Darya Y. Ostrikova, Elizaveta Golos, V. Beschastnyi, Egor Machnev, Yuliya V. Gaidamaka, Konstantin E. Samouylov
The performance of 5G/6G cellular systems operating in millimeter wave (mmWave, 30–100 GHz) and sub-terahertz (sub-THz, 100–300 GHz) bands is conventionally assessed by utilizing the static distributions of user locations. The rationale is that the use of the beam tracking procedure allows for keeping the beams of a base station (BS) and user equipment (UE) aligned at all times. However, by introducing 3GPP Reduced Capability (RedCap) UEs utilizing the Radio Resource Management (RRM) Relaxation procedure, this may no longer be the case, as UEs are allowed to skip synchronization signal blocks (SSB) to improve energy efficiency. Thus, to characterize the performance of such UEs, methods explicitly accounting for UE mobility are needed. In this paper, we will utilize the tools of the stochastic geometry and random walk theory to derive signal-to-noise ratio (SNR), spectral efficiency, and rate as an explicit function of time by accounting for mmWave/sub-THZ specifics, including realistic directional antenna radiation patterns and micro- and macro-mobilities causing dynamic antenna misalignment. Different from other studies in the field that consider time-averaged performance measures, these metrics are obtained as an explicit function of time. Our numerical results illustrate that the macro-mobility specifies the overall trend of the time-dependent spectral efficiency, while local dynamics at 1–3 s scales are mainly governed by micro-mobility. The difference between spectral efficiency corresponding to perfectly synchronized UE and BS antennas and time-dependent spectral efficiency in a completely desynchronized system is rather negligible for realistic cell coverages and stays within approximately 5–10% for a wide range of system parameters. These conclusions are not affected by the utilized antenna array at the BS side. However, accounting for realistic radiation patterns is critical for a time-dependent performance analysis of 5G/6G mmWave/sub-THz systems.
{"title":"Dynamic SNR, Spectral Efficiency, and Rate Characterization in 5G/6G mmWave/sub-THz Systems with Macro- and Micro-Mobilities","authors":"Darya Y. Ostrikova, Elizaveta Golos, V. Beschastnyi, Egor Machnev, Yuliya V. Gaidamaka, Konstantin E. Samouylov","doi":"10.3390/fi16070240","DOIUrl":"https://doi.org/10.3390/fi16070240","url":null,"abstract":"The performance of 5G/6G cellular systems operating in millimeter wave (mmWave, 30–100 GHz) and sub-terahertz (sub-THz, 100–300 GHz) bands is conventionally assessed by utilizing the static distributions of user locations. The rationale is that the use of the beam tracking procedure allows for keeping the beams of a base station (BS) and user equipment (UE) aligned at all times. However, by introducing 3GPP Reduced Capability (RedCap) UEs utilizing the Radio Resource Management (RRM) Relaxation procedure, this may no longer be the case, as UEs are allowed to skip synchronization signal blocks (SSB) to improve energy efficiency. Thus, to characterize the performance of such UEs, methods explicitly accounting for UE mobility are needed. In this paper, we will utilize the tools of the stochastic geometry and random walk theory to derive signal-to-noise ratio (SNR), spectral efficiency, and rate as an explicit function of time by accounting for mmWave/sub-THZ specifics, including realistic directional antenna radiation patterns and micro- and macro-mobilities causing dynamic antenna misalignment. Different from other studies in the field that consider time-averaged performance measures, these metrics are obtained as an explicit function of time. Our numerical results illustrate that the macro-mobility specifies the overall trend of the time-dependent spectral efficiency, while local dynamics at 1–3 s scales are mainly governed by micro-mobility. The difference between spectral efficiency corresponding to perfectly synchronized UE and BS antennas and time-dependent spectral efficiency in a completely desynchronized system is rather negligible for realistic cell coverages and stays within approximately 5–10% for a wide range of system parameters. These conclusions are not affected by the utilized antenna array at the BS side. However, accounting for realistic radiation patterns is critical for a time-dependent performance analysis of 5G/6G mmWave/sub-THz systems.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141671752","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}
In the rapidly evolving landscape of scientific semiconductor laboratories (commonly known as, cleanrooms), integrated with Internet of Things (IoT) technology and Cyber-Physical Systems (CPSs), several factors including operational changes, sensor aging, software updates and the introduction of new processes or equipment can lead to dynamic and non-stationary data distributions in evolving data streams. This phenomenon, known as concept drift, poses a substantial challenge for traditional data-driven digital twin static machine learning (ML) models for anomaly detection and classification. Subsequently, the drift in normal and anomalous data distributions over time causes the model performance to decay, resulting in high false alarm rates and missed anomalies. To address this issue, we present TWIN-ADAPT, a continuous learning model within a digital twin framework designed to dynamically update and optimize its anomaly classification algorithm in response to changing data conditions. This model is evaluated against state-of-the-art concept drift adaptation models and tested under simulated drift scenarios using diverse noise distributions to mimic real-world distribution shift in anomalies. TWIN-ADAPT is applied to three critical CPS datasets of Smart Manufacturing Labs (also known as “Cleanrooms”): Fumehood, Lithography Unit and Vacuum Pump. The evaluation results demonstrate that TWIN-ADAPT’s continual learning model for optimized and adaptive anomaly classification achieves a high accuracy and F1 score of 96.97% and 0.97, respectively, on the Fumehood CPS dataset, showing an average performance improvement of 0.57% over the offline model. For the Lithography and Vacuum Pump datasets, TWIN-ADAPT achieves an average accuracy of 69.26% and 71.92%, respectively, with performance improvements of 75.60% and 10.42% over the offline model. These significant improvements highlight the efficacy of TWIN-ADAPT’s adaptive capabilities. Additionally, TWIN-ADAPT shows a very competitive performance when compared with other benchmark drift adaptation algorithms. This performance demonstrates TWIN-ADAPT’s robustness across different modalities and datasets, confirming its suitability for any IoT-driven CPS framework managing diverse data distributions in real time streams. Its adaptability and effectiveness make it a versatile tool for dynamic industrial settings.
{"title":"TWIN-ADAPT: Continuous Learning for Digital Twin-Enabled Online Anomaly Classification in IoT-Driven Smart Labs","authors":"Ragini Gupta, Beitong Tian, Yaohui Wang, Klara Nahrstedt","doi":"10.3390/fi16070239","DOIUrl":"https://doi.org/10.3390/fi16070239","url":null,"abstract":"In the rapidly evolving landscape of scientific semiconductor laboratories (commonly known as, cleanrooms), integrated with Internet of Things (IoT) technology and Cyber-Physical Systems (CPSs), several factors including operational changes, sensor aging, software updates and the introduction of new processes or equipment can lead to dynamic and non-stationary data distributions in evolving data streams. This phenomenon, known as concept drift, poses a substantial challenge for traditional data-driven digital twin static machine learning (ML) models for anomaly detection and classification. Subsequently, the drift in normal and anomalous data distributions over time causes the model performance to decay, resulting in high false alarm rates and missed anomalies. To address this issue, we present TWIN-ADAPT, a continuous learning model within a digital twin framework designed to dynamically update and optimize its anomaly classification algorithm in response to changing data conditions. This model is evaluated against state-of-the-art concept drift adaptation models and tested under simulated drift scenarios using diverse noise distributions to mimic real-world distribution shift in anomalies. TWIN-ADAPT is applied to three critical CPS datasets of Smart Manufacturing Labs (also known as “Cleanrooms”): Fumehood, Lithography Unit and Vacuum Pump. The evaluation results demonstrate that TWIN-ADAPT’s continual learning model for optimized and adaptive anomaly classification achieves a high accuracy and F1 score of 96.97% and 0.97, respectively, on the Fumehood CPS dataset, showing an average performance improvement of 0.57% over the offline model. For the Lithography and Vacuum Pump datasets, TWIN-ADAPT achieves an average accuracy of 69.26% and 71.92%, respectively, with performance improvements of 75.60% and 10.42% over the offline model. These significant improvements highlight the efficacy of TWIN-ADAPT’s adaptive capabilities. Additionally, TWIN-ADAPT shows a very competitive performance when compared with other benchmark drift adaptation algorithms. This performance demonstrates TWIN-ADAPT’s robustness across different modalities and datasets, confirming its suitability for any IoT-driven CPS framework managing diverse data distributions in real time streams. Its adaptability and effectiveness make it a versatile tool for dynamic industrial settings.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141678233","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}
Badr Ben Elallid, Nabil Benamar, Miloud Bagaa, Yassine Hadjadj-Aoul
Autonomous vehicles have gained extensive attention in recent years, both in academia and industry. For these self-driving vehicles, decision-making in urban environments poses significant challenges due to the unpredictable behavior of traffic participants and intricate road layouts. While existing decision-making approaches based on Deep Reinforcement Learning (DRL) show potential for tackling urban driving situations, they suffer from slow convergence, especially in complex scenarios with high mobility. In this paper, we present a new approach based on the Soft Actor-Critic (SAC) algorithm to control the autonomous vehicle to enter roundabouts smoothly and safely and ensure it reaches its destination without delay. For this, we introduce a destination vector concatenated with extracted features using Convolutional Neural Networks (CNN). To evaluate the performance of our model, we conducted extensive experiments in the CARLA simulator and compared it with the Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) models. Qualitative results reveal that our model converges rapidly and achieves a high success rate in scenarios with high traffic compared to the DQN and PPO models.
{"title":"Enhancing Autonomous Driving Navigation Using Soft Actor-Critic","authors":"Badr Ben Elallid, Nabil Benamar, Miloud Bagaa, Yassine Hadjadj-Aoul","doi":"10.3390/fi16070238","DOIUrl":"https://doi.org/10.3390/fi16070238","url":null,"abstract":"Autonomous vehicles have gained extensive attention in recent years, both in academia and industry. For these self-driving vehicles, decision-making in urban environments poses significant challenges due to the unpredictable behavior of traffic participants and intricate road layouts. While existing decision-making approaches based on Deep Reinforcement Learning (DRL) show potential for tackling urban driving situations, they suffer from slow convergence, especially in complex scenarios with high mobility. In this paper, we present a new approach based on the Soft Actor-Critic (SAC) algorithm to control the autonomous vehicle to enter roundabouts smoothly and safely and ensure it reaches its destination without delay. For this, we introduce a destination vector concatenated with extracted features using Convolutional Neural Networks (CNN). To evaluate the performance of our model, we conducted extensive experiments in the CARLA simulator and compared it with the Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) models. Qualitative results reveal that our model converges rapidly and achieves a high success rate in scenarios with high traffic compared to the DQN and PPO models.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141679855","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}
The Internet of Things (IoT) has become ubiquitous. IoT devices are applied in a multitude of applications, e.g., in smart home scenarios, building automation, smart energy and smart cities, healthcare, and industrial environments. Fast and efficient implementation and roll-out of IoT devices is a critical factor for successs and acceptance of IoT devices. At the same time, the variety of hardware platforms that can be used for IoT applications, as well as the number of IoT orchestration platforms is increasing. Finding the right combination of tooling and hardware is not trivial, but essential for building applications that provide value. In this work, a Software-Bus-Toolchain (SBT) is introduced that encapsulates firmware design, data point definition, and communication protocol usage. Furthermore, an IoT control platform is provided to control and evaluate the IoT modules. Thus, using the SBT, solely the business logic has to be designed, while the hardware-design is automated to a high degree. Usage of the Zephyr framework allows the interchange of hardware modules, while interfaces provide easy adaption of data points and communication capabilities. The implementation of interfaces to the IoT-platform as well as to the communication layer provides a universal usage of logic and data elements. The SBT is evaluated in two application scenarios, where its flexible nature is shown.
{"title":"Software-Bus-Toolchain (SBT): Introducing a Versatile Method for Quickly Implementing (I)IoT-Scenarios","authors":"Simon D. Duque Anton","doi":"10.3390/fi16070237","DOIUrl":"https://doi.org/10.3390/fi16070237","url":null,"abstract":"The Internet of Things (IoT) has become ubiquitous. IoT devices are applied in a multitude of applications, e.g., in smart home scenarios, building automation, smart energy and smart cities, healthcare, and industrial environments. Fast and efficient implementation and roll-out of IoT devices is a critical factor for successs and acceptance of IoT devices. At the same time, the variety of hardware platforms that can be used for IoT applications, as well as the number of IoT orchestration platforms is increasing. Finding the right combination of tooling and hardware is not trivial, but essential for building applications that provide value. In this work, a Software-Bus-Toolchain (SBT) is introduced that encapsulates firmware design, data point definition, and communication protocol usage. Furthermore, an IoT control platform is provided to control and evaluate the IoT modules. Thus, using the SBT, solely the business logic has to be designed, while the hardware-design is automated to a high degree. Usage of the Zephyr framework allows the interchange of hardware modules, while interfaces provide easy adaption of data points and communication capabilities. The implementation of interfaces to the IoT-platform as well as to the communication layer provides a universal usage of logic and data elements. The SBT is evaluated in two application scenarios, where its flexible nature is shown.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682457","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}
In recent years, the attention paid to the metaverse in the scientific world has increased; the hottest topics include system architecture and enabling technologies, as well as business, privacy, ethical, and security issues. On the other side, at the mainstream level, it is well known that the company Meta (formerly Facebook) is striving to realize its interpretation of a “social” metaverse. As Meta is a big leader of social media, it is reasonable to guess that, in the future, users will participate in a new social platform, such as that which the company is building by depicting unlimited and engaging opportunities. Regardless of Meta, we ask what the opinion of people is about this possible future scenario. A literature search of previous works about this topic has been done; the few results we found were not properly on topic and showed heterogeneous content. A survey on interpretations of the metaverse of major information and communication technologies (ICT) companies that impact the consumer world was undertaken; the results show that Meta is the most prominent company with the mission of building a ”social” metaverse worldwide. Finally, a draft of a tool for assessing the predilection of people for a “social” metaverse, based on various facets of the future social platform, is proposed.
近年来，科学界对元宇宙的关注与日俱增；最热门的话题包括系统架构和使能技术，以及商业、隐私、伦理和安全问题。另一方面，在主流层面，众所周知，Meta 公司（前身为 Facebook）正在努力实现其对 "社交 "元宇宙的诠释。由于 Meta 公司是社交媒体领域的领军企业，我们有理由猜测，未来用户将参与到一个新的社交平台中，比如该公司通过描绘无限的参与机会而建立的平台。无论 Meta 如何，我们要问的是，人们对这种未来可能出现的情况有何看法。我们对以往有关这一主题的著作进行了文献检索，发现为数不多的成果并不符合主题，内容也参差不齐。我们还对影响消费者世界的主要信息和通信技术（ICT）公司对元宇宙的解释进行了调查；结果显示，Meta 是以在全球建立 "社会 "元宇宙为使命的最著名公司。最后，根据未来社交平台的各个方面，提出了评估人们对 "社交 "元宇宙偏好的工具草案。
{"title":"Does Anyone Care about the Opinion of People on Participating in a “Social” Metaverse? A Review and a Draft Proposal for a Surveying Tool","authors":"Stefano Mottura","doi":"10.3390/fi16070236","DOIUrl":"https://doi.org/10.3390/fi16070236","url":null,"abstract":"In recent years, the attention paid to the metaverse in the scientific world has increased; the hottest topics include system architecture and enabling technologies, as well as business, privacy, ethical, and security issues. On the other side, at the mainstream level, it is well known that the company Meta (formerly Facebook) is striving to realize its interpretation of a “social” metaverse. As Meta is a big leader of social media, it is reasonable to guess that, in the future, users will participate in a new social platform, such as that which the company is building by depicting unlimited and engaging opportunities. Regardless of Meta, we ask what the opinion of people is about this possible future scenario. A literature search of previous works about this topic has been done; the few results we found were not properly on topic and showed heterogeneous content. A survey on interpretations of the metaverse of major information and communication technologies (ICT) companies that impact the consumer world was undertaken; the results show that Meta is the most prominent company with the mission of building a ”social” metaverse worldwide. Finally, a draft of a tool for assessing the predilection of people for a “social” metaverse, based on various facets of the future social platform, is proposed.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141686995","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}
In recent years, various Remote Code Execution vulnerabilities on the Internet have been exposed frequently; thus, more and more security researchers have begun to pay attention to the detection of Remote Code Execution attacks. In this paper, we focus on three kinds of common Remote Code Execution attacks: XML External Entity, Expression Language Injection, and Insecure Deserialization. We propose a packet content-oriented Remote Code Execution attack payload detection model. For the XML External Entity attack, we propose an algorithm to construct the use-definition chain of XML entities, and implement detection based on the integrity of the chain and the behavior of the chain’s tail node. For the Expression Language Injection and Insecure Deserialization attack, we extract 34 features to represent the string operation and the use of sensitive classes/methods in the code, and then train a machine learning model to implement detection. At the same time, we build a dataset to evaluate the effect of the proposed model. The evaluation results show that the model performs well in detecting XML External Entity attacks, achieving a precision of 0.85 and a recall of 0.94. Similarly, the model performs well in detecting Expression Language Injection and Insecure Deserialization attacks, achieving a precision of 0.99 and a recall of 0.88.
近年来，互联网上各种远程代码执行（Remote Code Execution）漏洞频频曝光，越来越多的安全研究人员开始关注远程代码执行攻击的检测。本文重点讨论三种常见的远程代码执行攻击：XML 外部实体、表达式语言注入和不安全反序列化。我们提出了一种面向数据包内容的远程代码执行攻击有效载荷检测模型。针对 XML 外部实体攻击，我们提出了一种构建 XML 实体使用定义链的算法，并根据链的完整性和链尾节点的行为实施检测。针对表达式语言注入和不安全反序列化攻击，我们提取了 34 个特征来表示代码中的字符串操作和敏感类/方法的使用，然后训练一个机器学习模型来实现检测。同时，我们建立了一个数据集来评估所提出模型的效果。评估结果表明，该模型在检测 XML 外部实体攻击方面表现良好，精确度达到 0.85，召回率达到 0.94。同样，该模型在检测表达式语言注入和不安全反序列化攻击方面也表现出色，精确度达到 0.99，召回率达到 0.88。
{"title":"A Packet Content-Oriented Remote Code Execution Attack Payload Detection Model","authors":"Enbo Sun, Jiaxuan Han, Yiquan Li, Cheng Huang","doi":"10.3390/fi16070235","DOIUrl":"https://doi.org/10.3390/fi16070235","url":null,"abstract":"In recent years, various Remote Code Execution vulnerabilities on the Internet have been exposed frequently; thus, more and more security researchers have begun to pay attention to the detection of Remote Code Execution attacks. In this paper, we focus on three kinds of common Remote Code Execution attacks: XML External Entity, Expression Language Injection, and Insecure Deserialization. We propose a packet content-oriented Remote Code Execution attack payload detection model. For the XML External Entity attack, we propose an algorithm to construct the use-definition chain of XML entities, and implement detection based on the integrity of the chain and the behavior of the chain’s tail node. For the Expression Language Injection and Insecure Deserialization attack, we extract 34 features to represent the string operation and the use of sensitive classes/methods in the code, and then train a machine learning model to implement detection. At the same time, we build a dataset to evaluate the effect of the proposed model. The evaluation results show that the model performs well in detecting XML External Entity attacks, achieving a precision of 0.85 and a recall of 0.94. Similarly, the model performs well in detecting Expression Language Injection and Insecure Deserialization attacks, achieving a precision of 0.99 and a recall of 0.88.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141684201","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}
In data center networks, when facing challenges such as traffic volatility, low resource utilization, and the difficulty of a single traffic scheduling strategy to meet demands, it is necessary to introduce intelligent traffic scheduling mechanisms to improve network resource utilization, optimize network performance, and adapt to the traffic scheduling requirements in a dynamic environment. This paper proposes a fine-grained traffic scheduling scheme based on multi-agent deep reinforcement learning (MAFS). This approach utilizes In-Band Network Telemetry to collect real-time network states on the programmable data plane, establishes the mapping relationship between real-time network state information and the forwarding efficiency on the control plane, and designs a multi-agent deep reinforcement learning algorithm to calculate the optimal routing strategy under the current network state. The experimental results demonstrate that compared to other traffic scheduling methods, MAFS can effectively enhance network throughput. It achieves a 1.2× better average throughput and achieves a 1.4–1.7× lower packet loss rate.
{"title":"Multi-Agent Deep Reinforcement Learning-Based Fine-Grained Traffic Scheduling in Data Center Networks","authors":"Huiting Wang, Yazhi Liu, Wei Li, Zhigang Yang","doi":"10.3390/fi16040119","DOIUrl":"https://doi.org/10.3390/fi16040119","url":null,"abstract":"In data center networks, when facing challenges such as traffic volatility, low resource utilization, and the difficulty of a single traffic scheduling strategy to meet demands, it is necessary to introduce intelligent traffic scheduling mechanisms to improve network resource utilization, optimize network performance, and adapt to the traffic scheduling requirements in a dynamic environment. This paper proposes a fine-grained traffic scheduling scheme based on multi-agent deep reinforcement learning (MAFS). This approach utilizes In-Band Network Telemetry to collect real-time network states on the programmable data plane, establishes the mapping relationship between real-time network state information and the forwarding efficiency on the control plane, and designs a multi-agent deep reinforcement learning algorithm to calculate the optimal routing strategy under the current network state. The experimental results demonstrate that compared to other traffic scheduling methods, MAFS can effectively enhance network throughput. It achieves a 1.2× better average throughput and achieves a 1.4–1.7× lower packet loss rate.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140361224","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}
Manar Aldaoud, Dawood Al-Abri, M. Awadalla, F. Kausar
Named Data Networking (NDN) is a future Internet architecture that requires an Inter-Domain Routing (IDR) to route its traffic globally. Address resolution is a vital component of any IDR system that relies on a Domain Name System (DNS) resolver to translate domain names into their IP addresses in TCP/IP networks. This paper presents a novel two-element solution to enhance name-to-delivery location resolution in NDN networks, consisting of (1) a mapping table data structure and a searching mechanism and (2) a management protocol to automatically populate and modify the mapping table. The proposed solution is implemented and tested on the Peer Name Provider Server (PNPS) mapping table, and its performance is compared with two other algorithms: component and character tries. The findings show a notable enhancement in the operational speed of the mapping table when utilizing the proposed data structure. For instance, the insertion process is 37 times faster compared to previous algorithms.
{"title":"Data Structure and Management Protocol to Enhance Name Resolving in Named Data Networking","authors":"Manar Aldaoud, Dawood Al-Abri, M. Awadalla, F. Kausar","doi":"10.3390/fi16040118","DOIUrl":"https://doi.org/10.3390/fi16040118","url":null,"abstract":"Named Data Networking (NDN) is a future Internet architecture that requires an Inter-Domain Routing (IDR) to route its traffic globally. Address resolution is a vital component of any IDR system that relies on a Domain Name System (DNS) resolver to translate domain names into their IP addresses in TCP/IP networks. This paper presents a novel two-element solution to enhance name-to-delivery location resolution in NDN networks, consisting of (1) a mapping table data structure and a searching mechanism and (2) a management protocol to automatically populate and modify the mapping table. The proposed solution is implemented and tested on the Peer Name Provider Server (PNPS) mapping table, and its performance is compared with two other algorithms: component and character tries. The findings show a notable enhancement in the operational speed of the mapping table when utilizing the proposed data structure. For instance, the insertion process is 37 times faster compared to previous algorithms.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140361987","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}
Binita Kusum Dhamala, Babu R. Dawadi, Pietro Manzoni, B. K. Acharya
Graph representation is recognized as an efficient method for modeling networks, precisely illustrating intricate, dynamic interactions within various entities of networks by representing entities as nodes and their relationships as edges. Leveraging the advantage of the network graph data along with deep learning technologies specialized for analyzing graph data, Graph Neural Networks (GNNs) have revolutionized the field of computer networking by effectively handling structured graph data and enabling precise predictions for various use cases such as performance modeling, routing optimization, and resource allocation. The RouteNet model, utilizing a GNN, has been effectively applied in determining Quality of Service (QoS) parameters for each source-to-destination pair in computer networks. However, a prevalent issue in the current GNN model is their struggle with generalization and capturing the complex relationships and patterns within network data. This research aims to enhance the predictive power of GNN-based models by enhancing the original RouteNet model by incorporating an attention layer into its architecture. A comparative analysis is conducted to evaluate the performance of the Modified RouteNet model against the Original RouteNet model. The effectiveness of the added attention layer has been examined to determine its impact on the overall model performance. The outcomes of this research contribute to advancing GNN-based network performance prediction, addressing the limitations of existing models, and providing reliable frameworks for predicting network delay.
{"title":"Performance Evaluation of Graph Neural Network-Based RouteNet Model with Attention Mechanism","authors":"Binita Kusum Dhamala, Babu R. Dawadi, Pietro Manzoni, B. K. Acharya","doi":"10.3390/fi16040116","DOIUrl":"https://doi.org/10.3390/fi16040116","url":null,"abstract":"Graph representation is recognized as an efficient method for modeling networks, precisely illustrating intricate, dynamic interactions within various entities of networks by representing entities as nodes and their relationships as edges. Leveraging the advantage of the network graph data along with deep learning technologies specialized for analyzing graph data, Graph Neural Networks (GNNs) have revolutionized the field of computer networking by effectively handling structured graph data and enabling precise predictions for various use cases such as performance modeling, routing optimization, and resource allocation. The RouteNet model, utilizing a GNN, has been effectively applied in determining Quality of Service (QoS) parameters for each source-to-destination pair in computer networks. However, a prevalent issue in the current GNN model is their struggle with generalization and capturing the complex relationships and patterns within network data. This research aims to enhance the predictive power of GNN-based models by enhancing the original RouteNet model by incorporating an attention layer into its architecture. A comparative analysis is conducted to evaluate the performance of the Modified RouteNet model against the Original RouteNet model. The effectiveness of the added attention layer has been examined to determine its impact on the overall model performance. The outcomes of this research contribute to advancing GNN-based network performance prediction, addressing the limitations of existing models, and providing reliable frameworks for predicting network delay.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140366621","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}
Anton Dolhopolov, Arnaud Castelltort, Anne Laurent
Analytical data platforms have been used for decades to improve organizational performance. Starting from the data warehouses used primarily for structured data processing, through the data lakes oriented for raw data storage and post-hoc data analyses, to the data lakehouses—a combination of raw storage and business intelligence pre-processing for improving the platform’s efficacy. But in recent years, a new architecture called Data Mesh has emerged. The main promise of this architecture is to remove the barriers between operational and analytical teams in order to boost the overall value extraction from the big data. A number of attempts have been made to formalize and implement it in existing projects. Although being defined as a socio-technical paradigm, data mesh still lacks the technology support to enable its widespread adoption. To overcome this limitation, we propose a new view of the platform requirements alongside the formal governance definition that we believe can help in the successful adoption of the data mesh. It is based on fundamental aspects such as decentralized data domains and federated computational governance. In addition, we also present a blockchain-based implementation of a mesh platform as a practical validation of our theoretical proposal. Overall, this article demonstrates a novel research direction for information system decentralization technologies.
{"title":"Implementing Federated Governance in Data Mesh Architecture","authors":"Anton Dolhopolov, Arnaud Castelltort, Anne Laurent","doi":"10.3390/fi16040115","DOIUrl":"https://doi.org/10.3390/fi16040115","url":null,"abstract":"Analytical data platforms have been used for decades to improve organizational performance. Starting from the data warehouses used primarily for structured data processing, through the data lakes oriented for raw data storage and post-hoc data analyses, to the data lakehouses—a combination of raw storage and business intelligence pre-processing for improving the platform’s efficacy. But in recent years, a new architecture called Data Mesh has emerged. The main promise of this architecture is to remove the barriers between operational and analytical teams in order to boost the overall value extraction from the big data. A number of attempts have been made to formalize and implement it in existing projects. Although being defined as a socio-technical paradigm, data mesh still lacks the technology support to enable its widespread adoption. To overcome this limitation, we propose a new view of the platform requirements alongside the formal governance definition that we believe can help in the successful adoption of the data mesh. It is based on fundamental aspects such as decentralized data domains and federated computational governance. In addition, we also present a blockchain-based implementation of a mesh platform as a practical validation of our theoretical proposal. Overall, this article demonstrates a novel research direction for information system decentralization technologies.","PeriodicalId":509567,"journal":{"name":"Future Internet","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140366294","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：