# Electricity Transformer Dataset (ETDataset)
In this Github repo, we provide several datasets could be used for the long sequence time-series problem. All datasets have been preprocessed and they were stored as `.csv` files. The dataset ranges from 2016/07 to 2018/07. [中文版本 | ChineseVersion](https://github.com/zhouhaoyi/ETDataset/blob/main/README_CN.md)
*Dataset list* (updating)
- [x] **ETT-small**: The data of 2 Electricity Transformers at 2 stations, including load, oil temperature.
- [ ] **ETT-large**: The data of 39 Electricity Transformers at 39 stations, including load, oil temperature.
- [ ] **ETT-full**: The data of 69 Transformer station at 39 stations, including load, oil temperature, location, climate, demand.
If you use this dataset please cite the work `Informer @ AAAI2021 Best Paper Award`[\[paper\]](https://arxiv.org/abs/2012.07436)[\[code\]](https://github.com/zhouhaoyi/Informer2020)[\[video\]](https://slideslive.com/38948878):
```
@inproceedings{haoyietal-informer-2021,
author = {Haoyi Zhou and
Shanghang Zhang and
Jieqi Peng and
Shuai Zhang and
Jianxin Li and
Hui Xiong and
Wancai Zhang},
title = {Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting},
booktitle = {The Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Virtual Conference},
volume = {35},
number = {12},
pages = {11106--11115},
publisher = {{AAAI} Press},
year = {2021},
}
```
## Why *Oil Temperature* is involved in this dataset?
The electric power distribution problem is the distribution of electricity to different areas depends on its sequential usage. But predicting the following demand of a specific area is difficult, as it varies with weekdays, holidays, seasons, weather, temperatures, etc. However, no existing method can perform a long-term prediction based on super long-term real-world data with high precision. Any false prophecy may damage the electrical transformer. So currently, without an efficient method to predict future electric usage, managers have to make decisions based on the empirical number, which is much higher than the real-world demands. It causes unnecessary waste of electric and equipment depreciation. On the other hand, the oil temperatures can reflect the conditon of electricity Transformer. One of the most efficient strategies is to predict how the electrical transformers' oil temperature is safe and avoid unnecessary waste.
As a result, to address this problem, our team and Beijing Guowang Fuda Science & Technology Development Company built a real-world platform and collected 2-year data. We work on it to predict the electrical transformers' oil temperature and investigate the extreme load capacity.
## ETT-small:
We donated two years of data, in which each data point is recorded every minute (marked by *m*), and they were from two regions of a province of China, named ETT-small-m1 and ETT-small-m2, respectively. Each dataset contains 2 year * 365 days * 24 hours * 4 times = 70,080 data point. Besides, we also provide the hourly-level variants for fast development (marked by *h*), i.e. ETT-small-h1 and ETT-small-h2. Each data point consists of 8 features, including the date of the point, the predictive value "oil temperature", and 6 different types of external power load features.
<p align="center">
<img src="./img/appendix_dataset_year.png" height = "200" alt="" align=center />
<img src="./img/appendix_auto_correlation.png" height = "200" alt="" align=center />
<br><br>
<b>Figure 1.</b>The overall view of "OT" in the ETT-small. <b>Figure 2.</b>The autocorrelation graph of all variables.
</p>
Specifically, the dataset combines short-term periodical patterns, long-term periodical patterns, long-term trends, and many irregular patterns. We firstly give an overall view in Figure 1, and it shows evident seasonal trends. To better examine the existence of long-term and short-term repetitive patterns, we plot the autorcorrelation graph for all the variables of the ETT-small-h1 dataset in Figure 2. The blue line in the above is the target 'oil temperature', and it maintains some short-term local continuity. However, the other variables (power load) shows short-term daily pattern (every 24 hours) and long-term week pattern (every 7 days).
We use the `.csv` file format to save the data, a demo of the ETT-small data is illustrated in Figure 3. The first line (8 columns) is the horizontal header and includes "date", "HUFL", "HULL", "MUFL", "MULL", "LUFL", "LULL" and "OT". The detailed meaning of each column name is shown in the Table 1.
<p align="center">
<img src="./img/ETT%20data%20demo.png" height = "168" alt="" align=center />
<br><br>
<b>Figure 3.</b> A demo of the ETT data.
</p>
| Field | date | HUFL | HULL | MUFL | MULL | LUFL | LULL | OT |
| :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: |
| Description | The recorded **date** |**H**igh **U**se**F**ul **L**oad | **H**igh **U**se**L**ess **L**oad | **M**iddle **U**se**F**ul **L**oad | **M**iddle **U**se**L**ess **L**oad | **L**ow **U**se**F**ul **L**oad | **L**ow **U**se**L**ess **L**oad | **O**il **T**emperature (target) |
<p align="center"><b>Table 1.</b> Description for each columm.</p>
没有合适的资源?快使用搜索试试~ 我知道了~
电力变压器数据集,包括负载、油温,用于支撑长时间序列相关的研究 所有的数据都经过了预处理,并且以.csv的格式存储
共10个文件
csv:4个
png:3个
md:2个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 100 浏览量
2024-08-04
16:04:13
上传
评论
收藏 4.11MB ZIP 举报
温馨提示
电力变压器数据集,包括负载、油温,用于支撑”长时间序列”相关的研究。所有的数据都经过了预处理,并且以.csv的格式存储。 我们提供了两年的数据,每个数据点每分钟记录一次(用 m 标记),它们分别来自中国同一个省的两个不同地区,分别名为ETT-small-m1和ETT-small-m2。每个数据集包含2年 * 365天 * 24小时 * 4 = 70,080数据点。 此外,我们还提供一个小时级别粒度的数据集变体使用(用 h 标记),即ETT-small-h1和ETT-small-h2。 每个数据点均包含8维特征,包括数据点的记录日期、预测值“油温”以及6个不同类型的外部负载值。 具体来说,数据集中包含短周期模式,长周期模式,长期趋势和大量不规则模式。我们在图1给出了数据的总览,图中数据显示出了明显的季节趋势。为了更好地表示数据中长期和短期重复模式的存在,我们在图2中绘制了ETT-small-h1数据集中所有变量的自相关图,其中最上面的蓝色曲线是目标变量“油温”,它保持了一些短期的局部
资源推荐
资源详情
资源评论
收起资源包目录
ETDataset-main.zip (10个子文件)
ETDataset-main
README_CN.md 5KB
LICENSE 17KB
ETT-small
ETTh1.csv 2.47MB
ETTh2.csv 2.31MB
ETTm2.csv 9.23MB
ETTm1.csv 9.88MB
img
appendix_auto_correlation.png 460KB
ETT data demo.png 10KB
appendix_dataset_year.png 180KB
README.md 5KB
共 10 条
- 1
资源评论
yanglamei1962
- 粉丝: 2327
- 资源: 623
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功