Pub Date : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900582
Fatih Dönmez, A. Altuncu
Renewable energy systems, which are intermittent energy production systems, cannot always operate at high efficiency due to their nature. Since specific amounts of energy must be spent for energy production, it is essential to estimate the time intervals when the efficiency of the energy source is high. In order to actively monitor the system health, the communication traffic must be transferred to a monitoring room where the technical teams can easily observe the operating data of the equipment in the energy-generating plants. It has been assumed that the energy needs of vocational schools affiliated with the university are met by solar energy systems previously installed by the university administration in their fields. Thanks to the simulation programs, a communication network that does not violate the standards published by the International Electrotechnical Commission for solar energy systems has been designed. Contrary to the methods most preferred in wide area networks like Telecommunication Company’s tariff, we preferred wireless communication technologies. By choosing comprehensive area network technology WiMAX and local area network technology WiFi, we passed the required performance criteria under the name of related communication standards.
{"title":"Design of a Communication Network for Distributed Renewable Energy Generation Systems","authors":"Fatih Dönmez, A. Altuncu","doi":"10.1109/BalkanCom55633.2022.9900582","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900582","url":null,"abstract":"Renewable energy systems, which are intermittent energy production systems, cannot always operate at high efficiency due to their nature. Since specific amounts of energy must be spent for energy production, it is essential to estimate the time intervals when the efficiency of the energy source is high. In order to actively monitor the system health, the communication traffic must be transferred to a monitoring room where the technical teams can easily observe the operating data of the equipment in the energy-generating plants. It has been assumed that the energy needs of vocational schools affiliated with the university are met by solar energy systems previously installed by the university administration in their fields. Thanks to the simulation programs, a communication network that does not violate the standards published by the International Electrotechnical Commission for solar energy systems has been designed. Contrary to the methods most preferred in wide area networks like Telecommunication Company’s tariff, we preferred wireless communication technologies. By choosing comprehensive area network technology WiMAX and local area network technology WiFi, we passed the required performance criteria under the name of related communication standards.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130290292","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 : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900663
Miguel Lopes, Daniel Corujo, Paulo Duarte, Marco Araújo
Due to their dynamic nature, 5G communications bring additional complexity to operator networks. Due to their reliance on network softwarization and virtualization, 5G networks can adapt themselves by changing their topology or simply by adding or removing services and resources as needed, in regards to Quality of Service (QoS) metrics. For an operator, network monitoring and orchestration gain further importance for automation and management of virtual functions life-cycle. Monitoring is a crucial aspect of the life-cycle management of virtual functions in order to ensure that the QoS metrics are met at all times. Accordingly, network orchestration is one of the fundamental pillars for the implementation of the new generation of mobile networks use cases. The Open Network Automation Platform (ONAP) is an open-source project that provides management and orchestration support for end-to-end services and infrastructures. This paper aims to explore ONAP’s capabilities, coupled with the Prometheus monitoring tool, to address the possible QoS problems of a vCDN service, more precisely, the lack of a horizontal system scaling. An experimental proof of concept evaluation provided low instantiation times, allowing the system to recover from heavy workloads more efficiently.
{"title":"Service Assurance in 5G-based vCDN","authors":"Miguel Lopes, Daniel Corujo, Paulo Duarte, Marco Araújo","doi":"10.1109/BalkanCom55633.2022.9900663","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900663","url":null,"abstract":"Due to their dynamic nature, 5G communications bring additional complexity to operator networks. Due to their reliance on network softwarization and virtualization, 5G networks can adapt themselves by changing their topology or simply by adding or removing services and resources as needed, in regards to Quality of Service (QoS) metrics. For an operator, network monitoring and orchestration gain further importance for automation and management of virtual functions life-cycle. Monitoring is a crucial aspect of the life-cycle management of virtual functions in order to ensure that the QoS metrics are met at all times. Accordingly, network orchestration is one of the fundamental pillars for the implementation of the new generation of mobile networks use cases. The Open Network Automation Platform (ONAP) is an open-source project that provides management and orchestration support for end-to-end services and infrastructures. This paper aims to explore ONAP’s capabilities, coupled with the Prometheus monitoring tool, to address the possible QoS problems of a vCDN service, more precisely, the lack of a horizontal system scaling. An experimental proof of concept evaluation provided low instantiation times, allowing the system to recover from heavy workloads more efficiently.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130321715","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 : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900869
D. Krstić, S. Suljovic, N. Petrovic, Z. Popovic, Sinisa Minic
In this paper, a moment generating function (MGF)-based calculation of average bit error probability (ABEP) of multi-branch selection combining (SC) receiver under the influence of α-k-μ fading and α-k-μ co-channel interference will be carried out. The SC receiver is implemented to reduce the effects of multiple fading and interference on the bit error probability. The influence of parameters to the proposed radio communication system will be analyzed based on plotted graphs. Further, we introduce an approach aiming Quality of Service (QoS) estimation relying on classification using Weka machine learning Application Programming Interface (API) for Java, leveraging the calculated ABEP value as input variable. Several different classification algorithms were compared regarding accuracy and execution time. Decision table-based implementation gave the highest accuracy, while J48 decision tree shows just slightly lower rate, but has much faster training rate.
{"title":"MGF Based Calculation and Simulation of ABEP for Multi-branch SC Receiver in an Environment under α-K-μ Fading and Co-channel Interference","authors":"D. Krstić, S. Suljovic, N. Petrovic, Z. Popovic, Sinisa Minic","doi":"10.1109/BalkanCom55633.2022.9900869","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900869","url":null,"abstract":"In this paper, a moment generating function (MGF)-based calculation of average bit error probability (ABEP) of multi-branch selection combining (SC) receiver under the influence of α-k-μ fading and α-k-μ co-channel interference will be carried out. The SC receiver is implemented to reduce the effects of multiple fading and interference on the bit error probability. The influence of parameters to the proposed radio communication system will be analyzed based on plotted graphs. Further, we introduce an approach aiming Quality of Service (QoS) estimation relying on classification using Weka machine learning Application Programming Interface (API) for Java, leveraging the calculated ABEP value as input variable. Several different classification algorithms were compared regarding accuracy and execution time. Decision table-based implementation gave the highest accuracy, while J48 decision tree shows just slightly lower rate, but has much faster training rate.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126114494","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 : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900607
Blaž Bertalanič, G. Morano, Gregor Cerar
While the Global Positioning System (GPS) provides high accuracy it places a significant strain on the device’s battery. In search of alternative techniques for outdoor localization, several approaches have been explored and recently Bluetooth Low Energy (BLE) is becoming a viable alternative to GPS for outdoor localization. Despite its popularity, access to open-source datasets for outdoor localization is limited. In this paper, we present a new openly available BLE fingerprint-based localization dataset that has been collected on LOG-a-TEC testedbed at the Jožef Stefan Institute, Ljubljana, Slovenia. The presented dataset was also used to develop a machine learning model that is capable of correctly classifying fingerprints with an average F1-score of 96.1%. We also provide insight into the importance of each node to the performance of the model. Although fingerprint-based localization is proving to be a robust alternative to GPS, we also show how changes in the environment can negatively impact the localization performance.
{"title":"LOG-a-TEC Testbed outdoor localization using BLE beacons","authors":"Blaž Bertalanič, G. Morano, Gregor Cerar","doi":"10.1109/BalkanCom55633.2022.9900607","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900607","url":null,"abstract":"While the Global Positioning System (GPS) provides high accuracy it places a significant strain on the device’s battery. In search of alternative techniques for outdoor localization, several approaches have been explored and recently Bluetooth Low Energy (BLE) is becoming a viable alternative to GPS for outdoor localization. Despite its popularity, access to open-source datasets for outdoor localization is limited. In this paper, we present a new openly available BLE fingerprint-based localization dataset that has been collected on LOG-a-TEC testedbed at the Jožef Stefan Institute, Ljubljana, Slovenia. The presented dataset was also used to develop a machine learning model that is capable of correctly classifying fingerprints with an average F1-score of 96.1%. We also provide insight into the importance of each node to the performance of the model. Although fingerprint-based localization is proving to be a robust alternative to GPS, we also show how changes in the environment can negatively impact the localization performance.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123912877","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 : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900546
M. Aloqaily, I. Al Ridhawi, F. Karray, M. Guizani
Cyber-physical systems (CPS) have evolved over the years and are now integrated into intelligent manufactory. The Internet of Things (IoT) has played a significant role in the advancement of such systems. CPS have become more intelligent and self-automated with the aid of advances in Artificial Intelligence (AI). Automating the process of CPS management requires that AI and secure transaction processing be integrated within all stakeholders, including the cloud, fog, edge, network, storage, and industrial devices. This integration necessitates the distribution and decentralization of the self-configuring, self-managing, self-healing, and self-governing process in CPS. This paper presents a blockchain-based hierarchical federated learning (HFL) solution that maintains quick, secure, and accurate decision-making for industrial machines. A two-stage federated learning (FL) algorithm, where during the first stage, industrial devices are grouped into clusters and perform local ML training. Local models are shared with network edge devices and a set of global models are created using FL averaging. During the second stage, a main global model is created from the distributed first-stage global models using a FL aggregating algorithm. Blockchain is used to verify and validate the trained models on the edge. System evaluations are performed to compare the proposed HFL solution against traditional FL in terms of training accuracy and network overhead.
{"title":"Towards Blockchain-based Hierarchical Federated Learning for Cyber-Physical Systems","authors":"M. Aloqaily, I. Al Ridhawi, F. Karray, M. Guizani","doi":"10.1109/BalkanCom55633.2022.9900546","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900546","url":null,"abstract":"Cyber-physical systems (CPS) have evolved over the years and are now integrated into intelligent manufactory. The Internet of Things (IoT) has played a significant role in the advancement of such systems. CPS have become more intelligent and self-automated with the aid of advances in Artificial Intelligence (AI). Automating the process of CPS management requires that AI and secure transaction processing be integrated within all stakeholders, including the cloud, fog, edge, network, storage, and industrial devices. This integration necessitates the distribution and decentralization of the self-configuring, self-managing, self-healing, and self-governing process in CPS. This paper presents a blockchain-based hierarchical federated learning (HFL) solution that maintains quick, secure, and accurate decision-making for industrial machines. A two-stage federated learning (FL) algorithm, where during the first stage, industrial devices are grouped into clusters and perform local ML training. Local models are shared with network edge devices and a set of global models are created using FL averaging. During the second stage, a main global model is created from the distributed first-stage global models using a FL aggregating algorithm. Blockchain is used to verify and validate the trained models on the edge. System evaluations are performed to compare the proposed HFL solution against traditional FL in terms of training accuracy and network overhead.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115277739","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 : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900867
Avni Rustemi, V. Atanasovski, A. Risteski
Blockchain nowadays is finding great application in many areas, based on its security, decentralized mode of operation, however many things during its use remain challenging include the issue of data privacy, such as safe and effective data management, maintaining data integrity and data quality, etc. Through this paper we will try to make an overview of existing blockchain technologies, their use today and sublimating existing and future trends. We will briefly describe application of blockchain technology in various fields suggesting solutions, advantages and disadvantages of blockchain, cloud platforms for blockchain data storage. We will focus on data privacy by making a description of the strategies used in this regard. We will conclude the paper by giving the latest research regarding data storage, the importance of data storage and our views regarding the future of data management and storage.
{"title":"Overview of Blockchain Data Storage and Privacy Protection","authors":"Avni Rustemi, V. Atanasovski, A. Risteski","doi":"10.1109/BalkanCom55633.2022.9900867","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900867","url":null,"abstract":"Blockchain nowadays is finding great application in many areas, based on its security, decentralized mode of operation, however many things during its use remain challenging include the issue of data privacy, such as safe and effective data management, maintaining data integrity and data quality, etc. Through this paper we will try to make an overview of existing blockchain technologies, their use today and sublimating existing and future trends. We will briefly describe application of blockchain technology in various fields suggesting solutions, advantages and disadvantages of blockchain, cloud platforms for blockchain data storage. We will focus on data privacy by making a description of the strategies used in this regard. We will conclude the paper by giving the latest research regarding data storage, the importance of data storage and our views regarding the future of data management and storage.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116110626","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 : 2022-08-22DOI: 10.1109/BalkanCom55633.2022.9900759
Ritayan Biswas, Joonas Säe, Jukka Lempiäinen
The objective of this article is to evaluate the maximum range of ambient backscattering communications (AmBC). FM radio signals operating at 100 MHz are selected as the ambient signal due to their large communication ranges. The FM radio signals operate in one of the lowest commercially available frequency bands that can be utilized for AmBC. Additionally, due to the extensive deployment of FM radio, this technology is readily available worldwide. Simulations are performed in a rural highway environment to analyse the suitability of FM radio as an ambient signal for backscattering communications. The FM transmitter and receiver antenna are located in approximately the same area representing a monostatic form of operation for backscattering communications. The sensors are located in more or less the line of sight (LOS) of the TX/RX antenna. The FM signal is reflected back from the sensor towards the receiver for detection. The ray-tracing technique and the radar equation are utilized to perform the simulations. Based on the ray-tracing simulations, a distance of 14.5 km was obtained between the TX/RX antenna and the sensor. The achievable distances utilising the radar equation depend significantly on the cross-section of the sensor and different sizes were utilised in the simulations.
{"title":"Evaluation of Maximum Range for Backscattering Communications Utilising Ambient FM radio signals","authors":"Ritayan Biswas, Joonas Säe, Jukka Lempiäinen","doi":"10.1109/BalkanCom55633.2022.9900759","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900759","url":null,"abstract":"The objective of this article is to evaluate the maximum range of ambient backscattering communications (AmBC). FM radio signals operating at 100 MHz are selected as the ambient signal due to their large communication ranges. The FM radio signals operate in one of the lowest commercially available frequency bands that can be utilized for AmBC. Additionally, due to the extensive deployment of FM radio, this technology is readily available worldwide. Simulations are performed in a rural highway environment to analyse the suitability of FM radio as an ambient signal for backscattering communications. The FM transmitter and receiver antenna are located in approximately the same area representing a monostatic form of operation for backscattering communications. The sensors are located in more or less the line of sight (LOS) of the TX/RX antenna. The FM signal is reflected back from the sensor towards the receiver for detection. The ray-tracing technique and the radar equation are utilized to perform the simulations. Based on the ray-tracing simulations, a distance of 14.5 km was obtained between the TX/RX antenna and the sensor. The achievable distances utilising the radar equation depend significantly on the cross-section of the sensor and different sizes were utilised in the simulations.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114909713","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 : 2021-11-15DOI: 10.1109/BalkanCom55633.2022.9900818
N. A. Letizia, A. Tonello
The development of optimal and efficient machine learning-based communication systems is likely to be a key enabler of beyond 5G communication technologies. In this direction, physical layer design has been recently reformulated under a deep learning framework where the autoencoder paradigm foresees the full communication system as an end-to-end coding-decoding problem. Given the loss function, the autoencoder jointly learns the coding and decoding optimal blocks under a certain channel model. Because performance in communications typically refers to achievable rates and channel capacity, the mutual information between channel input and output can be included in the end-to-end training process, thus, its estimation becomes essential.In this paper, we present a set of novel discriminative mutual information estimators and we discuss how to exploit them to design capacity-approaching codes and ultimately estimate the channel capacity.
{"title":"Discriminative Mutual Information Estimation for the Design of Channel Capacity Driven Autoencoders","authors":"N. A. Letizia, A. Tonello","doi":"10.1109/BalkanCom55633.2022.9900818","DOIUrl":"https://doi.org/10.1109/BalkanCom55633.2022.9900818","url":null,"abstract":"The development of optimal and efficient machine learning-based communication systems is likely to be a key enabler of beyond 5G communication technologies. In this direction, physical layer design has been recently reformulated under a deep learning framework where the autoencoder paradigm foresees the full communication system as an end-to-end coding-decoding problem. Given the loss function, the autoencoder jointly learns the coding and decoding optimal blocks under a certain channel model. Because performance in communications typically refers to achievable rates and channel capacity, the mutual information between channel input and output can be included in the end-to-end training process, thus, its estimation becomes essential.In this paper, we present a set of novel discriminative mutual information estimators and we discuss how to exploit them to design capacity-approaching codes and ultimately estimate the channel capacity.","PeriodicalId":114443,"journal":{"name":"2022 International Balkan Conference on Communications and Networking (BalkanCom)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121423286","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：