Pub Date : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333934
Cheng-Che Huang, Yu-Cheng Chien, Jia-Cheng Zhang, N. Huang
A lightweight protocol stack is designed using layered approach and is versatile enough to be transplanted onto several LPWAN technologies. The design is implemented on the top of NB-IoT protocols in our experiments. Data aggregation and delay tolerance are expected to help IoT devices to improve data reliability. The proposed algorithm, Data Reselection Algorithm, retains all timelines of collected data in limited storage space. Finally, to validate the performance, related experiments conducted with the MCU nRF52832 are also done in this paper.
{"title":"Reliable and Delay Tolerant Transmission Protocols for LPWAN IoT Sensors","authors":"Cheng-Che Huang, Yu-Cheng Chien, Jia-Cheng Zhang, N. Huang","doi":"10.1109/ICOIN50884.2021.9333934","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333934","url":null,"abstract":"A lightweight protocol stack is designed using layered approach and is versatile enough to be transplanted onto several LPWAN technologies. The design is implemented on the top of NB-IoT protocols in our experiments. Data aggregation and delay tolerance are expected to help IoT devices to improve data reliability. The proposed algorithm, Data Reselection Algorithm, retains all timelines of collected data in limited storage space. Finally, to validate the performance, related experiments conducted with the MCU nRF52832 are also done in this paper.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"77 1","pages":"553-558"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73650200","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333911
Guangyu Zhu, Jaehyun Han, Sangjin Lee, Yongseok Son
Cloud computing arouses the need for large-scale data processing which in turn promises vigorous developments on distributed file systems. The performance of the underlying storage nodes determines the performance of the overall system. Emerging byte-addressable Non-volatile memories (NVM) are promising techniques that can greatly improve storage performance. Researchers have already investigated NVM or NVMaware file systems to take advantage of the characteristics of NVM. However, previous researchers usually perform the studies based on simulations or emulations. In this paper, we provide an empirical evaluation of NVM-aware file systems on the first commercially available byte-addressable NVM (i.e., the Intel Optane DC Persistent Memory Module (DCPMM)) We first evaluate the performance of Ext4, XFS, F2FS, Ext4-DAX, XFSDAX, and NOVA file systems on DCPMM, Optane SSD, and NVMe SSD. Then we compare them in terms of throughput and different access patterns. Second, we observe how remote NUMA node access and device mapper striping affect the performance of DCPMM. We anticipate that the experimental results and performance analysis will provide the implications on various memory and storage systems.
云计算引起了对大规模数据处理的需求，这反过来又保证了分布式文件系统的蓬勃发展。底层存储节点的性能决定着整个系统的性能。新兴的字节可寻址非易失性存储器(NVM)是一种很有前途的技术，可以极大地提高存储性能。研究人员已经研究了NVM或NVMaware文件系统，以利用NVM的特性。然而，以前的研究人员通常是基于模拟或仿真来进行研究的。在本文中，我们在第一个商业可用的字节可寻址NVM(即Intel Optane DC Persistent Memory Module (DCPMM))上对NVM感知文件系统进行了实证评估。我们首先在DCPMM、Optane SSD和NVMe SSD上评估了Ext4、XFS、F2FS、Ext4- dax、XFSDAX和NOVA文件系统的性能。然后比较它们的吞吐量和不同的访问模式。其次，我们观察了远程NUMA节点访问和设备映射器条带化如何影响DCPMM的性能。我们预计实验结果和性能分析将为各种内存和存储系统提供启示。
{"title":"An Empirical Evaluation of NVM-aware File Systems on Intel Optane DC Persistent Memory Modules","authors":"Guangyu Zhu, Jaehyun Han, Sangjin Lee, Yongseok Son","doi":"10.1109/ICOIN50884.2021.9333911","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333911","url":null,"abstract":"Cloud computing arouses the need for large-scale data processing which in turn promises vigorous developments on distributed file systems. The performance of the underlying storage nodes determines the performance of the overall system. Emerging byte-addressable Non-volatile memories (NVM) are promising techniques that can greatly improve storage performance. Researchers have already investigated NVM or NVMaware file systems to take advantage of the characteristics of NVM. However, previous researchers usually perform the studies based on simulations or emulations. In this paper, we provide an empirical evaluation of NVM-aware file systems on the first commercially available byte-addressable NVM (i.e., the Intel Optane DC Persistent Memory Module (DCPMM)) We first evaluate the performance of Ext4, XFS, F2FS, Ext4-DAX, XFSDAX, and NOVA file systems on DCPMM, Optane SSD, and NVMe SSD. Then we compare them in terms of throughput and different access patterns. Second, we observe how remote NUMA node access and device mapper striping affect the performance of DCPMM. We anticipate that the experimental results and performance analysis will provide the implications on various memory and storage systems.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"40 1","pages":"559-564"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77534522","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333930
S. Zulqarnain, Sanghwan Lee
Recently, some researchers consider remote driving as an augmentation of autonomous driving as level four autonomy in which the driver can rest while driving is not likely to be achieved in a near future. Besides functioning as an augmentation to autonomous driving, we consider remote driving as a major component to transform the current transportation system in a more fundamental way. Basically, all the vehicles in an area can be controlled by some remote controllers or drivers so that transportation can be performed in a more efficient way. For example, if a remote controller decides all the routes of the vehicles, the road capacity can be efficiently used so that the vehicles can arrive at the destinations faster. Fuel efficiency can also be achieved by creating a platoon with the vehicles having similar routes. However, one of the biggest challenges in remote driving is the communication latency between the remote driver and the vehicle. Thus, the remote drivers should be within a certain latency limit to avoid any type of safety problem. Actually, in our past work, we have introduced an algorithm called Longest Advance First (LAF) to select the locations of remote drivers for a single vehicle in a single journey. LAF can achieve an optimal selection of drivers in terms of the number of drivers. In this paper, we consider a remote driving framework where multiple vehicles are controlled by remote drivers at the same time. Applying LAF to each route may not be optimal for multiple routes. Thus, we propose a heuristic algorithm that can select locations of remote driving facilities in which remote drivers drive vehicles for multiple routes. Through simulations, we show that the proposed algorithm shows much better performance than applying LAF multiple times.
{"title":"An Efficient Driver Selection Algorithm for Controlling Multiple Vehicles in Remote Driving","authors":"S. Zulqarnain, Sanghwan Lee","doi":"10.1109/ICOIN50884.2021.9333930","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333930","url":null,"abstract":"Recently, some researchers consider remote driving as an augmentation of autonomous driving as level four autonomy in which the driver can rest while driving is not likely to be achieved in a near future. Besides functioning as an augmentation to autonomous driving, we consider remote driving as a major component to transform the current transportation system in a more fundamental way. Basically, all the vehicles in an area can be controlled by some remote controllers or drivers so that transportation can be performed in a more efficient way. For example, if a remote controller decides all the routes of the vehicles, the road capacity can be efficiently used so that the vehicles can arrive at the destinations faster. Fuel efficiency can also be achieved by creating a platoon with the vehicles having similar routes. However, one of the biggest challenges in remote driving is the communication latency between the remote driver and the vehicle. Thus, the remote drivers should be within a certain latency limit to avoid any type of safety problem. Actually, in our past work, we have introduced an algorithm called Longest Advance First (LAF) to select the locations of remote drivers for a single vehicle in a single journey. LAF can achieve an optimal selection of drivers in terms of the number of drivers. In this paper, we consider a remote driving framework where multiple vehicles are controlled by remote drivers at the same time. Applying LAF to each route may not be optimal for multiple routes. Thus, we propose a heuristic algorithm that can select locations of remote driving facilities in which remote drivers drive vehicles for multiple routes. Through simulations, we show that the proposed algorithm shows much better performance than applying LAF multiple times.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"209 1","pages":"20-23"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80566576","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333913
Ajit Kumar, N. Saxena, B. Choi
Electric grids are becoming smart due to the integration of Information and Communication Technology (ICT) with the traditional grid. However, it can also attract various kinds of Cyber-attacks to the grid infrastructure. The False Data Injection Attack (FDIA) is one of the lethal and most occurring attacks possible in both the physical and cyber part of the smart grid. This paper proposed an approach by applying machine learning algorithms to detect FDIAs in the power system. Several feature selection techniques are explored to investigate the most suitable features to achieve high accuracy. Various machine learning algorithms are tested to follow the most suitable method for building a detection system against such attacks. Also, the dataset has a skewed distribution between the two classes, and hence data imbalance issue is addressed during the experiments. Moreover, because the response time is critical in a smart grid, each experiment is also evaluated in terms of time complexity.
{"title":"Machine Learning Algorithm for Detection of False Data Injection Attack in Power System","authors":"Ajit Kumar, N. Saxena, B. Choi","doi":"10.1109/ICOIN50884.2021.9333913","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333913","url":null,"abstract":"Electric grids are becoming smart due to the integration of Information and Communication Technology (ICT) with the traditional grid. However, it can also attract various kinds of Cyber-attacks to the grid infrastructure. The False Data Injection Attack (FDIA) is one of the lethal and most occurring attacks possible in both the physical and cyber part of the smart grid. This paper proposed an approach by applying machine learning algorithms to detect FDIAs in the power system. Several feature selection techniques are explored to investigate the most suitable features to achieve high accuracy. Various machine learning algorithms are tested to follow the most suitable method for building a detection system against such attacks. Also, the dataset has a skewed distribution between the two classes, and hence data imbalance issue is addressed during the experiments. Moreover, because the response time is critical in a smart grid, each experiment is also evaluated in terms of time complexity.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"1 1","pages":"385-390"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88170969","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333921
Chaeeun Jeong, Seongju Kang, K. Chung
In online broadcasting, users are exposed to advertisements for various items. Traditional advertising systems do not satisfy the expectations of various users because they provide advertisements without considering the characteristics of individuals. Personalized advertisement services can be provided by introducing recommendation algorithms that take account of users’ context and history. However, since the existing recommendation system is based on users’ consumption history, it does not quickly reflect the users’ interests that change according to items appearing in the content. In addition, when the user’s history is sparse, the performance of the recommendation system is degraded. In this paper, we propose a recommendation system for online broadcasting advertisements. The proposed system calculates the similarity between users based on the user’s region of interest (ROI). The user’s preference for the item is predicted by comparing the rating history of similar users. To reduce the time for calculating the similarity between users, a tree-structured user profile model is introduced. Finally, we conduct experiments to evaluate the performance of the proposed advertisement recommendation system.
{"title":"Real-Time Recommendation System for Online Broadcasting Advertisement","authors":"Chaeeun Jeong, Seongju Kang, K. Chung","doi":"10.1109/ICOIN50884.2021.9333921","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333921","url":null,"abstract":"In online broadcasting, users are exposed to advertisements for various items. Traditional advertising systems do not satisfy the expectations of various users because they provide advertisements without considering the characteristics of individuals. Personalized advertisement services can be provided by introducing recommendation algorithms that take account of users’ context and history. However, since the existing recommendation system is based on users’ consumption history, it does not quickly reflect the users’ interests that change according to items appearing in the content. In addition, when the user’s history is sparse, the performance of the recommendation system is degraded. In this paper, we propose a recommendation system for online broadcasting advertisements. The proposed system calculates the similarity between users based on the user’s region of interest (ROI). The user’s preference for the item is predicted by comparing the rating history of similar users. To reduce the time for calculating the similarity between users, a tree-structured user profile model is introduced. Finally, we conduct experiments to evaluate the performance of the proposed advertisement recommendation system.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"8 1","pages":"413-416"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87383982","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9334011
Min-Hyung Rhie, Kyung-Hoon Kim, Dongyeop Hwang, Ki-Hyung Kim
In this paper, we analyzed the vulnerabilities that could occur when a third party who is not the owner of a Decentralized Identifier (DID) has the authority to modify a DID Document. DID is a technology that allows individuals to have data sovereignty. The DID Document contains information for authenticating the DID owner. A DID Controller has the authority to modify DID Document. This authority is being standardized so that it can be held by third parties as well as DID owners. It is a matter of changing the DID document against the will of the DID owner. To help owners assert their sovereignty even stronger, we propose a way for DID owners to use a policy, history, and service to verify the DID Document updating process.
{"title":"Vulnerability Analysis of DID Document’s Updating Process in the Decentralized Identifier Systems","authors":"Min-Hyung Rhie, Kyung-Hoon Kim, Dongyeop Hwang, Ki-Hyung Kim","doi":"10.1109/ICOIN50884.2021.9334011","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9334011","url":null,"abstract":"In this paper, we analyzed the vulnerabilities that could occur when a third party who is not the owner of a Decentralized Identifier (DID) has the authority to modify a DID Document. DID is a technology that allows individuals to have data sovereignty. The DID Document contains information for authenticating the DID owner. A DID Controller has the authority to modify DID Document. This authority is being standardized so that it can be held by third parties as well as DID owners. It is a matter of changing the DID document against the will of the DID owner. To help owners assert their sovereignty even stronger, we propose a way for DID owners to use a policy, history, and service to verify the DID Document updating process.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"99 1","pages":"517-520"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85900321","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333936
Min Wei, Xueqin Xiang, Cheng Li
With the rapid development of the industrial internet, more wireless networks are connected to the industrial network. Heterogeneous interconnection makes the industrial network flat, allowing the control flow, data flow, best effort flow and other flows in the network coexist in the same network. The scheduling problem in the network becomes a difficult problem. In order to solve the data scheduling problem after the flattening of the network in the factory, while satisfying the real-time and reliable transmission of industrial data, this paper proposes a traffic scheduling mechanism for industrial wireless network accessing IPv6 internet. A test system is implemented and the results show that the proposed scheduling mechanism may optimize network performance and improve network link utilization.
{"title":"A Traffic Scheduling Mechanism for Industrial Wireless Network Accessing IPv6 Internet","authors":"Min Wei, Xueqin Xiang, Cheng Li","doi":"10.1109/ICOIN50884.2021.9333936","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333936","url":null,"abstract":"With the rapid development of the industrial internet, more wireless networks are connected to the industrial network. Heterogeneous interconnection makes the industrial network flat, allowing the control flow, data flow, best effort flow and other flows in the network coexist in the same network. The scheduling problem in the network becomes a difficult problem. In order to solve the data scheduling problem after the flattening of the network in the factory, while satisfying the real-time and reliable transmission of industrial data, this paper proposes a traffic scheduling mechanism for industrial wireless network accessing IPv6 internet. A test system is implemented and the results show that the proposed scheduling mechanism may optimize network performance and improve network link utilization.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"43 1","pages":"764-769"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85237353","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333948
A. Suwannasa, M. Broadbent, A. Mauthe
In Named Data Networking (NDN), consumer mobility is supported by letting a consumer re-transmit an Interest packet to re-request a lost content object through a new NDN Access Router (NAR). The object is often replicated at a previous NAR, located close to the new NAR, and can be retrieved from there rather than the origin server. Replicas can also be found from other nodes in the vicinity or nearby vicinities depending on the replica density, inter alia. These replicas can be a better source for the mobile consumer than the best placed NAR. In this paper, we further develop a vicinity-based scheme leveraging content finding in mobile NDN environments that fit the characteristic of the mentioned communication model. We examine the scheme in comparison to the default best route strategy of NDN. The results demonstrate that the scheme provides significant performance gains with acceptable overhead costs in a mobile scenario.
{"title":"Effectiveness of Vicinity-based Content Finding in Mobile NDN Environments","authors":"A. Suwannasa, M. Broadbent, A. Mauthe","doi":"10.1109/ICOIN50884.2021.9333948","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333948","url":null,"abstract":"In Named Data Networking (NDN), consumer mobility is supported by letting a consumer re-transmit an Interest packet to re-request a lost content object through a new NDN Access Router (NAR). The object is often replicated at a previous NAR, located close to the new NAR, and can be retrieved from there rather than the origin server. Replicas can also be found from other nodes in the vicinity or nearby vicinities depending on the replica density, inter alia. These replicas can be a better source for the mobile consumer than the best placed NAR. In this paper, we further develop a vicinity-based scheme leveraging content finding in mobile NDN environments that fit the characteristic of the mentioned communication model. We examine the scheme in comparison to the default best route strategy of NDN. The results demonstrate that the scheme provides significant performance gains with acceptable overhead costs in a mobile scenario.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"2 1","pages":"343-348"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86938186","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333931
Jaeho Choi, Seunghyeok Oh, Soohyun Park, Jong-Kook Kim, Joongheon Kim
Advanced researches on the variational quantum algorithms are actively conducted. In particular, the quantum approximate optimization algorithm (QAOA) is one of the promising variational quantum algorithms and can be applied to various graph-based problems, and is a promising algorithm that shows good performance even in small quantum computers. As is widely known, QAOA obtains the approximate solution via the expectation value of the cost Hamiltonian on the parameterized state. Therefore, in addition to finding the optimal parameters, the proper design of the cost Hamiltonian is important. This paper designs the cost function of the combinatorial optimization problem via Boolean function and maps it to the proper cost Hamiltonian. The proposed cost Hamiltonian design method is applied to the maximum independent set (MIS) and minimum dominating set (MDS) problems.
{"title":"Proper Cost Hamiltonian Design for Combinatorial Optimization Problems: A Boolean Function Approach","authors":"Jaeho Choi, Seunghyeok Oh, Soohyun Park, Jong-Kook Kim, Joongheon Kim","doi":"10.1109/ICOIN50884.2021.9333931","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333931","url":null,"abstract":"Advanced researches on the variational quantum algorithms are actively conducted. In particular, the quantum approximate optimization algorithm (QAOA) is one of the promising variational quantum algorithms and can be applied to various graph-based problems, and is a promising algorithm that shows good performance even in small quantum computers. As is widely known, QAOA obtains the approximate solution via the expectation value of the cost Hamiltonian on the parameterized state. Therefore, in addition to finding the optimal parameters, the proper design of the cost Hamiltonian is important. This paper designs the cost function of the combinatorial optimization problem via Boolean function and maps it to the proper cost Hamiltonian. The proposed cost Hamiltonian design method is applied to the maximum independent set (MIS) and minimum dominating set (MDS) problems.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"42 1","pages":"469-472"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91190521","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9334016
Haemin Lee, Soohyun Park, Junghyun Kim, Joongheon Kim
This paper proposes an edge computing model that processes machine learning code offloading based on auction mechanisms. The code offloading is required to carry out training that is processed difficult for mobile devices with limited computing resources. In this system, mobile devices compete for using computing resource units by submitting their bids based on code complexity and data size. We use the Myerson auction model which uses the truthful second-price auction as a baseline, to maximize the seller’s revenue while meeting several desirable properties, i.e., individual rationality and incentive compatibility. The simulation results showed that our Myerson auction method overall improved the seller’s revenue while satisfying the above characteristics.
{"title":"Auction-based Deep Learning Computation Offloading for Truthful Edge Computing: A Myerson Auction Approach","authors":"Haemin Lee, Soohyun Park, Junghyun Kim, Joongheon Kim","doi":"10.1109/ICOIN50884.2021.9334016","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9334016","url":null,"abstract":"This paper proposes an edge computing model that processes machine learning code offloading based on auction mechanisms. The code offloading is required to carry out training that is processed difficult for mobile devices with limited computing resources. In this system, mobile devices compete for using computing resource units by submitting their bids based on code complexity and data size. We use the Myerson auction model which uses the truthful second-price auction as a baseline, to maximize the seller’s revenue while meeting several desirable properties, i.e., individual rationality and incentive compatibility. The simulation results showed that our Myerson auction method overall improved the seller’s revenue while satisfying the above characteristics.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"10 1","pages":"457-459"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91216658","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：