Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition

For renewable energy systems to operate as efficiently and as effectively as possible, maximum power point tracking (MPPT) controllers are essential. They make it possible to precisely and dynamically track the peak output of solar panels or wind turbines, ensuring that the system will be stable and...

Full description

Saved in:
Bibliographic Details
Main Authors: Yew W.H., Fat Chau C., Mahmood Zuhdi A.W., Syakirah Wan Abdullah W., Yew W.K., Amin N.
Other Authors: 58765606400
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers Inc. 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-34511
record_format dspace
spelling my.uniten.dspace-345112024-10-14T11:20:18Z Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition Yew W.H. Fat Chau C. Mahmood Zuhdi A.W. Syakirah Wan Abdullah W. Yew W.K. Amin N. 58765606400 25824209000 56589966300 57209655076 57361611300 7102424614 deep reinforcement learning energy maximum power point tracking (MPPT) off-grid PV partial shading conditions (PSC) particle swarm optimization (PSO) perturb and observe (P&O) Deep learning Global optimization Learning algorithms MATLAB Maximum power point trackers Particle swarm optimization (PSO) Renewable energy resources Condition Deep reinforcement learning Energy Maximum Power Point Tracking Off-grid PV Off-grids Partial shading Partial shading condition Particle swarm Particle swarm optimization Perturb and observe Reinforcement learnings Swarm optimization Reinforcement learning For renewable energy systems to operate as efficiently and as effectively as possible, maximum power point tracking (MPPT) controllers are essential. They make it possible to precisely and dynamically track the peak output of solar panels or wind turbines, ensuring that the system will be stable and reliable even in the face of changing environmental factors. Recently, more robust algorithms based on deep reinforcement learning (DRL) have been proposed. These DRL-based algorithms optimize the local and global maximum power point (MPP) using deep Q-learning and deep deterministic policy gradient (DDPG). In this study, MATLAB models of a DRL-based MPPT algorithm were developed, tested, and compared to simulation based on two established MPPT algorithms-the Particle Swarm Optimization (PSO), and the Perturb and Observe (P&O). The simulations were conducted under various conditions, including standard test conditions (STC), and partial shading conditions (PSC). Simulation results demonstrate that at STC, both the DRL-based MPPT and PSO algorithm tracks the steady-state power at 0.02 seconds, outperforming the traditional P&O technique of 0.08 seconds. However, the PSO algorithm manages to track 1.18% more power than DRL MPPT at PSC. Despite the limitations of training the DRL, it shows a promising method for addressing MPPT issues under PSC. � 2023 IEEE. Final 2024-10-14T03:20:18Z 2024-10-14T03:20:18Z 2023 Conference Paper 10.1109/RSM59033.2023.10326748 2-s2.0-85179849009 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85179849009&doi=10.1109%2fRSM59033.2023.10326748&partnerID=40&md5=01d82e586999d026817ffb2883a41b49 https://irepository.uniten.edu.my/handle/123456789/34511 9 12 Institute of Electrical and Electronics Engineers Inc. Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
topic deep reinforcement learning
energy
maximum power point tracking (MPPT)
off-grid PV
partial shading conditions (PSC)
particle swarm optimization (PSO)
perturb and observe (P&O)
Deep learning
Global optimization
Learning algorithms
MATLAB
Maximum power point trackers
Particle swarm optimization (PSO)
Renewable energy resources
Condition
Deep reinforcement learning
Energy
Maximum Power Point Tracking
Off-grid PV
Off-grids
Partial shading
Partial shading condition
Particle swarm
Particle swarm optimization
Perturb and observe
Reinforcement learnings
Swarm optimization
Reinforcement learning
spellingShingle deep reinforcement learning
energy
maximum power point tracking (MPPT)
off-grid PV
partial shading conditions (PSC)
particle swarm optimization (PSO)
perturb and observe (P&O)
Deep learning
Global optimization
Learning algorithms
MATLAB
Maximum power point trackers
Particle swarm optimization (PSO)
Renewable energy resources
Condition
Deep reinforcement learning
Energy
Maximum Power Point Tracking
Off-grid PV
Off-grids
Partial shading
Partial shading condition
Particle swarm
Particle swarm optimization
Perturb and observe
Reinforcement learnings
Swarm optimization
Reinforcement learning
Yew W.H.
Fat Chau C.
Mahmood Zuhdi A.W.
Syakirah Wan Abdullah W.
Yew W.K.
Amin N.
Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition
description For renewable energy systems to operate as efficiently and as effectively as possible, maximum power point tracking (MPPT) controllers are essential. They make it possible to precisely and dynamically track the peak output of solar panels or wind turbines, ensuring that the system will be stable and reliable even in the face of changing environmental factors. Recently, more robust algorithms based on deep reinforcement learning (DRL) have been proposed. These DRL-based algorithms optimize the local and global maximum power point (MPP) using deep Q-learning and deep deterministic policy gradient (DDPG). In this study, MATLAB models of a DRL-based MPPT algorithm were developed, tested, and compared to simulation based on two established MPPT algorithms-the Particle Swarm Optimization (PSO), and the Perturb and Observe (P&O). The simulations were conducted under various conditions, including standard test conditions (STC), and partial shading conditions (PSC). Simulation results demonstrate that at STC, both the DRL-based MPPT and PSO algorithm tracks the steady-state power at 0.02 seconds, outperforming the traditional P&O technique of 0.08 seconds. However, the PSO algorithm manages to track 1.18% more power than DRL MPPT at PSC. Despite the limitations of training the DRL, it shows a promising method for addressing MPPT issues under PSC. � 2023 IEEE.
author2 58765606400
author_facet 58765606400
Yew W.H.
Fat Chau C.
Mahmood Zuhdi A.W.
Syakirah Wan Abdullah W.
Yew W.K.
Amin N.
format Conference Paper
author Yew W.H.
Fat Chau C.
Mahmood Zuhdi A.W.
Syakirah Wan Abdullah W.
Yew W.K.
Amin N.
author_sort Yew W.H.
title Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition
title_short Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition
title_full Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition
title_fullStr Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition
title_full_unstemmed Investigating the Performance of Deep Reinforcement Learning-Based MPPT Algorithm under Partial Shading Condition
title_sort investigating the performance of deep reinforcement learning-based mppt algorithm under partial shading condition
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2024
_version_ 1814061059750756352
score 13.209306