Daan Rutten, Nicolas H. Christianson, Debankur Mukherjee, A. Wierman
We examine the problem of smoothed online optimization, where a decision maker must sequentially choose points in a normed vector space to minimize the sum of per-round, non-convex hitting costs and the costs of switching decisions between rounds. The decision maker has access to a black-box oracle, such as a machine learning model, that provides untrusted and potentially inaccurate predictions of the optimal decision in each round. The goal of the decision maker is to exploit the predictions if they are accurate, while guaranteeing performance that is not much worse than the hindsight optimal sequence of decisions, even when predictions are inaccurate. We impose the standard assumption that hitting costs are globally α-polyhedral. We propose a novel algorithm, Adaptive Online Switching (AOS), and prove that, for a large set of feasible δ > 0, it is (1+δ)-competitive if predictions are perfect, while also maintaining a uniformly bounded competitive ratio of 2~O (1/(α δ)) even when predictions are adversarial. Further, we prove that this trade-off is necessary and nearly optimal in the sense that any deterministic algorithm which is (1+δ)-competitive if predictions are perfect must be at least 2~Ω (1/(α δ)) -competitive when predictions are inaccurate. In fact, we observe a unique threshold-type behavior in this trade-off: if δ is not in the set of feasible options, then no algorithm is simultaneously (1 + δ)-competitive if predictions are perfect and ζ-competitive when predictions are inaccurate for any ζ < ∞. Furthermore, we discuss that memory is crucial in AOS by proving that any algorithm that does not use memory cannot benefit from predictions. We complement our theoretical results by a numerical study on a microgrid application.
{"title":"Smoothed Online Optimization with Unreliable Predictions","authors":"Daan Rutten, Nicolas H. Christianson, Debankur Mukherjee, A. Wierman","doi":"10.1145/3579442","DOIUrl":"https://doi.org/10.1145/3579442","url":null,"abstract":"We examine the problem of smoothed online optimization, where a decision maker must sequentially choose points in a normed vector space to minimize the sum of per-round, non-convex hitting costs and the costs of switching decisions between rounds. The decision maker has access to a black-box oracle, such as a machine learning model, that provides untrusted and potentially inaccurate predictions of the optimal decision in each round. The goal of the decision maker is to exploit the predictions if they are accurate, while guaranteeing performance that is not much worse than the hindsight optimal sequence of decisions, even when predictions are inaccurate. We impose the standard assumption that hitting costs are globally α-polyhedral. We propose a novel algorithm, Adaptive Online Switching (AOS), and prove that, for a large set of feasible δ > 0, it is (1+δ)-competitive if predictions are perfect, while also maintaining a uniformly bounded competitive ratio of 2~O (1/(α δ)) even when predictions are adversarial. Further, we prove that this trade-off is necessary and nearly optimal in the sense that any deterministic algorithm which is (1+δ)-competitive if predictions are perfect must be at least 2~Ω (1/(α δ)) -competitive when predictions are inaccurate. In fact, we observe a unique threshold-type behavior in this trade-off: if δ is not in the set of feasible options, then no algorithm is simultaneously (1 + δ)-competitive if predictions are perfect and ζ-competitive when predictions are inaccurate for any ζ < ∞. Furthermore, we discuss that memory is crucial in AOS by proving that any algorithm that does not use memory cannot benefit from predictions. We complement our theoretical results by a numerical study on a microgrid application.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129331981","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}
We study an online inventory trading problem where a user seeks to maximize the aggregate revenue of trading multiple inventories over a time horizon. The trading constraints and concave revenue functions are revealed sequentially in time, and the user needs to make irrevocable decisions. The problem has wide applications in various engineering domains. Existing works employ the primal-dual framework to design online algorithms with sub-optimal, albeit near-optimal, competitive ratios (CR). We exploit the problem structure to develop a new divide-and-conquer approach to solve the online multi-inventory problem by solving multiple calibrated single-inventory ones separately and combining their solutions. The approach achieves the optimal CR of łn θ + 1 if Nłeq łn θ + 1, where N is the number of inventories and θ represents the revenue function uncertainty; it attains a CR of 1/[1-e^-1/(łnθ+1) ] in [łn θ +1, łn θ +2) otherwise. The divide-and-conquer approach reveals novel structural insights for the problem, (partially) closes a gap in existing studies, and generalizes to broader settings. For example, it gives an algorithm with a CR within a constant factor to the lower bound for a generalized one-way trading problem with price elasticity with no previous results. When developing the above results, we also extend a recent CR-Pursuit algorithmic framework and introduce an online allocation problem with allowance augmentation, both of which can be of independent interest.
{"title":"Competitive Online Optimization with Multiple Inventories","authors":"Qiulin Lin, Yanfang Mo, Junyan Su, Minghua Chen","doi":"10.1145/3530902","DOIUrl":"https://doi.org/10.1145/3530902","url":null,"abstract":"We study an online inventory trading problem where a user seeks to maximize the aggregate revenue of trading multiple inventories over a time horizon. The trading constraints and concave revenue functions are revealed sequentially in time, and the user needs to make irrevocable decisions. The problem has wide applications in various engineering domains. Existing works employ the primal-dual framework to design online algorithms with sub-optimal, albeit near-optimal, competitive ratios (CR). We exploit the problem structure to develop a new divide-and-conquer approach to solve the online multi-inventory problem by solving multiple calibrated single-inventory ones separately and combining their solutions. The approach achieves the optimal CR of łn θ + 1 if Nłeq łn θ + 1, where N is the number of inventories and θ represents the revenue function uncertainty; it attains a CR of 1/[1-e^-1/(łnθ+1) ] in [łn θ +1, łn θ +2) otherwise. The divide-and-conquer approach reveals novel structural insights for the problem, (partially) closes a gap in existing studies, and generalizes to broader settings. For example, it gives an algorithm with a CR within a constant factor to the lower bound for a generalized one-way trading problem with price elasticity with no previous results. When developing the above results, we also extend a recent CR-Pursuit algorithmic framework and introduce an online allocation problem with allowance augmentation, both of which can be of independent interest.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"51 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114433296","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}
Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision processes (MDPs) under the constraints of differential privacy (DP). Compared to existing private RL algorithms that work only on tabular finite-state, finite-actions MDPs, we take the first step towards privacy-preserving learning in MDPs with large state and action spaces. Specifically, we consider MDPs with linear function approximation (in particular linear mixture MDPs) under the notion of joint differential privacy (JDP), where the RL agent is responsible for protecting users' sensitive data. We design two private RL algorithms that are based on value iteration and policy optimization, respectively, and show that they enjoy sub-linear regret performance while guaranteeing privacy protection. Moreover, the regret bounds are independent of the number of states, and scale at most logarithmically with the number of actions, making the algorithms suitable for privacy protection in nowadays large-scale personalized services. Our results are achieved via a general procedure for learning in linear mixture MDPs under changing regularizers, which not only generalizes previous results for non-private learning, but also serves as a building block for general private reinforcement learning.
{"title":"Differentially Private Reinforcement Learning with Linear Function Approximation","authors":"Xingyu Zhou","doi":"10.1145/3508028","DOIUrl":"https://doi.org/10.1145/3508028","url":null,"abstract":"Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision processes (MDPs) under the constraints of differential privacy (DP). Compared to existing private RL algorithms that work only on tabular finite-state, finite-actions MDPs, we take the first step towards privacy-preserving learning in MDPs with large state and action spaces. Specifically, we consider MDPs with linear function approximation (in particular linear mixture MDPs) under the notion of joint differential privacy (JDP), where the RL agent is responsible for protecting users' sensitive data. We design two private RL algorithms that are based on value iteration and policy optimization, respectively, and show that they enjoy sub-linear regret performance while guaranteeing privacy protection. Moreover, the regret bounds are independent of the number of states, and scale at most logarithmically with the number of actions, making the algorithms suitable for privacy protection in nowadays large-scale personalized services. Our results are achieved via a general procedure for learning in linear mixture MDPs under changing regularizers, which not only generalizes previous results for non-private learning, but also serves as a building block for general private reinforcement learning.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"90 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123173116","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}
Accurate and highly-granular channel capacity telemetry of the cellular last hop is crucial for the effective operation of transport layer protocols and cutting edge applications, such as video on demand and video telephony. This paper presents the design, implementation, and experimental performance evaluation of NG-Scope, the first such telemetry tool able to fuse physical-layer channel occupancy readings from the cellular control channel with higher-layer packet arrival statistics and make accurate capacity estimates. NG-Scope handles the latest cellular innovations, such as when multiple base stations aggregate their signals together to serve mobile users. End-to-end experiments in a commercial cellular network demonstrate that wireless capacity varies significantly with channel quality, mobility, competing traffic within each cell, and the number of aggregated cells. Our experiments demonstrate significantly improved cell load estimation accuracy, missing the detection of less than 1% of data capacity overall, a reduction of 82% compared to OWL, the state-of-the-art in cellular monitoring. Further experiments show that MobileInsight-based CLAW has a root-mean-squared capacity error of 30.5 Mbit/s, which is 3.3× larger than NG-Scope (9.2 Mbit/s).
{"title":"NG-Scope","authors":"Yaxiong Xie, K. Jamieson","doi":"10.1145/3508032","DOIUrl":"https://doi.org/10.1145/3508032","url":null,"abstract":"Accurate and highly-granular channel capacity telemetry of the cellular last hop is crucial for the effective operation of transport layer protocols and cutting edge applications, such as video on demand and video telephony. This paper presents the design, implementation, and experimental performance evaluation of NG-Scope, the first such telemetry tool able to fuse physical-layer channel occupancy readings from the cellular control channel with higher-layer packet arrival statistics and make accurate capacity estimates. NG-Scope handles the latest cellular innovations, such as when multiple base stations aggregate their signals together to serve mobile users. End-to-end experiments in a commercial cellular network demonstrate that wireless capacity varies significantly with channel quality, mobility, competing traffic within each cell, and the number of aggregated cells. Our experiments demonstrate significantly improved cell load estimation accuracy, missing the detection of less than 1% of data capacity overall, a reduction of 82% compared to OWL, the state-of-the-art in cellular monitoring. Further experiments show that MobileInsight-based CLAW has a root-mean-squared capacity error of 30.5 Mbit/s, which is 3.3× larger than NG-Scope (9.2 Mbit/s).","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117004991","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 ACM Proceedings of the ACM on Measurement and Analysis of Computing Systems (POMACS) focuses on the measurement and performance evaluation of computer systems and operates in close collaboration with the ACM Special Interest Group SIGMETRICS. All papers in this issue of POMACS will be presented during the ACM SIGMETRICS/Performance 2022 conference. The issue contains papers selected by the editorial board via a rigorous review process that follows a hybrid conference and journal model, with reviews conducted by the 93 members of our POMACS editorial board. Each paper was either conditionally accepted (and shepherded), allowed a "one-shot" revision (to be resubmitted to one of the subsequent two deadlines), or rejected (with resubmission allowed after a year). For this issue, which represents the summer deadline, POMACS publishes 17 papers out of 71 submissions. All submitted papers received at least 3 reviews and we held an online TPC meeting. Based on the indicated primary track, roughly 37% of the submissions were in the Theory track, 30% were in the Measurement & Applied Modeling track, 20% were in the Systems track, and 14% were in the Learning track. Many people contributed to the success of this issue of POMACS. First, we would like to thank the authors, who submitted their best work to SIGMETRICS/POMACS. Second, we would like to thank the TPC members who provided constructive feedback in their reviews to authors and participated in the online discussions and TPC meetings. We also thank the several external reviewers who provided their expert opinion on specific submissions that required additional input. We are also grateful to the SIGMETRICS Board Chair, Giuliano Casale, and to past TPC Chairs, Anshul Gandhi, Negar Kiyavash, and Jia Wang, who provided a wealth of information and guidance (including a template for writing this editorial note!). Finally, we are grateful to the Organization Committee and to the SIGMETRICS Board for their ongoing efforts and initiatives for creating an exciting program for ACM SIGMETRICS/Performance 2022.
{"title":"POMACS V5, N3, December 2021 Editorial","authors":"Niklas Carlsson, Edith Cohen, Philippe Robert","doi":"10.1145/3491041","DOIUrl":"https://doi.org/10.1145/3491041","url":null,"abstract":"The ACM Proceedings of the ACM on Measurement and Analysis of Computing Systems (POMACS) focuses on the measurement and performance evaluation of computer systems and operates in close collaboration with the ACM Special Interest Group SIGMETRICS. All papers in this issue of POMACS will be presented during the ACM SIGMETRICS/Performance 2022 conference. The issue contains papers selected by the editorial board via a rigorous review process that follows a hybrid conference and journal model, with reviews conducted by the 93 members of our POMACS editorial board. Each paper was either conditionally accepted (and shepherded), allowed a \"one-shot\" revision (to be resubmitted to one of the subsequent two deadlines), or rejected (with resubmission allowed after a year). For this issue, which represents the summer deadline, POMACS publishes 17 papers out of 71 submissions. All submitted papers received at least 3 reviews and we held an online TPC meeting. Based on the indicated primary track, roughly 37% of the submissions were in the Theory track, 30% were in the Measurement & Applied Modeling track, 20% were in the Systems track, and 14% were in the Learning track. Many people contributed to the success of this issue of POMACS. First, we would like to thank the authors, who submitted their best work to SIGMETRICS/POMACS. Second, we would like to thank the TPC members who provided constructive feedback in their reviews to authors and participated in the online discussions and TPC meetings. We also thank the several external reviewers who provided their expert opinion on specific submissions that required additional input. We are also grateful to the SIGMETRICS Board Chair, Giuliano Casale, and to past TPC Chairs, Anshul Gandhi, Negar Kiyavash, and Jia Wang, who provided a wealth of information and guidance (including a template for writing this editorial note!). Finally, we are grateful to the Organization Committee and to the SIGMETRICS Board for their ongoing efforts and initiatives for creating an exciting program for ACM SIGMETRICS/Performance 2022.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"343 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124242841","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}
Sourav Das, Nitin Awathare, Ling Ren, V. Ribeiro, U. Bellur
Proof-of-Work (PoW) based blockchains typically allocate only a tiny fraction (e.g., less than 1% for Ethereum) of the average interarrival time (I) between blocks for validating smart contracts present in transactions. In such systems, block validation and PoW mining are typically performed sequentially, the former by CPUs and the latter by ASICs. A trivial increase in validation time (τ) introduces the popularly known Verifier's Dilemma, and as we demonstrate, causes more forking and hurts fairness. Large τ also reduces the tolerance for safety against a Byzantine adversary. Solutions that offload validation to a set of non-chain nodes (a.k.a. off-chain approaches) suffer from trust and performance issues that are non-trivial to resolve. In this paper, we present Tuxedo, the first on-chain protocol to theoretically scale τ/I ≈1 in PoW blockchains. The key innovation in Tuxedo is to perform CPU-based block processing in parallel to ASIC mining. We achieve this by allowing miners to delay validation of transactions in a block by up to ζ blocks, where ζ is a system parameter. We perform security analysis of Tuxedo considering all possible adversarial strategies in a synchronous network with maximum end-to-end delay Δ and demonstrate that Tuxedo achieves security equivalent to known results for longest chain PoW Nakamoto consensus. Our prototype implementation of Tuxedo atop Ethereum demonstrates that it can scale τ without suffering the harmful effects of naive scaling up of τ/I in existing blockchains
{"title":"Tuxedo: Maximizing Smart Contract Computation in PoW Blockchains","authors":"Sourav Das, Nitin Awathare, Ling Ren, V. Ribeiro, U. Bellur","doi":"10.1145/3491053","DOIUrl":"https://doi.org/10.1145/3491053","url":null,"abstract":"Proof-of-Work (PoW) based blockchains typically allocate only a tiny fraction (e.g., less than 1% for Ethereum) of the average interarrival time (I) between blocks for validating smart contracts present in transactions. In such systems, block validation and PoW mining are typically performed sequentially, the former by CPUs and the latter by ASICs. A trivial increase in validation time (τ) introduces the popularly known Verifier's Dilemma, and as we demonstrate, causes more forking and hurts fairness. Large τ also reduces the tolerance for safety against a Byzantine adversary. Solutions that offload validation to a set of non-chain nodes (a.k.a. off-chain approaches) suffer from trust and performance issues that are non-trivial to resolve. In this paper, we present Tuxedo, the first on-chain protocol to theoretically scale τ/I ≈1 in PoW blockchains. The key innovation in Tuxedo is to perform CPU-based block processing in parallel to ASIC mining. We achieve this by allowing miners to delay validation of transactions in a block by up to ζ blocks, where ζ is a system parameter. We perform security analysis of Tuxedo considering all possible adversarial strategies in a synchronous network with maximum end-to-end delay Δ and demonstrate that Tuxedo achieves security equivalent to known results for longest chain PoW Nakamoto consensus. Our prototype implementation of Tuxedo atop Ethereum demonstrates that it can scale τ without suffering the harmful effects of naive scaling up of τ/I in existing blockchains","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127220450","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}
We consider a simple form of pricing for a crowdsourcing system, where pricing policy is published a priori, and workers then decide their task acceptance. Such a pricing form is widely adopted in practice for its simplicity, e.g., Amazon Mechanical Turk, although additional sophistication to pricing rule can enhance budget efficiency. With the goal of designing efficient and simple pricing rules, we study the impact of the following two design features in pricing policies: (i) personalization tailoring policy worker-by-worker and (ii) bonus payment to qualified task completion. In the Bayesian setting, where the only prior distribution of workers' profiles is available, we first study the Price of Agnosticism (PoA) that quantifies the utility gap between personalized and common pricing policies. We show that PoA is bounded within a constant factor under some mild conditions, and the impact of bonus is essential in common pricing. These analytic results imply that complex personalized pricing can be replaced by simple common pricing once it is equipped with a proper bonus payment. To provide insights on efficient common pricing, we then study the efficient mechanisms of bonus payment for several profile distribution regimes which may exist in practice. We provide primitive experiments on Amazon Mechanical Turk, which support our analytical findings.
{"title":"Power of Bonus in Pricing for Crowdsourcing","authors":"Suho Shin, Hoyong Choi, Yu Yi, Jungseul Ok","doi":"10.1145/3491048","DOIUrl":"https://doi.org/10.1145/3491048","url":null,"abstract":"We consider a simple form of pricing for a crowdsourcing system, where pricing policy is published a priori, and workers then decide their task acceptance. Such a pricing form is widely adopted in practice for its simplicity, e.g., Amazon Mechanical Turk, although additional sophistication to pricing rule can enhance budget efficiency. With the goal of designing efficient and simple pricing rules, we study the impact of the following two design features in pricing policies: (i) personalization tailoring policy worker-by-worker and (ii) bonus payment to qualified task completion. In the Bayesian setting, where the only prior distribution of workers' profiles is available, we first study the Price of Agnosticism (PoA) that quantifies the utility gap between personalized and common pricing policies. We show that PoA is bounded within a constant factor under some mild conditions, and the impact of bonus is essential in common pricing. These analytic results imply that complex personalized pricing can be replaced by simple common pricing once it is equipped with a proper bonus payment. To provide insights on efficient common pricing, we then study the efficient mechanisms of bonus payment for several profile distribution regimes which may exist in practice. We provide primitive experiments on Amazon Mechanical Turk, which support our analytical findings.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131949921","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}
As a first step of designing O ptical-circuit-switched D ata C enters (ODC), physical topology design is critical as it determines the scalability and the performance limit of the entire ODC. However, prior works on ODC have not yet paid much attention to physical topology design, and the adopted physical topologies either scale poorly, or lack performance guarantee. We offer a mathematical foundation for the design and performance analysis of ODC physical topologies in this paper. We introduce a new performance metric β(G ) to evaluate the gap between a physical topology G and the ideal physical topology. We develop a coupling technique that bypasses a significant amount of computational complexity of calculating β(G). Using β(G ) and the coupling technique, we study four physical topologies that are representative of those in literature, analyze their scalabilities and prove their performance guarantees. Our analysis may provide new guidance for network operators to design better physical topologies for their ODCs.
{"title":"Understanding the Performance Guarantee of Physical Topology Design for Optical Circuit Switched Data Centers","authors":"Shizhen Zhao, Peirui Cao, Xinbing Wang","doi":"10.1145/3491054","DOIUrl":"https://doi.org/10.1145/3491054","url":null,"abstract":"As a first step of designing O ptical-circuit-switched D ata C enters (ODC), physical topology design is critical as it determines the scalability and the performance limit of the entire ODC. However, prior works on ODC have not yet paid much attention to physical topology design, and the adopted physical topologies either scale poorly, or lack performance guarantee. We offer a mathematical foundation for the design and performance analysis of ODC physical topologies in this paper. We introduce a new performance metric β(G ) to evaluate the gap between a physical topology G and the ideal physical topology. We develop a coupling technique that bypasses a significant amount of computational complexity of calculating β(G). Using β(G ) and the coupling technique, we study four physical topologies that are representative of those in literature, analyze their scalabilities and prove their performance guarantees. Our analysis may provide new guidance for network operators to design better physical topologies for their ODCs.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122568388","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}
Chen Griner, Johannes Zerwas, Andreas Blenk, M. Ghobadi, S. Schmid, C. Avin
The bandwidth and latency requirements of modern datacenter applications have led researchers to propose various topology designs using static, dynamic demand-oblivious (rotor), and/or dynamic demand-aware switches. However, given the diverse nature of datacenter traffic, there is little consensus about how these designs would fare against each other. In this work, we analyze the throughput of existing topology designs under different traffic patterns and study their unique advantages and potential costs in terms of bandwidth and latency ''tax''. To overcome the identified inefficiencies, we propose Cerberus, a unified, two-layer leaf-spine optical datacenter design with three topology types. Cerberus systematically matches different traffic patterns with their most suitable topology type: e.g., latency-sensitive flows are transmitted via a static topology, all-to-all traffic via a rotor topology, and elephant flows via a demand-aware topology. We show analytically and in simulations that Cerberus can improve throughput significantly compared to alternative approaches and operate datacenters at higher loads while being throughput-proportional.
{"title":"Cerberus","authors":"Chen Griner, Johannes Zerwas, Andreas Blenk, M. Ghobadi, S. Schmid, C. Avin","doi":"10.1145/3491050","DOIUrl":"https://doi.org/10.1145/3491050","url":null,"abstract":"The bandwidth and latency requirements of modern datacenter applications have led researchers to propose various topology designs using static, dynamic demand-oblivious (rotor), and/or dynamic demand-aware switches. However, given the diverse nature of datacenter traffic, there is little consensus about how these designs would fare against each other. In this work, we analyze the throughput of existing topology designs under different traffic patterns and study their unique advantages and potential costs in terms of bandwidth and latency ''tax''. To overcome the identified inefficiencies, we propose Cerberus, a unified, two-layer leaf-spine optical datacenter design with three topology types. Cerberus systematically matches different traffic patterns with their most suitable topology type: e.g., latency-sensitive flows are transmitted via a static topology, all-to-all traffic via a rotor topology, and elephant flows via a demand-aware topology. We show analytically and in simulations that Cerberus can improve throughput significantly compared to alternative approaches and operate datacenters at higher loads while being throughput-proportional.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126086260","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}
It is challenging to conduct a large scale Internet censorship measurement, as it involves triggering censors through artificial requests and identifying abnormalities from corresponding responses. Due to the lack of ground truth on the expected responses from legitimate services, previous studies typically require a heavy, unscalable manual inspection to identify false positives while still leaving false negatives undetected. In this paper, we propose Disguiser, a novel framework that enables end-to-end measurement to accurately detect the censorship activities and reveal the censor deployment without manual efforts. The core of Disguiser is a control server that replies with a static payload to provide the ground truth of server responses. As such, we send requests from various types of vantage points across the world to our control server, and the censorship activities can be recognized if a vantage point receives a different response. In particular, we design and conduct a cache test to pre-exclude the vantage points that could be interfered by cache proxies along the network path. Then we perform application traceroute towards our control server to explore censors' behaviors and their deployment. With Disguiser, we conduct 58 million measurements from vantage points in 177 countries. We observe 292 thousand censorship activities that block DNS, HTTP, or HTTPS requests inside 122 countries, achieving a 10^-6 false positive rate and zero false negative rate. Furthermore, Disguiser reveals the censor deployment in 13 countries.
{"title":"Understanding the Practices of Global Censorship through Accurate, End-to-End Measurements","authors":"Lin Jin, Shuai Hao, Haining Wang, Chase Cotton","doi":"10.1145/3491055","DOIUrl":"https://doi.org/10.1145/3491055","url":null,"abstract":"It is challenging to conduct a large scale Internet censorship measurement, as it involves triggering censors through artificial requests and identifying abnormalities from corresponding responses. Due to the lack of ground truth on the expected responses from legitimate services, previous studies typically require a heavy, unscalable manual inspection to identify false positives while still leaving false negatives undetected. In this paper, we propose Disguiser, a novel framework that enables end-to-end measurement to accurately detect the censorship activities and reveal the censor deployment without manual efforts. The core of Disguiser is a control server that replies with a static payload to provide the ground truth of server responses. As such, we send requests from various types of vantage points across the world to our control server, and the censorship activities can be recognized if a vantage point receives a different response. In particular, we design and conduct a cache test to pre-exclude the vantage points that could be interfered by cache proxies along the network path. Then we perform application traceroute towards our control server to explore censors' behaviors and their deployment. With Disguiser, we conduct 58 million measurements from vantage points in 177 countries. We observe 292 thousand censorship activities that block DNS, HTTP, or HTTPS requests inside 122 countries, achieving a 10^-6 false positive rate and zero false negative rate. Furthermore, Disguiser reveals the censor deployment in 13 countries.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129967483","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：