The main idea is to build an AI based energy management system for house holds and offices. This will help in saving our resources.
Already have an account? Log in.
To make the experience fit your profile, pick a username and tell us what interests you.
The project's core are 2 AI applications:
1) LSTM predictor
2) ANN predict core
LSTM Predictor : In the project there was a need a predict the approximate future bill amount based on the current data.
ANN core : This core ANN monitors the temperature , human activity , power data , consumption pattern, etc then it gives out the optimal value. This data will be used to control the power consumption.
Gerber_PCB_2020-01-08 07_06_52_2020-05-20_09-40-08.zipGerber File for control cardx-zip-compressed - 97.63 kB - 05/20/2020 at 04:10 |
|
This project is still in its adolescent stages. We have just completed collecting real-time data, analyzing the trends and designing the PCB for the control card.
We have started developing the AI part of the code. The LSTM model is now complete and is set for testing. The ANN is under-development and soon going to be ready.
1) As I cannot share all of the data I put a small portion of it in the Jupyter Notebook in my github.
Step 1: Set up the sensors at the incoming power node and in the rooms. It is a serial based sensor so, tie it to a software serial and push the data to cloud using an ESP32.
Step 2: Download the feed from the cloud platform to use the data to train your AI
Step 3: Clean the data by filling NAN's and other improper data.
Step 4: Set all the elements in the data to float64 as the computations are mostly floating point and are very small so we need good precision.
Step 5 : Find the optimal values
Step 6 : Train your ANN
Step 7 : Deploy your application
Step 8 : After a month deploy a LSTM trained on the collected data for the entire duration and deploy your LSTM.
This is a brief description of the project.
srimanthtenneti
Anteneh Gashaw
Kemal Ficici
Tom Goff
Lobeware
I'm most interested to see what approaches you're considering for the final part of the response (trying to reduce usage). Peak usage reduction... something else?