Pub Date : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535610
A. Shelestov, L. Shumilo, Y. Bilokonska, A. Lavreniuk
State of the art methodologies for land degradations assessment accepted by United Nations, Food and Agriculture Organization and other official organizations that work on food security problems are based on the use of satellite data. In this case, the basis for the land degradation maps are vegetation indices, calculated using combinations of multispectral channels of satellite images. Evaluation of the land degradation state and trends is grounded on the analysis of land productivity maps changes over time (land productivity trend), land cover changes and carbon stocks changes.The most common methodology for the land degradation assessment is used for the UN Sustainable Development Goal 15.3.1 "Proportion of land that is degraded over total land area" calculation. This study considers the improvement for the calculation of land productivity / degradation based on the use of means of net primary productivity (NPP). For the NPP calculation we used open databases of satellite products of MODIS with spatial resolution 500 m and Landsat-8 with 30 m spatial resolution in the Google Earth Engine cloud platform. The satellite data for 2015 to 2019 years were used to build land productivity map and determine the areas of land degradation, productive and sustainable land for the territory of Ukraine. The use of NPP improve the land productivity assessment by consideration of agroclimatic conditions. The results were compared with product of Trends.Earth (official QGIS built-in plugin) which calculate land degradation maps by the UN methodology. The total areas of productive, degraded and sustainable land were calculated for the territory of Ukraine for 2015-2019 period.
{"title":"The Land Degradation Estimation Remote Sensing Methods Using RUE-adjusted NDVI","authors":"A. Shelestov, L. Shumilo, Y. Bilokonska, A. Lavreniuk","doi":"10.1109/EUROCON52738.2021.9535610","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535610","url":null,"abstract":"State of the art methodologies for land degradations assessment accepted by United Nations, Food and Agriculture Organization and other official organizations that work on food security problems are based on the use of satellite data. In this case, the basis for the land degradation maps are vegetation indices, calculated using combinations of multispectral channels of satellite images. Evaluation of the land degradation state and trends is grounded on the analysis of land productivity maps changes over time (land productivity trend), land cover changes and carbon stocks changes.The most common methodology for the land degradation assessment is used for the UN Sustainable Development Goal 15.3.1 \"Proportion of land that is degraded over total land area\" calculation. This study considers the improvement for the calculation of land productivity / degradation based on the use of means of net primary productivity (NPP). For the NPP calculation we used open databases of satellite products of MODIS with spatial resolution 500 m and Landsat-8 with 30 m spatial resolution in the Google Earth Engine cloud platform. The satellite data for 2015 to 2019 years were used to build land productivity map and determine the areas of land degradation, productive and sustainable land for the territory of Ukraine. The use of NPP improve the land productivity assessment by consideration of agroclimatic conditions. The results were compared with product of Trends.Earth (official QGIS built-in plugin) which calculate land degradation maps by the UN methodology. The total areas of productive, degraded and sustainable land were calculated for the territory of Ukraine for 2015-2019 period.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124248251","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535582
I. Spivak, S. Krepych, Mykola Litvynchuk, S. Spivak
The article describes the mechanism of validation and data processing in JSON format in the form of a modified model, which by its rules will implement a universal approach to the process of data processing of arbitrary structure with the ability to implement its logic of validation and processing of nodes with any level of complexity. Each node of this data must have its own logic for checking their format and a certain logic of post-operation of the node state. An example of implementation of a modified model of processing input data of arbitrary structure in JSON format is given.
{"title":"Validation and Data Processing in JSON Format","authors":"I. Spivak, S. Krepych, Mykola Litvynchuk, S. Spivak","doi":"10.1109/EUROCON52738.2021.9535582","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535582","url":null,"abstract":"The article describes the mechanism of validation and data processing in JSON format in the form of a modified model, which by its rules will implement a universal approach to the process of data processing of arbitrary structure with the ability to implement its logic of validation and processing of nodes with any level of complexity. Each node of this data must have its own logic for checking their format and a certain logic of post-operation of the node state. An example of implementation of a modified model of processing input data of arbitrary structure in JSON format is given.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121882700","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535639
Hritam Basak, Mayukhmali Das, Susmita Modak
Swarm optimization algorithms are widely used for feature selection before data mining and machine learning applications. The metaheuristic nature-inspired feature selection approaches are used for single-objective optimization task, though the major problem is their frequent premature convergence, leading to weak contribution to data mining. In this paper, we propose a novel feature selection algorithm named Reinforced Swarm Optimization (RSO) leveraging some of the existing problems in feature selection. This algorithm embeds the widely used Bee Swarm Optimization (BSO) algorithm along with Reinforcement Learning (RL) to maximize the reward of a superior search agent and punish the inferior ones. This hybrid optimization algorithm is more adaptive and robust with a good balance between exploitation and exploration of the search space. The proposed method is evaluated on 25 widely known UCI dataset containing a perfect blend of balanced and imbalanced data. The obtained results are compared with several other popular and recent feature selection algorithms with similar classifier configuration. The experimental outcome shows that our proposed model outperforms BSO in 22 out of 25 instances (88%). Moreover, experimental results also show that RSO performs the best among all the methods compared in this paper in 19 out of 25 cases (76%), establishing the superiority of our proposed method.
{"title":"RSO: A Novel Reinforced Swarm Optimization Algorithm for Feature Selection","authors":"Hritam Basak, Mayukhmali Das, Susmita Modak","doi":"10.1109/EUROCON52738.2021.9535639","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535639","url":null,"abstract":"Swarm optimization algorithms are widely used for feature selection before data mining and machine learning applications. The metaheuristic nature-inspired feature selection approaches are used for single-objective optimization task, though the major problem is their frequent premature convergence, leading to weak contribution to data mining. In this paper, we propose a novel feature selection algorithm named Reinforced Swarm Optimization (RSO) leveraging some of the existing problems in feature selection. This algorithm embeds the widely used Bee Swarm Optimization (BSO) algorithm along with Reinforcement Learning (RL) to maximize the reward of a superior search agent and punish the inferior ones. This hybrid optimization algorithm is more adaptive and robust with a good balance between exploitation and exploration of the search space. The proposed method is evaluated on 25 widely known UCI dataset containing a perfect blend of balanced and imbalanced data. The obtained results are compared with several other popular and recent feature selection algorithms with similar classifier configuration. The experimental outcome shows that our proposed model outperforms BSO in 22 out of 25 instances (88%). Moreover, experimental results also show that RSO performs the best among all the methods compared in this paper in 19 out of 25 cases (76%), establishing the superiority of our proposed method.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117262708","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535632
B. Siemers, S. Attarha, Jirapa Kamsamrong, Michael Brand, Maria Valliou, R. Pirta-Dreimane, J. Grabis, N. Kunicina, M. Mekkanen, Tero Vartiainen, S. Lehnhoff
The emerging of information technology (IT)and operational technology (OT) convergence has driven the smart grid technology adoption in the European (EU) energy system for better visibility and automated controllability. On the other hand, the energy system infrastructures can be threaten by the cyber attacks due to the increasing of information and communication technology integration. The cyber vulnerabilities are caused by the increasing of internet connection and the application complexities. It is crucial to identify essential skills in the field of cyber security protection and defense for the students. This paper presents the outcome of a literature review and a workshop with stakeholders from industry and academia about the state of the art and trends in the education of cyber security in smart grids.
{"title":"Modern Trends and Skill Gaps of Cyber Security in Smart Grid : Invited Paper","authors":"B. Siemers, S. Attarha, Jirapa Kamsamrong, Michael Brand, Maria Valliou, R. Pirta-Dreimane, J. Grabis, N. Kunicina, M. Mekkanen, Tero Vartiainen, S. Lehnhoff","doi":"10.1109/EUROCON52738.2021.9535632","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535632","url":null,"abstract":"The emerging of information technology (IT)and operational technology (OT) convergence has driven the smart grid technology adoption in the European (EU) energy system for better visibility and automated controllability. On the other hand, the energy system infrastructures can be threaten by the cyber attacks due to the increasing of information and communication technology integration. The cyber vulnerabilities are caused by the increasing of internet connection and the application complexities. It is crucial to identify essential skills in the field of cyber security protection and defense for the students. This paper presents the outcome of a literature review and a workshop with stakeholders from industry and academia about the state of the art and trends in the education of cyber security in smart grids.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115019466","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535580
L. Aranburu, A. Unzueta, M. Garín, Juan I. Modroño, Aitor Amezua
One of the problems faced by electric power distribution system operators is to know with certainty the actual location of all their assets in order to manage properly the grid and provide the best service to their customers. In this work, we present a procedure for the identification of low voltage feeders or distribution lines in smart grids that is based on the mathematical formulation of the problem as an optimization model. In particular, we define the model with 0-1 variables (as many as meters to be identified in the different feeders) and with as many restrictions as the number of points in time that are considered. Given the large size of the problem in practice, the use of conventional optimization software becomes unfeasible. Based on this approach, and making use of the linear relaxation of the problem, some analytics over the coefficients (i.e., meter loads) and the special structure of the problem itself, we have developed an iterative procedure that allows us to recover the entire solution of the initial model in an efficient way. We have carried out a computational experience on a set of anonymized real data, obtaining results that support the efficiency of the proposed procedure.
{"title":"Analytics and Optimization Techniques on Feeder Identification in Smart Grids","authors":"L. Aranburu, A. Unzueta, M. Garín, Juan I. Modroño, Aitor Amezua","doi":"10.1109/EUROCON52738.2021.9535580","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535580","url":null,"abstract":"One of the problems faced by electric power distribution system operators is to know with certainty the actual location of all their assets in order to manage properly the grid and provide the best service to their customers. In this work, we present a procedure for the identification of low voltage feeders or distribution lines in smart grids that is based on the mathematical formulation of the problem as an optimization model. In particular, we define the model with 0-1 variables (as many as meters to be identified in the different feeders) and with as many restrictions as the number of points in time that are considered. Given the large size of the problem in practice, the use of conventional optimization software becomes unfeasible. Based on this approach, and making use of the linear relaxation of the problem, some analytics over the coefficients (i.e., meter loads) and the special structure of the problem itself, we have developed an iterative procedure that allows us to recover the entire solution of the initial model in an efficient way. We have carried out a computational experience on a set of anonymized real data, obtaining results that support the efficiency of the proposed procedure.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"246 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123025681","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535622
Salma K. Elsokkary, Salma M. Soliman, Nada Badawy, Cherif R. Salama, H. Amer, G. Alkady, I. Adly
The focus in this paper is on FPGA-based systems with processors communicating with interchangeable device boards using shared interfaces implementing protocols such as UART, SPI, and I2C. A design is proposed to allow the dynamic interface switching using Dynamic Partial Reconfiguration (DPR) in order to increase performance or reliability during runtime. To this end, a reconfigurable interface block is introduced along with a switching block to connect any interface to different FPGA pins. Furthermore, it is shown how to add redundant interface blocks in order to achieve a pre-determined reliability level. Markov models are used in this analysis. All three protocols were implemented using DE10-Standard FPGA boards.
{"title":"Dynamic and Reliable Multichannel Interfacing System for FPGAs","authors":"Salma K. Elsokkary, Salma M. Soliman, Nada Badawy, Cherif R. Salama, H. Amer, G. Alkady, I. Adly","doi":"10.1109/EUROCON52738.2021.9535622","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535622","url":null,"abstract":"The focus in this paper is on FPGA-based systems with processors communicating with interchangeable device boards using shared interfaces implementing protocols such as UART, SPI, and I2C. A design is proposed to allow the dynamic interface switching using Dynamic Partial Reconfiguration (DPR) in order to increase performance or reliability during runtime. To this end, a reconfigurable interface block is introduced along with a switching block to connect any interface to different FPGA pins. Furthermore, it is shown how to add redundant interface blocks in order to achieve a pre-determined reliability level. Markov models are used in this analysis. All three protocols were implemented using DE10-Standard FPGA boards.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"301 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128623829","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535638
E. Tverytnykova, M. Gutnyk, Yulianna A. Demidova, H. Salata
The stages of the formation of scientific research in the field of converting equipment in Ukraine were investigated. It turned out that the initial research was started by Academician V. M. Khrushchev at the Kharkov Electrotechnical Institute in the early 1930s. The creation of the Institute of Energy (later – Institute of Electrical Engineering, Institute of Electrodynamics) within the system of the Academy of Sciences of Ukraine gave impetus to the development of research in this area, both in academic institutes and in polytechnic ones. An in-depth study of reports on the scientific research work of the Institute of Electrodynamics of the National Academy of Sciences of Ukraine made it possible to reveal that the research teams of the Institute made a significant contribution to the development of theoretical research and the creation of highly efficient electromagnetic and semiconductor converters for various purposes. O. M. Miliakh, together with his students, created new areas of research: a unique Kyiv school of transistor converting equipment under the leadership of Yu. I. Drabovich; research of thyristor converters for power supply systems (V. Yu. Tonkal); development of the theory, methods and technical methods of the parameters of electricity stabilizing and electromagnetic compatibility in electrical systems and networks (A. K. Shidlovsky). In addition, great contribution for the formation of the direction of converting technology in Ukraine made the fundamental developments of Academician I. M. Chizhenko and the achievements of the scientific school of converting equipment of the National Technical University "Kharkov Polytechnic Institute" (O. O. Mayevsky, V. T. Dolbnya, E. I. Sokol).
考察了乌克兰在转化设备领域科研的形成阶段。原来最初的研究是由哈尔科夫电工研究所的v·m·赫鲁晓夫院士于20世纪30年代初开始的。在乌克兰科学院系统内建立的能源研究所(后来的电气工程研究所，电动力学研究所)推动了这一领域的研究发展，无论是在学术机构还是在理工学院。对乌克兰国家科学院电动力学研究所的科学研究工作报告进行了深入研究，发现该研究所的研究小组为理论研究的发展和为各种目的制造高效率的电磁和半导体变换器作出了重大贡献。M. Miliakh和他的学生一起开创了新的研究领域:在Yu的领导下，在基辅建立了一个独特的晶体管转换设备学校。即Drabovich;供电系统用晶闸管变换器的研究[j]。Tonkal);电力系统和网络中电力稳定和电磁兼容参数的理论、方法和技术方法的发展(A. K. Shidlovsky)。此外，对乌克兰转化技术方向形成的巨大贡献是:Chizhenko院士的基础性发展和国立技术大学“哈尔科夫理工学院”转化设备科学学派的成就(O. O. Mayevsky, V. T. Dolbnya, E. I. Sokol)。
{"title":"Power Conversion Equipment in Ukraine: Experience and Prospects","authors":"E. Tverytnykova, M. Gutnyk, Yulianna A. Demidova, H. Salata","doi":"10.1109/EUROCON52738.2021.9535638","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535638","url":null,"abstract":"The stages of the formation of scientific research in the field of converting equipment in Ukraine were investigated. It turned out that the initial research was started by Academician V. M. Khrushchev at the Kharkov Electrotechnical Institute in the early 1930s. The creation of the Institute of Energy (later – Institute of Electrical Engineering, Institute of Electrodynamics) within the system of the Academy of Sciences of Ukraine gave impetus to the development of research in this area, both in academic institutes and in polytechnic ones. An in-depth study of reports on the scientific research work of the Institute of Electrodynamics of the National Academy of Sciences of Ukraine made it possible to reveal that the research teams of the Institute made a significant contribution to the development of theoretical research and the creation of highly efficient electromagnetic and semiconductor converters for various purposes. O. M. Miliakh, together with his students, created new areas of research: a unique Kyiv school of transistor converting equipment under the leadership of Yu. I. Drabovich; research of thyristor converters for power supply systems (V. Yu. Tonkal); development of the theory, methods and technical methods of the parameters of electricity stabilizing and electromagnetic compatibility in electrical systems and networks (A. K. Shidlovsky). In addition, great contribution for the formation of the direction of converting technology in Ukraine made the fundamental developments of Academician I. M. Chizhenko and the achievements of the scientific school of converting equipment of the National Technical University \"Kharkov Polytechnic Institute\" (O. O. Mayevsky, V. T. Dolbnya, E. I. Sokol).","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"384 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121762752","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535562
M. Stogiannos, Myron Papadimitrakis, H. Sarimveis, A. Alexandridis
This work presents a novel data-driven modeling approach for the direct prediction of a vessel’s trajectory through the use of AIS data. The proposed method is based on radial basis function neural networks trained with the fuzzy means algorithm, a combination which produces models of high accuracy and simple structures. The produced model is applied on real AIS data in order to approximate the behavioral patterns of cargo ships when moving in the vicinity of a busy port. Results show that the proposed method outperforms a well-established machine learning technique, namely multi-layer perceptrons, not only in terms of accuracy for one-step and multi-step-ahead prediction, but also by providing lower computational times; these facts make it suitable for use in receding horizon integrated control frameworks.
{"title":"Vessel Trajectory Prediction Using Radial Basis Function Neural Networks","authors":"M. Stogiannos, Myron Papadimitrakis, H. Sarimveis, A. Alexandridis","doi":"10.1109/EUROCON52738.2021.9535562","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535562","url":null,"abstract":"This work presents a novel data-driven modeling approach for the direct prediction of a vessel’s trajectory through the use of AIS data. The proposed method is based on radial basis function neural networks trained with the fuzzy means algorithm, a combination which produces models of high accuracy and simple structures. The produced model is applied on real AIS data in order to approximate the behavioral patterns of cargo ships when moving in the vicinity of a busy port. Results show that the proposed method outperforms a well-established machine learning technique, namely multi-layer perceptrons, not only in terms of accuracy for one-step and multi-step-ahead prediction, but also by providing lower computational times; these facts make it suitable for use in receding horizon integrated control frameworks.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128050403","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535567
Perica Ilak, L. Herenčić, Helena Benković, I. Rajšl
The introduction of new technologies and local energy trading concepts in distribution grids are on a rise. However, even though significant progress is being made, there is no single best solution applicable across all locations. To ensure benefits, concepts must find balance considering hardware and software requirements, user-friendliness, and provided functionalities. Further, due to the diverse regulatory and economic landscapes in Europe, feasibility is not granted, and concepts have to be tailor-made considering the applicable regulatory provisions. In this paper we present a novel trading concept based on supply function equilibrium (SFE) called approximated automated SFE trading algorithm (ASFET). The concept is designed for automated electrical energy trading in middle and low voltage distribution grids. The algorithm could ensure better calculation performance, easier implementation, and scalability. The aspects of the presented concept are discussed in the paper.
{"title":"Concept for Automated Energy Trading in MV and LV Electrical Distribution Grids Based on Approximated Supply Function Equilibrium","authors":"Perica Ilak, L. Herenčić, Helena Benković, I. Rajšl","doi":"10.1109/EUROCON52738.2021.9535567","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535567","url":null,"abstract":"The introduction of new technologies and local energy trading concepts in distribution grids are on a rise. However, even though significant progress is being made, there is no single best solution applicable across all locations. To ensure benefits, concepts must find balance considering hardware and software requirements, user-friendliness, and provided functionalities. Further, due to the diverse regulatory and economic landscapes in Europe, feasibility is not granted, and concepts have to be tailor-made considering the applicable regulatory provisions. In this paper we present a novel trading concept based on supply function equilibrium (SFE) called approximated automated SFE trading algorithm (ASFET). The concept is designed for automated electrical energy trading in middle and low voltage distribution grids. The algorithm could ensure better calculation performance, easier implementation, and scalability. The aspects of the presented concept are discussed in the paper.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131647074","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 : 2021-07-06DOI: 10.1109/EUROCON52738.2021.9535591
Ç. Yildiz, M. Aker, Y. Yaslan
Session-based recommendation systems became a very part of humankind’s daily life, as a result of the increasing transaction volume of e-commerce and e-marketing fields. Companies that can analyze the trails left by their current users on their systems and know their customers better than other firms, can become one step ahead of their rivals. In this concept, representations of items become a key point when related deep learning models are investigated closer. Since the relationship between each item within a session will have a direct effect on the task that involves predicting the next item in that session, extracting these relationships among each item needs to be handled in an effective manner. Using auto encoder systems to achieve the task of revealing hidden features between items and representing these relationships in a more meaningful way, will result in both boosting current state-of-art models’ performance and offering new session-based methods that can overperform the current state-of-art models. In this paper, state-of-the-art graph neural networks SR-GNN’s and TA-GNN’s weights are initialized with item embeddings that are obtained from autoencoder with RBM layers, and the performance of the models are compared with random weight initialization. According to the proposed weight initialization, using pre-trained item embeddings will increase the performance of the recommender model. Thanks to the pre-trained item embeddings, the hidden relationship between items modeled in a better way, and the introduced model has overperformed the current state-of-art techniques.
{"title":"Next Item Prediction Using Neural Networks with Embedding Initialized Weights","authors":"Ç. Yildiz, M. Aker, Y. Yaslan","doi":"10.1109/EUROCON52738.2021.9535591","DOIUrl":"https://doi.org/10.1109/EUROCON52738.2021.9535591","url":null,"abstract":"Session-based recommendation systems became a very part of humankind’s daily life, as a result of the increasing transaction volume of e-commerce and e-marketing fields. Companies that can analyze the trails left by their current users on their systems and know their customers better than other firms, can become one step ahead of their rivals. In this concept, representations of items become a key point when related deep learning models are investigated closer. Since the relationship between each item within a session will have a direct effect on the task that involves predicting the next item in that session, extracting these relationships among each item needs to be handled in an effective manner. Using auto encoder systems to achieve the task of revealing hidden features between items and representing these relationships in a more meaningful way, will result in both boosting current state-of-art models’ performance and offering new session-based methods that can overperform the current state-of-art models. In this paper, state-of-the-art graph neural networks SR-GNN’s and TA-GNN’s weights are initialized with item embeddings that are obtained from autoencoder with RBM layers, and the performance of the models are compared with random weight initialization. According to the proposed weight initialization, using pre-trained item embeddings will increase the performance of the recommender model. Thanks to the pre-trained item embeddings, the hidden relationship between items modeled in a better way, and the introduced model has overperformed the current state-of-art techniques.","PeriodicalId":328338,"journal":{"name":"IEEE EUROCON 2021 - 19th International Conference on Smart Technologies","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122363675","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：