Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836404
M. H. Kabir, Md. Shahriar Rajib, Abu Saleh Md. Mahfujur Rahman, M. Rahman, Samrat Kumar Dey
Network intrusion has become a prime concern issue for the industry and government organizations in the domain of the cyber-threat landscape. To counter this threat, a network intrusion detection system has been considered to be vital in identifying network traffic as normal or anomaly. Correct identification of the potential threat as an anomaly depends on the accuracy of the Network Intrusion Detection System (NIDS). Several approaches like single classical, hybrid, and ensemble methods are in practice to develop a network intrusion detection model. In this paper, two different stacking Machine Learning (ML) models with Extra Tree (ET) Classifier and Mutual Information Gain feature selection methods are proposed for better accuracy of the NIDS. We applied the models on the UNSW-NB15 packet-based dataset which contains the most recent attack types and experimentally proved that the testing accuracy of the stacking models is better than all individual models. Comparative results also depict that one of our proposed models shows better accuracy (96.24%) than any other existing competing models.
{"title":"Network Intrusion Detection Using UNSW-NB15 Dataset: Stacking Machine Learning Based Approach","authors":"M. H. Kabir, Md. Shahriar Rajib, Abu Saleh Md. Mahfujur Rahman, M. Rahman, Samrat Kumar Dey","doi":"10.1109/icaeee54957.2022.9836404","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836404","url":null,"abstract":"Network intrusion has become a prime concern issue for the industry and government organizations in the domain of the cyber-threat landscape. To counter this threat, a network intrusion detection system has been considered to be vital in identifying network traffic as normal or anomaly. Correct identification of the potential threat as an anomaly depends on the accuracy of the Network Intrusion Detection System (NIDS). Several approaches like single classical, hybrid, and ensemble methods are in practice to develop a network intrusion detection model. In this paper, two different stacking Machine Learning (ML) models with Extra Tree (ET) Classifier and Mutual Information Gain feature selection methods are proposed for better accuracy of the NIDS. We applied the models on the UNSW-NB15 packet-based dataset which contains the most recent attack types and experimentally proved that the testing accuracy of the stacking models is better than all individual models. Comparative results also depict that one of our proposed models shows better accuracy (96.24%) than any other existing competing models.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116066595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836388
Md. Rashedul Islam, M. Akhtar, M. Begum
The upcoming digital transformation of the modern industry will principally build upon the software systems. Certainly, any software system should commit to being fully reliable and free from any deficiency such as software faults. Maintaining the aforementioned consistency is the main objective of software reliability. The long short-term memory (LSTM) networks are employed for the first time in this kind of research to forecast software faults. The one-step walk-forward validation method is used to predict the software faults. Due to the exponential nature of data, we normalized our cumulative software fault count data using Min-Max Scalar and Box-Cox Transformation methods. Each type of normalized data is fed into the LSTM networks. With the same batch size, the number of neurons and epoch parameters were regulated with different tiers of combinations. The time-series-based software fault data were trained and tested after applying Min-Max and Box-Cox data transformation methods to obtain the root means square error (RMSE) values, and then both models were compared with each other. The RMSE values of the model with the Min-Max Scaler transforming method outperform the second model built with the Box-Cox Transformation method. From our very best knowledge, the obtained RMSE value from the software fault count data using LSTM is the first of its kind. Our models clearly show that the LSTM can be used to predict software faults. We also calculated the data dispersion from the observed independent RMSE data points of each model. The quantified data dispersion value of the second model was found to be less minimal than the first one.
{"title":"Long short-term memory (LSTM) networks based software fault prediction using data transformation methods","authors":"Md. Rashedul Islam, M. Akhtar, M. Begum","doi":"10.1109/icaeee54957.2022.9836388","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836388","url":null,"abstract":"The upcoming digital transformation of the modern industry will principally build upon the software systems. Certainly, any software system should commit to being fully reliable and free from any deficiency such as software faults. Maintaining the aforementioned consistency is the main objective of software reliability. The long short-term memory (LSTM) networks are employed for the first time in this kind of research to forecast software faults. The one-step walk-forward validation method is used to predict the software faults. Due to the exponential nature of data, we normalized our cumulative software fault count data using Min-Max Scalar and Box-Cox Transformation methods. Each type of normalized data is fed into the LSTM networks. With the same batch size, the number of neurons and epoch parameters were regulated with different tiers of combinations. The time-series-based software fault data were trained and tested after applying Min-Max and Box-Cox data transformation methods to obtain the root means square error (RMSE) values, and then both models were compared with each other. The RMSE values of the model with the Min-Max Scaler transforming method outperform the second model built with the Box-Cox Transformation method. From our very best knowledge, the obtained RMSE value from the software fault count data using LSTM is the first of its kind. Our models clearly show that the LSTM can be used to predict software faults. We also calculated the data dispersion from the observed independent RMSE data points of each model. The quantified data dispersion value of the second model was found to be less minimal than the first one.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116609136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836358
Sayed Md.Abrar Gani, Md. Rashidul Islam, M. Shafiullah, Jahid Hasan Tayeb, M. Hossain, Amjad Ali
An evolutionary algorithm-based power system stabilizers (PSS) design for low-frequency oscillations (LFO) damping in multi-machine power system networks (MMPSNs) is presented in this paper. A damping ratio-based objective function is developed to enhance the system damping where the widely employed lead-lag type PSS is considered in the problem formulation. The equilibrium Optimizer (EO), a recently developed metaheuristic algorithm that is capable of finding optimal solutions in complex engineering problems, is employed in this article. The algorithm's resilience is demonstrated by its ability to lead to the best PSS design regardless of the initial assumption made by the user. Two distinct multi-machine networks 2-area 4-machine and IEEE 10-machine 39-bus are used in this research. EO-based PSS results are compared with traditional PSS results to investigate which one yields better results for stability. According to the simulation findings, the EO technique reduces the settling time and overshoot significantly over the other techniques.
{"title":"Equilibrium Optimizer for LFO Damping in Multimachine Power System Networks","authors":"Sayed Md.Abrar Gani, Md. Rashidul Islam, M. Shafiullah, Jahid Hasan Tayeb, M. Hossain, Amjad Ali","doi":"10.1109/icaeee54957.2022.9836358","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836358","url":null,"abstract":"An evolutionary algorithm-based power system stabilizers (PSS) design for low-frequency oscillations (LFO) damping in multi-machine power system networks (MMPSNs) is presented in this paper. A damping ratio-based objective function is developed to enhance the system damping where the widely employed lead-lag type PSS is considered in the problem formulation. The equilibrium Optimizer (EO), a recently developed metaheuristic algorithm that is capable of finding optimal solutions in complex engineering problems, is employed in this article. The algorithm's resilience is demonstrated by its ability to lead to the best PSS design regardless of the initial assumption made by the user. Two distinct multi-machine networks 2-area 4-machine and IEEE 10-machine 39-bus are used in this research. EO-based PSS results are compared with traditional PSS results to investigate which one yields better results for stability. According to the simulation findings, the EO technique reduces the settling time and overshoot significantly over the other techniques.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123746870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836365
Md. Ether Deowan, Ahsan Kabir Nuhel, Mohammed Shakawath Hossain, A. Ullah, Shuvra Saha
5G is the next-generation cellular network that will have substantial improvement on high data rates, low latency, and reliable data transfer to keep up with the modern world. This network will be providing a flexible platform for upcoming services such as IoT, Artificial Intelligence, Cloud computing, Smart grid, Industrial automation, Natural Language Processing, machine communication, and all other latest technologies. 5G have a data rate of 10–100 times greater than 4G, and now 5G is in the testing phase in Bangladesh. To facilitate the key features of 5G proper architecture, spectrum allocation and policy are essential. In this paper, the authors present an overview of all important aspects of 5G technology for getting higher efficiency. The different Scopes, safety issues, and Challenges of implementing 5G technology in Bangladesh were also reviewed.
{"title":"A Study on the Aspects of 5G Implementation in Bangladesh","authors":"Md. Ether Deowan, Ahsan Kabir Nuhel, Mohammed Shakawath Hossain, A. Ullah, Shuvra Saha","doi":"10.1109/icaeee54957.2022.9836365","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836365","url":null,"abstract":"5G is the next-generation cellular network that will have substantial improvement on high data rates, low latency, and reliable data transfer to keep up with the modern world. This network will be providing a flexible platform for upcoming services such as IoT, Artificial Intelligence, Cloud computing, Smart grid, Industrial automation, Natural Language Processing, machine communication, and all other latest technologies. 5G have a data rate of 10–100 times greater than 4G, and now 5G is in the testing phase in Bangladesh. To facilitate the key features of 5G proper architecture, spectrum allocation and policy are essential. In this paper, the authors present an overview of all important aspects of 5G technology for getting higher efficiency. The different Scopes, safety issues, and Challenges of implementing 5G technology in Bangladesh were also reviewed.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116546643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836360
M. J. Hossain, P. C. Paul, S. S. Islam, M. Begum
A new mirror C-shaped with square split resonators engineered material unit cell structure proposed for L-, S-, and C-band applications. The design structure has shown the negative refractive index (NRI) property along with the x-axis wave propagation. The finite integration technique (FIT) based Computer Simulation Technology (CST) microwave studio software and finite element method based High Frequency Structure Simulator (HFSS) software are adopted to investigate the proposed design structure. The parametric studies have been done based on the substrate's thickness. The engineered material unit cell structure acquired higher effective medium ratio (21.71) and exhibited the NRI properties at 1.47 GHz frequency. The higher wideband (5.63 GHz) also attained by the proposed design structure. The results of the proposed engineered material demonstrated L-, S-, and C-bands response over the frequency ranges from 1 to 10 GHz. Hence, the proposed structure enables numerous application areas of L-, S-, and C-bands.
{"title":"Miniaturized Mirror C-Shaped Negative Index Engineered Material for L-, S-, and C-band Applications","authors":"M. J. Hossain, P. C. Paul, S. S. Islam, M. Begum","doi":"10.1109/icaeee54957.2022.9836360","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836360","url":null,"abstract":"A new mirror C-shaped with square split resonators engineered material unit cell structure proposed for L-, S-, and C-band applications. The design structure has shown the negative refractive index (NRI) property along with the x-axis wave propagation. The finite integration technique (FIT) based Computer Simulation Technology (CST) microwave studio software and finite element method based High Frequency Structure Simulator (HFSS) software are adopted to investigate the proposed design structure. The parametric studies have been done based on the substrate's thickness. The engineered material unit cell structure acquired higher effective medium ratio (21.71) and exhibited the NRI properties at 1.47 GHz frequency. The higher wideband (5.63 GHz) also attained by the proposed design structure. The results of the proposed engineered material demonstrated L-, S-, and C-bands response over the frequency ranges from 1 to 10 GHz. Hence, the proposed structure enables numerous application areas of L-, S-, and C-bands.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122516062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836479
Marzia Ahmed, Rony Shaha, Kaushik Sarker, Rifat Bin Mahi, M. A. Kashem
Rapid population expansion necessitated increased resource use in everyday living. As a result, the pace of trash gen-eration has increased dramatically, affecting the environment's hygiene system and other health concerns. Waste overflows in public spaces, and improved management is necessary. The purpose of this study is to develop a model of an intelligent trashcan for usage in smart cities. Additionally, to identify dangerous gases emitted by dustbins for subsequent management operations, as well as to monitor the amount of trash in the waste bin and warn the municipality through SMS. This system includes two ultrasonic sonar sensors for measuring trash level, a GSM module for sending SMS, three gas sensors for detecting harmful garbage gas, an infrared sensor for counting garbage droplets, and an Arduino Uno for managing all activities. The system notifies you whether the bin is full or empty and can also be controlled by voice command. Additionally, released gas may be monitored to determine the severity of the impairment and to notify the appropriate authorities. Most significantly, it will identify a failed trash drop in the bin and alert the user through alarm for truly considering the reduction of spilled garbage surrounding bins while using the system.
{"title":"Design and Implementation of Intelligent Dustbin with Garbage Gas Detection for Hygienic Environment based on IoT","authors":"Marzia Ahmed, Rony Shaha, Kaushik Sarker, Rifat Bin Mahi, M. A. Kashem","doi":"10.1109/icaeee54957.2022.9836479","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836479","url":null,"abstract":"Rapid population expansion necessitated increased resource use in everyday living. As a result, the pace of trash gen-eration has increased dramatically, affecting the environment's hygiene system and other health concerns. Waste overflows in public spaces, and improved management is necessary. The purpose of this study is to develop a model of an intelligent trashcan for usage in smart cities. Additionally, to identify dangerous gases emitted by dustbins for subsequent management operations, as well as to monitor the amount of trash in the waste bin and warn the municipality through SMS. This system includes two ultrasonic sonar sensors for measuring trash level, a GSM module for sending SMS, three gas sensors for detecting harmful garbage gas, an infrared sensor for counting garbage droplets, and an Arduino Uno for managing all activities. The system notifies you whether the bin is full or empty and can also be controlled by voice command. Additionally, released gas may be monitored to determine the severity of the impairment and to notify the appropriate authorities. Most significantly, it will identify a failed trash drop in the bin and alert the user through alarm for truly considering the reduction of spilled garbage surrounding bins while using the system.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115283426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836347
M. Rahman, Md. Ashik Jiddney, Nurul Amin Nahid, Md. Pias Khan, Md. Zulfiker Mahmud, Md. Hafizur Rahman
In this paper a brick wall shaped microstrip line feed antenna for fifth generation (5G) applications is proposed. The bandwidth of brick wall shaped rectangular patch feed by microstrip line is enhanced by applying the technique of coupling gap on radiating patch and by using the rectangular saw-tooth oriented partial ground plane. The proposed antenna has an impedance bandwidth of 21.6-30.0 GHz which covers the higher bandwidth of 5G applications. The overall size of proposed antenna is $21times 28 mm^{2}$ using the low cost commercially available FR4 Substrate. The designed antenna deals with the resonance frequency of 26.15 GHz. The co and cross polarizations at the resonant frequency are observed to be omnidirectional. With 90° directivity, the cross-polarization radiation pattern is enhanced the values of co-polarization are more negative than the values of cross-polarization. The uneven slots on the ground plane help the main radiator to escape trapping by providing ideal conditions. It has radiation efficiency of 44% with the peak gain of 4.5 dB across the operating bandwidth. 3D microwave studio Computer Simulation Technology (CST) is used as simulation tool to design and analyze the antenna geometry.
{"title":"Design & Development of Brick Wall Shaped Microstrip Miniaturized Ultra-Wide Band Patch Antenna for Fifth Generation (5G)","authors":"M. Rahman, Md. Ashik Jiddney, Nurul Amin Nahid, Md. Pias Khan, Md. Zulfiker Mahmud, Md. Hafizur Rahman","doi":"10.1109/icaeee54957.2022.9836347","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836347","url":null,"abstract":"In this paper a brick wall shaped microstrip line feed antenna for fifth generation (5G) applications is proposed. The bandwidth of brick wall shaped rectangular patch feed by microstrip line is enhanced by applying the technique of coupling gap on radiating patch and by using the rectangular saw-tooth oriented partial ground plane. The proposed antenna has an impedance bandwidth of 21.6-30.0 GHz which covers the higher bandwidth of 5G applications. The overall size of proposed antenna is $21times 28 mm^{2}$ using the low cost commercially available FR4 Substrate. The designed antenna deals with the resonance frequency of 26.15 GHz. The co and cross polarizations at the resonant frequency are observed to be omnidirectional. With 90° directivity, the cross-polarization radiation pattern is enhanced the values of co-polarization are more negative than the values of cross-polarization. The uneven slots on the ground plane help the main radiator to escape trapping by providing ideal conditions. It has radiation efficiency of 44% with the peak gain of 4.5 dB across the operating bandwidth. 3D microwave studio Computer Simulation Technology (CST) is used as simulation tool to design and analyze the antenna geometry.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129433627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An android application (Apps) can only access sensitive user information once it gets the user's consent via the ‘android permission system’. Permissions determine how much Personally Identifiable Information (PII) Apps can access and how harmful Apps can be. However, it is often noticed that android Apps developers often gather irrelevant information, directly conflicting with the Apps sole purpose. Consequently, willingly and unwillingly, users are often allowing permissions and putting their privacy at stake. This study investigates and compares whether the same purpose android Apps asking identical permissions or not. For investigation, this work explores widely used food-sharing and ride-sharing Apps from Bangladesh. Twenty (20) such Apps, including Foodpanda, Pathao, Uber, HungryNaki, Obhai were installed followed by a thorough inspection based on their purposes. In addition, this study also considers context-aware user information prioritization and ranks the considered Apps accordingly. This work finds that Android Apps collect more information than needed, although their purpose was identical. On top of that, popular Apps with more downloads and higher rankings tend to collect large-scale irrelevant permissions.
{"title":"Are the Ride and Food Sharing Apps Privacy-aware in Bangladesh? Investigating Android Permissions Usage","authors":"Ishorju Agnes Botlero, Merina Tanjin, Mourina Tasnim Hridita, Md. Mehedi Hassan Onik","doi":"10.1109/icaeee54957.2022.9836460","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836460","url":null,"abstract":"An android application (Apps) can only access sensitive user information once it gets the user's consent via the ‘android permission system’. Permissions determine how much Personally Identifiable Information (PII) Apps can access and how harmful Apps can be. However, it is often noticed that android Apps developers often gather irrelevant information, directly conflicting with the Apps sole purpose. Consequently, willingly and unwillingly, users are often allowing permissions and putting their privacy at stake. This study investigates and compares whether the same purpose android Apps asking identical permissions or not. For investigation, this work explores widely used food-sharing and ride-sharing Apps from Bangladesh. Twenty (20) such Apps, including Foodpanda, Pathao, Uber, HungryNaki, Obhai were installed followed by a thorough inspection based on their purposes. In addition, this study also considers context-aware user information prioritization and ranks the considered Apps accordingly. This work finds that Android Apps collect more information than needed, although their purpose was identical. On top of that, popular Apps with more downloads and higher rankings tend to collect large-scale irrelevant permissions.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"3 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121255052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836362
M. Iqbal, A. Hossain, Jahidul Islam, Amit Shaha Surja, M. Kabir
In this paper, a novel control scheme based on Reinforcement Learning (RL) controller for the Static Synchronous Compensator (STATCOM) is presented for inter-area multi-machine power system. It is a common criterion to develop an improved control strategy for STATCOM to enhance the voltage stability of multi-machine power system. To exemplify on this purpose, a STATCOM controller has been designed which does not depend on the structure and parameters of power system. Moreover, the proposed strategy also replaces the conventional PI controller by RL controller and provides more reliable controlling environment. In addition, the Twin-Delayed Deep Deterministic Policy Gradient (TD3) algorithm is adopted for this work and the parameters of the controller are being updated by TD3 algorithm using only local information. Finally, a simulated result of inter-area multi-machine power system is given, where the result shows the effectiveness of stable voltage maintenance and preventing voltage collapse.
{"title":"Enhancing Voltage Stability of Inter-Area Multi-Machine Power Systems using Reinforcement Learning-based STATCOM","authors":"M. Iqbal, A. Hossain, Jahidul Islam, Amit Shaha Surja, M. Kabir","doi":"10.1109/icaeee54957.2022.9836362","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836362","url":null,"abstract":"In this paper, a novel control scheme based on Reinforcement Learning (RL) controller for the Static Synchronous Compensator (STATCOM) is presented for inter-area multi-machine power system. It is a common criterion to develop an improved control strategy for STATCOM to enhance the voltage stability of multi-machine power system. To exemplify on this purpose, a STATCOM controller has been designed which does not depend on the structure and parameters of power system. Moreover, the proposed strategy also replaces the conventional PI controller by RL controller and provides more reliable controlling environment. In addition, the Twin-Delayed Deep Deterministic Policy Gradient (TD3) algorithm is adopted for this work and the parameters of the controller are being updated by TD3 algorithm using only local information. Finally, a simulated result of inter-area multi-machine power system is given, where the result shows the effectiveness of stable voltage maintenance and preventing voltage collapse.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116294339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-24DOI: 10.1109/icaeee54957.2022.9836356
Abdul Majid Hasan, M. Islam, M. Shafiullah, Md. Burhan Uddin
The power system is an extremely nonlinear structure with complicated characteristics. Power networks are electrically intertwined and they are susceptible caused by disruptions in anyone part of the system. In fact, low frequency oscillations (LFOs) caused by minor perturbations in any portion of the network might bring the entire system down. With the appropriate parameter settings, the power system stabilizer (PSS) effectively reduces these oscillations. This paper proposes a completely unique nature algorithm, to tune PID and Lead-Lag based controller using Multi-Verse Optimizer (MVO) for SMIB system to control LFOs by improving power system damping. By comparing simulation results with fixed gain traditional PSS, the performance of the MVO tuned PSS is analyzed. Furthermore, comparing between MVO and Genetic Algorithm based tuned PSS, eigenvalues and the damping ratio of the same network were evaluated.
{"title":"Multi-Verse Optimizer for LFO Damping in Single Machine Infinite Bus Power Networks","authors":"Abdul Majid Hasan, M. Islam, M. Shafiullah, Md. Burhan Uddin","doi":"10.1109/icaeee54957.2022.9836356","DOIUrl":"https://doi.org/10.1109/icaeee54957.2022.9836356","url":null,"abstract":"The power system is an extremely nonlinear structure with complicated characteristics. Power networks are electrically intertwined and they are susceptible caused by disruptions in anyone part of the system. In fact, low frequency oscillations (LFOs) caused by minor perturbations in any portion of the network might bring the entire system down. With the appropriate parameter settings, the power system stabilizer (PSS) effectively reduces these oscillations. This paper proposes a completely unique nature algorithm, to tune PID and Lead-Lag based controller using Multi-Verse Optimizer (MVO) for SMIB system to control LFOs by improving power system damping. By comparing simulation results with fixed gain traditional PSS, the performance of the MVO tuned PSS is analyzed. Furthermore, comparing between MVO and Genetic Algorithm based tuned PSS, eigenvalues and the damping ratio of the same network were evaluated.","PeriodicalId":383872,"journal":{"name":"2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127858034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：