AI MODEL FOR ELECTRICITY DEMAND
Minor Project Synopsis
Submitted by
Arooj Lateef (21048135132)
Syed Fiqa (21048135111)
Mehak Mushtaq (21048135133)
In partial fulfilment for the award of the degree
of
BACHELOR OF ENGINEERING
IN
COMPUTER ENGINEERING
at
SSM COLLEGE OF ENGINEERING
PARIHASPORA PATTAN, BARAMULLA,
AFFILIATED TO UNIVERSITY OF KASHMIR HAZRATBAL, SRINAGAR
April 2025
CERTIFICATE OF APPROVAL
We would like to request your approval for project entitled “AI MODEL FOR
ELECRICITY DEMAND”. The project’s tentative completion date is <---->
Furthermore, we will adopt time and cost-efficient methods in order to fulfil the
desired goal within stipulated time.
Arooj Lateef (21048135132)
Syed Fiqa (21048135111)
Mehak Mushtaq (21048135133)
The synopsis submitted by the above mentioned students is accepted on the condition that
the students will consider the suggestion(s) (if any) in their project failing which the project
will not be accepted.
Suggestion(s):
PROJECT CO-ORDINATOR HOD
1. Er.Shaif Makdoomi Er.Yasmeen
2. Er. Irfan
i
ABSTRACT
In the face of increasing energy consumption and the need for efficient resource management,
accurate electricity demand forecasting has become crucial. This project proposes an AI -based
model to predict electricity demand, leveraging advanced machine learning techniques to
enhance prediction accuracy. The proposed model utilizes historical electricity consumption
data, weather conditions, and socio-economic factors to generate precise demand forecasts.
This AI-enhanced forecasting model aims to support utility companies in optimizing their
operations, reducing costs, and ensuring a reliable power supply. Additionally, it contributes
to sustainable energy management by enabling better integration of renewable energy sources
and improving grid stability. The basic idea of this project is to determine the load of a user
and alert the user in order to reduce consumption of electricity through a web interface
accordingly. An efficient electricity prediction model is needed to minimize the electricity bills.
Here we are using machine learning through which we will interact with the user. Electricity
demand forecasting is important for economically efficient operation and effective control of
power systems and enables to plan the load of generating unit. Under prediction of the demands
leads to an insufficient reserve capacity preparation and can threaten the system stability, on
the other hand, over-prediction leads to an unnecessarily large reserve that leads to a high cost
preparations. The results of the project is developed system by a way of monitoring, forecasting
and to predicting the electrical demand through the use of machine learning. Proposed System
The proposed system for the Electricity Demand Prediction project leverages advanced
machine learning algorithms and historical consumption data to forecast future elect ricity
demands accurately. By analyzing patterns and external factors such as weather, holidays, and
economic indicators, it aims to provide utilities with valuable insights to optimize power
generation and distribution, ensuring a more efficient and reliable energy supply. This
predictive system will help reduce energy wastage, lower costs, and contribute to a more
sustainable energy infrastructure. Software Modules In an electricity demand prediction
project, various software modules play a crucial role in data processing, modelling,
and forecasting. In conclusion, the adoption of smart systems by electricity power companies
is an essential step toward creating a more efficient, resilient, and sustainable energy future.
By leveraging cutting-edge technologies, smart systems can transform how electricity is
produced, distributed, and consumed, benefiting both providers and end -users while
contributing to global sustainability goals.
ii
Table of Contents
S.No Contents Page No.
CERTIFICATE OF
1 APPROVAL i
2 ABSTRACT ii
3 INTRODUCTION 1
iii
4
iv
FORGET ME NOT YEAR: 2025
CHAPTER 1
INTRODUCTION
Understanding AI Model For Electricity Demand
An AI model for electricity demand forecasting is designed to predict future electricity consumption
by analyzing historical usage data and other influencing factors like weather conditions, economic
activities, and time of day. The process begins with data collection and preprocessing to ensure the
data is clean and relevant. Various machine learning algorithms, such as ARIMA, Random Forests, and
LSTM networks, are employed to identify patterns and trends within this data. The model is trained
to understand these patterns and validated to ensure its accuracy. Once trained, the model can make
accurate forecasts about future electricity demand, helping utility companies optimize power
generation and distribution. This leads to more efficient energy use, cost savings, and a sustainable
energy infrastructure.
Challenges
Developing an AI model for electricity demand forecasting presents several challenges. Ensuring data
quality and availability is paramount, as incomplete or incorrect data can skew predictions. Selecting
the most relevant features among numerous influencing factors is complex and critical for model
accuracy. Advanced models like LSTM networks require significant computational resources and can
be challenging to train effectively. Capturing dynamic and non-linear patterns in electricity demand,
influenced by factors such as sudden weather changes or economic shifts, adds another layer of
difficulty. Additionally, there's a risk of overfitting, where the model performs well on training data
but poorly on new, unseen data. Integrating the AI model into existing utility management systems
for real-time operation is also complex, requiring seamless synchronization. Furthermore, adhering to
regulatory standards and addressing privacy concerns, especially with sensitive data, is essential.
Addressing these challenges requires robust data handling practices, continuous model evaluation,
and careful planning to ensure the model's reliability and utility in practical applications.
Role of Ai Model for Electricity Demand
The role of an AI model in electricity demand forecasting is pivotal for modern energy
management. It provides accurate predictions of future electricity demand by analyzing
historical consumption data and various external factors. This capability allows utility
companies to optimize power generation and distribution, ensuring a stable and efficient
energy supply. Accurate forecasts help in reducing energy wastage, lowering operational
costs, and integrating renewable energy sources effectively. Moreover, it enables proactive
DEPARTMENT OF CSE 1
FORGET ME NOT YEAR: 2025
maintenance and management of the grid, enhancing reliability and sustainability. In essence,
the AI model acts as a critical tool for achieving a more resilient and responsive energy
infrastructure, benefiting both the providers and the consumers.
Introducing the Ai Model For Electricity Demand
The primary objective of this project is to design and develop a smart system for electricity
power companies that enhances the efficiency, reliability, and sustainability of electricity
distribution networks. The system will focus on optimizing grid management, reducing energy
loss, and integrating renewable energy sources through the use of advanced algorithms. This
project aims to incorporate real-time monitoring, fault detection, predictive maintenance, and
data-driven demand management strategies. The project also seeks to improve operational
decision-making processes within power companies by utilizing machine learning algorithms
such as Linear Regression, CNN (Convolutional Neural Networks). By doing so, it will
improve grid resilience, reduce operational costs, and provide consumers with more reliable
and transparent energy services. Additionally, the project will aim to contribute to reducing
carbon emissions and ensuring a smooth transition to sustainable energy solutions.
Core Features of Ai Model For Electricity Demand
The core features of an AI model for electricity demand forecasting include:
• Data Collection and Integration:
• Historical Data: Aggregating past electricity consumption records.
• External Data: Incorporating weather data, economic indicators, social events, and
more to enhance accuracy.
• Feature Selection and Engineering:
• Relevant Variables: Identifying and utilizing the most impactful factors on electricity
demand.
• Data Transformation: Normalizing and structuring data to be suitable for model
inputs.
• Model Training and Validation:
• Training: Teaching the model using historical data to learn patterns and relationships.
• Validation: Testing the model on separate datasets to ensure it generalizes well to
unseen data.
• Forecasting Capabilities:
• Real-Time Predictions: Offering immediate and dynamic forecasts.
DEPARTMENT OF CSE 2
FORGET ME NOT YEAR: 2025
• Long-Term Forecasting: Providing accurate long-term predictions to aid in strategic
planning.
Significance of the Ai Model For Electricity Demand
The AI model for electricity demand forecasting is highly significant in modern energy management.
By leveraging advanced algorithms and vast datasets, it provides accurate and reliable predictions of
future electricity consumption. This accuracy allows utility companies to optimize power generation
and distribution, minimizing energy wastage and operational costs. Additionally, the model supports
the integration of renewable energy sources, promoting a sustainable and environmentally friendly
energy infrastructure. It also enhances grid stability by maintaining a balance between supply and
demand, thereby reducing the risk of blackouts. Furthermore, the predictive capabilities of the model
enable proactive maintenance, helping to identify and address potential issues before they become
critical. Overall, this AI model is a vital tool for ensuring a reliable, efficient, and sustainable electricity
supply, benefiting both providers and consumers.
The Need for Ai Model For Electricity Model
The need for an AI model in electricity demand forecasting is driven by several crucial
factors. Firstly, accurate demand predictions are essential for optimizing power generation
and distribution, which reduces energy wastage and operational costs. Traditional forecasting
methods often fall short in capturing the complex and dynamic nature of electricity usage
influenced by various factors like weather, economic activities, and social events. An AI
model can analyze these multifaceted data points more effectively.
Additionally, the integration of renewable energy sources into the power grid requires precise
demand forecasting to ensure a stable supply and prevent disruptions. With the increasing
importance of sustainable energy solutions, an AI model helps balance the intermittency of
renewables, thereby contributing to a greener energy infrastructure.
Furthermore, such a model enhances grid reliability by predicting potential surges or drops in
demand, allowing for proactive maintenance and minimizing the risk of outages. It also
supports better policy-making and long-term planning, helping governments and regulatory
bodies to develop informed energy strategies. Overall, the AI model is indispensable for
achieving a more efficient, reliable, and sustainable electricity supply system.
SCOPE OF THE PROJECT
DEPARTMENT OF CSE 3
FORGET ME NOT YEAR: 2025
The scope of this project is to design a comprehensive smart system for electricity power
companies that incorporates advanced machine learning algorithms to enhance grid
management, optimize energy distribution, and ensure the integration of renewable energy
sources. The system will include modules for real-time monitoring, predictive failure detection,
fault localization, and load management. It will integrate IoT devices such as smart meters and
sensors to collect and analyze energy consumption and grid performance data. Furthermore,
the system will use AI algorithms such as Linear Regression and CNN to optimize operational
decision-making, improve energy forecasting, and reduce downtime. The project will focus on
providing an adaptive framework that allows electricity providers to manage their
infrastructure effectively while offering consumers more control and insight into their energy
use. It will also address the need for reducing carbon footprints by optimizing energy
consumption patterns. This project will be limited to the development and testing of the smart
system prototype and will not involve large-scale deployment or real-time operation across
entire utility networks.
DEPARTMENT OF CSE 4
FORGET ME NOT YEAR: 2025
CHAPTER 2
LITERATURE SURVEY
1. The paper introduces an AI-based model for peak power demand forecasting,
integrating economic and climate factors to improve accuracy. It explores key drivers
of energy demand and demonstrates the benefits of advanced machine learning
techniques for forecasting. Identified research gaps include the need for more granular
datasets, better integration of socio-economic variables, and consideration of emerging
climate trends. Future research could also focus on scalability and adapting these
models for regions with limited data availability.
2. focuses on AI-driven load forecasting models designed for India's load dispatch centers,
addressing the challenges of accurate electricity demand prediction in a dynamic energy
market. Research gaps might include integrating renewable energy sources, regional
data variability, and real-time adaptability.
3. The GitHub project "Machine Learning to Predict Energy Consumption" focuses on
forecasting electricity consumption using Finland's six-year hourly energy data. This
research employs a Long Short-Term Memory (LSTM) model to tackle the univariate
and seasonal nature of the dataset. The model is evaluated using Root Mean Squared
Error (RMSE) and is found to effectively predict energy usage. The insights gained
from the model can aid in planning renewable energy deployment, managing high/low
load days, and reducing energy wastage from standby generation
Research Gaps Identified:
Feature Expansion: The current model relies on a univariate time series, which may
limit the predictive power. Incorporating additional features such as weather conditions
or economic factors could improve accuracy.
Comparative Analysis: The study could explore and compare other machine learning
models, such as ARIMA, Random Forest, or Gradient Boosting, alongside LSTM to
identify the most suitable model.
DEPARTMENT OF CSE 5
FORGET ME NOT YEAR: 2025
Scalability and Generalization: Testing the model on diverse datasets from other
regions or countries would help understand its adaptability and robustness in varying
contexts.
Scalability and Generalization: Testing the model on diverse datasets from other
regions or countries would help understand its adaptability and robustness in varying
contexts.
Real-Time Deployment: Addressing challenges in deploying the model for real-time
forecasting in dynamic systems remains an unexplored area
4. The article from Neural Designer explains the application of machine learning,
particularly neural networks, in electricity demand forecasting. Using historical data
(e.g., temperatures, calendar events, and demand patterns), the model predicts future
electricity demand with high accuracy, benefiting energy companies by improving
decision-making. The key focus is on predicting daily demand based on recent trends.
Research Gaps:
Integration of broader socio-economic variables.
Testing scalability for different regions.
Improving real-time adaptability of the models.
5. The paper on Electricity Consumption Prediction Using Artificial Intelligence explores
the application of various AI techniques to forecast energy demand, emphasizing their
importance in optimizing energy systems and integrating renewable energy sources.
Summary:
AI Techniques Explored: Artificial Neural Networks (ANNs): Highlighted for their
ability to model complex nonlinear relationships in data.
Support Vector Machines (SVMs): Used for their robustness in small datasets.
Hybrid Models: Integration of traditional statistical methods with AI, such as ARIMA-
ANN hybrids, for enhanced accuracy.
DEPARTMENT OF CSE 6
FORGET ME NOT YEAR: 2025
Research Gaps:
Lack of Standardized Datasets: bThe absence of widely accepted datasets for energy
prediction hampers direct comparison across studies.
Model Interpretability: While AI models like deep learning provide high accuracy, they
often lack transparency, making it difficult to explain predictions.
Integration of External Factors: Insufficient consideration of external factors such as
socio-economic variables or policy impacts on energy consumption.
Scalability Challenges: Models need to be adapted for broader deployment across
diverse geographical and infrastructural contexts.
Energy Data Accessibility: Limited availability of real-time and high-resolution data
restricts the development and testing of robust models.
6. The UT Dallas researchers, in collaboration with Vistra Corp., applied AI and machine
learning to enhance energy supply and demand forecasting. This project focused on
optimizing electricity pricing for the Moss Landing Energy Storage Facility. AI
methods were used to predict near-real-time energy prices, assisting in strategic energy
storage and sale decisions. Research gaps include challenges in modeling fluctuating
renewable energy outputs and integrating diverse data sources to improve accuracy
further. The initiative highlights academia-industry collaboration for addressing
practical energy market issues.
7. The paper investigates using deep neural networks to forecast short-term electricity
demand in Thailand. It compares two scenarios: one excluding weekends and holidays,
and one including all days. The study finds that: Feedforward Neural Networks (FNN)
perform better for weekdays.Gated Recurrent Units (GRU) are more accurate when
including weekends and holidays.
Research Gaps
Renewable Energy: The study doesn’t include renewable energy sources.
Long-Term Forecasting: Focuses only on short-term predictions.
Geographical Diversity: Limited to Thai data.
Advanced Models: More advanced architectures could be explored.
8. The forecast of electricity demand has been a recurrent research topic for decades, due
to its economical and strategic relevance. Several Machine Learning (ML) techniques
DEPARTMENT OF CSE 7
FORGET ME NOT YEAR: 2025
have evolved in parallel with the complexity of the electric grid. This paper reviews a
wide selection of approaches that have used Artificial Neural Networks (ANN) to
forecast electricity demand, aiming to help newcomers and experienced researchers to
appraise the common practices and to detect areas where there is room for improvement
in the face of the current widespread deployment of smart meters and sensors, which
yields an unprecedented amount of data to work with. The review looks at the specific
problems tackled by each one of the selected papers, the results attained by their
algorithms, and the strategies followed to validate and compare the results. This way,
it is possible to highlight some peculiarities and algorithm configurations that seem to
consistently outperform others in specific settings
9. Objective: To forecast long-term electricity demand in India.
Methodology: Utilizes statistical methods and econometric models to predict future
electricity consumption.
Research Gaps
Integration of Renewable Energy: Limited focus on the impact of integrating renewable
energy sources on demand forecasting.
Technological Advancements: Need for incorporating the effects of emerging
technologies like electric vehicles and smart grids.
Regional Disparities: More detailed analysis required for regional variations in demand.
Climate Change Impact: Insufficient consideration of how climate change might affect
long-term electricity demand.
10. Objective: To review different methods of electricity demand forecasting and their
applications.
Key Points:
Techniques Reviewed: The paper discusses several forecasting methods, including
statistical models, machine learning techniques, and hybrid approaches.
Applications: Emphasizes the importance of accurate demand forecasting for planning
new power plants, managing energy resources, expanding electricity supply networks,
and policy making.
Advantages and Disadvantages: Each method’s strengths and weaknesses are analyzed
based on data availability and the specific context of the country.
Research Gaps
Integration of Emerging Technologies: Limited discussion on the impact of emerging
technologies like smart grids and electric vehicles on demand forecasting.
Renewable Energy Sources: Need for more research on incorporating renewable energy
sources into forecasting models.
Regional Specificity: Lack of detailed analysis on how regional differences affect
electricity demand and forecasting accuracy.
Advanced Machine Learning Models: More exploration needed on advanced machine
learning models and their potential to improve forecasting accuracy.
DEPARTMENT OF CSE 8
FORGET ME NOT YEAR: 2025
CHAPTER 3
AIMS AND OBJECTIVE:
1. AIM
The aim of this project is to develop an AI-based electricity demand forecasting model that can provide
accurate and reliable predictions of future electricity consumption. By analyzing historical data and
various influencing factors such as weather, economic activities, and social events, the model seeks to
optimize power generation and distribution. This will help utility companies reduce energy wastage,
lower operational costs, and integrate renewable energy sources more effectively. Additionally, the
project aims to enhance grid stability and reliability, support proactive maintenance, and contribute
to the creation of a more efficient, sustainable, and cost-effective electricity supply infrastructure. The
ultimate goal is to benefit both the providers and consumers by ensuring a stable and environmentally
friendly energy system.
Purpose
• By accurately predicting future electricity demand, utility companies can better plan their
power generation and distribution, reducing energy wastage and operational costs.
• Accurate demand forecasts help in seamlessly integrating renewable energy sources into the
power grid, promoting sustainability and reducing reliance on fossil fuels.
• By maintaining a balance between electricity supply and demand, the model helps prevent
blackouts and ensures a stable energy supply.
• Improved efficiency and cost-effectiveness in energy management lead to more reliable and
potentially lower-cost electricity for consumers.
Characteristics
The characteristics of this AI-based electricity demand forecasting project include:
1. Data-Driven Approach: The project relies on extensive historical data and relevant
external factors to make accurate predictions. This includes weather data, economic
indicators, and social events.
DEPARTMENT OF CSE 9
FORGET ME NOT YEAR: 2025
2. Advanced Machine Learning Algorithms: Utilizing state-of-the-art algorithms .
3. High Accuracy and Reliability: The model is designed to provide highly accurate
forecasts, reducing the margin of error in predicting future electricity demand.
4. Real-Time Forecasting: The ability to generate real-time predictions allows for
dynamic adjustments and more responsive energy management.
5. Scalability: The model is scalable, capable of handling large datasets and adaptable to
increasing amounts of data over time.
6. Integration with Existing Systems: Seamlessly incorporating the AI model into
existing utility management systems for efficient operation.
7. User-Friendly Interface: Featuring interactive dashboards and visualization tools to
present forecast results in an accessible and actionable format for decision-makers.
OBJECTIVES
• Accurate Demand Prediction: Develop an AI model to forecast future electricity
consumption with high precision.
• Optimization of Resources: Enhance the efficiency of power generation and
distribution to reduce energy wastage and operational costs.
• Integration of Renewable Energy: Facilitate the seamless integration of renewable
energy sources into the power grid.
• Grid Stability: Maintain a stable electricity supply by balancing demand and
preventing blackouts.
• Proactive Maintenance: Enable early detection of potential grid issues for timely and
effective maintenance.
• Real-Time Forecasting: Provide immediate and dynamic predictions to respond to
changing demand patterns.
• Scalability: Ensure the model can handle large datasets and adapt to increasing data
over time.
• User-Friendly Visualization: Present forecast results in an accessible and actionable
format for decision-makers.
• Sustainability: Contribute to a more sustainable energy infrastructure by optimizing
the use of renewable resources.
• Policy Support: Provide insights to support better energy policy-making and long-term
infrastructure planning.
DEPARTMENT OF CSE 10
FORGET ME NOT YEAR: 2025
CHAPTER 4
METHODOLOGY:
The methodology for developing an AI-based electricity demand forecasting project involves
several well-defined steps:
Step 1: Data Collection
• Historical Data: Gather historical electricity consumption data from utility
companies.
• External Factors: Collect data on weather conditions, economic indicators, social
events, and other relevant factors that may impact electricity demand.
Step 2: Data Preprocessing
• Cleaning: Remove any noise, errors, or inconsistencies in the data.
• Normalization: Standardize the data to ensure uniformity.
• Feature Engineering: Identify and select the most significant variables that influence
electricity demand.
Step 3: Model Selection
• Algorithm Choice: Choose appropriate machine learning algorithms for the
forecasting task, such as ARIMA.
• Hybrid Models: Consider using a combination of different algorithms to improve
accuracy and capture various aspects of the data.
Step 4: Model Training
• Training the Model: Use historical data to train the selected algorithms, teaching the
model to recognize patterns and relationships.
• Cross-Validation: Employ cross-validation techniques to ensure the model
generalizes well to new, unseen data.
Step 5: Model Evaluation
• Testing: Evaluate the model's performance using a separate test dataset.
• Metrics: Use metrics like Mean Absolute Error (MAE) and Root Mean Squared Error
(RMSE) to assess the model's accuracy.
Step 6: Forecasting
DEPARTMENT OF CSE 11
FORGET ME NOT YEAR: 2025
• Real-Time Predictions: Deploy the model to provide real-time electricity demand
forecasts.
• Long-Term Forecasting: Generate long-term forecasts to aid in strategic planning
and resource management.
Step 7: Integration and Deployment
• System Integration: Integrate the AI model into existing utility management systems
for seamless operation.
• Scalability: Ensure the system can handle large volumes of data and adapt to growing
demands.
Step 8: Monitoring and Maintenance
• Continuous Monitoring: Regularly monitor the model's performance to ensure
accuracy and reliability.
• Model Updates: Periodically retrain the model with new data to keep it up-to-date.
• Feedback Loop: Implement a feedback mechanism to refine and improve the model
continuously.
Step 9: Visualization and Reporting
• Interactive Dashboards: Create user-friendly dashboards to visualize forecast results
and trends.
• Reporting: Generate reports for stakeholders to aid in decision-making and strategic
planning
Flowchart Representation:
DEPARTMENT OF CSE 12
FORGET ME NOT YEAR: 2025
CHAPTER 6
DATASET
DEPARTMENT OF CSE 13
FORGET ME NOT YEAR: 2025
CHAPTER 7
TOOLS AND TECHNOLOGY:
Developing an AI model for electricity demand forecasting involves a range of tools
and technologies:
• Data Collection and Processing:
• Databases: SQL for storing and retrieving large datasets..
• APIs: Weather APIs (e.g., OpenWeatherMap), economic data APIs for collecting
external data.
• Programming Languages:
• Python: Widely used for data analysis, machine learning, and building AI models.
• R: Also popular for statistical analysis and modeling.
DEPARTMENT OF CSE 14
FORGET ME NOT YEAR: 2025
• Machine Learning Frameworks and Libraries:
• TensorFlow: An open-source platform for machine learning, particularly useful for
building deep learning models.
• Keras: A high-level neural networks API, running on top of TensorFlow.
• Scikit-learn: A machine learning library for Python, used for implementing
traditional algorithms like Random Forests and ARIMA.
• PyTorch: Another popular deep learning framework, especially for research and
development.
• Time Series Analysis:
• ARIMA Models: Used for time series forecasting.
• LSTM (Long Short-Term Memory) Networks: A type of recurrent neural network
(RNN) that excels at learning from sequences of data.
• Data Visualization:
• Matplotlib: A plotting library for Python.
• Seaborn: A statistical data visualization library based on Matplotlib.
• Plotly: An interactive graphing library.
• Development Environments:
• Jupyter Notebooks: An open-source web application for creating and sharing
documents containing live code, equations, visualizations, and narrative text.
• Integrated Development Environments (IDEs): Such as PyCharm, VSCode for
coding and development.
DEPARTMENT OF CSE 15
FORGET ME NOT YEAR: 2025
REFRENCES (IEEE format):
[1] https://www.ijmcer.com/wp-content/uploads/2022/04/IJMCER_BB0420279301.pdf
[2]
https://cea.nic.in/old/reports/others/planning/pslf/Long_Term_Electricity_Demand_Forecasti
ng_Report.pdf
[3] https://pmc.ncbi.nlm.nih.gov/articles/PMC8271411/
[4] https://www.mdpi.com/2571-5577/6/6/100
[5] https://cs.utdallas.edu/24575/ut-dallas-cs-researchers-apply-power-of-ai-to-forecast-
energy-supply-demand/
[6]
https://www.researchgate.net/publication/370506740_Electricity_consumption_prediction_us
ing_artificial_intelligence
[7] https://www.neuraldesigner.com/blog/electricity_demand_forecasting/
[8] https://github.com/MohamadNach/Machine-Learning-to-Predict-Energy-Consumption
[9] https://indiaai.gov.in/article/artificial-intelligence-based-load-forecasting-models-for-
load-dispatch-centers-in-india
[10] https://www.frontiersin.org/journals/energyresearch/articles/
DEPARTMENT OF CSE 16
FORGET ME NOT YEAR: 2025
10.3389/fenrg.2024.1328891/full
EVALUATION REPORT
Arooj Lateef (21048135132)
Syed Fiqa (21048135111)
Mehak Mushtaq (21048135133)
To be filled by Project Guide only:
1st Assessment:
___________________________________________________________________________
___________________________________________________________________________
DEPARTMENT OF CSE 17
FORGET ME NOT YEAR: 2025
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
2ndAssessment:
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
__________________________________________________________________________
3rdAssessment:
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
Final Assessment:
DEPARTMENT OF CSE 18
FORGET ME NOT YEAR: 2025
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
___________________________________________________________________________
PROJECT CO-ORDINATOR HOD
1. Er.Shaif Makdoomi Er.Yasmeen
2. Er. Irfan
DEPARTMENT OF CSE 19
