Applications of artificial intelligence in powerline communications in terms of noise detection and reduction : a review
- Shekoni, Olamide M., Hasan, Ali N., Shongwe, Thokozani
- Authors: Shekoni, Olamide M. , Hasan, Ali N. , Shongwe, Thokozani
- Date: 2018
- Subjects: Additive white Gaussian Noise (AWGN) , Artificial Intelligence (AI) , Impulsive Noise
- Language: English
- Type: Article
- Identifier: http://ujcontent.uj.ac.za8080/10210/364309 , http://hdl.handle.net/10210/274971 , uj:29360 , Citation: Olamide M. Shekoni, Ali N. Hasan & Thokozani Shongwe (2018) Applications of artificial intelligence in powerline communications in terms of noise detection and reduction: a review, Australian Journal of Electrical and Electronics Engineering, 15:1-2, 29-37, DOI: 10.1080/1448837X.2018.1496689
- Description: Abstract: The technology which utilizes the power line as a medium for transferring information known as powerline communication (PLC) has been in existence for over a hundred years. It is beneficial because it avoids new installation since it uses the present installation for electrical power to transmit data. However, transmission of data signals through a power line channel usually experience some challenges which include impulsive noise, frequency selectivity, high channel attenuation, low line impedance etc. The impulsive noise exhibits a power spectral density within the range of 10-15 dB higher than the background noise, which could cause a severe problem in a communication system. For better outcome of the PLC system, these noises must be detected and suppressed. This paper reviews various techniques used in detecting and mitigating the impulsive noise in PLC and suggests the application of machine learning algorithms for the detection and removal of impulsive noise in power line communication systems.
- Full Text:
- Authors: Shekoni, Olamide M. , Hasan, Ali N. , Shongwe, Thokozani
- Date: 2018
- Subjects: Additive white Gaussian Noise (AWGN) , Artificial Intelligence (AI) , Impulsive Noise
- Language: English
- Type: Article
- Identifier: http://ujcontent.uj.ac.za8080/10210/364309 , http://hdl.handle.net/10210/274971 , uj:29360 , Citation: Olamide M. Shekoni, Ali N. Hasan & Thokozani Shongwe (2018) Applications of artificial intelligence in powerline communications in terms of noise detection and reduction: a review, Australian Journal of Electrical and Electronics Engineering, 15:1-2, 29-37, DOI: 10.1080/1448837X.2018.1496689
- Description: Abstract: The technology which utilizes the power line as a medium for transferring information known as powerline communication (PLC) has been in existence for over a hundred years. It is beneficial because it avoids new installation since it uses the present installation for electrical power to transmit data. However, transmission of data signals through a power line channel usually experience some challenges which include impulsive noise, frequency selectivity, high channel attenuation, low line impedance etc. The impulsive noise exhibits a power spectral density within the range of 10-15 dB higher than the background noise, which could cause a severe problem in a communication system. For better outcome of the PLC system, these noises must be detected and suppressed. This paper reviews various techniques used in detecting and mitigating the impulsive noise in PLC and suggests the application of machine learning algorithms for the detection and removal of impulsive noise in power line communication systems.
- Full Text:
Commensurate Evaluation of Support Vector Machine and Recurrent Neural Network MPPT Algorithm for a PV system under different weather conditions
- Nkambule, Mpho Sam, Hasan, Ali N., Ahmed, Ali
- Authors: Nkambule, Mpho Sam , Hasan, Ali N. , Ahmed, Ali
- Date: 2020
- Subjects: Maximum power point tracking (MPPT) , Support Vector Machine (SVM) , Partial shading conditions (PSC)
- Language: English
- Type: Conference Proceedings
- Identifier: http://hdl.handle.net/10210/415404 , uj:35098 , Citation: Nkambule, M.S., Hasan, A.N., Ahmed, A. Commensurate Evaluation of Support Vector Machine and Recurrent Neural Network MPPT Algorithm for a PV system under different weather conditions.
- Description: Abstract: , The expeditious broadening of Photovoltaic (PV) energy has attracted the private and government precinct world-wide due to the reduction of costs and being cleaner source of energy. However, most of the maximum power point tracking (MPPT) controller are inefficient under rapid change of environmental conditions. Under partial shading conditions (PSC) MPPT controllers fail to track global maximum power point (GMPP). Therefore, it is essential to propose MPPT controller that will be able to locate GMPP. In this study, the two powerful machine learning and deep learning MPPT algorithms are used to force the PV system to operate at higher efficiency under sudden change in solar irradiance and temperature. Support Vector Machine (SVM) and Recurrent Neural Network (RNN) performances are validated and proved using MATLAB SIMULINK simulation software.
- Full Text:
- Authors: Nkambule, Mpho Sam , Hasan, Ali N. , Ahmed, Ali
- Date: 2020
- Subjects: Maximum power point tracking (MPPT) , Support Vector Machine (SVM) , Partial shading conditions (PSC)
- Language: English
- Type: Conference Proceedings
- Identifier: http://hdl.handle.net/10210/415404 , uj:35098 , Citation: Nkambule, M.S., Hasan, A.N., Ahmed, A. Commensurate Evaluation of Support Vector Machine and Recurrent Neural Network MPPT Algorithm for a PV system under different weather conditions.
- Description: Abstract: , The expeditious broadening of Photovoltaic (PV) energy has attracted the private and government precinct world-wide due to the reduction of costs and being cleaner source of energy. However, most of the maximum power point tracking (MPPT) controller are inefficient under rapid change of environmental conditions. Under partial shading conditions (PSC) MPPT controllers fail to track global maximum power point (GMPP). Therefore, it is essential to propose MPPT controller that will be able to locate GMPP. In this study, the two powerful machine learning and deep learning MPPT algorithms are used to force the PV system to operate at higher efficiency under sudden change in solar irradiance and temperature. Support Vector Machine (SVM) and Recurrent Neural Network (RNN) performances are validated and proved using MATLAB SIMULINK simulation software.
- Full Text:
Curve fitting polynomial technique compared to ANFIS technique for maximum power point tracking
- Farayola, Adedayo M., Hasan, Ali N., Ali, Ahmad
- Authors: Farayola, Adedayo M. , Hasan, Ali N. , Ali, Ahmad
- Date: 2017
- Subjects: ANFIS , Artificial Intelligence (AI) , Curve fitting polynomials
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/232998 , uj:23778 , Citation: Farayola, A.M., Hasan, A.N. & Ali, A. 2017. Curve fitting polynomial technique compared to ANFIS technique for maximum power point tracking. The 8th International Renewable Energy Congress (IREC 2017).
- Description: Abstract: In this paper, an approach of designing a fast tracking MPPT is introduced using a predicted sixth order polynomial curve fitting MPPT technique. The results are compared with the lower order polynomials curve fitting MPPT and also compared with the Artificial Neuro-Fuzzy Inference System (ANFIS) results. The polynomials were generated from an offline solar data. This work was done to validate the effect of using a higher order polynomials under various weather conditions using modified CUK DC-DC converter. Findings suggest that using the 6th order polynomial curve fitting and the ANFIS techniques could track the highest maximum power point than the lower order curve techniques.
- Full Text:
- Authors: Farayola, Adedayo M. , Hasan, Ali N. , Ali, Ahmad
- Date: 2017
- Subjects: ANFIS , Artificial Intelligence (AI) , Curve fitting polynomials
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/232998 , uj:23778 , Citation: Farayola, A.M., Hasan, A.N. & Ali, A. 2017. Curve fitting polynomial technique compared to ANFIS technique for maximum power point tracking. The 8th International Renewable Energy Congress (IREC 2017).
- Description: Abstract: In this paper, an approach of designing a fast tracking MPPT is introduced using a predicted sixth order polynomial curve fitting MPPT technique. The results are compared with the lower order polynomials curve fitting MPPT and also compared with the Artificial Neuro-Fuzzy Inference System (ANFIS) results. The polynomials were generated from an offline solar data. This work was done to validate the effect of using a higher order polynomials under various weather conditions using modified CUK DC-DC converter. Findings suggest that using the 6th order polynomial curve fitting and the ANFIS techniques could track the highest maximum power point than the lower order curve techniques.
- Full Text:
Effective use of artificial intelligence in predicting energy consumption and underground dam levels in two gold mines in South Africa
- Authors: Hasan, Ali N.
- Date: 2015-02-12
- Subjects: Artificial intelligence , Artificial intelligence - Engineering applications , Expert systems (Computer science) Electric power consumption
- Type: Thesis
- Identifier: uj:13316 , http://hdl.handle.net/10210/13332
- Description: D.Ing. (Electrical and Electronic Engineering) , The electricity shortage in South Africa has required the implementation of demand side management (DSM) projects. The DSM projects were implemented by installing energy monitoring and control systems to monitor certain mining aspects such as water pumping systems. Certain energy saving procedures and control systems followed by the mining industry are not sustainable and must be updated regularly in order to meet any changes in the water pumping system. In addition, the present water pumping, monitoring, and control system does not predict the energy consumption or the underground water dam levels. Hence, there is a need to introduce new monitoring system that could control and predict the energy consumption of the underground water pumping system and dam levels based on present and historical data. The work is undertaken to investigate the feasibility of using artificial intelligence in certain aspects of the mining industry. If successful, artificial intelligence systems could lead to improved safety and reduced electrical energy consumption, and decreased human error that could occur throughout the pump station monitoring and control process ...
- Full Text:
- Authors: Hasan, Ali N.
- Date: 2015-02-12
- Subjects: Artificial intelligence , Artificial intelligence - Engineering applications , Expert systems (Computer science) Electric power consumption
- Type: Thesis
- Identifier: uj:13316 , http://hdl.handle.net/10210/13332
- Description: D.Ing. (Electrical and Electronic Engineering) , The electricity shortage in South Africa has required the implementation of demand side management (DSM) projects. The DSM projects were implemented by installing energy monitoring and control systems to monitor certain mining aspects such as water pumping systems. Certain energy saving procedures and control systems followed by the mining industry are not sustainable and must be updated regularly in order to meet any changes in the water pumping system. In addition, the present water pumping, monitoring, and control system does not predict the energy consumption or the underground water dam levels. Hence, there is a need to introduce new monitoring system that could control and predict the energy consumption of the underground water pumping system and dam levels based on present and historical data. The work is undertaken to investigate the feasibility of using artificial intelligence in certain aspects of the mining industry. If successful, artificial intelligence systems could lead to improved safety and reduced electrical energy consumption, and decreased human error that could occur throughout the pump station monitoring and control process ...
- Full Text:
Gold mine dam levels and energy consumption classification using artificial intelligence methods
- Hasan, Ali N., Twala, Bhekisipho, Marwala, Tshilidzi
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Support vector machines , Energy monitoring , Ensembles
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16619 , uj:15789 , Citation: Hasan, A.N., Twala, B. & Marwala, T. 2013. Gold mine dam levels and energy consumption classification using artificial intelligence methods. IEEE Business Engineering and Industrial Applications Colloquium (BEIAC):623–628. , ISBN: 978-1-4673-5968-9
- Description: Abstract: In this paper a comparison between two single classifier methods (support vector machine, artificial neural network) and two ensemble methods (bagging, and boosting) is applied to a real-world mining problem. The four methods are used to classify, thus monitoring underground dam levels and underground pumps energy consumption on a doublepump station deep gold in South Africa. In terms of misclassification error, the results show support vector machines (SVM) to be more efficient for classification of underground pumps energy consumption compared to artificial neural network (ANN),...
- Full Text:
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Support vector machines , Energy monitoring , Ensembles
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16619 , uj:15789 , Citation: Hasan, A.N., Twala, B. & Marwala, T. 2013. Gold mine dam levels and energy consumption classification using artificial intelligence methods. IEEE Business Engineering and Industrial Applications Colloquium (BEIAC):623–628. , ISBN: 978-1-4673-5968-9
- Description: Abstract: In this paper a comparison between two single classifier methods (support vector machine, artificial neural network) and two ensemble methods (bagging, and boosting) is applied to a real-world mining problem. The four methods are used to classify, thus monitoring underground dam levels and underground pumps energy consumption on a doublepump station deep gold in South Africa. In terms of misclassification error, the results show support vector machines (SVM) to be more efficient for classification of underground pumps energy consumption compared to artificial neural network (ANN),...
- Full Text:
Improving load forecasting process for a power distribution network using hybrid AI and deep learning algorithms
- Motepe, Sibonelo, Hasan, Ali N., Stopforth, Riaan
- Authors: Motepe, Sibonelo , Hasan, Ali N. , Stopforth, Riaan
- Date: 2019
- Subjects: Adaptive Neuro-Fuzzy Inference Systems , Artificial Intelligence , Deep Learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/395319 , uj:32773 , Citation: Motepe, S., Hasan, A.N. & Stopforth, R. 2019. Improving load forecasting process for a power distribution network using hybrid AI and deep learning algorithms.
- Description: Abstract: Load forecasting is useful for various applications including maintenance planning. The study of load forecasting using recent state-of-the-art hybrid artificial intelligence (AI) and deep learning (DL) techniques is limited in South Africa (SA) and South African power distribution networks. This paper proposes a novel hybrid AI and DL South African distribution network load forecasting system. The system comprises of modules that handle the collection of the loading data from the field, analysis of data integrity using fuzzy logic, data preprocessing, consolidation of the loading and the temperature data, and load forecasting. The load forecasting results are then used to inform maintenance planning. The load forecasting is conducted using a hybrid AI/DL load forecasting module. A novel comparative study of recent state of the art AI techniques is also presented to determine the best technique to deploy in this module when forecasting South African power redistributing customers’ loads. The impact of the inclusion of weather parameters and loading data clean up on the load forecasting performance of a hybrid AI technique, optimally pruned extreme learning machines (OP-ELM), and a deep learning technique, long short-term memory (LSTM), is also investigated. These techniques are compared with each other and also with a commonly used powerful hybrid AI technique, adaptive neuro-fuzzy inference system (ANFIS). LSTM was found to achieve higher load forecasting accuracies than ANFIS and OP-ELM in forecasting the two distribution customers’ loads in this study. Only LSTM models’ performance improved with the inclusion of temperature in their development.
- Full Text:
- Authors: Motepe, Sibonelo , Hasan, Ali N. , Stopforth, Riaan
- Date: 2019
- Subjects: Adaptive Neuro-Fuzzy Inference Systems , Artificial Intelligence , Deep Learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/395319 , uj:32773 , Citation: Motepe, S., Hasan, A.N. & Stopforth, R. 2019. Improving load forecasting process for a power distribution network using hybrid AI and deep learning algorithms.
- Description: Abstract: Load forecasting is useful for various applications including maintenance planning. The study of load forecasting using recent state-of-the-art hybrid artificial intelligence (AI) and deep learning (DL) techniques is limited in South Africa (SA) and South African power distribution networks. This paper proposes a novel hybrid AI and DL South African distribution network load forecasting system. The system comprises of modules that handle the collection of the loading data from the field, analysis of data integrity using fuzzy logic, data preprocessing, consolidation of the loading and the temperature data, and load forecasting. The load forecasting results are then used to inform maintenance planning. The load forecasting is conducted using a hybrid AI/DL load forecasting module. A novel comparative study of recent state of the art AI techniques is also presented to determine the best technique to deploy in this module when forecasting South African power redistributing customers’ loads. The impact of the inclusion of weather parameters and loading data clean up on the load forecasting performance of a hybrid AI technique, optimally pruned extreme learning machines (OP-ELM), and a deep learning technique, long short-term memory (LSTM), is also investigated. These techniques are compared with each other and also with a commonly used powerful hybrid AI technique, adaptive neuro-fuzzy inference system (ANFIS). LSTM was found to achieve higher load forecasting accuracies than ANFIS and OP-ELM in forecasting the two distribution customers’ loads in this study. Only LSTM models’ performance improved with the inclusion of temperature in their development.
- Full Text:
Improving load forecasting process for a power distribution network using hybrid AI and deep learning algorithms
- Motepe, Sibonelo, Hasan, Ali N., Stopforth, Riaan
- Authors: Motepe, Sibonelo , Hasan, Ali N. , Stopforth, Riaan
- Date: 2019
- Subjects: Adaptive Neuro-Fuzzy Inference Systems , Artificial Intelligence , Deep Learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/404551 , uj:33931 , Citation: Motepe, S., Hasan, A.N. & Stopforth, R. 2019. Improving load forecasting process for a power distribution network using hybrid AI and deep learning algorithms.
- Description: Abstract: Load forecasting is useful for various applications including maintenance planning. The study of load forecasting using recent state-of-the-art hybrid artificial intelligence (AI) and deep learning (DL) techniques is limited in South Africa (SA) and South African power distribution networks. This paper proposes a novel hybrid AI and DL South African distribution network load forecasting system. The system comprises of modules that handle the collection of the loading data from the field, analysis of data integrity using fuzzy logic, data preprocessing, consolidation of the loading and the temperature data, and load forecasting. The load forecasting results are then used to inform maintenance planning. The load forecasting is conducted using a hybrid AI/DL load forecasting module. A novel comparative study of recent state of the art AI techniques is also presented to determine the best technique to deploy in this module when forecasting South African power redistributing customers’ loads. The impact of the inclusion of weather parameters and loading data clean up on the load forecasting performance of a hybrid AI technique, optimally pruned extreme learning machines (OP-ELM), and a deep learning technique, long short-term memory (LSTM), is also investigated. These techniques are compared with each other and also with a commonly used powerful hybrid AI technique, adaptive neuro-fuzzy inference system (ANFIS). LSTM was found to achieve higher load forecasting accuracies than ANFIS and OP-ELM in forecasting the two distribution customers’ loads in this study. Only LSTM models’ performance improved with the inclusion of temperature in their development.
- Full Text:
- Authors: Motepe, Sibonelo , Hasan, Ali N. , Stopforth, Riaan
- Date: 2019
- Subjects: Adaptive Neuro-Fuzzy Inference Systems , Artificial Intelligence , Deep Learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/404551 , uj:33931 , Citation: Motepe, S., Hasan, A.N. & Stopforth, R. 2019. Improving load forecasting process for a power distribution network using hybrid AI and deep learning algorithms.
- Description: Abstract: Load forecasting is useful for various applications including maintenance planning. The study of load forecasting using recent state-of-the-art hybrid artificial intelligence (AI) and deep learning (DL) techniques is limited in South Africa (SA) and South African power distribution networks. This paper proposes a novel hybrid AI and DL South African distribution network load forecasting system. The system comprises of modules that handle the collection of the loading data from the field, analysis of data integrity using fuzzy logic, data preprocessing, consolidation of the loading and the temperature data, and load forecasting. The load forecasting results are then used to inform maintenance planning. The load forecasting is conducted using a hybrid AI/DL load forecasting module. A novel comparative study of recent state of the art AI techniques is also presented to determine the best technique to deploy in this module when forecasting South African power redistributing customers’ loads. The impact of the inclusion of weather parameters and loading data clean up on the load forecasting performance of a hybrid AI technique, optimally pruned extreme learning machines (OP-ELM), and a deep learning technique, long short-term memory (LSTM), is also investigated. These techniques are compared with each other and also with a commonly used powerful hybrid AI technique, adaptive neuro-fuzzy inference system (ANFIS). LSTM was found to achieve higher load forecasting accuracies than ANFIS and OP-ELM in forecasting the two distribution customers’ loads in this study. Only LSTM models’ performance improved with the inclusion of temperature in their development.
- Full Text:
Impulse noise detection in OFDM communication system using machine learning ensemble algorithms
- Hasan, Ali N., Shongwe, Thokozani
- Authors: Hasan, Ali N. , Shongwe, Thokozani
- Date: 2016
- Subjects: Ensemble , prediction , Bagging
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/213466 , uj:21156 , Hasan, A.N & Shongwe, T. 2016. Impulse noise detection in OFDM communication system using machine learning ensemble algorithms.
- Description: Abstract: An impulse noise detection scheme employing machine learning (ML) algorithm in Orthogonal Frequency Division Multiplexing (OFDM) is in-vestigated. Four powerful ML's multi-classifiers (ensemble) algorithms (Boost-ing (Bos), Bagging (Bag), Stacking (Stack) and Random Forest (RF)) were used at the receiver side of the OFDM system to detect if the received noisy signal contained impulse noise or not. The ML's ensembles were trained with the Middleton Class A noise model which was the noise model used in the OFDM system. In terms of prediction accuracy, the results obtained from the four ML’s Ensembles techniques show that ML can be used to predict impulse noise in communication systems, in particular OFDM.
- Full Text:
- Authors: Hasan, Ali N. , Shongwe, Thokozani
- Date: 2016
- Subjects: Ensemble , prediction , Bagging
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/213466 , uj:21156 , Hasan, A.N & Shongwe, T. 2016. Impulse noise detection in OFDM communication system using machine learning ensemble algorithms.
- Description: Abstract: An impulse noise detection scheme employing machine learning (ML) algorithm in Orthogonal Frequency Division Multiplexing (OFDM) is in-vestigated. Four powerful ML's multi-classifiers (ensemble) algorithms (Boost-ing (Bos), Bagging (Bag), Stacking (Stack) and Random Forest (RF)) were used at the receiver side of the OFDM system to detect if the received noisy signal contained impulse noise or not. The ML's ensembles were trained with the Middleton Class A noise model which was the noise model used in the OFDM system. In terms of prediction accuracy, the results obtained from the four ML’s Ensembles techniques show that ML can be used to predict impulse noise in communication systems, in particular OFDM.
- Full Text:
Mitigation of impulse noise in powerline systems using ANFIS technique
- Shekoni, Olamide M., Hasan, Ali N., Shongwe, T.
- Authors: Shekoni, Olamide M. , Hasan, Ali N. , Shongwe, T.
- Date: 2018
- Subjects: Machine learning , Orthogonal frequency division multiplexing , Additive white Gaussian noise
- Language: English
- Type: Conference proceeding
- Identifier: http://hdl.handle.net/10210/289914 , uj:31464 , Citation: Shekoni, O.M., Hasan, A.N. & Shongwe, T. 2018. Mitigation of impulse noise in powerline systems using ANFIS technique.
- Description: Abstract: The use of OFDM channel for the transmission of data in power line communication (PLC) system has been of several importance to technology development. However, during transmission, the OFDM channel is greatly disturbed by impulse noise that causes a wrong information to be received. Several techniques such as iteration, coding, clipping and nulling methods have been used to lessen the upshot of impulse noise in OFDM channel. However, these techniques still suffer some drawbacks and require a high signal-to-noise (SNR) power for high performance. This paper presents an advanced use of artificial neuro-fuzzy inference system (ANFIS) technique in removing the complete impulse noise and some of the additive white Gaussian noise (AWGN) that were mixed with the transmitted data in an OFDM channel and using the minimum SNR power. Obtained results propose that ANFIS technique can be used to mitigate impulse noise from a powerline communication channel.
- Full Text:
- Authors: Shekoni, Olamide M. , Hasan, Ali N. , Shongwe, T.
- Date: 2018
- Subjects: Machine learning , Orthogonal frequency division multiplexing , Additive white Gaussian noise
- Language: English
- Type: Conference proceeding
- Identifier: http://hdl.handle.net/10210/289914 , uj:31464 , Citation: Shekoni, O.M., Hasan, A.N. & Shongwe, T. 2018. Mitigation of impulse noise in powerline systems using ANFIS technique.
- Description: Abstract: The use of OFDM channel for the transmission of data in power line communication (PLC) system has been of several importance to technology development. However, during transmission, the OFDM channel is greatly disturbed by impulse noise that causes a wrong information to be received. Several techniques such as iteration, coding, clipping and nulling methods have been used to lessen the upshot of impulse noise in OFDM channel. However, these techniques still suffer some drawbacks and require a high signal-to-noise (SNR) power for high performance. This paper presents an advanced use of artificial neuro-fuzzy inference system (ANFIS) technique in removing the complete impulse noise and some of the additive white Gaussian noise (AWGN) that were mixed with the transmitted data in an OFDM channel and using the minimum SNR power. Obtained results propose that ANFIS technique can be used to mitigate impulse noise from a powerline communication channel.
- Full Text:
Mitigation of impulsive noise in OFDM channels using ANN technique
- Shekoni, Olamide M., Hasan, Ali N., Shongwe, T.
- Authors: Shekoni, Olamide M. , Hasan, Ali N. , Shongwe, T.
- Date: 2018
- Subjects: Artificial Neural Network , Bayesian regularization , Bit error rate, Binary Phase Shift Keying
- Language: English
- Type: Conference proceeding
- Identifier: http://ujcontent.uj.ac.za8080/10210/373743 , http://hdl.handle.net/10210/289921 , uj:31465 , Citation: Shekoni, O.M., Hasan, A.N. & Shongwe, T. 2018. Mitigation of impulsive noise in OFDM channels using ANN technique.
- Description: Abstract: Orthogonal frequency division multiplexer (OFDM) is a recent modulation scheme used to transmit signals across power line communication (PLC) channel due to its robustness against some known PLC problems. However, this scheme is greatly affected by the impulsive noise (IN) and often causes corruption with the transmitted bits. Different impulsive noise error correcting methods have been introduced and used to remove impulsive noise in OFDM systems. However, these techniques suffer some limitations and require much signal to noise ratio (SNR) power to operate. In this paper, an approach of designing an effective impulsive-noise error-correcting technique was introduced using three-known artificial neural network techniques (Levenberg-Marquardt, Scaled conjugate gradient, and Bayesian regularization). Findings suggest that both Bayesian regularization and Levenberg-Marquardt ANN techniques can be used to effectively remove the impulsive noise present in an OFDM channel and using the least SNR power.
- Full Text:
- Authors: Shekoni, Olamide M. , Hasan, Ali N. , Shongwe, T.
- Date: 2018
- Subjects: Artificial Neural Network , Bayesian regularization , Bit error rate, Binary Phase Shift Keying
- Language: English
- Type: Conference proceeding
- Identifier: http://ujcontent.uj.ac.za8080/10210/373743 , http://hdl.handle.net/10210/289921 , uj:31465 , Citation: Shekoni, O.M., Hasan, A.N. & Shongwe, T. 2018. Mitigation of impulsive noise in OFDM channels using ANN technique.
- Description: Abstract: Orthogonal frequency division multiplexer (OFDM) is a recent modulation scheme used to transmit signals across power line communication (PLC) channel due to its robustness against some known PLC problems. However, this scheme is greatly affected by the impulsive noise (IN) and often causes corruption with the transmitted bits. Different impulsive noise error correcting methods have been introduced and used to remove impulsive noise in OFDM systems. However, these techniques suffer some limitations and require much signal to noise ratio (SNR) power to operate. In this paper, an approach of designing an effective impulsive-noise error-correcting technique was introduced using three-known artificial neural network techniques (Levenberg-Marquardt, Scaled conjugate gradient, and Bayesian regularization). Findings suggest that both Bayesian regularization and Levenberg-Marquardt ANN techniques can be used to effectively remove the impulsive noise present in an OFDM channel and using the least SNR power.
- Full Text:
MPPT under partial shading conditions based on perturb & observe and incremental conductance
- Nkambule, Mpho Sam, Hasan, Ali N., Ahmed, Ali
- Authors: Nkambule, Mpho Sam , Hasan, Ali N. , Ahmed, Ali
- Date: 2020
- Subjects: Maximum power point tracking (MPPT) , Perturb and Observe , Incremental Conductance
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/415373 , uj:35094 , Citation: Nkambule, M.S., Ahmed, A., Hasan, A.N. MPPT under partial shading conditions based on perturb & observe and incremental conductance.
- Description: Abstract: , Maximum power point tracking (MPPT) under uniform and different weather conditions is the main challenge in photovoltaic (PV) system. Partial shaded conditions (PSC) causes several power peaks on a P-V curve. This paper compares two powerful MPPT algorithm of Perturb & Observe (P&O) and Incremental Conductance (INC) under PSC. The PV system is developed using MATLAB simulation software with the Boost DC/DC converter interconnected. The proposed algorithms are tested under standard test and different weather conditions to prove their performance looking at their tracking speed, convergence and the settling time around the MPP.
- Full Text:
- Authors: Nkambule, Mpho Sam , Hasan, Ali N. , Ahmed, Ali
- Date: 2020
- Subjects: Maximum power point tracking (MPPT) , Perturb and Observe , Incremental Conductance
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/415373 , uj:35094 , Citation: Nkambule, M.S., Ahmed, A., Hasan, A.N. MPPT under partial shading conditions based on perturb & observe and incremental conductance.
- Description: Abstract: , Maximum power point tracking (MPPT) under uniform and different weather conditions is the main challenge in photovoltaic (PV) system. Partial shaded conditions (PSC) causes several power peaks on a P-V curve. This paper compares two powerful MPPT algorithm of Perturb & Observe (P&O) and Incremental Conductance (INC) under PSC. The PV system is developed using MATLAB simulation software with the Boost DC/DC converter interconnected. The proposed algorithms are tested under standard test and different weather conditions to prove their performance looking at their tracking speed, convergence and the settling time around the MPP.
- Full Text:
Optimization of PV Model using Fuzzy- Neural Network for DC-DC converter systems
- Authors: Ali, Ahmed , Hasan, Ali N.
- Date: 2018
- Subjects: Fuzzy Neural Network , Maximum power point tracking , Photo- voltaic
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/274566 , uj:29300 , Citation: Ali, A. & Hasan, A.N. 2018. Optimization of PV Model using Fuzzy- Neural Network for DC-DC converter systems.
- Description: Abstract: Due to the large demand on energy, energy sources, as well as the problems of the environment such as the dynamic weather conditions. Hence the world researchers nowadays are moving toward using solar energy because it gives different advantages over the traditional energy sources such as low maintenance costs, eternal sun energy, and the lack of revival of the gases of green houses. As a result, the photo- voltaic (PV) systems' power will be reduced. Under different weather conditions, maximizing the power point tracking (MPPT) is an important part to improve the solar systems power. In this paper, we introduce the neural network approaches for the PV systems. This paper also presents a novel application of Fuzzy Neural Network (FNN) in modeling a PV. The photovoltaic system model is designed with the use of MATLAB/SIMULINK software program with the connection of a DC-DC boost converter, a Maximum Power Point Tracking (MPPT) controller, a one-phase Voltage Source Converter (VSC) and a three-level bridge. The MPPT controller is used to cover the need for advanced controller that can detect the maximum power point in solar cell systems that have unstable current and voltage and keep the resultant power per cost low.
- Full Text:
- Authors: Ali, Ahmed , Hasan, Ali N.
- Date: 2018
- Subjects: Fuzzy Neural Network , Maximum power point tracking , Photo- voltaic
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/274566 , uj:29300 , Citation: Ali, A. & Hasan, A.N. 2018. Optimization of PV Model using Fuzzy- Neural Network for DC-DC converter systems.
- Description: Abstract: Due to the large demand on energy, energy sources, as well as the problems of the environment such as the dynamic weather conditions. Hence the world researchers nowadays are moving toward using solar energy because it gives different advantages over the traditional energy sources such as low maintenance costs, eternal sun energy, and the lack of revival of the gases of green houses. As a result, the photo- voltaic (PV) systems' power will be reduced. Under different weather conditions, maximizing the power point tracking (MPPT) is an important part to improve the solar systems power. In this paper, we introduce the neural network approaches for the PV systems. This paper also presents a novel application of Fuzzy Neural Network (FNN) in modeling a PV. The photovoltaic system model is designed with the use of MATLAB/SIMULINK software program with the connection of a DC-DC boost converter, a Maximum Power Point Tracking (MPPT) controller, a one-phase Voltage Source Converter (VSC) and a three-level bridge. The MPPT controller is used to cover the need for advanced controller that can detect the maximum power point in solar cell systems that have unstable current and voltage and keep the resultant power per cost low.
- Full Text:
Predicting mine dam levels and energy consumption using artificial intelligence methods
- Hasan, Ali N., Twala, Bhekisipho, Marwala, Tshilidzi
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Machine learning algorithms , De-watering system , Energy consumption
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16857 , uj:15816 , Citation: Hasan, A.N., Twala, B. & T Marwala. 2013. Predicting mine dam levels and energy consumption using artificial intelligence methods. IEEE Computational Intelligence for Engineering Solutions (CIES), Singapore:171-175. DOI: 10.1109/cies.2013.6611745
- Description: Abstract: Four machine learning algorithms (artificial neural networks, a naive Bayes' classifier, a support vector machines and decision trees) wwere applied for a single pump station mine to monitor and predict the dam levels and energy consumption.
- Full Text:
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Machine learning algorithms , De-watering system , Energy consumption
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16857 , uj:15816 , Citation: Hasan, A.N., Twala, B. & T Marwala. 2013. Predicting mine dam levels and energy consumption using artificial intelligence methods. IEEE Computational Intelligence for Engineering Solutions (CIES), Singapore:171-175. DOI: 10.1109/cies.2013.6611745
- Description: Abstract: Four machine learning algorithms (artificial neural networks, a naive Bayes' classifier, a support vector machines and decision trees) wwere applied for a single pump station mine to monitor and predict the dam levels and energy consumption.
- Full Text:
Use of MPPT techniques to reduce the energy pay-back time in PV systems
- Farayola, Adedayo M., Hasan, Ali N., Ali, Ahmed
- Authors: Farayola, Adedayo M. , Hasan, Ali N. , Ali, Ahmed
- Date: 2018
- Subjects: Artificial Intelligence (AI) , ANFIS , ANN
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/274581 , uj:29302 , Citation: Farayola, A.M., Hasan, A.N. & Ali, A. 2018. Use of MPPT techniques to reduce the energy pay-back time in PV systems.
- Description: Abstract: Photovoltaic (PV) energy is a free-energy that is used as an alternative to fossil fuel energy. However, PV system without maximum power point tracking (MPPT) produces a low, unstable power and with a long energy pay-back time. This paper presents an innovative artificial neuro-fuzzy inference system (ANFIS) MPPT technique that could extract maximum power from a complete PV system and with a lessened EPBT. To confirm the effectiveness of the ANFIS algorithm, its result was compared with the results of PV system using Perturb&Observe (P&O) technique, non-MPPT technique, combination of artificial neural network and support vector machine as ANN-SVM technique and using Pretoria city weather data as case studies. Results show that ANFIS-MPPT yielded the best result and with the lowest EPBT.
- Full Text:
- Authors: Farayola, Adedayo M. , Hasan, Ali N. , Ali, Ahmed
- Date: 2018
- Subjects: Artificial Intelligence (AI) , ANFIS , ANN
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/274581 , uj:29302 , Citation: Farayola, A.M., Hasan, A.N. & Ali, A. 2018. Use of MPPT techniques to reduce the energy pay-back time in PV systems.
- Description: Abstract: Photovoltaic (PV) energy is a free-energy that is used as an alternative to fossil fuel energy. However, PV system without maximum power point tracking (MPPT) produces a low, unstable power and with a long energy pay-back time. This paper presents an innovative artificial neuro-fuzzy inference system (ANFIS) MPPT technique that could extract maximum power from a complete PV system and with a lessened EPBT. To confirm the effectiveness of the ANFIS algorithm, its result was compared with the results of PV system using Perturb&Observe (P&O) technique, non-MPPT technique, combination of artificial neural network and support vector machine as ANN-SVM technique and using Pretoria city weather data as case studies. Results show that ANFIS-MPPT yielded the best result and with the lowest EPBT.
- Full Text:
- «
- ‹
- 1
- ›
- »