Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162742
Tianqiong Chen, Jian He, Huiling Zhu, Lin Cai, Peng Yue, Jiangzhou Wang
It is crucial for emergency communication networks to properly manage and coordinate between rescuers and disaster-affected users. Low-cost and high-mobility drones become important contributors to build up such kind of emergency communication networks. In this paper, we consider the drone as a deployed base station to provide communication for ground users in the post-disaster area. Considering the importance of providing guaranteed service for rescuers (compared to normal users), we have investigated power and subcarrier allocation to maximize the downlink system capacity in the drone-assisted emergency communication system. Due to the complexity of the formulated problem. a suboptimal solution is proposed by dividing users into two priority groups: high-priority users (rescuers) and low-priority users (affected people). According to analyses, the complexity of the proposed scheme is much lower than the optimal scheme. Simulation results have shown that when the transmit power of the drone is not very high, the performance of the proposed resource allocation scheme is very close to the optimal scheme.
{"title":"Resource Allocation in Drone-Assisted Emergency Communication Systems","authors":"Tianqiong Chen, Jian He, Huiling Zhu, Lin Cai, Peng Yue, Jiangzhou Wang","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162742","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162742","url":null,"abstract":"It is crucial for emergency communication networks to properly manage and coordinate between rescuers and disaster-affected users. Low-cost and high-mobility drones become important contributors to build up such kind of emergency communication networks. In this paper, we consider the drone as a deployed base station to provide communication for ground users in the post-disaster area. Considering the importance of providing guaranteed service for rescuers (compared to normal users), we have investigated power and subcarrier allocation to maximize the downlink system capacity in the drone-assisted emergency communication system. Due to the complexity of the formulated problem. a suboptimal solution is proposed by dividing users into two priority groups: high-priority users (rescuers) and low-priority users (affected people). According to analyses, the complexity of the proposed scheme is much lower than the optimal scheme. Simulation results have shown that when the transmit power of the drone is not very high, the performance of the proposed resource allocation scheme is very close to the optimal scheme.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115857611","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 : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162746
Yihan Liang, Yejun He, Jian Qiao
Simultaneous wireless information and power transfer (SWIPT)-enabled millimeter-wave (mmWave) network is one of the most effective solutions to solve the problem of high power consumption at wireless devices caused by high data rate applications. In this paper, we propose a SWIPT-enabled mmWave network and investigate the influence of mmWave propagation features on rate-energy (R-E) tradeoff of SWIPT system. In addition, an optimal power splitting (PS) policy is proposed to minimize the duration until battery exhausting, communication interruption and information loss occur. Finally, the proposed PS policy is modeled by Markov decision process (MDP) problem and realized by reinforcement learning (RL) algorithm. Simulation results show that the proposed RL-based PS policy can achieve higher battery energy level and stable data rate which can keep a good QoS of the whole SWIPT-enabled mmWave network.
{"title":"Optimal Power Splitting for Simultaneous Wireless Information and Power Transfer in Millimeter-wave Networks","authors":"Yihan Liang, Yejun He, Jian Qiao","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162746","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162746","url":null,"abstract":"Simultaneous wireless information and power transfer (SWIPT)-enabled millimeter-wave (mmWave) network is one of the most effective solutions to solve the problem of high power consumption at wireless devices caused by high data rate applications. In this paper, we propose a SWIPT-enabled mmWave network and investigate the influence of mmWave propagation features on rate-energy (R-E) tradeoff of SWIPT system. In addition, an optimal power splitting (PS) policy is proposed to minimize the duration until battery exhausting, communication interruption and information loss occur. Finally, the proposed PS policy is modeled by Markov decision process (MDP) problem and realized by reinforcement learning (RL) algorithm. Simulation results show that the proposed RL-based PS policy can achieve higher battery energy level and stable data rate which can keep a good QoS of the whole SWIPT-enabled mmWave network.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123418742","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 : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9163053
Doga Can Atabay, E. Uysal, O. Kaya
We study Age of Information (AoI) in a random access channel where a number of devices try to send status updates over a common medium. Assuming a time-slotted scenario where multiple transmissions result in collision, we propose a threshold-based lazy version of Slotted ALOHA and derive the time average AoI achieved by this policy. We demonstrate that the average AoI performance of the lazy policy is significantly better than Slotted ALOHA, and close to the ideal round robin benchmark.
{"title":"Improving Age of Information in Random Access Channels","authors":"Doga Can Atabay, E. Uysal, O. Kaya","doi":"10.1109/INFOCOMWKSHPS50562.2020.9163053","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9163053","url":null,"abstract":"We study Age of Information (AoI) in a random access channel where a number of devices try to send status updates over a common medium. Assuming a time-slotted scenario where multiple transmissions result in collision, we propose a threshold-based lazy version of Slotted ALOHA and derive the time average AoI achieved by this policy. We demonstrate that the average AoI performance of the lazy policy is significantly better than Slotted ALOHA, and close to the ideal round robin benchmark.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128231450","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 : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9163051
Xiao Wu, Han Qiu, Shuyi Zhang, G. Memmi, Keke Gai, Wei Cai
Nowadays, many novel blockchain-based architecture and frameworks are proposed to solve issues in computer science and financial service. Smart contracts with blockchain systems, especially consortium blockchain systems, can help to provide many reliable and efficient functions for existing systems like smart grid payments. The novel concept of smart contract as a service is proposed but the difficulty of developing smart contracts on various kinds of blockchain systems are also significantly increasing which brings the additional cost for both developers and infrastructure builders. In this paper, we present an updated cloud-based smart integrated smart contract development system, ChainIDE 2.0, for the ultra-efficient development of blockchain-based smart contracts on multiple kinds of blockchain systems. Not only we stay as the most popular cloud-based developing Integrated Development Environment (IDE) for the Libra blockchain, but also we introduce the consortium blockchain systems such as Ant Financial Open-Chain (Ant OC) and served as the first cloud-based IDE supporting the Ant Financial OpenChain test net. Today, we have served almost 1 million compiled smart contracts which makes us the most popular cloud-based blockchain development IDE in the world.
{"title":"ChainIDE 2.0: Facilitating Smart Contract Development for Consortium Blockchain","authors":"Xiao Wu, Han Qiu, Shuyi Zhang, G. Memmi, Keke Gai, Wei Cai","doi":"10.1109/infocomwkshps50562.2020.9163051","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9163051","url":null,"abstract":"Nowadays, many novel blockchain-based architecture and frameworks are proposed to solve issues in computer science and financial service. Smart contracts with blockchain systems, especially consortium blockchain systems, can help to provide many reliable and efficient functions for existing systems like smart grid payments. The novel concept of smart contract as a service is proposed but the difficulty of developing smart contracts on various kinds of blockchain systems are also significantly increasing which brings the additional cost for both developers and infrastructure builders. In this paper, we present an updated cloud-based smart integrated smart contract development system, ChainIDE 2.0, for the ultra-efficient development of blockchain-based smart contracts on multiple kinds of blockchain systems. Not only we stay as the most popular cloud-based developing Integrated Development Environment (IDE) for the Libra blockchain, but also we introduce the consortium blockchain systems such as Ant Financial Open-Chain (Ant OC) and served as the first cloud-based IDE supporting the Ant Financial OpenChain test net. Today, we have served almost 1 million compiled smart contracts which makes us the most popular cloud-based blockchain development IDE in the world.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129857745","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 : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9162925
Kun Yang, Cong Shen, Tie Liu
There is a growing interest in applying deep reinforcement learning (DRL) methods to optimizing the operation of wireless networks. In this paper, we compare three state of the art DRL methods, Deep Deterministic Policy Gradient (DDPG), Neural Episodic Control (NEC), and Variance Based Control (VBC), for the application of wireless network optimization. We describe how the general network optimization problem is formulated as RL and give details of the three methods in the context of wireless networking. Extensive experiments using a real-world network operation dataset are carried out, and the performance in terms of improving rate and convergence speed for these popular DRL methods is compared. We note that while DDPG and VBC demonstrate good potential in automating wireless network optimization, NEC has a much improved convergence rate but suffers from the limited action space and does not perform competitively in its current form.
{"title":"Deep Reinforcement Learning based Wireless Network Optimization: A Comparative Study","authors":"Kun Yang, Cong Shen, Tie Liu","doi":"10.1109/infocomwkshps50562.2020.9162925","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162925","url":null,"abstract":"There is a growing interest in applying deep reinforcement learning (DRL) methods to optimizing the operation of wireless networks. In this paper, we compare three state of the art DRL methods, Deep Deterministic Policy Gradient (DDPG), Neural Episodic Control (NEC), and Variance Based Control (VBC), for the application of wireless network optimization. We describe how the general network optimization problem is formulated as RL and give details of the three methods in the context of wireless networking. Extensive experiments using a real-world network operation dataset are carried out, and the performance in terms of improving rate and convergence speed for these popular DRL methods is compared. We note that while DDPG and VBC demonstrate good potential in automating wireless network optimization, NEC has a much improved convergence rate but suffers from the limited action space and does not perform competitively in its current form.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130600710","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 : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9162967
Jingjie Zong, Shuangzhi Li, Di Zhang, G. Han, X. Mu, A. Bashir, J. Rodrigues
In this paper, we concern the uplink of an industrial Internet of Things (IIoT) communication system, in which multiple single-antenna users timely upload data to a receiver having a large number of antennas over Rayleigh fading channels. To satisfy the stringent requirement of latency in the channel estimation phase of this system, we first use a phase-shift keying (PSK) modulation division scheme for each pair of users. Specifically, the absolutely additively uniquely decomposable constellation pair (AAUDCP) is allocated for two random users. With the same pilot sequence, it proves the modulated PSK symbols can be uniquely identified when the number of receiver antennas goes to infinity in a noise-free case. In a noise case, to improve the reliability of this system, we propose a smart user pairing algorithm with low complexity by maximizing the minimum signal to interference plus noise ratio at the receiver for all pairs of users. Finally, the computer simulations show that the proposed scheme can improve the system's error performance effectively.
{"title":"Smart User Pairing for Massive MIMO Enabled Industrial IoT Communications","authors":"Jingjie Zong, Shuangzhi Li, Di Zhang, G. Han, X. Mu, A. Bashir, J. Rodrigues","doi":"10.1109/infocomwkshps50562.2020.9162967","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162967","url":null,"abstract":"In this paper, we concern the uplink of an industrial Internet of Things (IIoT) communication system, in which multiple single-antenna users timely upload data to a receiver having a large number of antennas over Rayleigh fading channels. To satisfy the stringent requirement of latency in the channel estimation phase of this system, we first use a phase-shift keying (PSK) modulation division scheme for each pair of users. Specifically, the absolutely additively uniquely decomposable constellation pair (AAUDCP) is allocated for two random users. With the same pilot sequence, it proves the modulated PSK symbols can be uniquely identified when the number of receiver antennas goes to infinity in a noise-free case. In a noise case, to improve the reliability of this system, we propose a smart user pairing algorithm with low complexity by maximizing the minimum signal to interference plus noise ratio at the receiver for all pairs of users. Finally, the computer simulations show that the proposed scheme can improve the system's error performance effectively.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129583883","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 : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9162959
Fuyou Li, Zitian Zhang, Yunpeng Zhu, J. Zhang
With the rapidly increasing number of online social network (OSN) users, the study of OSN application-specific mobile network traffic has attracted many research efforts in recent years. In this work, we study the temporal characteristics of Twitter traffic and propose a Twitter traffic prediction framework which combines statistical analytics and machine learning techniques. Experimental results based on real-world Twitter traffic dataset collected in central London have shown that the proposed framework has a high prediction accuracy with low computation complexity and low demand for the size of the dataset.
随着在线社交网络OSN (online social network, OSN)用户数量的迅速增加，针对OSN应用的移动网络流量研究近年来备受关注。在这项工作中，我们研究了Twitter流量的时间特征，并提出了一个结合统计分析和机器学习技术的Twitter流量预测框架。基于伦敦市中心真实Twitter流量数据集的实验结果表明，该框架具有较高的预测精度、较低的计算复杂度和对数据集大小的低要求。
{"title":"Prediction of Twitter Traffic Based on Machine Learning and Data Analytics","authors":"Fuyou Li, Zitian Zhang, Yunpeng Zhu, J. Zhang","doi":"10.1109/infocomwkshps50562.2020.9162959","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162959","url":null,"abstract":"With the rapidly increasing number of online social network (OSN) users, the study of OSN application-specific mobile network traffic has attracted many research efforts in recent years. In this work, we study the temporal characteristics of Twitter traffic and propose a Twitter traffic prediction framework which combines statistical analytics and machine learning techniques. Experimental results based on real-world Twitter traffic dataset collected in central London have shown that the proposed framework has a high prediction accuracy with low computation complexity and low demand for the size of the dataset.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126319262","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 : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9162912
Itamar Cohen, Gil Einziger, M. Goldstein, Yaniv Sa'ar, Gabriel Scalosub, Erez Waisbard
Efficient on-demand deployment of VMs is at the core of cloud infrastructure but the existing resource management approaches are too slow to fulfill this promise. Parallel resource management is a promising direction for boosting performance, but when applied naïvely, it significantly increases the communication overhead and the decline ratio of deployment attempts. We propose a new dynamic and randomized algorithm, APSR, for parallel assignment of VMs to hosts in a cloud environment. APSR is guaranteed to satisfy an SLA containing decline ratio constraints, and communication overheads constraints. Furthermore, via extensive simulations, we show that APSR obtains a higher throughput than other commonly employed policies (including those used in OpenStack) while achieving a reduction of up to 13x in decline ratio and a reduction of over 85% in communication overheads.
{"title":"Poster Abstract: Parallel VM Placement with Provable Guarantees","authors":"Itamar Cohen, Gil Einziger, M. Goldstein, Yaniv Sa'ar, Gabriel Scalosub, Erez Waisbard","doi":"10.1109/infocomwkshps50562.2020.9162912","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162912","url":null,"abstract":"Efficient on-demand deployment of VMs is at the core of cloud infrastructure but the existing resource management approaches are too slow to fulfill this promise. Parallel resource management is a promising direction for boosting performance, but when applied naïvely, it significantly increases the communication overhead and the decline ratio of deployment attempts. We propose a new dynamic and randomized algorithm, APSR, for parallel assignment of VMs to hosts in a cloud environment. APSR is guaranteed to satisfy an SLA containing decline ratio constraints, and communication overheads constraints. Furthermore, via extensive simulations, we show that APSR obtains a higher throughput than other commonly employed policies (including those used in OpenStack) while achieving a reduction of up to 13x in decline ratio and a reduction of over 85% in communication overheads.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127555598","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 : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162922
Xu Wang, R. Berry
Vehicular networking offers the promise of greatly improving transportation safety but has stringent requirements on information age as well as information reachability, where the later refers to the range over which information is propagated. We consider an idealized model of a one-dimensional vehicular networks and show that there is a basic trade-off between these two metrics: a smaller age can be obtained by reducing the reachability of information. We apply this to two current technologies: Cellular V2X (C-V2X) and Dedicated Short Range Communication (DSRC) and derive an equation that characterizes the trade-off between these two metrics for both technologies. In the case of exponential path loss and negligible noise, this relationship becomes a fixed invariant ratio. Given this relationship, under high congestion, these two protocols tradeoff these metrics differently. C-V2X tends to achieve a smaller age while DSRC tends to maintain a larger reachability. The idealized model is also applied to analyze the steady state of rate control and power control mechanisms such as those in the SAE standard J2945/1. We show that the ratio of age and reachability is still governed by the same trade-off curve: rate control tries to maintain a large reachability, while power control helps improve the age.
{"title":"MAC Trade-offs Between Age and Reachability of Information in Vehicular Safety Applications","authors":"Xu Wang, R. Berry","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162922","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162922","url":null,"abstract":"Vehicular networking offers the promise of greatly improving transportation safety but has stringent requirements on information age as well as information reachability, where the later refers to the range over which information is propagated. We consider an idealized model of a one-dimensional vehicular networks and show that there is a basic trade-off between these two metrics: a smaller age can be obtained by reducing the reachability of information. We apply this to two current technologies: Cellular V2X (C-V2X) and Dedicated Short Range Communication (DSRC) and derive an equation that characterizes the trade-off between these two metrics for both technologies. In the case of exponential path loss and negligible noise, this relationship becomes a fixed invariant ratio. Given this relationship, under high congestion, these two protocols tradeoff these metrics differently. C-V2X tends to achieve a smaller age while DSRC tends to maintain a larger reachability. The idealized model is also applied to analyze the steady state of rate control and power control mechanisms such as those in the SAE standard J2945/1. We show that the ratio of age and reachability is still governed by the same trade-off curve: rate control tries to maintain a large reachability, while power control helps improve the age.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127743529","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 : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9162916
G. Sviridov, Cedric Beliard, A. Bianco, P. Giaccone, Dario Rossi
Quality of Experience (QoE) assessment for video games is known for being a heavy-weight process, typically requiring the active involvement of several human players and bringing limited transferability across games. Clearly, to some extent, QoE is correlated with the achieved in-game score, as player frustration will arise whenever realized performance is far from what is expected due to conditions beyond player control such as network congestion in the increasingly prevalent case of networked games. To disrupt the status quo, we propose to remove human players from the loop and instead exploit Deep Reinforcement Learning (DRL) agents to play games under varying network conditions. We apply our framework to a set of Atari games with different types of interaction, showing that the score degradation observed with DRL agents can be exploited in networking devices (e.g., by prioritizing scheduling decisions), reinforcing fairness across games, and thus enhancing the overall quality of gaming experience.
{"title":"Removing human players from the loop: AI-assisted assessment of Gaming QoE","authors":"G. Sviridov, Cedric Beliard, A. Bianco, P. Giaccone, Dario Rossi","doi":"10.1109/infocomwkshps50562.2020.9162916","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162916","url":null,"abstract":"Quality of Experience (QoE) assessment for video games is known for being a heavy-weight process, typically requiring the active involvement of several human players and bringing limited transferability across games. Clearly, to some extent, QoE is correlated with the achieved in-game score, as player frustration will arise whenever realized performance is far from what is expected due to conditions beyond player control such as network congestion in the increasingly prevalent case of networked games. To disrupt the status quo, we propose to remove human players from the loop and instead exploit Deep Reinforcement Learning (DRL) agents to play games under varying network conditions. We apply our framework to a set of Atari games with different types of interaction, showing that the score degradation observed with DRL agents can be exploited in networking devices (e.g., by prioritizing scheduling decisions), reinforcing fairness across games, and thus enhancing the overall quality of gaming experience.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114601121","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：