Power Consumption prediction model for efficient use of energy using Machine learning.

About Myself

Github - ujjwalll

facebook - Ujjwal Singh

Power Consumption, why it is a problem, and what does the Machine learning has to do with it.

Energy Crisis

Within two generations 90 percent of the world's oil reserves are expected to be depleted
Our demand for energy grows by about 3% per year.
Fossil fuels are declining at a very large scale than the evolvement of cheap electric and solar energy.

How ML helps?

- Can analyze any pattern, given proper algorithms and data.

- Can perform large scale calculations

- Easy to do data visualizations.

My approach to solve this problem

- Based on the research paper return by Mr. Phuspendra Singh | Professor at IIITD.

- Four steps to the brief whole procedure

Collect data
Analyze data
Create Models
Predict power consumptions

Explation of each step with some examples.

I am not going to discuss My model in depth because it is closed research.

Data Collection

- Specific Kind of electricity meter

- Code to connect the meter with database

- Storing Database into sheets or any other SQL, NoSQL databases.

How data looks like

This is how the data looks like which is recorded from the electricity meters

Data of IIITD buildings

Data Visualisation

This is how the data patterns are being recorded

in the dataset we have obtained from the various IIITD buildings

Daily Trends

Yearly Trends

Yearly Trends - (Seven months)

So far, we have discussed how we can visualize the data and collect the data for this process.

Now lets come to the prediction part.

LSTM Techinques

Long short-term memory (LSTM) is an artificial recurrent neural network (RNN) architecture used in the field of deep learning. Unlike standard feedforward neural networks, LSTM has feedback connections that make it a "general purpose computer" (that is, it can compute anything that a Turing machine can). It can not only process single data points (such as images), but also entire sequences of data (such as speech or video). For example, LSTM is applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

How It helps

Brief Overview

Predictions made by us for demo purposes

Power Consumption map

This a map we have created so that a person who doesn't have so much knowledge about the technical aspects can still look at the map and get broader idea of whole consumption