In this paper,we developed a new customizable low energy Software Defined Networking(SDN)based Internet of Things(IoT)platform that can be reconfigured according to the requirements of the target IoT applications.Tech...In this paper,we developed a new customizable low energy Software Defined Networking(SDN)based Internet of Things(IoT)platform that can be reconfigured according to the requirements of the target IoT applications.Technically,the platform consists of a set of low cost and energy efficient single-board computers,which are interconnected within a network with the software defined configuration.The proposed SDN switch is deployed on Raspberry Pi 3 board usingOpen vSwitch(OvS)software,while theFloodlight controller is deployed on the Orange Pi Prime board.We firstly presented and implemented the method formeasuring a delay introduced by each component of the IoT infrastructure,ranging from the sensor,the core of SDN,the IoT broker,to an IoT subscriber.Thus,we presented the approach for estimating energy efficiency for SDN based IoT platform proportional to the traffic.The experiments carried out on a real SDN topology based on single-board computers show that our approach not only saves up to 53.56%of energy at low traffic intensity,but also provides QoS guarantee for IoT applications.展开更多
The rapidly increasing number of Internet of Things(IoT)devices and Quality of Service(QoS)requirements have made the provisioning of network solutions to meet this demand a major research topic.Providing fast and rel...The rapidly increasing number of Internet of Things(IoT)devices and Quality of Service(QoS)requirements have made the provisioning of network solutions to meet this demand a major research topic.Providing fast and reliable routing paths based on the QoS requirements of IoT devices is very important task for Industry 4.0.The software-defined network is one of the most current interesting research developments,offering an efficient and effective solution for centralized control and network intelligence.A new SDN-IoT paradigm has been proposed to improve network QoS,taking advantage of SDN architecture in IoT networks.At the present time,most publish-subscribe IoT platforms assume the same QoS requirements for all customers.However,in many real-world scenarios of IoT applications,different subscribers may have different E2E delay requirements.Providing reliable differentiated services has become a relevant problem.For this we developed a technique for classifying IoT flows with the individual subscriber recommendation on the importance of certain parameters for particular classes of traffic taken into account.To improve the QoS for mission-critical IoT applications in large-scale SDN-IoT infrastructure,we focused on optimizing routing in the SDN.For this purpose,a centralized routing model based on QoS parameters and IoT priority flow for the SDN was proposed and implemented.We have compared the proposed routing model with the state-of-art deterministic multiconstrained centralized QoS routing model(DMCQR).The developed centralized routing model in comparison with the known DMCQR flow routing achieved better balance of channel resources load due to rational choice of transmission paths for different traffic.And it was possible to reduce up to 3 times the average delay of real time flows service from end to end,for which with the existing DMCQR routing model the permissible delay rates were not met.展开更多
The extensive proliferation of modern information services and ubiquitous digitization of society have raised cybersecurity challenges to new levels.With the massive number of connected devices,opportunities for poten...The extensive proliferation of modern information services and ubiquitous digitization of society have raised cybersecurity challenges to new levels.With the massive number of connected devices,opportunities for potential network attacks are nearly unlimited.An additional problem is that many low-cost devices are not equippedwith effective security protection so that they are easily hacked and applied within a network of bots(botnet)to perform distributed denial of service(DDoS)attacks.In this paper,we propose a novel intrusion detection system(IDS)based on deep learning that aims to identify suspicious behavior in modern heterogeneous information systems.The proposed approach is based on a deep recurrent autoencoder that learns time series of normal network behavior and detects notable network anomalies.An additional feature of the proposed IDS is that it is trained with an optimized dataset,where the number of features is reduced by 94%without classification accuracy loss.Thus,the proposed IDS remains stable in response to slight system perturbations,which do not represent network anomalies.The proposed approach is evaluated under different simulation scenarios and provides a 99%detection accuracy over known datasets while reducing the training time by an order of magnitude.展开更多
基金This research was supported by the Ukrainian Project No.0120U102201“Development the methods and unified software-hardware means for the deployment of the energy efficient intent-based multi-purpose information and communication networks”.
文摘In this paper,we developed a new customizable low energy Software Defined Networking(SDN)based Internet of Things(IoT)platform that can be reconfigured according to the requirements of the target IoT applications.Technically,the platform consists of a set of low cost and energy efficient single-board computers,which are interconnected within a network with the software defined configuration.The proposed SDN switch is deployed on Raspberry Pi 3 board usingOpen vSwitch(OvS)software,while theFloodlight controller is deployed on the Orange Pi Prime board.We firstly presented and implemented the method formeasuring a delay introduced by each component of the IoT infrastructure,ranging from the sensor,the core of SDN,the IoT broker,to an IoT subscriber.Thus,we presented the approach for estimating energy efficiency for SDN based IoT platform proportional to the traffic.The experiments carried out on a real SDN topology based on single-board computers show that our approach not only saves up to 53.56%of energy at low traffic intensity,but also provides QoS guarantee for IoT applications.
基金This research was supported by the Ukrainian project No.0120U102201“Development the methods and unified software-hardware means for the deployment of the energy efficient intent-based multi-purpose information and communication networks”and Comenius University in Bratislava,Faculty of Management.
文摘The rapidly increasing number of Internet of Things(IoT)devices and Quality of Service(QoS)requirements have made the provisioning of network solutions to meet this demand a major research topic.Providing fast and reliable routing paths based on the QoS requirements of IoT devices is very important task for Industry 4.0.The software-defined network is one of the most current interesting research developments,offering an efficient and effective solution for centralized control and network intelligence.A new SDN-IoT paradigm has been proposed to improve network QoS,taking advantage of SDN architecture in IoT networks.At the present time,most publish-subscribe IoT platforms assume the same QoS requirements for all customers.However,in many real-world scenarios of IoT applications,different subscribers may have different E2E delay requirements.Providing reliable differentiated services has become a relevant problem.For this we developed a technique for classifying IoT flows with the individual subscriber recommendation on the importance of certain parameters for particular classes of traffic taken into account.To improve the QoS for mission-critical IoT applications in large-scale SDN-IoT infrastructure,we focused on optimizing routing in the SDN.For this purpose,a centralized routing model based on QoS parameters and IoT priority flow for the SDN was proposed and implemented.We have compared the proposed routing model with the state-of-art deterministic multiconstrained centralized QoS routing model(DMCQR).The developed centralized routing model in comparison with the known DMCQR flow routing achieved better balance of channel resources load due to rational choice of transmission paths for different traffic.And it was possible to reduce up to 3 times the average delay of real time flows service from end to end,for which with the existing DMCQR routing model the permissible delay rates were not met.
基金This work was supported by the Slovak Research and Development Agency,project number APVV-18-0214by the Scientific Grant Agency of the Ministry of Education,science,research and sport of the Slovak Republic under the contract:1/0268/19by the Ukrainian government projects No.0120U102201“Development the methods and unified software-hardware means for the deployment of the energy efficient intent-based multi-purpose information and communication networks,”and No.0120U100674,“Designing the novel decentralized mobile network based on blockchain architecture and artificial intelligence for 5G/6G development in Ukraine.”。
文摘The extensive proliferation of modern information services and ubiquitous digitization of society have raised cybersecurity challenges to new levels.With the massive number of connected devices,opportunities for potential network attacks are nearly unlimited.An additional problem is that many low-cost devices are not equippedwith effective security protection so that they are easily hacked and applied within a network of bots(botnet)to perform distributed denial of service(DDoS)attacks.In this paper,we propose a novel intrusion detection system(IDS)based on deep learning that aims to identify suspicious behavior in modern heterogeneous information systems.The proposed approach is based on a deep recurrent autoencoder that learns time series of normal network behavior and detects notable network anomalies.An additional feature of the proposed IDS is that it is trained with an optimized dataset,where the number of features is reduced by 94%without classification accuracy loss.Thus,the proposed IDS remains stable in response to slight system perturbations,which do not represent network anomalies.The proposed approach is evaluated under different simulation scenarios and provides a 99%detection accuracy over known datasets while reducing the training time by an order of magnitude.