Scribd
Upload
22 views11 pages

Smart Energy Management System

Uploaded by

lathagirish151975
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
22 views11 pages

Smart Energy Management System

Uploaded by

lathagirish151975
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/ 11

SMART ENERGY MANAGEMENT

SYSTEM USING AI

VIJAYA VITTALA INSTITUTE OF TECHNOLOGY

ADITYA B [1VJ22AI003]
HEMANTH KUMAR CM [1VJ22AI010]
RAGHAV G [1VJ22AI027]
CHINTAM VIJAYA LAKSHMI [1VJ22AI006]
MOULYA MR [1VJ22AI020]
Problem Statement
• Design and develop a Smart Energy Management System using Artificial Intelligence and Machine
Learning (AIML) to optimize energy usage in residential and commercial spaces. The system will predict
energy consumption patterns, identify wastage, and provide actionable insights for efficient energy
utilization. It will also incorporate real-time monitoring, anomaly detection, and recommendations for
renewable energy integration to reduce costs and environmental impact.
• KEY OBJECTIVES
1. Real-Time Energy Monitoring
Using IoT sensor to monitor electricity usage of appliances in real time.
Display consumption data on a user-friendly dashboard.
2. Energy Usage Prediction
Implement AI algorithms to analyze historical energy data and predict future consumption patterns.
3. Load Optimization
Automate the operation of energy-intensive appliances during off-peak hours

Source : ResearchGate | Find and share research


4.Renewable Energy Integration
Incorporate solar panels or wind turbines and manage their energy contributions efficiently.

5. Fault Detection and Alerts


Use machine learning to detect anomalies in energy usage, indicating faulty appliances or overconsumption

6. User Recommendations
Provide actionable suggestions for reducing energy waste, such as turning off unused devices or switching
to energy-efficient alternatives.
Dataset Overview

This dataset describes the release of the detailed building operation data, including electricity
consumption and indoor environmental measurements, of the seven-story 11,700-m2 office building
located in Bangkok, Thailand.
The electricity consumption data (kW) are that of individual air conditioning units, lighting, and plug loads
in each of the 33 zones of the building. The indoor environmental sensor data comprise temperature
(°C), relative humidity (%), and ambient light (lux) measurements of the same zones.
This datasets can be used to support a wide range of applications, such as zone-level, floor-level, and
building-level load forecasting, indoor thermal model development, validation of building simulation
models, development of demand response algorithms by load type, anomaly detection methods, and
reinforcement learning algorithms for control of multiple AC units.

Source : ResearchGate | Find and share research, www.kaggle.com


Dataset overview

The entire datasets are divided into 14 comma-separated value (csv) files according to the floor and year of
the data recorded. Note that one CSV file is provided for each floor of the building. This makes the total of
seven CSV files for each year. Since each file does include data of each zone on a single floor, a user has
the flexibility to work with any individual zones, which can be extracted (based on the column names)
from the CSV files.

Each file combines the measurements available in each zone on the same floor of the building in a
particular year. These measurements are the electricity consumption (kW) of individual air conditioning (AC)
units, lighting loads and plug loads, as well as the environmental sensor data, including indoor temperature
(°C), relative humidity (%) and ambient light (lux). Note that the monitored loads do not include the two
elevators and emergency exit signs. These loads added up to about 1–2 percent of the total building loads.

Reference :CU-BEMS, smart building energy and IAQ data


Methodology
Data Collection: Gather data from sensors (e.g., electricity usage, temperature, weather, and occupancy
patterns).
Data Processing: Use AI algorithms to analyze real-time and historical energy consumption.
Energy Prediction: Employ machine learning models to forecast future energy needs.
Optimization: Apply AI to optimize energy distribution and minimize waste by controlling devices.
Automation: Use smart controllers for real-time adjustments (e.g., adjusting lighting, heating, or cooling).
User Interaction: Provide insights via dashboards or apps for monitoring and decision-making.
Energy Savings: Continuous learning and improvement to maximize efficiency and reduce costs.

Source : ResearchGate | Find and share research


Algorithms Used:

1.Machine Learning Algorithms:


Regression Model: Linear and Ridge regression.
Decision Trees: for energy consumption pattern analysis.
Support vector machines: to classify and optimize energy usage scenarios.

2. Deep Learning Algorithms:


Recurrent Neural Network: for time-series energy forecasting.
Convolution Neural Network: for processing energy usage patterns from visual or sequential data.
Autoencoders: for anomaly detection in energy system.

3. Optimization Algorithms:
Genetic Algorithms: to optimize energy distribution and minimize losses.
Particle swarm optimization: for scheduling energy resources.
Linear programming: for cost and resource optimization in energy.

4.Reinforcement Learning:
Adaptive control strategies for real-time energy management and dynamic pricing
Technologies and Tools
1.Programming Languages: Python (for AI models), JavaScript (for app development).

2.AI Libraries: TensorFlow, PyTorch, Scikit-learn.

3.IoT Platforms: MQTT, ThingsBoard, Blynk.

4.Database: Firebase, PostgreSQL, or InfluxDB for time-series data.

5.Hardware: Raspberry Pi, ESP8266, or ESP32 microcontrollers.


Conclusion
• Summary:
• Smart Energy Management Systems use AI-driven technologies to optimize energy consumption, reduce
waste, and promote sustainability.
• By leveraging machine learning, deep learning, and optimization algorithms, these systems forecast energy
demand, automate controls, and integrate renewable energy efficiently.
• AI enables real-time decision-making, user engagement through insights, and better energy resource
utilization in smart grids and buildings.
• Future Work:
• Enhanced Integration with IoT
• Advanced Predictive Models
• Renewable Energy Adaptation
• Sustainability Metrics
• Cost Reduction
Source : ResearchGate | Find and share research
References
• https://www.researchgate.net/publication/328742676_Smart_energy_management_systems_a_
literature_review

• https://www.researchgate.net/publication/357092992_Smart_Energy_Management_System_for
_Homes

• https://www.researchgate.net/publication/377832798_Smart_Energy_Management_System_Usi
ng_Machine_Learning

• Industrial Energy Efficiency - Siemens Global


Thank You

You might also like