Renewable Energy Source Technology with Geo-Spatial-Based Intelligent Vision Sensing and Monitoring System for Solar Aerators in Fish Ponds

This chapter’s significance is that it informs readers of how to increase the efficiency of solar panels equipped with indigenous solar tracking devices. If the solar panel efficiency is increased, it becomes easy to power the fish ponds using solar energy, a non-hazardous, renewable, inexhaustible energy source. The key objective is to design a hybrid maximum power tracking algorithm for solar photovoltaic systems with optimal power output to back up the electrical energy crisis for aeration systems in fish ponds. Conversely, the execution of this technique entails an exact control, which is essential to construct a sophisticated system of tracking. By merging the global positioning system (GPS), the artificial neural network (ANN) model with image processing (IP) techniques is utilized to estimate the astronomical characteristics of the sun. This GPS gives the geo-spatial information along with the images of the sun captured by an image sensor. The hybrid algorithm proposed here combines meta-heuristics and conventional ANN using backpropagation algorithm (BPA) with whale optimization perturb and observe (WOPO) and salp swarm perturb and observe (SSPO) algorithms for optimization of weights. The features collected from the sun’s image acquired by the camera utilizing IP approaches are employed as inputs for hybrid algorithms used in a decision-making AI process to distinguish between sunny and cloudy weather situations. The sun tracking system determines the approximate use of astronomical calculations based on the data acquired. Experimentation results are made available on the cloud service for coordination, allowing the proposed high-tech arrangement to be examined and validated.