Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ datasets:
|
|
10 |
**Owner:** DataBloom AI, Inc.
|
11 |
|
12 |
### Model Overview ###
|
13 |
-
LSTEnergy [last energy] is a Long-
|
14 |
some smartmeter data (5 cols, > 12mil. instances, cols: id, device_name, property, value, timestamp) and creates a custom forecast based on selected window.
|
15 |
|
16 |
Please notice that once you load up the smartmeter data, there are inputs created on the timestamp col like wd_input (the weekday of the timestamp), as well as a cos(inus) and sin(us)
|
@@ -21,9 +21,9 @@ After that, some functions are used to give the user the ability to use time win
|
|
21 |
|
22 |
The first models created are a simple baseline model, used for evaluating the performance of the later on built LTSM model. The baseline model simply shifts the values by t=1. Hence,
|
23 |
there is no t=0 and each timestamp uses the value from t-1.
|
24 |
-
Finally, there's the 2-layer plain vanilla
|
25 |
for which this seems appropriate.
|
26 |
|
27 |
-
![
|
28 |
|
29 |
***Happy Hacking!***
|
|
|
10 |
**Owner:** DataBloom AI, Inc.
|
11 |
|
12 |
### Model Overview ###
|
13 |
+
LSTEnergy [last energy] is a Long short-term memory model to predict energy consumption forecasts based on historical data. It basically takes
|
14 |
some smartmeter data (5 cols, > 12mil. instances, cols: id, device_name, property, value, timestamp) and creates a custom forecast based on selected window.
|
15 |
|
16 |
Please notice that once you load up the smartmeter data, there are inputs created on the timestamp col like wd_input (the weekday of the timestamp), as well as a cos(inus) and sin(us)
|
|
|
21 |
|
22 |
The first models created are a simple baseline model, used for evaluating the performance of the later on built LTSM model. The baseline model simply shifts the values by t=1. Hence,
|
23 |
there is no t=0 and each timestamp uses the value from t-1.
|
24 |
+
Finally, there's the 2-layer plain vanilla LSTM. After 11 epochs, I reached a loss of 10.86 which is rather mediocre. However, the main idea here is to build a basic forecasting model
|
25 |
for which this seems appropriate.
|
26 |
|
27 |
+
![LSTM](https://github.com/databloom-ai/LLM-LTSM/blob/main/LSTEnergy/LTSM.png?raw=true)
|
28 |
|
29 |
***Happy Hacking!***
|