A review of machine learning approaches to power system security and stability
- Alimi, Oyeniyi Akeem, Ouahada, Khmaies, Abu-Mahfouz, Adnan M.
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies , Abu-Mahfouz, Adnan M.
- Date: 2020
- Subjects: Classifiers , Cyberattacks , Deep reinforcement learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/459980 , uj:40915 , Citation: Alimi, O.A., Ouahada, K. & Abu-Mahfouz, A.M. 2020. A review of machine learning approaches to power system security and stability. , DOI: 10.1109/ACCESS.2020.3003568
- Description: Abstract: Please refer to full text to view abstract.
- Full Text:
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies , Abu-Mahfouz, Adnan M.
- Date: 2020
- Subjects: Classifiers , Cyberattacks , Deep reinforcement learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/459980 , uj:40915 , Citation: Alimi, O.A., Ouahada, K. & Abu-Mahfouz, A.M. 2020. A review of machine learning approaches to power system security and stability. , DOI: 10.1109/ACCESS.2020.3003568
- Description: Abstract: Please refer to full text to view abstract.
- Full Text:
Real time security assessment of the power system using a hybrid support vector machine and multilayer perceptron neural network algorithms
- Alimi, Oyeniyi Akeem, Ouahada, Khmaies, Abu-Mahfouz, Adnan M.
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies , Abu-Mahfouz, Adnan M.
- Date: 2019
- Subjects: Multilayer perceptron neural network , Support vector machine , Cyberattacks
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/404703 , uj:33952 , Citation : Alimi, O.A., Abu-Mahfouz, A.M., Ouahada, K. : 2019. Real time security assessment of the power system using a hybrid support vector machine and multilayer perceptron neural network algorithms.
- Description: Abstract : In today’s grid, the technological based cyber-physical systems have continued to be plagued with cyberattacks and intrusions. Any intrusive action on the power system’s Optimal Power Flow (OPF) modules can cause a series of operational instabilities, failures, and financial losses. Real time intrusion detection has become a major challenge for the power community and energy stakeholders. Current conventional methods have continued to exhibit shortfalls in tackling these security issues. In order to address this security issue, this paper proposes a hybrid Support Vector Machine and Multilayer Perceptron Neural Network (SVMNN) algorithm that involves the combination of Support Vector Machine (SVM) and multilayer perceptron neural network (MPLNN) algorithms for predicting and detecting cyber intrusion attacks into power system networks. In this paper, a modified version of the IEEE Garver 6-bus test system and a 24-bus system were used as case studies. The IEEE Garver 6-bus test system was used to describe the attack scenarios, whereas load flow analysis was conducted on real time data of a modified Nigerian 24-bus system to generate the bus voltage dataset that considered several cyberattack events for the hybrid algorithm. Sising various performance metricion and load/generator injections, en included in the manuscriptmulation results showed the relevant influences of cyberattacks on power systems in terms of voltage, power, and current flows. To demonstrate the performance of the proposed hybrid SVMNN algorithm, the results are compared with other models in related studies. The results demonstrated that the hybrid algorithm achieved a detection accuracy of 99.6%, which is better than recently proposed schemes.
- Full Text:
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies , Abu-Mahfouz, Adnan M.
- Date: 2019
- Subjects: Multilayer perceptron neural network , Support vector machine , Cyberattacks
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/404703 , uj:33952 , Citation : Alimi, O.A., Abu-Mahfouz, A.M., Ouahada, K. : 2019. Real time security assessment of the power system using a hybrid support vector machine and multilayer perceptron neural network algorithms.
- Description: Abstract : In today’s grid, the technological based cyber-physical systems have continued to be plagued with cyberattacks and intrusions. Any intrusive action on the power system’s Optimal Power Flow (OPF) modules can cause a series of operational instabilities, failures, and financial losses. Real time intrusion detection has become a major challenge for the power community and energy stakeholders. Current conventional methods have continued to exhibit shortfalls in tackling these security issues. In order to address this security issue, this paper proposes a hybrid Support Vector Machine and Multilayer Perceptron Neural Network (SVMNN) algorithm that involves the combination of Support Vector Machine (SVM) and multilayer perceptron neural network (MPLNN) algorithms for predicting and detecting cyber intrusion attacks into power system networks. In this paper, a modified version of the IEEE Garver 6-bus test system and a 24-bus system were used as case studies. The IEEE Garver 6-bus test system was used to describe the attack scenarios, whereas load flow analysis was conducted on real time data of a modified Nigerian 24-bus system to generate the bus voltage dataset that considered several cyberattack events for the hybrid algorithm. Sising various performance metricion and load/generator injections, en included in the manuscriptmulation results showed the relevant influences of cyberattacks on power systems in terms of voltage, power, and current flows. To demonstrate the performance of the proposed hybrid SVMNN algorithm, the results are compared with other models in related studies. The results demonstrated that the hybrid algorithm achieved a detection accuracy of 99.6%, which is better than recently proposed schemes.
- Full Text:
Security assessment of the smart grid : a review focusing on the NAN architecture
- Alimi, Oyeniyi Akeem, Ouahada, Khmaies
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies
- Date: 2018
- Subjects: Smart grid , Cyber-security , Neighbourhood Area Network
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/283770 , uj:30616 , Citation: Alimi, O.A. & Ouahada, K. 2018. Security assessment of the smart grid : a review focusing on the NAN architecture.
- Description: Abstract: This paper presents a comprehensive review on the security aspect of the smart grid communication network. The paper focus on the Neighborhood Area Network (NAN) cybersecurity and it laid emphasis on how the NAN architecture is such an attractive target to intruders and attackers. The paper aims at summarizing recent research efforts on some of the attacks and the various techniques employed in tackling them as they were discussed in recent literatures and research works. Furthermore, the paper presents a detailed review on the smart grid communication layers, wireless technology standards, networks and the security challenges the grid is currently facing. The work concludes by explaining current and future directions NAN communication security could consider in terms of data privacy measures. The data privacy measures are discussed in terms of prevention and detection techniques.
- Full Text:
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies
- Date: 2018
- Subjects: Smart grid , Cyber-security , Neighbourhood Area Network
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/283770 , uj:30616 , Citation: Alimi, O.A. & Ouahada, K. 2018. Security assessment of the smart grid : a review focusing on the NAN architecture.
- Description: Abstract: This paper presents a comprehensive review on the security aspect of the smart grid communication network. The paper focus on the Neighborhood Area Network (NAN) cybersecurity and it laid emphasis on how the NAN architecture is such an attractive target to intruders and attackers. The paper aims at summarizing recent research efforts on some of the attacks and the various techniques employed in tackling them as they were discussed in recent literatures and research works. Furthermore, the paper presents a detailed review on the smart grid communication layers, wireless technology standards, networks and the security challenges the grid is currently facing. The work concludes by explaining current and future directions NAN communication security could consider in terms of data privacy measures. The data privacy measures are discussed in terms of prevention and detection techniques.
- Full Text:
Smart home appliances scheduling to manage energy usage
- Alimi, Oyeniyi Akeem, Ouahada, Khmaies
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies
- Date: 2018
- Subjects: Demand side management , Home energy management system , Smart home appliances
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/281991 , uj:30381 , Citation: Alimi, O.A. & Ouahada, K. 2018. Smart home appliances scheduling to manage energy usage.
- Description: Abstract: It is imperative to manage household appliances in a cost-effective way to realize efficient energy utilization, reduce spending on electricity bills and increase grid reliability. This study presents a Home energy management system (HEMS) scheduling analysis. The scheduling plan avoids the electricity wastages which arise majorly due resident’s negligence on appliances control. The home appliances employed in the research work are classified in terms of their operating periods. The energy consumption was evaluated using a Fixed Pricing (FP) data. The appliances scheduling plan was developed using Microsoft.net framework with C# Programming language whereas the front end showing the scheduled operating periods for the appliances was developed using Telerik UI framework for Windows forms. Simulation results of the scheduling plan show energy consumption in homes can be planned, monitored and controlled to avoid energy wastage and minimize energy expenditure.
- Full Text:
- Authors: Alimi, Oyeniyi Akeem , Ouahada, Khmaies
- Date: 2018
- Subjects: Demand side management , Home energy management system , Smart home appliances
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/281991 , uj:30381 , Citation: Alimi, O.A. & Ouahada, K. 2018. Smart home appliances scheduling to manage energy usage.
- Description: Abstract: It is imperative to manage household appliances in a cost-effective way to realize efficient energy utilization, reduce spending on electricity bills and increase grid reliability. This study presents a Home energy management system (HEMS) scheduling analysis. The scheduling plan avoids the electricity wastages which arise majorly due resident’s negligence on appliances control. The home appliances employed in the research work are classified in terms of their operating periods. The energy consumption was evaluated using a Fixed Pricing (FP) data. The appliances scheduling plan was developed using Microsoft.net framework with C# Programming language whereas the front end showing the scheduled operating periods for the appliances was developed using Telerik UI framework for Windows forms. Simulation results of the scheduling plan show energy consumption in homes can be planned, monitored and controlled to avoid energy wastage and minimize energy expenditure.
- Full Text:
Using call admission control and call duration control for mobile network congestion management
- Authors: Alimi, Oyeniyi Akeem
- Date: 2016
- Subjects: Mobile communication systems , Wireless communication systems - Management , Cell phone systems
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/233166 , uj:23799
- Description: M.Tech. (Electrical Engineering) , Abstract: Wireless communications have experienced massive development remarkably in the past decade. Networks such as global system for mobile communications (GSM) and universal mobile telecommunication service (UMTS) has enjoyed enormous patronization, hence leading to massive mobile network congestion. The problem of network congestion is a network managerial issue that affects the Quality of Service (QoS) rendered by a network. Hence for the sustainability of the system, there is a need to fully manage the radio resources during peak and off peak periods. Call Admission Control (CAC) schemes are constantly being used extensively in managing mobile network congestion. CAC is an approach that can provide credible QoS by regulating the number of connections into the cellular network thereby allowing good use of the radio resources, reducing network congestions, interference and other QoS problems. Network resources cannot be available for all users at all times especially during busy hour traffic. Hence, these resources require effective and efficient allocation so that more subscribers are being allowed to use the network irrespective of the network traffic at a particular reference time. Mobile network congestion can be controlled by suppressing the mobile network traffic demand. The traffic demand varies proportionally with average rate of call arrival and the average duration of the calls. Hence marginalizing the average call duration will minimize traffic load, thereby reducing network congestion. Some network users due to their lifestyle of being affluent or business demands, holds on to a particular channel during long duration of calls at the detriment of other network users. CAC scheme cannot solve congestion problems due to the selfishness of these particular sets of users. Here, the combination of a channel reservation CAC scheme with Call Duration Control (CDC) scheme was proposed, in which users that have stayed over a predetermined period in the network will be served a termination notice so as to make the channel available for new users. The motive is to provide the available channels to accommodate more users. A simulation-based approach was used to model the combination of the two schemes and the combination produces good results in reducing the congestion menace. The network type deployed in the research is GSM. The result of the CAC/CDC combination schemes were compared to the result of the ordinary CAC schemes in order to verify the impact of the...
- Full Text:
- Authors: Alimi, Oyeniyi Akeem
- Date: 2016
- Subjects: Mobile communication systems , Wireless communication systems - Management , Cell phone systems
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/233166 , uj:23799
- Description: M.Tech. (Electrical Engineering) , Abstract: Wireless communications have experienced massive development remarkably in the past decade. Networks such as global system for mobile communications (GSM) and universal mobile telecommunication service (UMTS) has enjoyed enormous patronization, hence leading to massive mobile network congestion. The problem of network congestion is a network managerial issue that affects the Quality of Service (QoS) rendered by a network. Hence for the sustainability of the system, there is a need to fully manage the radio resources during peak and off peak periods. Call Admission Control (CAC) schemes are constantly being used extensively in managing mobile network congestion. CAC is an approach that can provide credible QoS by regulating the number of connections into the cellular network thereby allowing good use of the radio resources, reducing network congestions, interference and other QoS problems. Network resources cannot be available for all users at all times especially during busy hour traffic. Hence, these resources require effective and efficient allocation so that more subscribers are being allowed to use the network irrespective of the network traffic at a particular reference time. Mobile network congestion can be controlled by suppressing the mobile network traffic demand. The traffic demand varies proportionally with average rate of call arrival and the average duration of the calls. Hence marginalizing the average call duration will minimize traffic load, thereby reducing network congestion. Some network users due to their lifestyle of being affluent or business demands, holds on to a particular channel during long duration of calls at the detriment of other network users. CAC scheme cannot solve congestion problems due to the selfishness of these particular sets of users. Here, the combination of a channel reservation CAC scheme with Call Duration Control (CDC) scheme was proposed, in which users that have stayed over a predetermined period in the network will be served a termination notice so as to make the channel available for new users. The motive is to provide the available channels to accommodate more users. A simulation-based approach was used to model the combination of the two schemes and the combination produces good results in reducing the congestion menace. The network type deployed in the research is GSM. The result of the CAC/CDC combination schemes were compared to the result of the ordinary CAC schemes in order to verify the impact of the...
- Full Text:
- «
- ‹
- 1
- ›
- »