Pub Date : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966906
Siham Bouchelaghem, Hakim Boudjelaba, Mawloud Omar, M. Amad
Geolocation technology is the most exciting area of advancement in 5G, leveraging massive sources of accurate location data to provide users with effective location-positioning services and applications. As research on user mobility prediction is steadily growing in the context of 5G networks, the need for available mobility-related data is of utmost importance to support the development and evaluation of new individual mobility patterns. This paper presents a novel mobility dataset generation method for 5G networks based on users' GPS trajectory data. First, we propose aggregating the user's GPS trajectories and modeling his location history by a mobility graph representing the set of cell base stations he passed through. Second, we implement the proposed modeling approach to build a custom mobility dataset and provide a detailed description of our methodology. The generated dataset relies on mobility traces from the real-world Geolife dataset and contains the mobility graph records of 128 users. Finally, we discuss selected use cases for which we believe our dataset would be valuable.
{"title":"User Mobility Dataset for 5G Networks Based on GPS Geolocation","authors":"Siham Bouchelaghem, Hakim Boudjelaba, Mawloud Omar, M. Amad","doi":"10.1109/CAMAD55695.2022.9966906","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966906","url":null,"abstract":"Geolocation technology is the most exciting area of advancement in 5G, leveraging massive sources of accurate location data to provide users with effective location-positioning services and applications. As research on user mobility prediction is steadily growing in the context of 5G networks, the need for available mobility-related data is of utmost importance to support the development and evaluation of new individual mobility patterns. This paper presents a novel mobility dataset generation method for 5G networks based on users' GPS trajectory data. First, we propose aggregating the user's GPS trajectories and modeling his location history by a mobility graph representing the set of cell base stations he passed through. Second, we implement the proposed modeling approach to build a custom mobility dataset and provide a detailed description of our methodology. The generated dataset relies on mobility traces from the real-world Geolife dataset and contains the mobility graph records of 128 users. Finally, we discuss selected use cases for which we believe our dataset would be valuable.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116029856","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966893
Katherine McLeod, P. Spachos
Wellness assessment can provide important data to improve the health of an individual. However, constantly monitoring individual wellness has challenges due to the different and several activities people participate in throughout the day. The availability and popularity of low-cost and inexpensive Internet of Things (IoT) devices can alleviate this issue. In this work, an IoT framework is presented to examine the relationship between an individual's wellness and their surrounding environment. It uses an IoT device to collect data and forwards them using WiFi and Bluetooth Low Energy (BLE). The participants in this study are two groups of ten undergraduate students at the University of Guelph. Each group took the experiment at different times of the year. Each participant is given an Android smartphone equipped with an application, in order to complete a brief psychological survey three times per day. During the periods of completion, an IoT device in their possession is reading environmental data. The five environmental variables collected are temperature, humidity, air pressure, luminosity, and noise level. Upon submission of the survey, the results of the survey and the environmental data are sent to a server via WiFi. According to experimental results, the first group to complete the experiment indicated a correlation between stress and noise, while the second group indicated a correlation between distress and light.
{"title":"Towards an IoT Framework for Wellness Assessment","authors":"Katherine McLeod, P. Spachos","doi":"10.1109/CAMAD55695.2022.9966893","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966893","url":null,"abstract":"Wellness assessment can provide important data to improve the health of an individual. However, constantly monitoring individual wellness has challenges due to the different and several activities people participate in throughout the day. The availability and popularity of low-cost and inexpensive Internet of Things (IoT) devices can alleviate this issue. In this work, an IoT framework is presented to examine the relationship between an individual's wellness and their surrounding environment. It uses an IoT device to collect data and forwards them using WiFi and Bluetooth Low Energy (BLE). The participants in this study are two groups of ten undergraduate students at the University of Guelph. Each group took the experiment at different times of the year. Each participant is given an Android smartphone equipped with an application, in order to complete a brief psychological survey three times per day. During the periods of completion, an IoT device in their possession is reading environmental data. The five environmental variables collected are temperature, humidity, air pressure, luminosity, and noise level. Upon submission of the survey, the results of the survey and the environmental data are sent to a server via WiFi. According to experimental results, the first group to complete the experiment indicated a correlation between stress and noise, while the second group indicated a correlation between distress and light.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126073197","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966919
Farhad Rezazadeh, N. Bartzoudis
The prevalence of the Internet of things (IoT) and smart meters devices in smart grids is providing key support for measuring and analyzing the power consumption patterns. This approach enables end-user to play the role of prosumers in the market and subsequently contributes to diminish the carbon footprint and the burden on utility grids. The coordination of trading surpluses of energy that is generated by house renewable energy resources (RERs) and the supply of shortages by external networks (main grid) is a necessity. This paper proposes a hierarchical architecture to manage energy in multiple smart buildings leveraging federated deep reinforcement learning (FDRL) with dynamic load in a distributed manner. Within the context of the developed FDRL-based framework, each agent that is hosted in local building energy management systems (BEMS) trains a local deep reinforcement learning (DRL) model and shares its experience in the form of model hyperparameters to the federation layer in the energy management system (EMS). Simulation studies are conducted using one EMS and up to twenty smart houses that are equipped with photovoltaic (PV) systems and batteries. This iterative training approach enables the proposed discretized soft actor-critic (SAC) agents to aggregate the collected knowledge to expedite the overall learning procedure and reduce costs and CO2 emissions, while the federation approach can mitigate privacy breaches. The numerical results confirm the performance of the proposed framework under different daytime periods, loads, and temperatures.
{"title":"A Federated DRL Approach for Smart Micro-Grid Energy Control with Distributed Energy Resources","authors":"Farhad Rezazadeh, N. Bartzoudis","doi":"10.1109/CAMAD55695.2022.9966919","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966919","url":null,"abstract":"The prevalence of the Internet of things (IoT) and smart meters devices in smart grids is providing key support for measuring and analyzing the power consumption patterns. This approach enables end-user to play the role of prosumers in the market and subsequently contributes to diminish the carbon footprint and the burden on utility grids. The coordination of trading surpluses of energy that is generated by house renewable energy resources (RERs) and the supply of shortages by external networks (main grid) is a necessity. This paper proposes a hierarchical architecture to manage energy in multiple smart buildings leveraging federated deep reinforcement learning (FDRL) with dynamic load in a distributed manner. Within the context of the developed FDRL-based framework, each agent that is hosted in local building energy management systems (BEMS) trains a local deep reinforcement learning (DRL) model and shares its experience in the form of model hyperparameters to the federation layer in the energy management system (EMS). Simulation studies are conducted using one EMS and up to twenty smart houses that are equipped with photovoltaic (PV) systems and batteries. This iterative training approach enables the proposed discretized soft actor-critic (SAC) agents to aggregate the collected knowledge to expedite the overall learning procedure and reduce costs and CO2 emissions, while the federation approach can mitigate privacy breaches. The numerical results confirm the performance of the proposed framework under different daytime periods, loads, and temperatures.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125824525","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966910
Alessandro Brighenti, Matteo Drago, Tommaso Zugno, M. Zorzi, P. Casari
One of the main challenges of future automotive networks is the need to make vehicles aware of their surroundings. Each car will be required to collect data about the environment through dedicated sensors, and share it with its neighbors. Communicating in the millimeter wave spectrum could provide a solution for addressing such requirements. The huge amount of bandwidth available at millimeter wave frequencies, along with an optimized use of the physical resources, could provide massive data rates and low latency capabilities and enable the dissemination of real-time information. In this paper, we focus on platoons of vehicles that share LiDAR pointclouds with their platoon leader, and we use MilliCar, the ns-3 module based on the 3GPP NR V2X specifications, to provide an end-to-end performance evaluation. In particular, we study the trade-offs between using a semi-persistent resource allocation of time slots, with respect to a contention-based approach. By comparing different scheduling alternatives and different clear channel assessment thresholds, we show that coordination among different platoons can mitigate the inter-platoon interference and increase the reliability, whereas a contention-based approach achieves lower transmission delay.
未来汽车网络的主要挑战之一是需要让车辆了解周围环境。每辆车都需要通过专用传感器收集有关环境的数据，并与相邻车辆共享。在毫米波频谱中通信可以为满足这些需求提供解决方案。毫米波频率下的大量可用带宽，以及对物理资源的优化利用，可以提供巨大的数据速率和低延迟能力，并实现实时信息的传播。在本文中，我们将重点放在与排长共享激光雷达点云的车辆排上，并使用基于3GPP NR V2X规范的ns-3模块MilliCar来提供端到端的性能评估。特别是，我们研究了使用半持久的时隙资源分配与基于争用的方法之间的权衡。通过比较不同的调度方案和不同的清晰信道评估阈值，我们发现不同排之间的协调可以减少排间干扰，提高可靠性，而基于竞争的方法可以降低传输延迟。
{"title":"Performance Evaluation of Contention-based Channel Access for mmWave Sidelink Communications","authors":"Alessandro Brighenti, Matteo Drago, Tommaso Zugno, M. Zorzi, P. Casari","doi":"10.1109/CAMAD55695.2022.9966910","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966910","url":null,"abstract":"One of the main challenges of future automotive networks is the need to make vehicles aware of their surroundings. Each car will be required to collect data about the environment through dedicated sensors, and share it with its neighbors. Communicating in the millimeter wave spectrum could provide a solution for addressing such requirements. The huge amount of bandwidth available at millimeter wave frequencies, along with an optimized use of the physical resources, could provide massive data rates and low latency capabilities and enable the dissemination of real-time information. In this paper, we focus on platoons of vehicles that share LiDAR pointclouds with their platoon leader, and we use MilliCar, the ns-3 module based on the 3GPP NR V2X specifications, to provide an end-to-end performance evaluation. In particular, we study the trade-offs between using a semi-persistent resource allocation of time slots, with respect to a contention-based approach. By comparing different scheduling alternatives and different clear channel assessment thresholds, we show that coordination among different platoons can mitigate the inter-platoon interference and increase the reliability, whereas a contention-based approach achieves lower transmission delay.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"521 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123441113","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966889
Ezechiel Tape, Samir Medjiah, C. Chassot
Transmission Control Protocol (TCP) services are not suitable for all Internet applications. Also, the performance provided by TCP is suboptimal for many networks. Given this situation, several alternative protocols and new transport layer architectures have been proposed to provide efficient end-to-end communication services for QoS-constrained applications. Yet, these solutions are not deployed or adopted because they only target new applications or force the rewriting of classic socket-based (aka “legacy”) applications. At the same time, new communication paradigms (SDN/NFV, etc.) and technologies (eBPF, DPDK, RDMA, etc.) have recently emerged. These evolutions can break the ossification of the Transport layer. However, they are unequally distributed on the Internet, posing a heterogeneity problem. This article proposes a software framework (named VTL for Virtual Transport Layer) that aims to take advantage of these new technologies according to their availability, with the goal of offering the most appropriate Transport services according to the application and network context. Relying on existing protocols or Transport layer frameworks, the VTL makes it possible to deploy the best protocol solution on the end hosts or the data paths in response to the QoS needs of the applications, whether or not they are aware of the existence of the VTL.
{"title":"A Pragmatic and Realistic Approach for Providing Adapted Transport Services for All Applications","authors":"Ezechiel Tape, Samir Medjiah, C. Chassot","doi":"10.1109/CAMAD55695.2022.9966889","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966889","url":null,"abstract":"Transmission Control Protocol (TCP) services are not suitable for all Internet applications. Also, the performance provided by TCP is suboptimal for many networks. Given this situation, several alternative protocols and new transport layer architectures have been proposed to provide efficient end-to-end communication services for QoS-constrained applications. Yet, these solutions are not deployed or adopted because they only target new applications or force the rewriting of classic socket-based (aka “legacy”) applications. At the same time, new communication paradigms (SDN/NFV, etc.) and technologies (eBPF, DPDK, RDMA, etc.) have recently emerged. These evolutions can break the ossification of the Transport layer. However, they are unequally distributed on the Internet, posing a heterogeneity problem. This article proposes a software framework (named VTL for Virtual Transport Layer) that aims to take advantage of these new technologies according to their availability, with the goal of offering the most appropriate Transport services according to the application and network context. Relying on existing protocols or Transport layer frameworks, the VTL makes it possible to deploy the best protocol solution on the end hosts or the data paths in response to the QoS needs of the applications, whether or not they are aware of the existence of the VTL.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128207555","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966899
Sreelakshmi Vattaparambil Sudarsan, O. Schelén, Ulf Bodin, Nicklas Nyström
Large-scale onboarding of industrial cyber physical systems requires efficiency and security. In situations with the dynamic addition of devices (e.g., from subcontractors entering a workplace), automation of the onboarding process is desired. The Eclipse Arrowhead framework, which provides a platform for industrial automation, requires reliable, flexible, and secure device onboarding to local clouds. In this paper, we propose a device onboarding method in the Arrowhead framework where decentralized authorization is provided by Power of Attorney. The model allows users to subgrant power to trusted autonomous devices to act on their behalf. We present concepts, an implementation of the proposed system, and a use case for scalable onboarding where Powers of Attorney at two levels are used to allow a subcontractor to onboard its devices to an industrial site. We also present performance evaluation results.
{"title":"Device Onboarding in Eclipse Arrowhead Using Power of Attorney Based Authorization","authors":"Sreelakshmi Vattaparambil Sudarsan, O. Schelén, Ulf Bodin, Nicklas Nyström","doi":"10.1109/CAMAD55695.2022.9966899","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966899","url":null,"abstract":"Large-scale onboarding of industrial cyber physical systems requires efficiency and security. In situations with the dynamic addition of devices (e.g., from subcontractors entering a workplace), automation of the onboarding process is desired. The Eclipse Arrowhead framework, which provides a platform for industrial automation, requires reliable, flexible, and secure device onboarding to local clouds. In this paper, we propose a device onboarding method in the Arrowhead framework where decentralized authorization is provided by Power of Attorney. The model allows users to subgrant power to trusted autonomous devices to act on their behalf. We present concepts, an implementation of the proposed system, and a use case for scalable onboarding where Powers of Attorney at two levels are used to allow a subcontractor to onboard its devices to an industrial site. We also present performance evaluation results.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130524517","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966890
Yutong Song, Wei Wang, K. Sohraby
Non-Orthogonal Multiple Access (NOMA), is con-sidered as a potential solution for resource sharing in wireless multimedia networks because of its high spectral efficiency. In this research, we propose a new pricing scheme to uberize the NOMA network between users in the same resource block, leveraging the ride-sharing concept for better NOMA resource allocation. The pricing scheme between different users is similar to the Uber/Lyft ride-sharing system where the driver and passenger make a deal and share the power, time frame and frequency spectrum resource provided by the base station. The NOMA passenger user pays some virtual payment for wireless riding and the NOMA driver user is rewarded for willing to sharing the resource block after paying commission to the base station. The utility functions of users are derived based on the quality of wireless multimedia. The pricing and power allocation strategy is to make both driver and passenger users achieve their maximum utilities by deriving game-theoretic Nash Equilibrium. The simulation results show that the proposed NOMA ubertization game solution has potential improvement of system utility performance comparing with the orthogonal multiple access (OMA) pricing strategy.
{"title":"Uberization of NOMA Wireless Network Resource Sharing: A Driver-Passenger Game-Theoretic Approach","authors":"Yutong Song, Wei Wang, K. Sohraby","doi":"10.1109/CAMAD55695.2022.9966890","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966890","url":null,"abstract":"Non-Orthogonal Multiple Access (NOMA), is con-sidered as a potential solution for resource sharing in wireless multimedia networks because of its high spectral efficiency. In this research, we propose a new pricing scheme to uberize the NOMA network between users in the same resource block, leveraging the ride-sharing concept for better NOMA resource allocation. The pricing scheme between different users is similar to the Uber/Lyft ride-sharing system where the driver and passenger make a deal and share the power, time frame and frequency spectrum resource provided by the base station. The NOMA passenger user pays some virtual payment for wireless riding and the NOMA driver user is rewarded for willing to sharing the resource block after paying commission to the base station. The utility functions of users are derived based on the quality of wireless multimedia. The pricing and power allocation strategy is to make both driver and passenger users achieve their maximum utilities by deriving game-theoretic Nash Equilibrium. The simulation results show that the proposed NOMA ubertization game solution has potential improvement of system utility performance comparing with the orthogonal multiple access (OMA) pricing strategy.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133507503","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966892
Mahzabeen Emu, Salimur Choudhury, K. Salomaa
Embedding Service Function Chain (SFC) into the massive and resource-hungry Internet of Things (IoT) substrate graph is a critical optimization research problem. Unfortunately, the classical Integer Linear Programming (ILP) formulation for such problems is usually NP-hard. Thus, this research study presses on the need to go beyond the realms and employ Quantum Annealing (QA) to speed up the computation. To comply, we reformulate the SFC embedding problem into IoT graphs as Quadratic Unconstrained Binary Optimization (QUBO) format and propose a hybrid warm start quantum annealing (WSQA) optimization technique. Simulation results show that our proposed WSQA can improve resource utilization, accelerate computing time, and achieve a better scalability success rate at solving large-scale SFC deployment compared to standalone QA. Further along the line, this research inspires the application of quantum optimization for resource allocation in next-generation networks even with the limited availability of qubits.
{"title":"Resource Optimization of SFC Embedding for IoT Networks Using Quantum Computing","authors":"Mahzabeen Emu, Salimur Choudhury, K. Salomaa","doi":"10.1109/CAMAD55695.2022.9966892","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966892","url":null,"abstract":"Embedding Service Function Chain (SFC) into the massive and resource-hungry Internet of Things (IoT) substrate graph is a critical optimization research problem. Unfortunately, the classical Integer Linear Programming (ILP) formulation for such problems is usually NP-hard. Thus, this research study presses on the need to go beyond the realms and employ Quantum Annealing (QA) to speed up the computation. To comply, we reformulate the SFC embedding problem into IoT graphs as Quadratic Unconstrained Binary Optimization (QUBO) format and propose a hybrid warm start quantum annealing (WSQA) optimization technique. Simulation results show that our proposed WSQA can improve resource utilization, accelerate computing time, and achieve a better scalability success rate at solving large-scale SFC deployment compared to standalone QA. Further along the line, this research inspires the application of quantum optimization for resource allocation in next-generation networks even with the limited availability of qubits.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129776049","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966885
Gonzalo García-Valle, S. Colodrero, Victor Cuadrat, Guillermo Gutiérrez, Sirio Beneitez, Sergio Martínez-Navas
Optimizing power generation with photovoltaic panels seeks to achieve the best performance and efficiency, both of single panels and grids comprising several of them. The outcomes depend on ambient conditions, such as irradiance or temperature, but also on external causes (e.g., soiling) that may lead to critical power losses. This paper proposes a smart metering device containing sensors to monitor these panels continuously by collecting I-V curves, a Maximum Power Point Tracker (MPPT) to maintain the optimal operation, as well as security elements to prevent external accesses and protect the generated data. The objective is to create a predictive maintenance system with artificial intelligence algorithms on the edge. Developing those algorithms requires a characterization of the selected panels to get optimal results, detecting failures and troubles swiftly, both of the panel and the smart device. Moreover, periodically or in case of noteworthy events, the device reports the information to a cloud platform by using LoRa 2.4GHz communication protocol. The device must ensure the proper operation of panels, allowing to take sustainable corrective measures by preventing an unnecessary waste of resources (electricity or water, among others). The aim is to avoid irreparable failures that imply high costs and reach high efficiency of the monitoring system and the energy generation process.
{"title":"Design of a Smart Metering Device with Edge Computing for Monitoring Silicon Photovoltaic Panels","authors":"Gonzalo García-Valle, S. Colodrero, Victor Cuadrat, Guillermo Gutiérrez, Sirio Beneitez, Sergio Martínez-Navas","doi":"10.1109/CAMAD55695.2022.9966885","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966885","url":null,"abstract":"Optimizing power generation with photovoltaic panels seeks to achieve the best performance and efficiency, both of single panels and grids comprising several of them. The outcomes depend on ambient conditions, such as irradiance or temperature, but also on external causes (e.g., soiling) that may lead to critical power losses. This paper proposes a smart metering device containing sensors to monitor these panels continuously by collecting I-V curves, a Maximum Power Point Tracker (MPPT) to maintain the optimal operation, as well as security elements to prevent external accesses and protect the generated data. The objective is to create a predictive maintenance system with artificial intelligence algorithms on the edge. Developing those algorithms requires a characterization of the selected panels to get optimal results, detecting failures and troubles swiftly, both of the panel and the smart device. Moreover, periodically or in case of noteworthy events, the device reports the information to a cloud platform by using LoRa 2.4GHz communication protocol. The device must ensure the proper operation of panels, allowing to take sustainable corrective measures by preventing an unnecessary waste of resources (electricity or water, among others). The aim is to avoid irreparable failures that imply high costs and reach high efficiency of the monitoring system and the energy generation process.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126427654","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.10128789
Lili He, Defeng Du, Hongtao Bai, Kai Wang
At present, it is difficult to implement on-line detection on underwater equipment due to the large model of biometric algorithm. In this paper, a YOLOv4 lightweight whale detection algorithm suitable for embedded equipment is proposed. MobileNetv3 was used as the backbone network of YOLOv4 to reduce the network scale, and the neck and head network were optimized by Depthwise Separable Convolutional to achieve lightweight feature extraction. Experimental results on whale data set show that compared with YOLOv4 algorithm, the number of network parameters is reduced by 87.2%, and the detection speed is improved by 1.65 times under GPU-only and 12.56 times under CPU-only. The method presented in this paper can theoretically implement underwater whale on-line detection in embedded devices.
{"title":"Lightweight YOLOV4 algorithm for underwater whale detection","authors":"Lili He, Defeng Du, Hongtao Bai, Kai Wang","doi":"10.1109/CAMAD55695.2022.10128789","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.10128789","url":null,"abstract":"At present, it is difficult to implement on-line detection on underwater equipment due to the large model of biometric algorithm. In this paper, a YOLOv4 lightweight whale detection algorithm suitable for embedded equipment is proposed. MobileNetv3 was used as the backbone network of YOLOv4 to reduce the network scale, and the neck and head network were optimized by Depthwise Separable Convolutional to achieve lightweight feature extraction. Experimental results on whale data set show that compared with YOLOv4 algorithm, the number of network parameters is reduced by 87.2%, and the detection speed is improved by 1.65 times under GPU-only and 12.56 times under CPU-only. The method presented in this paper can theoretically implement underwater whale on-line detection in embedded devices.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124458455","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：