Scribd
Upload
6 views15 pages

Energy Usage 1

The project aims to predict energy usage patterns in smart cities using AI to enhance efficiency and support sustainability. By analyzing historical and real-time data with models like regression and neural networks, the study addresses the challenges of unpredictable energy demands due to urbanization. Future work includes integrating IoT sensors and reinforcement learning for improved energy management.

Uploaded by

jorajeca772
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
6 views15 pages

Energy Usage 1

The project aims to predict energy usage patterns in smart cities using AI to enhance efficiency and support sustainability. By analyzing historical and real-time data with models like regression and neural networks, the study addresses the challenges of unpredictable energy demands due to urbanization. Future work includes integrating IoT sensors and reinforcement learning for improved energy management.

Uploaded by

jorajeca772
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

ENERGY USAGE PREDICTION

Submitted by
Karthikeyan R
Palanivel Rajan T
Logeshwara K
Joseph Raymond W
Content:
• Abstract
• Problem Statement
• Objective
• Data Collection and Preparation
• Proposed Solution (Methodology)
• Model Performance Evaluation
• Screenshots / Demonstration (video)
• Future Scope
• Conclusion
Abstract :
This project focuses on predicting energy usage
patterns in smart cities using artificial intelligence. By
analyzing historical and real- time data, we aim to enhance
energy efficiency, reduce waste, and support sustainable urban
development.
AI models such as regression and neural
networks are employed to make accurate predictions.
Problem Statement :
Rapid urbanization leads to unpredictable
energy demands in cities. Traditional systems are
inefficient at managing energy consumption dynamically.
There is a need for intelligent
prediction systems to optimize usage and avoid shortages
or overconsumption.
Objective:
1. Predict future energy consumption based on historical and
real-time data.
2. Improve decision-making for energy distribution.
3. Support sustainability goals in smart cities
using AI models.
Data Collection and Preparation:
1. Datasets from public energy consumption records
(e.g., UCI, Kaggle)
2. Preprocessing: handling missing values,normalization,
time-series formatting.
3. Feature selection: temperature, time of day,season,
appliance use, etc.
Dataset:

https://1drv.ms/x/c/3b2e632567e8617b/Ea5GxcQ2yeZHv0
0Kzo33PAcBJE4cxLunoZUG4GS7JggGyw
Proposed Solution (Methodology)
1. Models used: Linear Regression, Random Forest, and
LSTM (Deep Learning).
2. Training and testing with 80/20 split.
3. Evaluation using MSE, RMSE, and R² score.
Model Performance Evaluation:
1. Random Forest gave better accuracy (e.g., RMSE =
0.15).
2. LSTM performed well on time-series forecasting.
3. Visual comparisons included in charts.
Screenshoot :
Sample screenshots from the model implementation
and predictions.
Demonstration (video) :
Future Scope:
1. Integrating real-time IoT sensors for live prediction.
2. Applying reinforcement learning for adaptive energy
management.
3. Deploying the model in actual smart grids or smart
homes.
Conclusion:
This project demonstrates the potential of AI in
energy prediction for smart cities. Accurate forecasts can lead
to efficient energy management, reduced costs, and
sustainable urban development.
Future integration with real-world systems can
significantly improve outcomes.

You might also like