Intelligent control for processing solar photovoltaic energy

Simple item page
dc.contributor.advisorBah, Bubacarren_ZA
dc.contributor.advisorVargas, Alessandroen_ZA
dc.contributor.authorWacira, Joseph Muthuien_ZA
dc.contributor.otherStellenbosch University. Faculty of Science. Dept. of Applied Mathematics.en_ZA
dc.date.accessioned2023-11-29T05:04:56Zen_ZA
dc.date.accessioned2024-01-08T14:43:29Zen_ZA
dc.date.available2023-11-29T05:04:56Zen_ZA
dc.date.available2024-01-08T14:43:29Zen_ZA
dc.date.issued2023-12en_ZA
dc.descriptionThesis (MSc)--Stellenbosch University, 2023.en_ZA
dc.description.abstractENGLISH ABSTRACT: Maximum Power Point Tracking (MPPT) techniques play a pivotal role in optimizing the performance of photovoltaic systems within renewable energy. Traditional MPPT methods, often reliant on Proportional Integral and Derivative (PID) controllers, face challenges when applied to nonlinear systems with dynamic operating conditions, typical in photovoltaic systems where temperature and irradiance continually fluctuate. The inherent static nature of the PID parameters leads to power losses, thereby reducing their efficiency. Additionally, they rely on trial-and-error approaches to determine the actual Maximum Power Point (MPP). This study introduces two novel MPPT approaches: the Gradient Descent Approach and the Deep Q-Network (DQN) approach. These methods share a common feature: they require knowledge of the maximum power point (MPP). An ANN was employed to predict the MPP under current operating conditions. Once the MPP is known, the Gradient Descent Approach aims to minimize the mean squared error by adjusting the duty cycle, whereas the DQN Approach employs a state-action-reward system that penalizes deviations from the MPP and large actions. To evaluate the effectiveness o f t hese a pproaches, s imulations were conducted under uniform operating conditions using MATLAB/Simulink, with data sourced from the NSRBD website for Brazil. The results were compared with those of the conventional Perturb and Observe algorithm with a PI controller tuned using the Ziegler-Nichols method under Standard Test Conditions. Simulations revealed that the proposed methodologies exhibited significantly higher efficiency than the benchmark algorithm. Furthermore, they demonstrate fast response times and minimal steady-state errors. Although these findings underscore the promise of the proposed approaches, further validation in real-world environments is necessary to confirm their superiority and practical applicability.en_ZA
dc.description.abstractAFRIKAANS OPSOMMING: Maksimum Power Point Tracking (MPPT) tegnieke speel ’n deurslaggewende rol in die optimalisering van die werkverrigting van fotovoltaïese stelsels binne hernubare energie. Tradisionele MPPT-metodes, wat dikwels afhanklik is van proporsionele integrale en afgeleide (PID) beheerders, staar uitdagings in die gesig wanneer dit toegepas word op nie-lineêre stelsels met dinamiese bedryfstoestande, tipies in fotovoltaïese stelsels waar temperatuur en bestraling voortdurend fluktueer. D ie i nherente s tatiese a ard v an d ie PID-parameters lei tot kragverliese, wat hul doeltreffendheid v erminder. Daarbenewens maak hulle staat op proef-en-fout-benaderings om die werklike maksimum kragpunt (MPP) te bepaal. Hierdie studie stel twee nuwe MPPT-benaderings bekend: die Gradient Descent Benadering en die Deep Q-Network (DQN) benadering. Hierdie metodes deel ’n gemeenskaplike kenmerk: hulle vereis kennis van die maksimum kragpunt (MPP). ’n ANN is gebruik om die MPP onder huidige bedryfstoestande te voorspel. Sodra die MPP bekend is, poog die Gradient Descent Benadering om die gemiddelde kwadraatfout te minimaliseer deur die dienssiklus aan te pas, terwyl die DQN Benadering ’n staat-aksie-beloningstelsel gebruik wat afwykings van die MPP en groot aksies penaliseer. Om die doeltreffendheid van hierdie b enaderings t e e valueer, i s simulasies uitgevoer met behulp van MATLAB/Simulink, met data afkomstig van die NSRBD-webwerf vir Brasilië. Die resultate is vergelyk met dié van die konvensionele Perturb en Observe algoritme met ’n PI kontroleerder wat ingestel is met behulp van die Ziegler-Nichols metode onder Standaard Toets Voorwaardes. Simulasies het aan die lig gebring dat die voorgestelde metodologieë aansienlik hoër doeltreffendheid as die maatstafalgoritme getoon het. Verder toon hulle vinnige reaksietye en minimale bestendige toestandfoute. Alhoewel hierdie bevindinge die belofte van die voorgestelde benaderings beklemtoon, is verdere validering in werklike omgewings nodig om hul meerderwaardigheid en praktiese toepaslikheid te bevestig.af_ZA
dc.description.versionMastersen_ZA
dc.format.extentxii, 94 pages : illustrationsen_ZA
dc.identifier.urihttps://scholar.sun.ac.za/handle/10019.1/128889en_ZA
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch University,en_ZA
dc.subject.lcshPhotovoltaic power systemsen_ZA
dc.subject.lcshMaximum Power Point Trackingen_ZA
dc.subject.lcshPID controllersen_ZA
dc.subject.lcshNonlinear systemsen_ZA
dc.subject.lcshAlgorithmsen_ZA
dc.subject.lcshRenewable natural resourcesen_ZA
dc.subject.lcshReinforcement learningen_ZA
dc.titleIntelligent control for processing solar photovoltaic energyen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
wacira_intelligent_2023.pdf
Size:
4.14 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters Degrees (Applied Mathematics)