National Institute Of Technology Sikkim

राष्ट्रीय प्रौद्योगिकी संस्थान सिक्किम

EVALUATING THE OPTIMAL TILT ANGLE FOR IMPROVED

SOLAR PANEL OUTPUT USING SOFT COMPUTING
TECHNIQUES

Presented by : Under Supervision of:

Mithilesh Kumar Shahare (B200115EE) Dr. Amit Kumar Yadav
Rohit Singh (B200120EE) Assistant Professor at Department of Electrical
Bobby Kumar (B200124EE) and Electronics Engineering,
NIT Sikkim
Content
1. Introduction
2. Literature Review
3. Problem Formulation
4. Objective
5. Methodology
6. Work Done And Simulated Model
7. Future Work
8. Conclusions
9. References
Introduction
➤Solar energy is radiation from the Sun capable of producing heat, causing chemical reactions, or generating
electricity.

➤The tilt angle is the angle between the solar panel and the horizontal plane, and it affects how much solar
radiation the panel can capture throughout the year. Therefore, finding the optimal tilt angle for solar panels is an
important task for maximizing the solar energy output and reducing the cost of electricity.

➤The optimal tilt angle varies depending on factors such as location, season, and weather conditions.

➤In this project we are going to deploy Soft computing techniques, including machine learning and artificial
intelligence, to predict and optimize the tilt angle for solar panels.

➤The project aims to evaluate different soft computing techniques to identify the most effective method for
determining the optimal tilt angle for solar panels.

➤By optimizing the tilt angle, the project seeks to improve the energy production and efficiency of solar panels,
particularly in regions with varying weather conditions.
Literature Review
S.No Authors Year Key Findings Limitaions
1. M.A.A. 2022 The study investigates the performance of The study focuses on the effect of tilt angle
Mamun, PV modules under different tilt angles in on the performance and electrical parameters
M.M. Islam, both indoor and outdoor experimental of PV modules, not considering other factors
M. settings.The research aims to identify the such as temperature, humidity, or shading
Hasanuzzam optimal tilt angle for PV modules to that could influence PV performance.
an, Jeyraj maximize energy production and
Selvara efficiency.
2. Sthitapragy 2015 Soft computing models, such as ANFIS While soft computing models can provide
an Mohanty (Adaptive Neuro-Fuzzy Infer more flexibility and adaptability, they may
n Prashanta ence System), are used to estimate solar
Kumar also be more complex and computationally
radiation, providing a more flexible and
Patra, adaptive approach compared to traditional intensive compared to some traditional
Sudhansu methods.
methods
Sekhar

3. Makbul 2015 .The research used a case study approach The study focused on a specific geographical
A.M. Ramli and a specific set of input data, which may location (Saudi Arabia) and may not be
Ssennoga limit the broader applicability of the directly generalizable to other regions with
Twaha b , findings different climatic conditions
Yusuf A. Al-
Turki a
Problem Formulation

➤Traditional solar panel setups face challenges in maintaining optimal tilt angles, leading to
suboptimal energy capture. This project addresses the need for a dynamic solution by utilizing soft
computing techniques. The focus is on creating an intelligent system that continuously evaluates
environmental variables and solar positions to dynamically adjust the tilt angle. By doing so, the
project aims to unlock the full potential of solar panels and elevate their energy output in real-time.

➤The project will explore the integration of machine learning algorithms to analyze historical
performance data. This predictive element aims to enhance the system's foresight, allowing it to
anticipate optimal tilt angles based on patterns and trends. By combining adaptability with predictive
capabilities, our intelligent system aspires to revolutionize solar panel efficiency, paving the way for a
sustainable and maximized energy harvesting solution
Objective
➤Investigate the impact of the optimal tilt angle on the output power of solar panels and its potential for
emission reduction.
➤Determine the optimal tilt angle for solar panels to maximize energy production and efficiency using soft
computing techniques.

➤Evaluate the performance of different soft computing techniques in predicting the optimal tilt angle for
solar panels

➤Compare the results of soft computing techniques with traditional methods for determining the optimal tilt
angle of solar panels.

➤The most important to develop a predictive model for determining the optimal tilt angle of solar panels
based on location, season, and weather conditions using soft computing techniques.
Methodology
➤Literature Review:

● Review existing literature on soft computing techniques and their application in optimizing the tilt angle for
solar panels.
➤Data Collection:
● Gather historical solar panel output data, including power generation, tilt angles, and environmental
conditions such as sunlight intensity and temperature.
● Collect metadata on the solar panels, including their specifications and installation details.

➤Model Development:
● Develop a predictive model using soft computing techniques, such as machine learning, to determine the
optimal tilt angle for solar panels based on the collected data.
● Train the model using historical data and validate its performance using appropriate metrics
Contd.
➤Experimental Setup:

● Set up a test-bed consisting of solar panels with adjustable tilt angles to collect real-time data on power
generation.
● Store the power generation data in a database, along with information on the tilt angles and environmental
conditions.

➤Model Evaluation:

● Apply the developed model to the real-time data to predict the optimal tilt angle for the solar panels.
● Compare the predicted tilt angles with the actual tilt angles to evaluate the accuracy of the model.

➤Analysis and Results:

● Analyze the impact of the optimal tilt angle on the output power of the solar panels and its potential for energy
production improvement.
● Compare the results obtained from the soft computing model with traditional methods for determining the
optimal tilt angle.
Work Done And Simulated Model

● Till now in this project, we have plotted some curves with the help of Matlab code for
variation of Power output for PV module and irradiance with respect to varying Tilt angle for
which the codes are embedded here.
● We have used a Nodemcu model with tilt sensor and accelerometer to measure the
inclination angle of sun with respect to our PV model and tilt angle of PV module with the
respective former and later sensors as mentioned.
● We have simulated a PV module for stand alone system in a software called PVsyst.PVsyst
is a software package designed for the analysis and simulation of photovoltaic (PV) systems.
It is widely used in the solar energy industry to assess the performance of PV installations,
design solar systems, and conduct feasibility studies.
Contd.

Power output (w) and Irradiance (w/m^2)

Fig. (1)The above figure shows the plot for variation of output power of PV module
and irradiance vs Tilt angle.
Contd.
In this we have used Tilt
sensor for measuring the
inclination of the Sun with
respect to our Model and the
accelerometer for measuring
the tilt angle of our PV
module.The Nodemcu is
communicating with the
sensors and storing the data on
a cloud.

Fig. (2) shows circuit diagram for connection

of the mentioned sensors with Nodemcu.
Contd.

fig.(3)
Contd.

fig.(4)
Contd.

Fig.(3), and Fig.(4) shows graphs obtained from the simulation done PVsyst Software
which shows different graphs for Incident Irradiation Cumulative distribution,
Performance Ratio and SF, Daily Array Output Energy,Array Power Distribution and
Array Temperature vs Effective Irradiance.

The report Obtained from the PVsyst simulation Is embedded here.

Future Work
In the next phase, the project will advance by incorporating advanced machine learning
techniques, such as deep learning and reinforcement learning, to optimize the tilt angle of PV
modules for maximum power generation. The focus includes real-time adaptive learning,
improved interpretability, robust cross-validation, and integration with IoT and weather
forecasting. The aim is to develop a user-friendly interface for practical implementation and
contribute to the ongoing evolution of sustainable energy technologies.Ultimately, this evolving
project aspires not only to advance the state-of-the-art in soft computing applications for solar
energy but also to play a pivotal role in shaping the future landscape of sustainable energy
technologies. The journey continues towards a more efficient, adaptive, and user-centric solution
for optimizing the tilt angle of PV modules, contributing to the broader goals of a sustainable
energy transition
Conclusion
In summary, the project focused on leveraging soft computing techniques, particularly machine learning, to assess
and optimize the optimal tilt angle for solar panels. The results affirm the efficacy of the developed model in
dynamically adjusting tilt angles, leading to a substantial improvement in solar panel energy output when compared
to static configurations. The adaptability of the model to varying environmental conditions and its real-time
adjustment capabilities were key highlights. Validation using appropriate performance metrics underscored the
accuracy and reliability of the predictive model in determining optimal tilt angles. This project's success not only
addresses the longstanding challenge of suboptimal energy capture but also holds promise for practical applications.
Designers and operators of solar energy systems can benefit from the model's insights, contributing to informed
decision-making and maximizing the efficiency of solar power utilization. Looking ahead, the project sets the stage
for future advancements, including the integration of more advanced machine learning algorithms and real-time
data sources. The overall impact positions this research as a valuable contribution to the ongoing efforts in
promoting sustainable and efficient solar energy solutions.
Refrences
1.Prediction and application of solar radiation with soft computing over traditional and conventional
approach – A comprehensive review by Sthitapragyan Mohanty n , Prashanta Kumar Patra, Sudhansu Sekhar
Sahoo.

2.1.Effect of tilt angle on the performance and electrical parameters of a PV module: Comparative indoor
and outdoor experimental investigation by M.A.A. Mamun, M.M. Islam, M. Hasanuzzaman, Jeyraj Selvaraj.

3.Investigating the performance of support vector machine and artificial neural networks in predicting solar
radiation on a tilted surface: Saudi Arabia case study by Makbul A.M. Ramli a,c, ⇑ , Ssennoga Twaha b ,
Yusuf A. Al-Turki.
Thank you