Abstract

In addition to the load demand, the temperature difference between the hot and cold sides of the thermoelectric generator (TEG) module determines the output power for thermoelectric generator systems. Maximum power point tracking (MPPT) control is needed to track the optimal global power point as operating conditions change. The growing use of electricity and the decline in the use of fossil fuels have sparked interest in photovoltaic-TEG system utilization in the energy sector. Thermoelectric generation systems are meant to recover waste heat as a green energy supply. Concentrated solar can overcome the drawbacks of inefficient power generation. The feasibility of employing a machine learning and metaheuristic-based control strategy to yield maximum power from a hybrid photovoltaic and thermoelectric generator system under various operating situations is examined in this study. The output of both TEG and PV modules is affected by the environment; PV panels create heat as a result of shade and wind speed. Maximum energy harvesting of PV-TEG under non-uniform temperature settings is proposed in this paper using a feed-forward neural network (FFNN) trained by a squirrel search optimization (SQS). TEG systems have several local maxima due to this non-uniform state. MPPT algorithms based on gradients are unlikely to discover actual GMPP in the majority of cases. The unique SQSFFNN is evaluated under non-uniform temperature distribution and variable load and temperature circumstances as a possible answer to this non-linear issue. Certain advances are made in this study by addressing concerns of global maximum power point tracking with non-uniform temperature distribution, low efficiency, higher settling and tracking time, and oscillations. Particle swarm optimization, Cuckoo search optimization (CSA), CSA-FFNN, and grey wolf optimization algorithms are compared to the outcomes. Four experiments are carried out under various meteorological situations. Experiments and MATLAB/SIMULINK are used to validate and prove the results. The experimental results, comparisons with existing techniques, and statistical data show that the suggested SQDFFNN technique achieves a greater performance, distinguishing PV-TEG as a cleaner source of electrical power generation.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.