Pub Date : 2023-05-23DOI: 10.1109/SACI58269.2023.10158597
G. Shahgholian, M. Moazzami, S. M. Zanjani, Amir H. Mosavi, Arman Fathollahi
Hydropower is a reliable, clean, and efficient alternative to conventional fossil fuels and other renewable energy sources. The hydro turbine is the core of a hydropower plant, and the proper maintenance and operation of all other components are essential for maximizing energy production. Besides electricity generation, hydropower plants play a critical role in storing irrigation and drinking water and controlling floods. This study presents a concise overview of hydroelectric power plant classification based on the output power generated by peak water drop and storage. Pumped storage water plants are the most applicable classification based on water conditions. The study reviews the application of Artificial Intelligence (AI) in various aspects of hydropower plants, highlighting the potential benefits and challenges of integrating AI technologies in the energy production process. This paper emphasizes the importance of proper maintenance and operation of hydropower plants and provides insights into AI’s potential role in optimizing energy production and improving plant efficiency.
{"title":"A Hydroelectric Power Plant Brief: Classification and Application of Artificial Intelligence","authors":"G. Shahgholian, M. Moazzami, S. M. Zanjani, Amir H. Mosavi, Arman Fathollahi","doi":"10.1109/SACI58269.2023.10158597","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158597","url":null,"abstract":"Hydropower is a reliable, clean, and efficient alternative to conventional fossil fuels and other renewable energy sources. The hydro turbine is the core of a hydropower plant, and the proper maintenance and operation of all other components are essential for maximizing energy production. Besides electricity generation, hydropower plants play a critical role in storing irrigation and drinking water and controlling floods. This study presents a concise overview of hydroelectric power plant classification based on the output power generated by peak water drop and storage. Pumped storage water plants are the most applicable classification based on water conditions. The study reviews the application of Artificial Intelligence (AI) in various aspects of hydropower plants, highlighting the potential benefits and challenges of integrating AI technologies in the energy production process. This paper emphasizes the importance of proper maintenance and operation of hydropower plants and provides insights into AI’s potential role in optimizing energy production and improving plant efficiency.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116768302","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158574
István Márk Tóth, Ágnes Csiszárik-Kocsir
Resilience, managing change appropriately and effectively, is crucial for both individuals and organisations in today’s world. This is one of the main reasons why the agile approach, which originated in the world of software development, is becoming more and more widespread, as it is precisely the ability to adapt to change that is one of its main strengths. However, the agility of organisations and the agile execution of projects is unthinkable without the agility of individuals, which is the result of a combination of different attributes, competences, skills and abilities. These may vary from generation to generation. The aim of our research is to answer the question of what are the most important human attributes for an agile approach and how these attributes vary between generations.
{"title":"Examining the competences needed for an agile approach in different generations","authors":"István Márk Tóth, Ágnes Csiszárik-Kocsir","doi":"10.1109/SACI58269.2023.10158574","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158574","url":null,"abstract":"Resilience, managing change appropriately and effectively, is crucial for both individuals and organisations in today’s world. This is one of the main reasons why the agile approach, which originated in the world of software development, is becoming more and more widespread, as it is precisely the ability to adapt to change that is one of its main strengths. However, the agility of organisations and the agile execution of projects is unthinkable without the agility of individuals, which is the result of a combination of different attributes, competences, skills and abilities. These may vary from generation to generation. The aim of our research is to answer the question of what are the most important human attributes for an agile approach and how these attributes vary between generations.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116908846","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158600
A. Berdich, Patricia Iosif, Camelia Burlacu, A. Anistoroaei, B. Groza
Fingerprinting smartphones using their accelerometers has several applications, including activity recognition, driving style classification and device to device authentication. In this work, we study accelerometer-based smartphone fingerprinting. We gather data from mobile devices placed together to record identical vibrations. Then, we extract time domain features, which we use to train multiple traditional machine learning algorithms based on statistical properties of the data. Finally, we use the raw data in a more complex Convolutional Neural Network and compare the results. To make the investigations more challenging, we discuss fingerprinting both distinct and identical smartphones and reach an accuracy close to 100% with several traditional classifiers.
{"title":"Fingerprinting Smartphone Accelerometers with Traditional Classifiers and Deep Learning Networks","authors":"A. Berdich, Patricia Iosif, Camelia Burlacu, A. Anistoroaei, B. Groza","doi":"10.1109/SACI58269.2023.10158600","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158600","url":null,"abstract":"Fingerprinting smartphones using their accelerometers has several applications, including activity recognition, driving style classification and device to device authentication. In this work, we study accelerometer-based smartphone fingerprinting. We gather data from mobile devices placed together to record identical vibrations. Then, we extract time domain features, which we use to train multiple traditional machine learning algorithms based on statistical properties of the data. Finally, we use the raw data in a more complex Convolutional Neural Network and compare the results. To make the investigations more challenging, we discuss fingerprinting both distinct and identical smartphones and reach an accuracy close to 100% with several traditional classifiers.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116939868","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158560
Mahdi Taleb, B. Fani, G. Shahgholian, Amir H. Mosavi, Arman Fathollahi
The need to reduce greenhouse gas emissions and the high price of fossil fuels have made renewable resources attractive in energy-based economies around the world. Renewable energy sources will make up a significant part of the modern energy system in the future because they have promising potential. Many countries are already working to increase their capacity for renewable energy. The placement of renewable resources in power systems has gained significant attention due to their potential to provide power to distribution feeders or near consumers. However, the integration of these resources can have adverse effects on the distribution network, which necessitates their placement to be carefully considered. In this study, a novel method of coordinating protection devices based on the current control of distributed production sources using their current-voltage diagram during fault conditions is suggested. The proposed method aims to address the coordination and regulation problems encountered when integrating scattered resources into the network. To evaluate the effectiveness of our approach, we compare the impact of the presence of renewable sources at various points on the network during flooding. We conduct simulations using the ETAP software and present the obtained results. The proposed protection coordination method effectively mitigates the challenges of integrating renewable resources into the distribution network, providing a promising solution to support the transition towards a more sustainable energy future.
{"title":"Maintaining Fuse in the Presence of Distributed Generation Sources in the Distribution Network to Improve Protection System","authors":"Mahdi Taleb, B. Fani, G. Shahgholian, Amir H. Mosavi, Arman Fathollahi","doi":"10.1109/SACI58269.2023.10158560","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158560","url":null,"abstract":"The need to reduce greenhouse gas emissions and the high price of fossil fuels have made renewable resources attractive in energy-based economies around the world. Renewable energy sources will make up a significant part of the modern energy system in the future because they have promising potential. Many countries are already working to increase their capacity for renewable energy. The placement of renewable resources in power systems has gained significant attention due to their potential to provide power to distribution feeders or near consumers. However, the integration of these resources can have adverse effects on the distribution network, which necessitates their placement to be carefully considered. In this study, a novel method of coordinating protection devices based on the current control of distributed production sources using their current-voltage diagram during fault conditions is suggested. The proposed method aims to address the coordination and regulation problems encountered when integrating scattered resources into the network. To evaluate the effectiveness of our approach, we compare the impact of the presence of renewable sources at various points on the network during flooding. We conduct simulations using the ETAP software and present the obtained results. The proposed protection coordination method effectively mitigates the challenges of integrating renewable resources into the distribution network, providing a promising solution to support the transition towards a more sustainable energy future.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127152677","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158572
L. Popa, Camil Jichici, Tudor Andreica, Pal-Stefan Murvay, B. Groza
Voltage patterns generated by Controller Area Network (CAN) nodes have been commonly proposed as a source for sender identification as this exposes fine grain manufacturing characteristics. However, the influence of wiring on voltage patterns was insufficiently studied so far and it may be critical in understanding the accuracy of the fingerprinting process. Here we study the influence of wiring on three voltage characteristics: slew rate distribution of recessive to dominant transitions, peak-to-peak and peak-to-root mean square distributions on the plateau area of a dominant bit. Using collected voltage data, we identify slew rate variations depending on the wiring used in each experimental setup. Voltage patterns collected in a laboratory setup with automotive grade cables seem to be identical with those from real-world vehicles, which suggests that this type of cables should be used for realistic experiments.
{"title":"Impact of Wiring Characteristics on Voltage-based Fingerprinting in Controller Area Networks","authors":"L. Popa, Camil Jichici, Tudor Andreica, Pal-Stefan Murvay, B. Groza","doi":"10.1109/SACI58269.2023.10158572","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158572","url":null,"abstract":"Voltage patterns generated by Controller Area Network (CAN) nodes have been commonly proposed as a source for sender identification as this exposes fine grain manufacturing characteristics. However, the influence of wiring on voltage patterns was insufficiently studied so far and it may be critical in understanding the accuracy of the fingerprinting process. Here we study the influence of wiring on three voltage characteristics: slew rate distribution of recessive to dominant transitions, peak-to-peak and peak-to-root mean square distributions on the plateau area of a dominant bit. Using collected voltage data, we identify slew rate variations depending on the wiring used in each experimental setup. Voltage patterns collected in a laboratory setup with automotive grade cables seem to be identical with those from real-world vehicles, which suggests that this type of cables should be used for realistic experiments.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124878752","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158577
N. Karballaeezadeh, Ali Maaruof, S. DanialMohammadzadeh, Sepehr Zamani, Mohammed Mudabbiruddin
In order to maintain, manage, and budget for pavement infrastructure, road pavement condition assessment is necessary. Several pavement characteristics are measured to assess its condition, including pavement strength, roughness, and surface distresses. It is important to categorize studies at deeper levels due to the rapid growth of articles published in this field. The objective of this paper is to provide an overview of machine learning-based pavement evaluation studies and their contributions to the area. In order to facilitate the exploration of the studies employing similar methodologies, the studies are organized based on their goals. Therefore, studies are classified based on the two main categories of goals employed in them, namely: 1. Studies with aim of pavement condition prediction and 2. Studies with the aim of pavement distress detection/classification. It is observed that research of category 1 has grown very well during the past years. Also, category 2 includes studies that mostly focus on crack detection and it can be felt that there is a need for expanding the focus of studies on other types of distresses.
{"title":"Machine Learning Approaches for Detection/Classification and Prediction Purposes in Pavement Engineering Studies: An Overview","authors":"N. Karballaeezadeh, Ali Maaruof, S. DanialMohammadzadeh, Sepehr Zamani, Mohammed Mudabbiruddin","doi":"10.1109/SACI58269.2023.10158577","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158577","url":null,"abstract":"In order to maintain, manage, and budget for pavement infrastructure, road pavement condition assessment is necessary. Several pavement characteristics are measured to assess its condition, including pavement strength, roughness, and surface distresses. It is important to categorize studies at deeper levels due to the rapid growth of articles published in this field. The objective of this paper is to provide an overview of machine learning-based pavement evaluation studies and their contributions to the area. In order to facilitate the exploration of the studies employing similar methodologies, the studies are organized based on their goals. Therefore, studies are classified based on the two main categories of goals employed in them, namely: 1. Studies with aim of pavement condition prediction and 2. Studies with the aim of pavement distress detection/classification. It is observed that research of category 1 has grown very well during the past years. Also, category 2 includes studies that mostly focus on crack detection and it can be felt that there is a need for expanding the focus of studies on other types of distresses.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125045377","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158604
Dávid Holecska, A. Dineva
This paper addresses the pressing issue of meeting energy demand sustainably, which has become increasingly challenging in recent years due to the rising prices and limited supply of fossil fuels. In response, the use of distributed renewable energy generation systems has emerged as a potential solution. The European Union has shifted its regulatory focus towards promoting renewable energy communities, as opposed to centralized fossil fuel production. To overcome the variability and unpredictability of renewable sources, electrical energy storage devices are often used, typically Li-ion batteries. Proper sizing and control of batteries and the entire system is crucial for optimal performance. The objective of this paper is to develop a simulation framework suitable for developing AI-based energy management solutions for a grid-connected system with solar cells and a shared battery energy storage that serves the energy needs of multiple residential consumers. The simulation is conducted using actual solar radiation and load data in the Matlab Simulink environment. Finally, the study aims to investigate the impact of various consumption profiles and seasonal variation in solar energy production on battery utilization.
{"title":"Towards Sustainable Energy Management: Analyzing AI-Based Solutions for PV Systems with Battery in Energy Communities","authors":"Dávid Holecska, A. Dineva","doi":"10.1109/SACI58269.2023.10158604","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158604","url":null,"abstract":"This paper addresses the pressing issue of meeting energy demand sustainably, which has become increasingly challenging in recent years due to the rising prices and limited supply of fossil fuels. In response, the use of distributed renewable energy generation systems has emerged as a potential solution. The European Union has shifted its regulatory focus towards promoting renewable energy communities, as opposed to centralized fossil fuel production. To overcome the variability and unpredictability of renewable sources, electrical energy storage devices are often used, typically Li-ion batteries. Proper sizing and control of batteries and the entire system is crucial for optimal performance. The objective of this paper is to develop a simulation framework suitable for developing AI-based energy management solutions for a grid-connected system with solar cells and a shared battery energy storage that serves the energy needs of multiple residential consumers. The simulation is conducted using actual solar radiation and load data in the Matlab Simulink environment. Finally, the study aims to investigate the impact of various consumption profiles and seasonal variation in solar energy production on battery utilization.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122908533","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158649
E. Gatial, Z. Balogh, Sepideh Hassankhani Dolatabadi, Hatem Ghorbel, S. Carrino, Jonathan Dreyer, V. R. Montequín, A. Gligor, László Barna Iantovics
The paper describes a real-time job scheduling method designed for production of goods with different characteristics on machines with different processing parameters. The objective is to maximize the global reward of the factory as a sum of the rewards for each machine job. Traditionally, the task assignment problems deal with the assignment of m-tasks to n-agents and are calculated by analytical methods or heuristics. The proposed method is based on online auctions that distributes the tasks to the machines using the software agents. The method is implemented using the ERTS (Erlang Real-Time System) that allows adopting the features of fault-tolerance and real-time processing. The paper starts with introduction and review of related state-of-the-art. The following chapter briefly describes the problem and the specific requirements. The following chapter describes the software architecture of the online auction system, the use-case and the motivation for developing this method. The proposed method auction-based task assignment and its implementation are described in the next chapters. At the end of the work, the results of the method are presented in comparison with the optimal solution and the performance characteristics are also described. In the conclusion, possible advances and future work are proposed.
{"title":"Auction-Based Job Scheduling for Smart Manufacturing","authors":"E. Gatial, Z. Balogh, Sepideh Hassankhani Dolatabadi, Hatem Ghorbel, S. Carrino, Jonathan Dreyer, V. R. Montequín, A. Gligor, László Barna Iantovics","doi":"10.1109/SACI58269.2023.10158649","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158649","url":null,"abstract":"The paper describes a real-time job scheduling method designed for production of goods with different characteristics on machines with different processing parameters. The objective is to maximize the global reward of the factory as a sum of the rewards for each machine job. Traditionally, the task assignment problems deal with the assignment of m-tasks to n-agents and are calculated by analytical methods or heuristics. The proposed method is based on online auctions that distributes the tasks to the machines using the software agents. The method is implemented using the ERTS (Erlang Real-Time System) that allows adopting the features of fault-tolerance and real-time processing. The paper starts with introduction and review of related state-of-the-art. The following chapter briefly describes the problem and the specific requirements. The following chapter describes the software architecture of the online auction system, the use-case and the motivation for developing this method. The proposed method auction-based task assignment and its implementation are described in the next chapters. At the end of the work, the results of the method are presented in comparison with the optimal solution and the performance characteristics are also described. In the conclusion, possible advances and future work are proposed.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114401325","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158657
Miklós Vincze, Bence Biricz, M. Kozlovszky, Abdallah Benhamida
Nowadays, medical science is faced with many challenges that prevent doctors and researchers from working quickly and efficiently. Such a challenge is, for example, the evaluation of digitized 3D pathological serial sections in a consultative manner. This selected example brings to the surface several obstacles, the solution of which can improve everyday work and medical education in other medical fields as well. One of these difficulties is overcoming the distance, and the other is reducing the need for hardware resources since not all users can be expected to have the most modern computer components. Our goal was to design and implement a solution that enables users (doctors, researchers, educators, medical students) from anywhere in the world to participate in the evaluation of 3D digitized pathological samples, even with the use of limited hardware resources, all in an environment provided by virtual reality technology within.
{"title":"Real-time video streaming in medicine using virtual reality","authors":"Miklós Vincze, Bence Biricz, M. Kozlovszky, Abdallah Benhamida","doi":"10.1109/SACI58269.2023.10158657","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158657","url":null,"abstract":"Nowadays, medical science is faced with many challenges that prevent doctors and researchers from working quickly and efficiently. Such a challenge is, for example, the evaluation of digitized 3D pathological serial sections in a consultative manner. This selected example brings to the surface several obstacles, the solution of which can improve everyday work and medical education in other medical fields as well. One of these difficulties is overcoming the distance, and the other is reducing the need for hardware resources since not all users can be expected to have the most modern computer components. Our goal was to design and implement a solution that enables users (doctors, researchers, educators, medical students) from anywhere in the world to participate in the evaluation of 3D digitized pathological samples, even with the use of limited hardware resources, all in an environment provided by virtual reality technology within.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122101775","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158559
D. Petcu
Cloud Continuum is the extension of the traditional Cloud towards multiple entities like Internet of Things devices, Edge or Fog nodes that provide analysis, processing, storage, and data generation capabilities [1]. Cognitive Cloud Continuum, i.e. AI-enabled Cloud continuum, aims to automatically adapt to the growing complexity and data deluge by integrating seamlessly diverse computing and data environments by learning from monitoring and management of deployed services or applying AI techniques for dynamic load balancing to optimize energy consumption, resource usage or network traffic. To achieve this aim several efforts are underway. We will focus on the recent results related to coupling federated learning mechanisms and intelligent resource discovery to achieve an adaptive hosting environment capable of running both on Cloud and close to the Edge, machine learning in anomaly detection, or transprecision computing for distributed stream processing [2], [3], [4].
{"title":"Cognitive Cloud Continuum : Plenary Talk","authors":"D. Petcu","doi":"10.1109/SACI58269.2023.10158559","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158559","url":null,"abstract":"Cloud Continuum is the extension of the traditional Cloud towards multiple entities like Internet of Things devices, Edge or Fog nodes that provide analysis, processing, storage, and data generation capabilities [1]. Cognitive Cloud Continuum, i.e. AI-enabled Cloud continuum, aims to automatically adapt to the growing complexity and data deluge by integrating seamlessly diverse computing and data environments by learning from monitoring and management of deployed services or applying AI techniques for dynamic load balancing to optimize energy consumption, resource usage or network traffic. To achieve this aim several efforts are underway. We will focus on the recent results related to coupling federated learning mechanisms and intelligent resource discovery to achieve an adaptive hosting environment capable of running both on Cloud and close to the Edge, machine learning in anomaly detection, or transprecision computing for distributed stream processing [2], [3], [4].","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116623059","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：