Pub Date : 2021-12-01DOI: 10.1109/ICPADS53394.2021.00122
Jiannan Zheng, Haitao Zhang, Yilin Jin, Huadong Ma
With the rapid development of high-speed Internet access and popularization of high-performance smart devices, past decade has witnessed the great development of crowdsourced live streaming (CLS) service. Transcoding and video distribution are essential in CLS service to guarantee viewer engagement. Large CLS systems gradually migrate their services to multi-cloud platforms. However, highly dynamic viewers' requests influence transcoding and CDN distribution decisions, eventually lead to fluctuation in QoE and increase in operational cost. It is challenging for the CLS system to serve viewer's requests in multi-cloud platforms with fluctuation in cloud transcoding and distribution performance. In this paper, we propose a collaborative framework of cloud transcoding and distribution supporting CLS service. First, we define cost model and QoE model in multi-cloud platforms, comprehensively considering cloud transcoding and distribution. Second, we propose a collaborative cost-efficient approach based on multi-agent decision model. We use a G-Greedy exploration approach to learn what actions to take by exploration and exploitation based on the state of current environment. The trace-driven experiments demonstrate that our proposed approach is cost-efficient and QoE-maintained and can reduce operational cost compared with alternatives (5.37%-21.21%) while maintaining QoE of viewers.
{"title":"Collaborative Framework of Cloud Transcoding and Distribution Supporting Cost-Efficient Crowdsourced Live Streaming","authors":"Jiannan Zheng, Haitao Zhang, Yilin Jin, Huadong Ma","doi":"10.1109/ICPADS53394.2021.00122","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00122","url":null,"abstract":"With the rapid development of high-speed Internet access and popularization of high-performance smart devices, past decade has witnessed the great development of crowdsourced live streaming (CLS) service. Transcoding and video distribution are essential in CLS service to guarantee viewer engagement. Large CLS systems gradually migrate their services to multi-cloud platforms. However, highly dynamic viewers' requests influence transcoding and CDN distribution decisions, eventually lead to fluctuation in QoE and increase in operational cost. It is challenging for the CLS system to serve viewer's requests in multi-cloud platforms with fluctuation in cloud transcoding and distribution performance. In this paper, we propose a collaborative framework of cloud transcoding and distribution supporting CLS service. First, we define cost model and QoE model in multi-cloud platforms, comprehensively considering cloud transcoding and distribution. Second, we propose a collaborative cost-efficient approach based on multi-agent decision model. We use a G-Greedy exploration approach to learn what actions to take by exploration and exploitation based on the state of current environment. The trace-driven experiments demonstrate that our proposed approach is cost-efficient and QoE-maintained and can reduce operational cost compared with alternatives (5.37%-21.21%) while maintaining QoE of viewers.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131502174","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}
With the rapid development of edge computing, edge clusters need to deal with a tremendous amount of tasks, making some edge clusters overloaded, which further translates into task completion lag. Previous works usually copy the tasks from overloaded edges to idle edges so as to reduce the task queuing and computing delay. However, the completion delay of tasks copied to different edges cannot be predicted before the replication decision is made, which affects the overall task replication performance. In this paper, we propose an online task replication algorithm based on the predictions derived from multi-armed bandit. Via rigorous proof, the regret is ensured to be sub-linear upon the bandit, measuring the gap between the online decisions and the offline optimum. Extensive simulations are conducted to confirm the superiority of the proposed algorithm over state-of-the-art replication strategies.
{"title":"TRAN: Task Replication with Guarantee via Multi-armed Bandit","authors":"Yitong Zhou, Bowen Peng, Jingmian Wang, Weiwei Miao, Zeng Zeng, Yibo Jin, Sheng Z. Zhang, Zhuzhong Qian","doi":"10.1109/ICPADS53394.2021.00048","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00048","url":null,"abstract":"With the rapid development of edge computing, edge clusters need to deal with a tremendous amount of tasks, making some edge clusters overloaded, which further translates into task completion lag. Previous works usually copy the tasks from overloaded edges to idle edges so as to reduce the task queuing and computing delay. However, the completion delay of tasks copied to different edges cannot be predicted before the replication decision is made, which affects the overall task replication performance. In this paper, we propose an online task replication algorithm based on the predictions derived from multi-armed bandit. Via rigorous proof, the regret is ensured to be sub-linear upon the bandit, measuring the gap between the online decisions and the offline optimum. Extensive simulations are conducted to confirm the superiority of the proposed algorithm over state-of-the-art replication strategies.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114544716","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 : 2021-12-01DOI: 10.1109/icpads53394.2021.00003
{"title":"[Copyright notice]","authors":"","doi":"10.1109/icpads53394.2021.00003","DOIUrl":"https://doi.org/10.1109/icpads53394.2021.00003","url":null,"abstract":"","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125390495","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 : 2021-12-01DOI: 10.1109/ICPADS53394.2021.00030
James R. Clavin, Yue Huang, Xin Wang, Pradeep M. Prakash, Sisi Duan, Jianwu Wang, S. Peisert
We present a framework for evaluating the performance of Byzantine fault-tolerant (BFT) protocols theoretically. Our motivation is to identify protocols suitable for a particular power grid application. In this application, replicas are located in a LAN network where latency is the priority. To fully understand the performance of BFT, we provide a generic approach that quantifies the performance of BFT protocols based on the number of cryptographic operations under five different scenarios (in the presence of failures and without failures). We present the performance of three representative BFT protocols: PBFT, Prime, and SBFT. To validate our framework, we also evaluate the protocols experimentally in the CloudLab testbed. Our experimental results match the findings predicted by the framework. Although a variety of factors may affect the performance of the protocols, our framework can be used as a valuable reference to understand the performance of BFT.
{"title":"A Framework for Evaluating BFT","authors":"James R. Clavin, Yue Huang, Xin Wang, Pradeep M. Prakash, Sisi Duan, Jianwu Wang, S. Peisert","doi":"10.1109/ICPADS53394.2021.00030","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00030","url":null,"abstract":"We present a framework for evaluating the performance of Byzantine fault-tolerant (BFT) protocols theoretically. Our motivation is to identify protocols suitable for a particular power grid application. In this application, replicas are located in a LAN network where latency is the priority. To fully understand the performance of BFT, we provide a generic approach that quantifies the performance of BFT protocols based on the number of cryptographic operations under five different scenarios (in the presence of failures and without failures). We present the performance of three representative BFT protocols: PBFT, Prime, and SBFT. To validate our framework, we also evaluate the protocols experimentally in the CloudLab testbed. Our experimental results match the findings predicted by the framework. Although a variety of factors may affect the performance of the protocols, our framework can be used as a valuable reference to understand the performance of BFT.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116014766","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}
Consortium blockchain has been widely used in many application scenarios, where there is the demand for a universal user authentication and key exchange mechanism for all the application users in the system like Know Your Customer. Since current solutions heavily rely on traditional public-key cryptosystems that are vulnerable to attacks from quantum computers, we design and implement the first post-quantum (PQ) user authentication and key exchange system for consortium blockchain, which is integrated with all the PQ public-key (i.e., signature and encryption/KEM) algorithms in the current round of NIST call for national standard. Furthermore, we also provide chaincodes, related APIs together with client codes for further development. Last but not least, we perform a systematic evaluation on the performance of the system including the consumed time of chaincodes execution and the needed on-chain storage space. Based on the experiment results, we discuss the implications of our findings, which are helpful for the PQ blockchain-based application developers, the undergoing NIST call and the developers of the PQ algorithms.
财团b区块链已被广泛应用于许多应用场景中，这些场景需要为系统中的所有应用程序用户提供通用的用户身份验证和密钥交换机制，例如Know Your Customer。由于目前的解决方案严重依赖于传统的公钥密码系统，容易受到量子计算机的攻击，我们为联盟b区块链设计并实现了第一个后量子(PQ)用户身份验证和密钥交换系统，该系统集成了当前一轮NIST国家标准呼吁中的所有PQ公钥(即签名和加密/KEM)算法。此外，我们还提供链码，相关api以及客户端代码，以供进一步开发。最后但并非最不重要的是，我们对系统的性能进行了系统的评估，包括链码执行的消耗时间和所需的链上存储空间。根据实验结果，我们讨论了我们的研究结果的含义，这对基于PQ区块链的应用程序开发人员，正在进行的NIST呼叫和PQ算法的开发人员有帮助。
{"title":"Post-Quantum User Authentication and Key Exchange Based on Consortium Blockchain","authors":"Shiwei Xu, Ao Sun, Xiaowen Cai, Zhengwei Ren, Yizhi Zhao, Jianying Zhou","doi":"10.1109/ICPADS53394.2021.00089","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00089","url":null,"abstract":"Consortium blockchain has been widely used in many application scenarios, where there is the demand for a universal user authentication and key exchange mechanism for all the application users in the system like Know Your Customer. Since current solutions heavily rely on traditional public-key cryptosystems that are vulnerable to attacks from quantum computers, we design and implement the first post-quantum (PQ) user authentication and key exchange system for consortium blockchain, which is integrated with all the PQ public-key (i.e., signature and encryption/KEM) algorithms in the current round of NIST call for national standard. Furthermore, we also provide chaincodes, related APIs together with client codes for further development. Last but not least, we perform a systematic evaluation on the performance of the system including the consumed time of chaincodes execution and the needed on-chain storage space. Based on the experiment results, we discuss the implications of our findings, which are helpful for the PQ blockchain-based application developers, the undergoing NIST call and the developers of the PQ algorithms.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116944716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The advanced persistent threat (APT) is a stealthy cyber attack perpetrated by a group that gains unauthorized access to a computer network and remains undiscovered to steal specific data and resources. Fast detection and defense of APT attacks are critical tasks in cyber security. Previous works use simple feature extraction and classification methods to distinguish APT information flow from the normal one. However, APT attacks are latent, with very little flow and mixed in many normal information flows. Moreover, APT attacks can adjust their behavior according to the environment, making it challenging to be discovered and extract features. Meanwhile, dynamic information flow tracking (DIFT) is a tool for tracking information flow, which can also adjust the marking strategy according to the environment and is often used to track and detect APT information flow. On the other hand, game theory is a mathematical model that expresses the game of two or more parties. Therefore, this motivates us to model a game theory to solve the above challenge. In this paper, to solve the above obstacles, we propose an intelligent game theory framework named DPS, which models the strategic interaction between APTs and DIFT and aims to get a high reward for DIFT. Our proposed DPS framework utilizes deep reinforcement learning to find the Nash equilibrium. The game model is a nonzero-sum, average reward stochastic game. Specifically, we design a subgraph pruning strategy and deep Q-network to guide the player in exploring new strategies in the information flow graph. Finally, we implement our framework to compute an optimal defender strategy to defend cyber security. Based on 2 real-world datasets, the experiment results demonstrate that the DPS framework can delay APT intrusions under equilibrium in 3 epochs and get a better reward than the Uniform policy.
高级持续性威胁(APT)是一种隐蔽的网络攻击，由一个组织未经授权访问计算机网络，并在不被发现的情况下窃取特定数据和资源。快速检测和防御APT攻击是网络安全的关键任务。以往的工作使用简单的特征提取和分类方法来区分APT信息流和正常信息流。然而，APT攻击是潜在的，流量很小，并且混合在许多正常的信息流中。此外，APT攻击可以根据环境调整自己的行为，这给发现和提取特征带来了挑战。同时，动态信息流跟踪(dynamic information flow tracking, DIFT)是一种跟踪信息流的工具，它还可以根据环境调整标记策略，常用于跟踪和检测APT信息流。另一方面，博弈论是表达两方或多方博弈的数学模型。因此，这促使我们建立一个博弈论模型来解决上述挑战。为了解决上述障碍，本文提出了一个名为DPS的智能博弈论框架，该框架对apt和DIFT之间的战略互动进行建模，旨在为DIFT获得高回报。我们提出的DPS框架利用深度强化学习来寻找纳什均衡。游戏模型是非零和、平均奖励的随机游戏。具体来说，我们设计了子图修剪策略和深度q网络来指导玩家在信息流图中探索新的策略。最后，我们实现了我们的框架来计算最优防御策略来防御网络安全。基于2个真实数据集的实验结果表明，DPS框架可以在3个epoch的均衡状态下延迟APT入侵，并且比统一策略获得更好的奖励。
{"title":"An Intelligent Game Theory Framework for Detecting Advanced Persistent Threats","authors":"Hao Yan, Qianzhen Zhang, Junjie Xie, Ziyue Lu, Sheng Chen, Deke Guo","doi":"10.1109/ICPADS53394.2021.00062","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00062","url":null,"abstract":"The advanced persistent threat (APT) is a stealthy cyber attack perpetrated by a group that gains unauthorized access to a computer network and remains undiscovered to steal specific data and resources. Fast detection and defense of APT attacks are critical tasks in cyber security. Previous works use simple feature extraction and classification methods to distinguish APT information flow from the normal one. However, APT attacks are latent, with very little flow and mixed in many normal information flows. Moreover, APT attacks can adjust their behavior according to the environment, making it challenging to be discovered and extract features. Meanwhile, dynamic information flow tracking (DIFT) is a tool for tracking information flow, which can also adjust the marking strategy according to the environment and is often used to track and detect APT information flow. On the other hand, game theory is a mathematical model that expresses the game of two or more parties. Therefore, this motivates us to model a game theory to solve the above challenge. In this paper, to solve the above obstacles, we propose an intelligent game theory framework named DPS, which models the strategic interaction between APTs and DIFT and aims to get a high reward for DIFT. Our proposed DPS framework utilizes deep reinforcement learning to find the Nash equilibrium. The game model is a nonzero-sum, average reward stochastic game. Specifically, we design a subgraph pruning strategy and deep Q-network to guide the player in exploring new strategies in the information flow graph. Finally, we implement our framework to compute an optimal defender strategy to defend cyber security. Based on 2 real-world datasets, the experiment results demonstrate that the DPS framework can delay APT intrusions under equilibrium in 3 epochs and get a better reward than the Uniform policy.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"52 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124215227","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 : 2021-12-01DOI: 10.1109/ICPADS53394.2021.00099
Han Zheng, Yan Zhang, Lan Zhang, Hao Xia, Shaojie Bai, G. Shen, Tian He, Xiangyang Li
Wi-Fi fingerprinting using the received signal strength (RSS) of the access point (AP) as a physical signal feature is widely studied in the indoor localization area with various applications. One main problem with fingerprinting based approach is the uncertainty of RSS measurements, which often leads to instability and decline of localization performance. In this work, we propose GraFin, a graph-based fingerprinting approach, to provide accurate and robust indoor localization without tedious site surveys and extra assistant information. The key idea lies in the insight that despite the RSS measurement of one AP at one reference point (RP) can be noisy, the proximity pattern, which describes one AP's relative position to other APs and RPs, is usually more stable. Specifically, GraFin models APs and RPs on a graph based on limited RSS measurements and provides position-aware fingerprints for APs and RPs based on an inductive deep graph model. We evaluate GraFin on a public indoor localization dataset, and the results demonstrate the effectiveness and robustness of our approach. Furthermore, we apply our approach to the arrival-departure time estimation task for instant delivery service. Experiment results on the enterprise dataset from one of the largest instant delivery platforms in China show that GraFin outperforms baseline approaches with significantly lower time estimation error.
{"title":"GraFin: An Applicable Graph-based Fingerprinting Approach for Robust Indoor Localization","authors":"Han Zheng, Yan Zhang, Lan Zhang, Hao Xia, Shaojie Bai, G. Shen, Tian He, Xiangyang Li","doi":"10.1109/ICPADS53394.2021.00099","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00099","url":null,"abstract":"Wi-Fi fingerprinting using the received signal strength (RSS) of the access point (AP) as a physical signal feature is widely studied in the indoor localization area with various applications. One main problem with fingerprinting based approach is the uncertainty of RSS measurements, which often leads to instability and decline of localization performance. In this work, we propose GraFin, a graph-based fingerprinting approach, to provide accurate and robust indoor localization without tedious site surveys and extra assistant information. The key idea lies in the insight that despite the RSS measurement of one AP at one reference point (RP) can be noisy, the proximity pattern, which describes one AP's relative position to other APs and RPs, is usually more stable. Specifically, GraFin models APs and RPs on a graph based on limited RSS measurements and provides position-aware fingerprints for APs and RPs based on an inductive deep graph model. We evaluate GraFin on a public indoor localization dataset, and the results demonstrate the effectiveness and robustness of our approach. Furthermore, we apply our approach to the arrival-departure time estimation task for instant delivery service. Experiment results on the enterprise dataset from one of the largest instant delivery platforms in China show that GraFin outperforms baseline approaches with significantly lower time estimation error.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"189 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132655285","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}
Deep neural networks (DNNs) play an important role in a variety of intelligent applications (e.g. image classification and target recognition), yet at the cost of heavy computation burden, that makes DNNs difficult to deploy on resource-constrained IoT devices. To solve this problem, there are two categories of model computation adjustment methods: model compression and model segmentation. However, model compression mainly reduces resource consumption at the cost of accuracy while model segmentation reduces resource consumption according to the cost of communication latency. In this paper, we propose Joint Search for Model Compression and Segmentation (JointCS) that highlights the following aspects: 1) we integrate both model compression and model segmentation under an automatic and progressive framework, it simplifies model to fit the different IoT resource requirements. JointCS achieves a series slim models that outperform better both in accuracy and latency. 2) we train a network architecture-aware latency predictor to fast measure the latency of the slimed model on heterogeneous IoT devices. 3) we introduce a search algorithm to select the optimal state in progressively joint search. Finally, we evaluate the performance of our proposed method for image classification on CIFAR datasets comparing with the state-of-the-art approach, the inference time of the proposed method has inference speedup of 12.2 % −30.9 % under the same accuracy.
{"title":"JointCS: Joint Search for Deep Model Compression and Segmentation on Heterogeneous IoT Devices","authors":"Xinyu Li, Bin Guo, Sicong Liu, Chen Qiu, Yunji Liang, Zhiwen Yu","doi":"10.1109/ICPADS53394.2021.00059","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00059","url":null,"abstract":"Deep neural networks (DNNs) play an important role in a variety of intelligent applications (e.g. image classification and target recognition), yet at the cost of heavy computation burden, that makes DNNs difficult to deploy on resource-constrained IoT devices. To solve this problem, there are two categories of model computation adjustment methods: model compression and model segmentation. However, model compression mainly reduces resource consumption at the cost of accuracy while model segmentation reduces resource consumption according to the cost of communication latency. In this paper, we propose Joint Search for Model Compression and Segmentation (JointCS) that highlights the following aspects: 1) we integrate both model compression and model segmentation under an automatic and progressive framework, it simplifies model to fit the different IoT resource requirements. JointCS achieves a series slim models that outperform better both in accuracy and latency. 2) we train a network architecture-aware latency predictor to fast measure the latency of the slimed model on heterogeneous IoT devices. 3) we introduce a search algorithm to select the optimal state in progressively joint search. Finally, we evaluate the performance of our proposed method for image classification on CIFAR datasets comparing with the state-of-the-art approach, the inference time of the proposed method has inference speedup of 12.2 % −30.9 % under the same accuracy.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"2 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133080756","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}
Traffic signal control is essential to efficient transportation networks since it can mitigate traffic congestion significantly. Trial-and-error approach in reinforcement learning will lead to traffic jams, even traffic accidents in the real scene, which is in violation of safety for traffic signal control. Besides, most signal control systems still rely on oversimplified information, which makes item challenging to adapt to dynamic traffic. In this paper, we focus on the edge coordinated optimization of large-scale traffic signal control, and propose a two-layeR edge-assisted pressUre balaNce (RUN) approach based on cooperative game. The external layer utilizes cooperative game to divide the traffic network into multiple coalitions. The internal layer uses pressure control and weighted queue to coordinate actions within each coalition and handle dynamic traffic situations over time. We derive a Pareto stable solution for the multi-intersection signal cooperative game with pressure control, and prove that it is non-superadditive. Moreover, we conduct extensive simulations to verify the significant performances of RUN based on both real data and synthetic data.
{"title":"Two-Layer Traffic Signal Optimization: A Edge-assisted Pressure Balance Approach Based on Cooperative Game","authors":"Zhenhua Han, Mingjun Xiao, Haisheng Tan, Guoju Gao","doi":"10.1109/ICPADS53394.2021.00016","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00016","url":null,"abstract":"Traffic signal control is essential to efficient transportation networks since it can mitigate traffic congestion significantly. Trial-and-error approach in reinforcement learning will lead to traffic jams, even traffic accidents in the real scene, which is in violation of safety for traffic signal control. Besides, most signal control systems still rely on oversimplified information, which makes item challenging to adapt to dynamic traffic. In this paper, we focus on the edge coordinated optimization of large-scale traffic signal control, and propose a two-layeR edge-assisted pressUre balaNce (RUN) approach based on cooperative game. The external layer utilizes cooperative game to divide the traffic network into multiple coalitions. The internal layer uses pressure control and weighted queue to coordinate actions within each coalition and handle dynamic traffic situations over time. We derive a Pareto stable solution for the multi-intersection signal cooperative game with pressure control, and prove that it is non-superadditive. Moreover, we conduct extensive simulations to verify the significant performances of RUN based on both real data and synthetic data.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"284 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132229128","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 : 2021-12-01DOI: 10.1109/ICPADS53394.2021.00091
Chengyu Zhu, Yanmin Zhu, Xuansheng Lu
User interests are significant components in recommendation systems. Modeling user interests based on users' historical behaviors is a challenging problem, and many recommendation models have been proposed for user interests modeling, such as long-term and short-term interests modeling. In the real world, users' interests always change over time, however, existing models rarely consider users' interest changes. The purpose of this research is to apply graph neural networks to capture users' interest changes. This research first conducts data analysis on two public datasets, and results show that there are considerable amounts of users with a trend of interest changes. Based on this analysis, we construct user-category dynamic differential graphs, and we design a novel neural network based on dynamic differential graphs to learn users' interest changes representations from dynamic differential graphs. The learned representations are integrated with long-term and short-term interest representations to get users' final representations and make recommendations by getting scores with items. Different types of experiments are conducted to evaluate the performance of our proposed model, and experiment results show that the proposed model outperforms other baseline models.
{"title":"Modeling User Interest Changes with Dynamic Differential Graphs for Item Recommendation","authors":"Chengyu Zhu, Yanmin Zhu, Xuansheng Lu","doi":"10.1109/ICPADS53394.2021.00091","DOIUrl":"https://doi.org/10.1109/ICPADS53394.2021.00091","url":null,"abstract":"User interests are significant components in recommendation systems. Modeling user interests based on users' historical behaviors is a challenging problem, and many recommendation models have been proposed for user interests modeling, such as long-term and short-term interests modeling. In the real world, users' interests always change over time, however, existing models rarely consider users' interest changes. The purpose of this research is to apply graph neural networks to capture users' interest changes. This research first conducts data analysis on two public datasets, and results show that there are considerable amounts of users with a trend of interest changes. Based on this analysis, we construct user-category dynamic differential graphs, and we design a novel neural network based on dynamic differential graphs to learn users' interest changes representations from dynamic differential graphs. The learned representations are integrated with long-term and short-term interest representations to get users' final representations and make recommendations by getting scores with items. Different types of experiments are conducted to evaluate the performance of our proposed model, and experiment results show that the proposed model outperforms other baseline models.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132233745","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：