Browsing by Author "Muyeen, S. M."

Now showing 1 - 6 of 6

Adaptive Fault Detection Scheme Using an Optimized Self-healing Ensemble Machine Learning Algorithm
(CHINA ELECTRIC POWER RESEARCH INST, 2022) Yavuz, Levent; Soran, Ahmet; Onen, Ahmet; Li, Xiangjun; Muyeen, S. M.; 0000-0003-1398-9447; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü; Yavuz, Levent; Soran, Ahmet
This paper proposes a new cost-efficient, adaptive, and self-healing algorithm in real time that detects faults in a short period with high accuracy, even in the situations when it is difficult to detect. Rather than using traditional machine learning (ML) algorithms or hybrid signal processing techniques, a new framework based on an optimization enabled weighted ensemble method is developed that combines essential ML algorithms. In the proposed method, the system will select and compound appropriate ML algorithms based on Particle Swarm Optimization (PSO) weights. For this purpose, power system failures are simulated by using the PSCAD-Python co-simulation. One of the salient features of this study is that the proposed solution works on real-time raw data without using any pre-computational techniques or pre-stored information. Therefore, the proposed technique will be able to work on different systems, topologies, or data collections. The proposed fault detection technique is validated by using PSCAD-Python co-simulation on a modified and standard IEEE-14 and standard IEEE-39 bus considering network faults which are difficult to detect.
Enhancing smart grid with microgrids: Challenges and opportunities
(PERGAMON-ELSEVIER SCIENCE LTDTHE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND, 2017) Yoldas, Yeliz; Onen, Ahmet; Muyeen, S. M.; Vasilakos, Athanasios V.; Alan, Irfan; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü; Yoldas, Yeliz; Onen, Ahmet; Alan, Irfan
The modern electric power systems are going through a revolutionary change because of increasing demand of electric power worldwide, developing political pressure and public awareness of reducing carbon emission, incorporating large scale renewable power penetration, and blending information and communication technologies with power system operation. These issues initiated in establishing microgrid concept which has gone through major development and changes in last decade, and recently got a boost in its growth after being blessed by smart grid technologies. The objective of this paper is to presents a detailed technical overview of microgrid and smart grid in light of present development and future trend. First, it discusses microgrid architecture and functions. Then, smart features are added to the microgrid to demonstrate the recent architecture of smart grid. Finally, existing technical challenges, communication features, policies and regulation, etc. are discussed from where the future smart grid architecture can be visualized.
Peer-to-Peer Energy Trading in Virtual Power Plant Based on Blockchain Smart Contracts
(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 445 HOES LANE, PISCATAWAY, NJ 08855-4141 USA, 2020) Seven, Serkan; Yao, Gang; Soran, Ahmet; Onen, Ahmet; Muyeen, S. M.; 0000-0003-0683-1836; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü
A novel Peer-to-peer (P2P) energy trading scheme for a Virtual Power Plant (VPP) is proposed by using Smart Contracts on Ethereum Blockchain Platform. The P2P energy trading is the recent trend the power society is keen to adopt carrying out several trial projects as it eases to generate and share the renewable energy sources in a distributed manner inside local community. Blockchain and smart contracts are the up-and-coming phenomena in the scene of the information technology used to be considered as the cutting-edge research topics in power systems. Earlier works on P2P energy trading including and excluding blockchain technology were focused mainly on the optimization algorithm, Information and Communication Technology, and Internet of Things. Therefore, the financial aspects of P2P trading in a VPP framework is focused and in that regard a P2P energy trading mechanism and bidding platform are developed. The proposed scheme is based on public blockchain network and auction is operated by smart contract addressing both cost and security concerns. The smart contract implementation and execution in a VPP framework including bidding, withdrawal, and control modules developments are the salient feature of this work. The proposed architecture is validated using realistic data with the Ethereum Virtual Machine (EVM) environment of Ropsten Test Network.
PSO Supported Ensemble Algorithm for Bad Data Detection Against Intelligent Hacking Algorithm
(FRONTIERS MEDIA SAAVENUE DU TRIBUNAL FEDERAL 34, LAUSANNE CH-1015, SWITZERLAND, 2021) Yavuz, Levent; Soran, Ahmet; Onen, Ahmet; Muyeen, S. M.; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü; Yavuz, Levent; Soran, Ahmet; Onen, Ahmet
Power system cybersecurity has recently become important due to cyber-attacks. Due to advanced computer science and machine learning (ML) applications being used by malicious attackers, cybersecurity is becoming crucial to creating sustainable, reliable, efficient, and well-protected cyber-systems. Power system operators are needed to develop sophisticated detection mechanisms. In this study, a novel machine-learning-based detection algorithm that combines the five most popular ML algorithms with Particle Swarm Optimizer (PSO) is developed and tested by using an intelligent hacking algorithm that is specially developed to measure the effectiveness of this study. The hacking algorithm provides three different types of injections: random, continuous random, and slow injections by adaptive manner. This would make detection harder. Results shows that recall values with the proposed algorithm for each different type of attack have been increased.
Rooftop Solar PV Penetration Impacts on Distribution Network and Further Growth Factors-A Comprehensive Review
(MDPIST ALBAN-ANLAGE 66, CH-4052 BASEL, SWITZERLAND, 2021) Uzum, Busra; Onen, Ahmet; Hasanien, Hany M.; Muyeen, S. M.; 0000-0001-7086-5112; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü; Uzum, Busra; Onen, Ahmet
In order to meet the electricity needs of domestic or commercial buildings, solar energy is more attractive than other renewable energy sources in terms of its simplicity of installation, less dependence on the field and its economy. It is possible to extract solar energy from photovoltaic (PV) including rooftop, ground-mounted, and building integrated PV systems. Interest in rooftop PV system applications has increased in recent years due to simple installation and not occupying an external area. However, the negative effects of increased PV penetration on the distribution system are troublesome. The power loss, reverse power flow (RPF), voltage fluctuations, voltage unbalance, are causing voltage quality problems in the power network. On the other hand, variations in system frequency, power factor, and harmonics are affecting the power quality. The excessive PV penetration also the root cause of voltage stability and has an adverse effect on protection system. The aim of this article is to extensively examines the impacts of rooftop PV on distribution network and evaluate possible solution methods in terms of the voltage quality, power quality, system protection and system stability. Moreover, it is to present a comparison of the advantages/disadvantages of the solution methods discussed, and an examination of the solution methods in which artificial intelligence, deep learning and machine learning based optimization and techniques are discussed with common methods.
Transformation of microgrid to virtual power plant - a comprehensive review
(INST ENGINEERING TECHNOLOGY-IET, MICHAEL FARADAY HOUSE SIX HILLS WAY STEVENAGE, HERTFORD SG1 2AY, ENGLAND, 2019) Yavuz, Levent; Onen, Ahmet; Muyeen, S. M.; Kamwa, Innocent; 0000-0002-3568-3716; 0000-0003-4955-6889; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü
To provide continuity of balancing demand and generation, renewable sources will be more active than today in near future due to the tendency of massive investment on renewable energy sources (RESs) by countries. However, due to the uncertain and intermittent nature of RESs, RESs would create problems on power system operations such as power quality, efficiency, stability and reliability. Owing to having problems with RESs integration, virtual power plant (VPP) has introduced to make this integration smooth without compromising the grid stability and reliability along with offering many other techno-economic benefits. This study reviews structures, types, architecture and operations of VPP along with the status of present implementations worldwide. The types of VPP are introduced in details with the optimisation algorithm used with each type. In addition, VPP is linked with the most of the components in power systems such as distributed generation, active prosumers, transmission system operator and distribution system operator, grid services such as fault ride through, reactive power control as well as with the help of technology such as communications, control and optimisations. This study gives a comprehensive outline of transforming microgrid to VPP that is useful for researchers, consumers, prosumers and utility operators.