Pub Date : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4931-4941
N. Watjanatepin, Khanittha Wannakam, Paiboon Kiatsookkanatorn, C. Boonmee, Patcharanan Sritanauthaikorn
A phosphor-converted light-emitting diode (LED) solar simulator is an illuminance device that produced irradiance intensity and spectral close to the sunlight. It is determined as spectral mismatch, non-uniformity of irradiance, and temporal instability. This paper has improved the LED solar simulator (LSS) system to have a spectral distribution consistent with the AM1.5G spectrum at 100%. It was developed as a new prototype to have the AAA class spectral characteristics, time instability, and inconsistency according to IEC 60904-9. The results showed that an optimal approach was to use phosphor-converted natural white LED (pc-nWLED), combining a monochromatic near-infrared (NIR) (730, 800, 850, 940, and 1,000 nm) as well as the proposed LSS system capable of generating 1,000 W/m2 irradiation over the test plane of 125×125 mm and operated continuously in a constant temperature LED state for at least 2 hours, therefore suitable for demonstration of solar cell features under standard test condition (STC) in the laboratory.
{"title":"Improved spectral mismatch and performance of a phosphor-converted light-emitting diode solar simulator","authors":"N. Watjanatepin, Khanittha Wannakam, Paiboon Kiatsookkanatorn, C. Boonmee, Patcharanan Sritanauthaikorn","doi":"10.11591/ijece.v13i5.pp4931-4941","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4931-4941","url":null,"abstract":"A phosphor-converted light-emitting diode (LED) solar simulator is an illuminance device that produced irradiance intensity and spectral close to the sunlight. It is determined as spectral mismatch, non-uniformity of irradiance, and temporal instability. This paper has improved the LED solar simulator (LSS) system to have a spectral distribution consistent with the AM1.5G spectrum at 100%. It was developed as a new prototype to have the AAA class spectral characteristics, time instability, and inconsistency according to IEC 60904-9. The results showed that an optimal approach was to use phosphor-converted natural white LED (pc-nWLED), combining a monochromatic near-infrared (NIR) (730, 800, 850, 940, and 1,000 nm) as well as the proposed LSS system capable of generating 1,000 W/m2 irradiation over the test plane of 125×125 mm and operated continuously in a constant temperature LED state for at least 2 hours, therefore suitable for demonstration of solar cell features under standard test condition (STC) in the laboratory.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44300668","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4909-4918
Ali Tarraq, F. El Mariami, Abdelaziz Belfqih
This paper investigates, for the first time, the accuracy of normalized power curves (NPCs), often used to incorporate uncertainties related to wind and solar power generation, when integrating renewable distributed generation (RDG), in the radial distribution system (RDS). In this regard, the present study proposes a comprehensive, simple, and more accurate model, for estimating the expected hourly solar and wind power generation, by adopting a purely probabilistic approach. Actually, in the case of solar RDG, the proposed model allows the calculation of the expected power, without going through a specific probability density function (PDF). The validation of this model is performed through a case study comparing between the classical and the proposed model. The results show that the proposed model generates seasonal NPCs in a less complex and more relevant way compared to the discrete classical model. Furthermore, the margin of error of the classical model for estimating the expected supplied energy is about 12.6% for the photovoltaic (PV) system, and 9% for the wind turbine (WT) system. This introduces an offset of about 10% when calculating the total active losses of the RDS after two RDGs integration.
{"title":"New typical power curves generation approach for accurate renewable distributed generation placement in the radial distribution system","authors":"Ali Tarraq, F. El Mariami, Abdelaziz Belfqih","doi":"10.11591/ijece.v13i5.pp4909-4918","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4909-4918","url":null,"abstract":"This paper investigates, for the first time, the accuracy of normalized power curves (NPCs), often used to incorporate uncertainties related to wind and solar power generation, when integrating renewable distributed generation (RDG), in the radial distribution system (RDS). In this regard, the present study proposes a comprehensive, simple, and more accurate model, for estimating the expected hourly solar and wind power generation, by adopting a purely probabilistic approach. Actually, in the case of solar RDG, the proposed model allows the calculation of the expected power, without going through a specific probability density function (PDF). The validation of this model is performed through a case study comparing between the classical and the proposed model. The results show that the proposed model generates seasonal NPCs in a less complex and more relevant way compared to the discrete classical model. Furthermore, the margin of error of the classical model for estimating the expected supplied energy is about 12.6% for the photovoltaic (PV) system, and 9% for the wind turbine (WT) system. This introduces an offset of about 10% when calculating the total active losses of the RDS after two RDGs integration.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46629364","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5617-5631
Arkan Hammoodi Hasan Kabla, Mohammed Anbar, Shady Hamouda, A. A. Bahashwan, Taief Alaa Al-Amiedy, I. Hasbullah, S. Faisal
The rapid development of information and communication technologies has increased the demand for internet-facing devices that require publicly accessible internet protocol (IP) addresses, resulting in the depletion of internet protocol version 4 (IPv4) address space. As a result, internet protocol version 6 (IPv6) was designed to address this issue. However, IPv6 is still not widely used because of security concerns. An intrusion detection system (IDS) is one example of a security mechanism used to secure networks. Lately, the use of machine learning (ML) or deep learning (DL) detection models in IDSs is gaining popularity due to their ability to detect threats on IPv6 networks accurately. However, there is an apparent lack of studies that review ML and DL in IDS. Even the existing reviews of ML and DL fail to compare those techniques. Thus, this paper comprehensively elucidates ML and DL techniques and IPv6-based distributed denial of service (DDoS) attacks. Additionally, this paper includes a qualitative comparison with other related works. Moreover, this work also thoroughly reviews the existing ML and DL-based IDSs for detecting IPv6 and IPv4 attacks. Lastly, researchers could use this review as a guide in the future to improve their work on DL and ML-based IDS.
{"title":"Machine and deep learning techniques for detecting internet protocol version six attacks: a review","authors":"Arkan Hammoodi Hasan Kabla, Mohammed Anbar, Shady Hamouda, A. A. Bahashwan, Taief Alaa Al-Amiedy, I. Hasbullah, S. Faisal","doi":"10.11591/ijece.v13i5.pp5617-5631","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5617-5631","url":null,"abstract":"The rapid development of information and communication technologies has increased the demand for internet-facing devices that require publicly accessible internet protocol (IP) addresses, resulting in the depletion of internet protocol version 4 (IPv4) address space. As a result, internet protocol version 6 (IPv6) was designed to address this issue. However, IPv6 is still not widely used because of security concerns. An intrusion detection system (IDS) is one example of a security mechanism used to secure networks. Lately, the use of machine learning (ML) or deep learning (DL) detection models in IDSs is gaining popularity due to their ability to detect threats on IPv6 networks accurately. However, there is an apparent lack of studies that review ML and DL in IDS. Even the existing reviews of ML and DL fail to compare those techniques. Thus, this paper comprehensively elucidates ML and DL techniques and IPv6-based distributed denial of service (DDoS) attacks. Additionally, this paper includes a qualitative comparison with other related works. Moreover, this work also thoroughly reviews the existing ML and DL-based IDSs for detecting IPv6 and IPv4 attacks. Lastly, researchers could use this review as a guide in the future to improve their work on DL and ML-based IDS.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43072474","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5147-5155
Anisatul Munawaroh, E. Jamzuri
This research study aims to develop automatic optical inspection (AOI) for detecting keycaps misplacement on the keyboard. The AOI hardware has been designed using an industrial camera with an additional mechanical jig and lighting system. Optical character recognition (OCR) using the Tesseract OCR engine is the proposed method to detect keycaps misplacement. In addition, captured images were cropped using a predefined region of interest (ROI) during the setup. Subsequently, the cropped ROIs were processed to acquire binary images. Furthermore, Tesseract processed these binary images to recognize the text on the keycaps. Keycaps misplacement could be identified by comparing the predicted text with the actual text on the golden sample. Experiments on 25 defects and 25 non-defected samples provided a classification accuracy of 97.34%, a precision of 100%, and a recall of 90.70%. Meanwhile, the character error rate (CER) obtained from the test on a total of 57 characters provided a performance of 10.53%. This outcome has implications for developing AOI for various keyboard products. In addition, the precision level of 100% signifies that the proposed method always offers correct results in detecting product defects. Such outcomes are critical in industrial applications to prevent defective products from circulating in the market.
{"title":"Automatic optical inspection for detecting keycaps misplacement using Tesseract optical character recognition","authors":"Anisatul Munawaroh, E. Jamzuri","doi":"10.11591/ijece.v13i5.pp5147-5155","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5147-5155","url":null,"abstract":"This research study aims to develop automatic optical inspection (AOI) for detecting keycaps misplacement on the keyboard. The AOI hardware has been designed using an industrial camera with an additional mechanical jig and lighting system. Optical character recognition (OCR) using the Tesseract OCR engine is the proposed method to detect keycaps misplacement. In addition, captured images were cropped using a predefined region of interest (ROI) during the setup. Subsequently, the cropped ROIs were processed to acquire binary images. Furthermore, Tesseract processed these binary images to recognize the text on the keycaps. Keycaps misplacement could be identified by comparing the predicted text with the actual text on the golden sample. Experiments on 25 defects and 25 non-defected samples provided a classification accuracy of 97.34%, a precision of 100%, and a recall of 90.70%. Meanwhile, the character error rate (CER) obtained from the test on a total of 57 characters provided a performance of 10.53%. This outcome has implications for developing AOI for various keyboard products. In addition, the precision level of 100% signifies that the proposed method always offers correct results in detecting product defects. Such outcomes are critical in industrial applications to prevent defective products from circulating in the market.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41465631","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5653-5661
T. Swe, Naw Lay Wah
Many social media emerged and provided services during these years. Most people, especially in Myanmar, use them to express their emotions or moods, learn subjects, sell products, read up-to-date news, and communicate with each other. Emotion detection on social users makes critical tasks in the opinion mining and sentiment analysis. This paper presents the emotion detection system on social media (Facebook) user status or post written in Myanmar (Burmese) language. Before the emotion detection process, the user posts are pre-processed under segmentation, stemming, part-of-speech (POS) tagging, and stop word removal. The system then uses our preconstructed Myanmar word-emotion Lexicon, M-Lexicon, to extract the emotion words from the segmented POS post. The system provides six types of emotion such as surprise, disgust, fear, anger, sadness, and happiness. The system applies naïve Bayes (NB) emotion classifier to examine the emotion in the case of more than two words with different emotion values are extracted. The classifiers also classify the emotion of the users on their posts. The experiment shows that the system can detect 85% accuracy in NB based emotion detection while 86% in recurrent neural network (RNN).
{"title":"Emotion detection on social media status in Myanmar language","authors":"T. Swe, Naw Lay Wah","doi":"10.11591/ijece.v13i5.pp5653-5661","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5653-5661","url":null,"abstract":"Many social media emerged and provided services during these years. Most people, especially in Myanmar, use them to express their emotions or moods, learn subjects, sell products, read up-to-date news, and communicate with each other. Emotion detection on social users makes critical tasks in the opinion mining and sentiment analysis. This paper presents the emotion detection system on social media (Facebook) user status or post written in Myanmar (Burmese) language. Before the emotion detection process, the user posts are pre-processed under segmentation, stemming, part-of-speech (POS) tagging, and stop word removal. The system then uses our preconstructed Myanmar word-emotion Lexicon, M-Lexicon, to extract the emotion words from the segmented POS post. The system provides six types of emotion such as surprise, disgust, fear, anger, sadness, and happiness. The system applies naïve Bayes (NB) emotion classifier to examine the emotion in the case of more than two words with different emotion values are extracted. The classifiers also classify the emotion of the users on their posts. The experiment shows that the system can detect 85% accuracy in NB based emotion detection while 86% in recurrent neural network (RNN).","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48915707","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5717-5726
Muhamad Hafiz Masran, Syariza Abdul-Rahman, W. Ariffin
Nowadays, a significant number of researchers are focusing on utilizing soft computing approaches to address the issue of scheduling in applications concerned with hazardous waste management. In Malaysia, there is thoughtless awareness of the management of hazardous waste, even though the production of wastes in hazardous domains at the industrial and domestic levels has been rising lately. According to previous research findings, the location routing problem (LRP) can be designated as one of the models closer to the actual situation, evaluating the most suitable and optimal location for establishing facilities and utilizing transportation for pick-up and distribution. Recent studies have focused on enhancing the LRP model, and its methodologies approach to solve the waste management problem in hazardous domains. In this paper, a comprehensive review of the better promising and practicable mathematical model of LRP and its methodology approach is discussed, as well as an analysis of the publishing pattern and the trend of research over the preceding five years and more, as retrieved from the web of science (WoS) database. In conclusion, this research is significant in ensuring the effectiveness of reliable mathematical model development and suitable methodologies in the future for solving hazardous waste management problems.
目前，大量的研究人员正在关注利用软计算方法来解决与危险废物管理有关的应用程序中的调度问题。在马来西亚，人们对危险废物的管理缺乏深思熟虑的认识，尽管工业和家庭两级在危险领域产生的废物最近一直在增加。根据前人的研究成果，定位路径问题(location routing problem, LRP)可以被定义为一种更接近实际情况的模型，用于评估最适合和最优的位置，以建立设施并利用交通进行取货和配送。近年来的研究主要集中在改进LRP模型及其方法来解决危险领域的废物管理问题。本文从web of science (WoS)数据库中检索了LRP的研究成果，对LRP的数学模型及其方法论进行了综述，并分析了近5年的发表模式和研究趋势。总之，这项研究对于确保可靠的数学模型开发和未来解决危险废物管理问题的适当方法的有效性具有重要意义。
{"title":"Soft computing for hazardous waste routing in Malaysia: a review","authors":"Muhamad Hafiz Masran, Syariza Abdul-Rahman, W. Ariffin","doi":"10.11591/ijece.v13i5.pp5717-5726","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5717-5726","url":null,"abstract":"Nowadays, a significant number of researchers are focusing on utilizing soft computing approaches to address the issue of scheduling in applications concerned with hazardous waste management. In Malaysia, there is thoughtless awareness of the management of hazardous waste, even though the production of wastes in hazardous domains at the industrial and domestic levels has been rising lately. According to previous research findings, the location routing problem (LRP) can be designated as one of the models closer to the actual situation, evaluating the most suitable and optimal location for establishing facilities and utilizing transportation for pick-up and distribution. Recent studies have focused on enhancing the LRP model, and its methodologies approach to solve the waste management problem in hazardous domains. In this paper, a comprehensive review of the better promising and practicable mathematical model of LRP and its methodology approach is discussed, as well as an analysis of the publishing pattern and the trend of research over the preceding five years and more, as retrieved from the web of science (WoS) database. In conclusion, this research is significant in ensuring the effectiveness of reliable mathematical model development and suitable methodologies in the future for solving hazardous waste management problems.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47869738","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5101-5108
S. Prongnuch, S. Sitjongsataporn, T. Wiangtong
In this paper, diffusion strategies used by QR-decomposition based on recursive least squares algorithm (DQR-RLS) and the sign version of DQR-RLS algorithm (DQR-sRLS) are introduced for distributed networks. In terms of the QR-decomposition method and Cholesky factorization, a modified Kalman vector is given adaptively with the help of unitary rotation that can decrease the complexity from inverse autocorrelation matrix to vector. According to the diffusion strategies, combine-then-adapt (CTA) and adapt-then-combine (ATC) based on DQR-RLS and DQR-sRLS algorithms are proposed with the combination and adaptation steps. To minimize the cost function, diffused versions of CTA-DQR-RLS, ATC-DQR-RLS, CTA-DQR-sRLS and ATC-DiQR-sRLS algorithms are compared. Simulation results depict that the proposed DQR-RLS-based and DQR-sRLS-based algorithms can clearly achieve the better performance than the standard combine-then-adapt-diffusion RLS (CTA-DRLS) and ATC-DRLS mechanisms.
{"title":"Diffusion recursive least squares algorithm based on triangular decomposition","authors":"S. Prongnuch, S. Sitjongsataporn, T. Wiangtong","doi":"10.11591/ijece.v13i5.pp5101-5108","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5101-5108","url":null,"abstract":"In this paper, diffusion strategies used by QR-decomposition based on recursive least squares algorithm (DQR-RLS) and the sign version of DQR-RLS algorithm (DQR-sRLS) are introduced for distributed networks. In terms of the QR-decomposition method and Cholesky factorization, a modified Kalman vector is given adaptively with the help of unitary rotation that can decrease the complexity from inverse autocorrelation matrix to vector. According to the diffusion strategies, combine-then-adapt (CTA) and adapt-then-combine (ATC) based on DQR-RLS and DQR-sRLS algorithms are proposed with the combination and adaptation steps. To minimize the cost function, diffused versions of CTA-DQR-RLS, ATC-DQR-RLS, CTA-DQR-sRLS and ATC-DiQR-sRLS algorithms are compared. Simulation results depict that the proposed DQR-RLS-based and DQR-sRLS-based algorithms can clearly achieve the better performance than the standard combine-then-adapt-diffusion RLS (CTA-DRLS) and ATC-DRLS mechanisms.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48062944","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4856-4867
J. Guillot, Diego Restrepo Leal, Carlos Robles-Algarín, I. Oliveros, P. A. Niño-Suárez
The monitoring of wind installations is key for predicting their future behavior, due to the strong dependence on weather conditions and the stochastic nature of the wind. However, in some places, in situ measurements are not always available. In this paper, active power predictions for the city of Santa Marta-Colombia using a nonlinear autoregressive exogenous model (NARX) network were performed. The network was trained with a reliable dataset from a wind farm located in Turkey, because the meteorological data from the city of Santa Marta are unavailable or unreliable on certain dates. Three training and testing cases were designed, with different input variables and varying the network target between active power and wind speed. The dataset was obtained from the Kaggle platform, and is made up of five variables: date, active power, wind speed, theoretical power, and wind direction; each with 50,530 samples, which were preprocessed and, in some cases, normalized, to facilitate the neural network learning. For the training, testing and validation processes, a correlation coefficient of 0.9589 was obtained for the best scenario with the data from Turkey, while the best correlation coefficient for the data from Santa Marta was 0.8537.
{"title":"Wind power prediction using a nonlinear autoregressive exogenous model network: the case of Santa Marta, Colombia","authors":"J. Guillot, Diego Restrepo Leal, Carlos Robles-Algarín, I. Oliveros, P. A. Niño-Suárez","doi":"10.11591/ijece.v13i5.pp4856-4867","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4856-4867","url":null,"abstract":"The monitoring of wind installations is key for predicting their future behavior, due to the strong dependence on weather conditions and the stochastic nature of the wind. However, in some places, in situ measurements are not always available. In this paper, active power predictions for the city of Santa Marta-Colombia using a nonlinear autoregressive exogenous model (NARX) network were performed. The network was trained with a reliable dataset from a wind farm located in Turkey, because the meteorological data from the city of Santa Marta are unavailable or unreliable on certain dates. Three training and testing cases were designed, with different input variables and varying the network target between active power and wind speed. The dataset was obtained from the Kaggle platform, and is made up of five variables: date, active power, wind speed, theoretical power, and wind direction; each with 50,530 samples, which were preprocessed and, in some cases, normalized, to facilitate the neural network learning. For the training, testing and validation processes, a correlation coefficient of 0.9589 was obtained for the best scenario with the data from Turkey, while the best correlation coefficient for the data from Santa Marta was 0.8537.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48264470","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4810-4823
Ali Tarraq, F. El Mariami, Abdelaziz Belfqih
This paper introduces a new approach based on a chaotic strategy and a neural network algorithm (NNA), called chaotic-based NNA (CNNA), to solve the optimal distributed generation allocation (ODGA), in the radial distribution system (RDS). This consists of determining the optimal locations and sizes of one or several distributed generations (DGs) to be inserted into the RDS to minimize one or multiple objectives while meeting a set of security limits. The robustness of the proposed method is demonstrated by applying it to two different typical RDSs, namely IEEE 33-bus and 69-bus. In this regard, simulations are performed for three DGs in the cases of unity power factor (UPF) and optimal power factor (OPF), considering single and multi-objective optimization, by minimizing the total active losses and improving the voltage profile, voltage deviation (VD) and voltage stability index (VSI). Compared to its original version and recently reported methods, the CNNA solutions are more competitive without increasing the complexity of the optimization algorithm, especially when the RDS size and problem dimension are extended.
{"title":"Multi-objective distributed generation integration in radial distribution system using modified neural network algorithm","authors":"Ali Tarraq, F. El Mariami, Abdelaziz Belfqih","doi":"10.11591/ijece.v13i5.pp4810-4823","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4810-4823","url":null,"abstract":"This paper introduces a new approach based on a chaotic strategy and a neural network algorithm (NNA), called chaotic-based NNA (CNNA), to solve the optimal distributed generation allocation (ODGA), in the radial distribution system (RDS). This consists of determining the optimal locations and sizes of one or several distributed generations (DGs) to be inserted into the RDS to minimize one or multiple objectives while meeting a set of security limits. The robustness of the proposed method is demonstrated by applying it to two different typical RDSs, namely IEEE 33-bus and 69-bus. In this regard, simulations are performed for three DGs in the cases of unity power factor (UPF) and optimal power factor (OPF), considering single and multi-objective optimization, by minimizing the total active losses and improving the voltage profile, voltage deviation (VD) and voltage stability index (VSI). Compared to its original version and recently reported methods, the CNNA solutions are more competitive without increasing the complexity of the optimization algorithm, especially when the RDS size and problem dimension are extended.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47093164","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4845-4855
Jose Galarza, David Condezo
Meteorological and electrical measurements using predictive computational techniques have been used in the analysis of photovoltaic system operation and maintenance. International standards establish general and no standardized criteria on the quality control and validation of these measurements. In the present work, a methodology has been developed to correct erroneous photovoltaic experimental measurements: radiation, temperature, current, and voltage. We validated the proposed approach with 12 case studies with more than 5,000 meteorological and electric measurements from an experimental 3 kWp photovoltaic system. The approach is based on a set of non-intrusive criteria developed from the one diode model, the approach allowed to correct about 80% of the erroneous data, 30% more using polynomial regression. As for the regression methodology, we have shown that the proposed methodology includes 4 meteorologicalelectrical variables allowing a more rigorous analysis. For 75% of the cases evaluated, the proposed methodology achieves a better data correction.
{"title":"Quality control test for unreliable meteorological and electrical photovoltaic measurements","authors":"Jose Galarza, David Condezo","doi":"10.11591/ijece.v13i5.pp4845-4855","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4845-4855","url":null,"abstract":"Meteorological and electrical measurements using predictive computational techniques have been used in the analysis of photovoltaic system operation and maintenance. International standards establish general and no standardized criteria on the quality control and validation of these measurements. In the present work, a methodology has been developed to correct erroneous photovoltaic experimental measurements: radiation, temperature, current, and voltage. We validated the proposed approach with 12 case studies with more than 5,000 meteorological and electric measurements from an experimental 3 kWp photovoltaic system. The approach is based on a set of non-intrusive criteria developed from the one diode model, the approach allowed to correct about 80% of the erroneous data, 30% more using polynomial regression. As for the regression methodology, we have shown that the proposed methodology includes 4 meteorologicalelectrical variables allowing a more rigorous analysis. For 75% of the cases evaluated, the proposed methodology achieves a better data correction.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44832581","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：