Smart Solar Tracker using AI

Project Title

Smart Solar Tracker using AI

Project Area of Specialization Artificial IntelligenceProject Summary

Renewable energy is playing an importance role as fuel price energy prices unstable. Solar energy is one of the furthermost popular renewable energy sources. 

Improving the converting of solar energy to electric supply is an attention to the future energy. At present, solar energy systems are used in many fields of life, especially for solar electric generation. In all solar applications, the output from the solar system depends on the amount of solar radiation received by the system.

Solar system are usually installed in domestic and commercial roof fittings without a sun tracking structures. But solar radiation received by the solar system varies with the angle of the Sun's rays made with the plan of the system. The solar tracker is a system that follows the sun and keeps the sun's rays almost normal to the plane of the solar system all time.

To enhance the outcome of Solar trackers Machine learning to be introduce in the tracking device. Machine learning is seen as a subset of artificial intelligence.

Machine learning is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead.

This Project is about to design and development of Artificial Intelligence Dual axis Solar tracking system which can predcit the path Sun by means of Mahine Learning. By using this method is able to control the panel for optimizing and maximizing the amount of solar energy that can be received from the sun by controlling the rotation of the panel

Project Objectives

Solar tracking is essential for many solar energy-based power systems, concentrators or flat-plate, to improve the overall system performance.

The main aim of the project is to demonstrate intelligence solar tracking system methods that involve both hardware and software development.

• Solar Tracker:

The solar tracker to be developed is a two-axis azimuth-elevation solar tracking system. The system senses the tracker position via the optical encoders that built within the system and applies inputs to the motors through the I/O devices. Machine Learning Phenomenon will be introduced for Prediction of sun path and improve the stability.

• Neural network:

Neural networks are a specific set of algorithms that have revolutionized machine learning. Neural Networks are themselves general function approximations, which is why they can be applied to almost any machine learning problem about learning a complex mapping from the input to the output space.

The solar tracker operation depends mainly on the climatic conditions (solar radiation and wind speed) and the type of the solar system installed with the tracker (flat plate, line focus or point focus collectors). Since the solar radiation and the wind speed have non-liner characteristics, then the solar tracker system can be considered as a non-liner system.

Since the neural network matches well with the non-liner systems, it can be accurately model the solar tracker. A series parallel feed-forward neural network was used to construct a suitable identification model to the two-axis solar tracker. Fig., shows the basic identification scheme using the artificial neural network.

Project Implementation Method

Software Implementation:

A neuron is a cell made up of a cellular body and a cone in which the cellular body ramifies to form the dendrites
dendrites transfer the information between the neuron and
the soma, body of the neuron. There is an intercellular
space between the axon of the related neuron works like a
valve controlling the rate of flow of information and is
called as synapse. It is necessary to parameterize all these
synapse to achieve a goal. The neural network works
according to equation

Figure shows the neural Network flow cart of the
system operation.

HARDWARE IMPLEMENTATION
After completion of the Software Implementation part, a Dual Axis Solar Tracker to be built.
The setup uses a Solar Panel, Raspberry Pi 4, Arduino, Photo-resistors, Servo Motors. This whole set-up is
incorporated in an aluminium frame.
With respect to the earth’s movement, the sun moves every second based on the revolution of the earth. Now as the sun
moves, the radiations changes and forms the base of our dual axis solar tracker. The LDRs attached receives the
radiation and sends relative signals to the controller. The signals are worked out according to the program fed andthe servo motors work completing the response and hence the cycle of the process of tracking the sun.
In the tracker, the LDRs placed on the solar panel, receives the radiation signals which are fed to the controller. It
analyses the signals by comparing each response and sends the control signals to the servo motors which based on the signal rotates accordingly.

Benefits of the Project

A solar panel tracker helps by allowing the solar panel to automatically shift with sunlight. This can mean the same array of solar panels collects many more photons than it would if it were fixed to the spot. Rather than a few hours of optimal light, solar panels that follow the sun have a chance to be optimally positioned from sunrise to sunset.

And it shows in their overall solar energy generation. Sun tracking solar panels collect between 25% to 40% more energy than fixed solar trackers. The same exact solar panel is more efficient when paired with a solar panel tracking system.

Solar tracking panels have a number of great benefits. They are popular because of some of the ways they improve on fixed solar panels. The main benefits include:

• Efficiency

• Variety of Models

• Space Savings

• Energy Cost Reduction

The above benefits are of conventional Solar Tracking system the proposed system will have following benefits:

• Solar Trackers available at commercial market totally relies on sensors which can easily be Deceive by individuals by means of setting light from another angle than Sun.
• An AI based solar tracker system to be work on Machine learning Phenomenon will not be deceive because it will predict the path.

Technical Details of Final Deliverable

Final Delliverables will consist of a combination of Hardware and software integrated system. A solar tracking system which can predict the path of Sun with the help of Machine Learning.

Hardware part would consist of solar panel mounted upon aluminium frame with LDR sensors which will collect the data for training.

Software part would develop a Machine learning technique using Libraries from TensorFlow to use that data for training and predict from the data.

Flow chart of working prototype is given:

A Computer-Aided Design (CAD) developed of final deliverables of prototype.

Final Deliverable of the Project HW/SW integrated systemCore Industry Energy Other Industries Others Core Technology Artificial Intelligence(AI)Other Technologies Internet of Things (IoT)Sustainable Development Goals Affordable and Clean Energy, Industry, Innovation and Infrastructure, Sustainable Cities and Communities, Responsible Consumption and ProductionRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	45420
Raspberry Pi 4	Equipment	1	13000	13000
Arduino	Equipment	1	600	600
Solar Panel	Equipment	1	5000	5000
Stepper Motor	Equipment	2	3000	6000
Node MCU	Equipment	1	700	700
LDR	Equipment	4	30	120
Foundry work	Equipment	1	10000	10000
Stationary, Printing	Miscellaneous	1	10000	10000