specifications**
|
37 |
+
|
38 |
+
4. **Run the Script**
|