Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315363
Nuurshadieq, A. Wibowo
The rapid development of the Japanese animation industry has produce tons of anime movies which made interest to groups of people. Each anime movie has its own characteristic which complies with specific user's interests. Therefore, a personalization engine was needed to provide recommendations. The use of collaborative filtering based recommender system that only takes into account historic explicit interactions (such as rating) was able to provide recommendations. However, we might able to improve the personalization by taking into account the users' and items' side information. Our contributions in this paper are follows. First, we collected 301,136 ratings provided by 116,126 users to 9,444 anime works in which crawled from MyAnimeList, as well as users' and items' side information. Second, we proposed a deep learning method that incorporates side information from both users and anime works into a hybrid model. This model learns the embedding separately for users and anime, in which we also add a LSTM layer to extract information from long text feature like Synopsis which will be combined and feed into a deep neural network to predict the rating of given user and anime work. And finally, we experimented and calculated the performance. The result shows that the model with side information gain result around 5% better than the SVD model.
{"title":"Leveraging Side Information to Anime Recommender System using Deep learning","authors":"Nuurshadieq, A. Wibowo","doi":"10.1109/ISRITI51436.2020.9315363","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315363","url":null,"abstract":"The rapid development of the Japanese animation industry has produce tons of anime movies which made interest to groups of people. Each anime movie has its own characteristic which complies with specific user's interests. Therefore, a personalization engine was needed to provide recommendations. The use of collaborative filtering based recommender system that only takes into account historic explicit interactions (such as rating) was able to provide recommendations. However, we might able to improve the personalization by taking into account the users' and items' side information. Our contributions in this paper are follows. First, we collected 301,136 ratings provided by 116,126 users to 9,444 anime works in which crawled from MyAnimeList, as well as users' and items' side information. Second, we proposed a deep learning method that incorporates side information from both users and anime works into a hybrid model. This model learns the embedding separately for users and anime, in which we also add a LSTM layer to extract information from long text feature like Synopsis which will be combined and feed into a deep neural network to predict the rating of given user and anime work. And finally, we experimented and calculated the performance. The result shows that the model with side information gain result around 5% better than the SVD model.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128200343","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315368
A. Mulyanto, Rohmat Indra Borman, Purwono Prasetyawan, W. Jatmiko, P. Mursanto, Aprian Sinaga
Traffic violations are one of the causes of the increasing number of road traffic fatalities every year, apart from driver negligence or ignorance of traffic signs. ADAS does not totally forestall mishap, however they can all more likely shield us from a few human elements and human mistake. The goal of ADAS is to automate vehicle systems for better driving and safety, such as Traffic Sign Recognition (TSR). This paper presents a study to recognize traffic sign patterns using YOLOv4 using the Indonesia Traffic Signs (ITS) dataset. The ITS dataset consists of four categories (warning, prohibitory, mandatory and directive) with twenty six signs. The deep learning model of YOLOv4 is based CSP-DarkNet53 backbone which has shown good performance with main Average Precision (mAP@0.5) of 74.91% for 26 signs of Indonesian Traffic Signs.
{"title":"Indonesian Traffic Sign Recognition For Advanced Driver Assistent (ADAS) Using YOLOv4","authors":"A. Mulyanto, Rohmat Indra Borman, Purwono Prasetyawan, W. Jatmiko, P. Mursanto, Aprian Sinaga","doi":"10.1109/ISRITI51436.2020.9315368","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315368","url":null,"abstract":"Traffic violations are one of the causes of the increasing number of road traffic fatalities every year, apart from driver negligence or ignorance of traffic signs. ADAS does not totally forestall mishap, however they can all more likely shield us from a few human elements and human mistake. The goal of ADAS is to automate vehicle systems for better driving and safety, such as Traffic Sign Recognition (TSR). This paper presents a study to recognize traffic sign patterns using YOLOv4 using the Indonesia Traffic Signs (ITS) dataset. The ITS dataset consists of four categories (warning, prohibitory, mandatory and directive) with twenty six signs. The deep learning model of YOLOv4 is based CSP-DarkNet53 backbone which has shown good performance with main Average Precision (mAP@0.5) of 74.91% for 26 signs of Indonesian Traffic Signs.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123241470","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315484
K. M. Hindrayani, Tresna Maulana Fahrudin, R. Prismahardi Aji, E. M. Safitri
Predicting stock prices is an interesting field in Data Mining. There are many variables affecting stock prices. Especially in this covid19 era which impacts in economy, the stock prices become unpredictable. Telecommunications companies are observed in this research as it is one of the sectors that's still very much in demand in this pandemic situation. Fundamental data will be used to predict the Indonesian telecommunications stock price. Regression techniques will be used as the proposed model. The correlation coefficient shows that despite the covid19 era, fundamental data still play a role in stock market price. Decision Tree Regression produced competitive results compared to other methods.
{"title":"Indonesian Stock Price Prediction including Covid19 Era Using Decision Tree Regression","authors":"K. M. Hindrayani, Tresna Maulana Fahrudin, R. Prismahardi Aji, E. M. Safitri","doi":"10.1109/ISRITI51436.2020.9315484","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315484","url":null,"abstract":"Predicting stock prices is an interesting field in Data Mining. There are many variables affecting stock prices. Especially in this covid19 era which impacts in economy, the stock prices become unpredictable. Telecommunications companies are observed in this research as it is one of the sectors that's still very much in demand in this pandemic situation. Fundamental data will be used to predict the Indonesian telecommunications stock price. Regression techniques will be used as the proposed model. The correlation coefficient shows that despite the covid19 era, fundamental data still play a role in stock market price. Decision Tree Regression produced competitive results compared to other methods.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126456362","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315354
Raki Anwar Ekaniza, S. Suyanto
The purpose of Activity Recognition (AR) is to recognize human activity using a sensor to get the data needed. Then, a machine learning approach is used to determine the type of activity performed. A machine learning technique often used in the classification problem is Artificial Neural Network (ANN), which is trained using a backpropagation algorithm. Although this technique has been significantly developed, it still has a few disadvantages compared to others. One of the disadvantages of the ANN is that the result is not always optimum because of randomized initialization and epoch limit. In this paper, a Particle Swarm Optimization (PSO) is proposed to train the ANN. Some experiments on a dataset of 10 k activities with six imbalanced classes show that the PSO-based ANN produces effectiveness of 100% and an F1 score micro of 0.88, which are much higher than the back propagation-based ANN that gives the effectiveness of 75% and an F1 score micro of 0.87.
{"title":"PSO-Learned Artificial Neural Networks for Activity Recognition","authors":"Raki Anwar Ekaniza, S. Suyanto","doi":"10.1109/ISRITI51436.2020.9315354","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315354","url":null,"abstract":"The purpose of Activity Recognition (AR) is to recognize human activity using a sensor to get the data needed. Then, a machine learning approach is used to determine the type of activity performed. A machine learning technique often used in the classification problem is Artificial Neural Network (ANN), which is trained using a backpropagation algorithm. Although this technique has been significantly developed, it still has a few disadvantages compared to others. One of the disadvantages of the ANN is that the result is not always optimum because of randomized initialization and epoch limit. In this paper, a Particle Swarm Optimization (PSO) is proposed to train the ANN. Some experiments on a dataset of 10 k activities with six imbalanced classes show that the PSO-based ANN produces effectiveness of 100% and an F1 score micro of 0.88, which are much higher than the back propagation-based ANN that gives the effectiveness of 75% and an F1 score micro of 0.87.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130384019","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315505
T. Asfihani, Khusnul Chotimah, I. Fitria, Subchan
A ship heading control can drive the ship to follow the desired heading angle. A ship heading control is used in the autopilot system of the ship. The ship motion can be written mathematically with nonlinear equations. The method that can solve the ship heading control problem on a nonlinear model is Nonlinear Model Predictive Control (NMPC). This study aims to design the ship heading control and the system model used is the 3 DOF (degree of freedom) model equation. The best condition for simulation is obtained based on the value of time sampling and the number of prediction horizon. Based on simulations, NMPC can be applied in the ship heading control effectively and satisfy the constraints.
{"title":"Ship Heading Control Using Nonlinear Model Predictive Control","authors":"T. Asfihani, Khusnul Chotimah, I. Fitria, Subchan","doi":"10.1109/ISRITI51436.2020.9315505","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315505","url":null,"abstract":"A ship heading control can drive the ship to follow the desired heading angle. A ship heading control is used in the autopilot system of the ship. The ship motion can be written mathematically with nonlinear equations. The method that can solve the ship heading control problem on a nonlinear model is Nonlinear Model Predictive Control (NMPC). This study aims to design the ship heading control and the system model used is the 3 DOF (degree of freedom) model equation. The best condition for simulation is obtained based on the value of time sampling and the number of prediction horizon. Based on simulations, NMPC can be applied in the ship heading control effectively and satisfy the constraints.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125754492","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315410
A. Julzarika, T. Aditya, Subaryono, Harintaka
DEM is needed for monitoring peatland dynamics. Currently, available free DEMs have low vertical accuracy and are not up to date. Commercial DEMs have high resolution but is expensive. DEM Pleiades is an example of a commercial DEM. One solution to overcome this problem is to use the latest DTM, which has the advantage of being up to date. This study aims to compare the vertical accuracy of the latest DTM with DEM Pleiades on peatlands. The study area is located on the peatlands of the “Palangkaraya-Pulang Pisau” border. This region has relatively flat topography. The latest DTM is extracted from a combination of InSAR ALOS PALSAR/PALSAR-2 and DInSAR Sentinel. The latest DTM is the integration of the DTM master with the latest displacement. The vertical accuracy of the latest DTM needs to be tested on the DEM Pleiades data with a spatial resolution of 0.5 m and field measurement data using GNSS. DEM Pleiades, the latest DTM, and field measurements using the EGM 2008 for the height reference field. The height data on the DEM Pleiades and the latest DTM were extracted and adjusted for 15 field measurement points. The result obtained is the mean height differences between DEM Pleiades and the latest DTM which is ammounting 0.923 m. The mean height differences between DEM Pleaides and field measurements is 0.557 m. The mean height differences between the latest DTM and field measurements is 0.705 m. Furthermore, a longitudinal profile is made according to 15 field measurement points on the DEM Pleiades and the latest DTM. The results obtained are that DEM Pleiades still has more height errors than the latest DTM. The latest DTM can be an alternative to DEM Pleaides for peatlands mapping with relatively flat topography.
{"title":"Comparison of the Latest DTM with DEM Pleiades in Monitoring the Dynamic Peatland","authors":"A. Julzarika, T. Aditya, Subaryono, Harintaka","doi":"10.1109/ISRITI51436.2020.9315410","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315410","url":null,"abstract":"DEM is needed for monitoring peatland dynamics. Currently, available free DEMs have low vertical accuracy and are not up to date. Commercial DEMs have high resolution but is expensive. DEM Pleiades is an example of a commercial DEM. One solution to overcome this problem is to use the latest DTM, which has the advantage of being up to date. This study aims to compare the vertical accuracy of the latest DTM with DEM Pleiades on peatlands. The study area is located on the peatlands of the “Palangkaraya-Pulang Pisau” border. This region has relatively flat topography. The latest DTM is extracted from a combination of InSAR ALOS PALSAR/PALSAR-2 and DInSAR Sentinel. The latest DTM is the integration of the DTM master with the latest displacement. The vertical accuracy of the latest DTM needs to be tested on the DEM Pleiades data with a spatial resolution of 0.5 m and field measurement data using GNSS. DEM Pleiades, the latest DTM, and field measurements using the EGM 2008 for the height reference field. The height data on the DEM Pleiades and the latest DTM were extracted and adjusted for 15 field measurement points. The result obtained is the mean height differences between DEM Pleiades and the latest DTM which is ammounting 0.923 m. The mean height differences between DEM Pleaides and field measurements is 0.557 m. The mean height differences between the latest DTM and field measurements is 0.705 m. Furthermore, a longitudinal profile is made according to 15 field measurement points on the DEM Pleiades and the latest DTM. The results obtained are that DEM Pleiades still has more height errors than the latest DTM. The latest DTM can be an alternative to DEM Pleaides for peatlands mapping with relatively flat topography.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134613879","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315450
M. I. Nashiruddin, Nomarhinta Solihah
Digital economy development requires enterprises to seek solutions to cater increasing demand for internet bandwidth. Enterprise customer require a reliable connection for delivering their business solution with the symmetric speed between upload and download, such as XGS-PON technology (10 Gigabit Capable Symmetric Passive Optical Network). However, standards and regulations for using XGS-PON ONT (Optical Network Terminal) equipment intended for enterprise customers do not exist. This research aims to determine the XGS-PON ONT capabilities for enterprise customers to ensure its service quality. XGS-PON ONT's performance evaluates optical interface capability parameters such as nominal line rate, operating wavelength, mean launch power, sensitivity, and overload. Also, data function capability parameters testing includes the VLAN ID, VLAN translate, and jumbo frame. Optical interface test results show that the XGS-PON ONT enterprise has an upstream nominal line rate capability of 9.81221 Gbps and supports an upstream operating wavelength of 1269,509 nm. The XGS-PON ONT results of mean launch power, sensitivity, and overload comply with the Optical Distribution Network (ODN) class requirements of N1 and N2. The test results of data function capability show that the XGS-PON ONT for enterprise customers can deliver 4000 Virtual Local Area Network Identifiers (VLAN IDs), supports the VLAN translate function jumbo frames from 2000 to 9000 bytes. The optical interface and data function capability of XGS-PON ONT shows the results following ITU-T G.9807, IEEE 802.1q, and Broadband Forum technical reports.
{"title":"Performance Evaluation of XGS-PON Optical Network Termination for Enterprise Customer","authors":"M. I. Nashiruddin, Nomarhinta Solihah","doi":"10.1109/ISRITI51436.2020.9315450","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315450","url":null,"abstract":"Digital economy development requires enterprises to seek solutions to cater increasing demand for internet bandwidth. Enterprise customer require a reliable connection for delivering their business solution with the symmetric speed between upload and download, such as XGS-PON technology (10 Gigabit Capable Symmetric Passive Optical Network). However, standards and regulations for using XGS-PON ONT (Optical Network Terminal) equipment intended for enterprise customers do not exist. This research aims to determine the XGS-PON ONT capabilities for enterprise customers to ensure its service quality. XGS-PON ONT's performance evaluates optical interface capability parameters such as nominal line rate, operating wavelength, mean launch power, sensitivity, and overload. Also, data function capability parameters testing includes the VLAN ID, VLAN translate, and jumbo frame. Optical interface test results show that the XGS-PON ONT enterprise has an upstream nominal line rate capability of 9.81221 Gbps and supports an upstream operating wavelength of 1269,509 nm. The XGS-PON ONT results of mean launch power, sensitivity, and overload comply with the Optical Distribution Network (ODN) class requirements of N1 and N2. The test results of data function capability show that the XGS-PON ONT for enterprise customers can deliver 4000 Virtual Local Area Network Identifiers (VLAN IDs), supports the VLAN translate function jumbo frames from 2000 to 9000 bytes. The optical interface and data function capability of XGS-PON ONT shows the results following ITU-T G.9807, IEEE 802.1q, and Broadband Forum technical reports.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134054325","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315406
Elta Sonalitha, Bambang Nurdewanto, A. Zubair, Salnan Ratih Asriningtias, Kukuh Yudhistiro, Irfan Mujahidin
The classification of artistic expertise in an area on products and actors of art greatly affects the progress of artistic life. One method of classifying cultural data is the taxonomic method. In the taxonomic method, an art product can be categorized into several domains. For example, the product of Kawung (Indonesian) batik cloth can be included in the domains of fashion, philosophy, and fine arts. An example from the taxonomy of art actors, for example, an artist can have various expertise in music, dance, fine arts, or others. The source of information used to classify this research is the big data of art actors in Malang, Indonesia. Big data is obtained from art actors directly who provide input from the instrument about the suitability of the art field with the expertise possessed by each of them. Individual artists generally have more than one artistic skill which can be classified taxonomically and ranked using fuzzy clustering. The purpose of ranking with fuzzy clustering is to determine the weight of artistic skills starting from the level just done to the most proficient to do. To achieve accurate weighing results, a taxonomy application for mapping and data analysis of artists and works of art was created. This research discusses functional testing (black-box testing) of the taxonomy application of mapping and data analysis on web-based artists and artworks.
{"title":"Blackbox Testing Model Boundary Value Of Mapping Taxonomy Applications and Data Analysis of Art and Artworks","authors":"Elta Sonalitha, Bambang Nurdewanto, A. Zubair, Salnan Ratih Asriningtias, Kukuh Yudhistiro, Irfan Mujahidin","doi":"10.1109/ISRITI51436.2020.9315406","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315406","url":null,"abstract":"The classification of artistic expertise in an area on products and actors of art greatly affects the progress of artistic life. One method of classifying cultural data is the taxonomic method. In the taxonomic method, an art product can be categorized into several domains. For example, the product of Kawung (Indonesian) batik cloth can be included in the domains of fashion, philosophy, and fine arts. An example from the taxonomy of art actors, for example, an artist can have various expertise in music, dance, fine arts, or others. The source of information used to classify this research is the big data of art actors in Malang, Indonesia. Big data is obtained from art actors directly who provide input from the instrument about the suitability of the art field with the expertise possessed by each of them. Individual artists generally have more than one artistic skill which can be classified taxonomically and ranked using fuzzy clustering. The purpose of ranking with fuzzy clustering is to determine the weight of artistic skills starting from the level just done to the most proficient to do. To achieve accurate weighing results, a taxonomy application for mapping and data analysis of artists and works of art was created. This research discusses functional testing (black-box testing) of the taxonomy application of mapping and data analysis on web-based artists and artworks.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134374963","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315385
Ponsuda Prutphongs, D. Sutivong
This research designs and develops a Decision Support System (DSS) for evaluating a power plant improvement investment, given a generation plan, contract accounting and associated technical data. In practice, most owners often decide on an improvement investment by considering forward an immediate short period of revenue and expenses. This decision support system helps the owner take into account a more comprehensive period of cash flows in order to maximize the asset value and make an optimal decision. Specifically, the model calculation is based on the Life Cycle Cost Management (LCCM) under certain business rules. Our proposed evaluation model consists of five steps: 1) Consider the structure of revenue and expenses according to the Power Purchase Agreement (PPA). 2) Analyze accounting and technical data. 3) Estimate demand from the energy plan according to the system operator's yearly report. 4) Incorporate the data according to its business rule and the PPA constraints into the forecasting calculation. 5) Evaluate the investment using economic measures, such as Net Present Value (NPV) and Internal Rate of Return (IRR).
{"title":"Decision Support System for Power Plant Improvement Investment Using Life-Cycle Cost","authors":"Ponsuda Prutphongs, D. Sutivong","doi":"10.1109/ISRITI51436.2020.9315385","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315385","url":null,"abstract":"This research designs and develops a Decision Support System (DSS) for evaluating a power plant improvement investment, given a generation plan, contract accounting and associated technical data. In practice, most owners often decide on an improvement investment by considering forward an immediate short period of revenue and expenses. This decision support system helps the owner take into account a more comprehensive period of cash flows in order to maximize the asset value and make an optimal decision. Specifically, the model calculation is based on the Life Cycle Cost Management (LCCM) under certain business rules. Our proposed evaluation model consists of five steps: 1) Consider the structure of revenue and expenses according to the Power Purchase Agreement (PPA). 2) Analyze accounting and technical data. 3) Estimate demand from the energy plan according to the system operator's yearly report. 4) Incorporate the data according to its business rule and the PPA constraints into the forecasting calculation. 5) Evaluate the investment using economic measures, such as Net Present Value (NPV) and Internal Rate of Return (IRR).","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132058983","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315446
Mahardira Dewantara, L. M. Putranto, R. Irnawan, Sarjiya
The main concern of renewable generation is that it can help reduce power losses in the grid. Renewable power plants such as Photovoltaic (PV) assisted by a Battery Energy Storage System (BESS) with the right placement and size can provide significant benefits they can certainly further help reduce power loss. This paper, it aims to simulate the power flow by optimizing the placement and size of the PV and BESS considering the power loss using the integrated python DIgSILENT PowerFactory. The proposed methodology concept uses a modified IEEE 33 bus. There are two scenarios, namely systems that are only supported by PV and systems that are supported by PV and BESS, which see the state of charge (SOC). Optimization of placement and size using a Genetic Algorithm (GA). The results obtained from the optimized placement and size show a decrease in power loss, where in the first case, the placement of PV is located on bus 9 with PV capacity can reduce power loss to 2201.66 kW, and the second case, placement of PV is located on bus 9 with PV capacity and BESS is located on bus 16 by looking at the battery operation pattern can reduce the power loss to 2180.01 kW
{"title":"Minimization of Power Losses through Optimal Placement and Sizing from Solar Power and Battery Energy Storage System in Distribution System","authors":"Mahardira Dewantara, L. M. Putranto, R. Irnawan, Sarjiya","doi":"10.1109/ISRITI51436.2020.9315446","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315446","url":null,"abstract":"The main concern of renewable generation is that it can help reduce power losses in the grid. Renewable power plants such as Photovoltaic (PV) assisted by a Battery Energy Storage System (BESS) with the right placement and size can provide significant benefits they can certainly further help reduce power loss. This paper, it aims to simulate the power flow by optimizing the placement and size of the PV and BESS considering the power loss using the integrated python DIgSILENT PowerFactory. The proposed methodology concept uses a modified IEEE 33 bus. There are two scenarios, namely systems that are only supported by PV and systems that are supported by PV and BESS, which see the state of charge (SOC). Optimization of placement and size using a Genetic Algorithm (GA). The results obtained from the optimized placement and size show a decrease in power loss, where in the first case, the placement of PV is located on bus 9 with PV capacity can reduce power loss to 2201.66 kW, and the second case, placement of PV is located on bus 9 with PV capacity and BESS is located on bus 16 by looking at the battery operation pattern can reduce the power loss to 2180.01 kW","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134160817","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}