{"title":"What is an Optimal Policy in Time-Average MDP?","authors":"Nicolas Gast, Bruno Gaujal, Kimang Khun","doi":"10.1145/3626570.3626582","DOIUrl":"https://doi.org/10.1145/3626570.3626582","url":null,"abstract":"This paper discusses the notion of optimality for time-average MDPs. We argue that while most authors claim to use the \"average reward\" criteria, the notion that is implicitly used is in fact the notion of what we call Bellman optimality. We show that it does not coincide with other existing notions of optimality, like gain-optimality and bias-optimality but has strong connection with canonical-policies (policies that are optimal for any finite horizons) as well as value iteration and policy iterations algorithms.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426410","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}
{"title":"Designing Traffic Monitoring Systems for Self-Driving Networks","authors":"Chris Misa","doi":"10.1145/3626570.3626602","DOIUrl":"https://doi.org/10.1145/3626570.3626602","url":null,"abstract":"Traffic monitoring is a critical component of self-driving networks. In particular, any system that seeks to automatically manage a network's operation must first be equipped with insights about traffic currently flowing through the network. Typically, dedicated traffic monitoring systems deliver such insights in the form of traffic features to high-level human or automated decision makers. Inspired by the exciting capabilities of programmable dataplanes and the persistent challenges of network management, the research community has focused on improving the flexibility and efficiency of traffic monitoring systems for a variety of management tasks. However, a significant gap remains between the traffic monitoring requirements of practical, deployable self-driving networks and the capabilities of current state-of-the-art systems. This short paper provides a brief background of traffic monitoring systems, discusses how their claims and limitations relate to requirements of self-driving networks, and proposes several open challenges as exciting starting points for future research. Addressing these challenges requires large-scale efforts in traffic monitoring techniques and selfdriving network design, as well as enhanced dialog between researchers in both domains.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426411","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}
Isaac Grosof, Mor Harchol-Balter, Alan Scheller-Wolf
{"title":"New Stability Results for Multiserver-job Models via Product-form Saturated Systems","authors":"Isaac Grosof, Mor Harchol-Balter, Alan Scheller-Wolf","doi":"10.1145/3626570.3626574","DOIUrl":"https://doi.org/10.1145/3626570.3626574","url":null,"abstract":"Multiserver-job (MSJ) models are increasingly common in today's datacenters. In these models, each job runs on multiple servers concurrently, for some duration. The most common service ordering for jobs is First-Come First-Served (FCFS). Unfortunately, MSJ FCFS models are hard to analyze, and even the stability region of MSJ FCFS models is not well understood. Stability has only been analyzed in the case where all jobs have independent exponentially-distributed durations with the same mean (the \"single duration\" setting). This does not allow, however, for modeling the common situation where jobs with higher server need (number of servers required) also have higher expected duration. This paper provides the first analysis of stability for MSJ FCFS models in the two-class setting, where each class of jobs has its own server need and its own exponentially-distributed duration. To analyze stability, we make use of the saturated system, whose throughput determines the stability region. While the saturated system has been useful in deriving stability regions in the past, it has never been applied in settings where jobs occupy multiple servers. By looking at the saturated system in a new light, we find that its solution has an attractive product form in the two-class setting, and a different product form in the single-duration setting, both novel results. Besides solving our problem, this product form may also serve as a gateway to analyzing other complex models.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426423","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}
{"title":"Reducing Heavy-Traffic Response Time with Asymmetric Dispatching","authors":"Runhan Xie, Ziv Scully","doi":"10.1145/3626570.3626584","DOIUrl":"https://doi.org/10.1145/3626570.3626584","url":null,"abstract":"Reducing mean response time has always been a desirable goal in queueing systems. If job sizes (a.k.a. service times) are known to the scheduler, the policy that minimizes mean response time of a single-server queue is SRPT (Shortest Remaining Processing Time). This is true even for queues that are part of a larger system, such as immediate-dispatch systems where jobs are sent to one of multiple single-server queues upon arrival.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426569","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}
{"title":"GHZ distillation protocols in the presence of decoherence","authors":"S´ebastian de Bone, David Elkouss","doi":"10.1145/3626570.3626599","DOIUrl":"https://doi.org/10.1145/3626570.3626599","url":null,"abstract":"In this paper, we introduce a novel heuristic approach designed to optimize the performance of Greenberger-Horne- Zeilinger (GHZ) creation and distillation protocols under decoherence. Our methodology converts these protocols into a practical set of instructions, demonstrating, through simulations, the production of higher-quality GHZ states than previously known protocols. This advancement contributes to the field of distributed quantum computing by addressing the need for high-quality entanglement required for operations between different quantum computers.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426272","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}
Walter Willinger, Arpit Gupta, Roman Beltiukov, Wenbo Guo
{"title":"A NetAI Manifesto (Part II): Less Hubris, more Humility","authors":"Walter Willinger, Arpit Gupta, Roman Beltiukov, Wenbo Guo","doi":"10.1145/3626570.3626610","DOIUrl":"https://doi.org/10.1145/3626570.3626610","url":null,"abstract":"The application of the latest techniques from artificial intelligence (AI) and machine learning (ML) to improve and automate the decision-making required for solving real-world network security and performance problems (NetAI, for short) has generated great excitement among networking researchers. However, network operators have remained very reluctant when it comes to deploying NetAIbased solutions in their production networks. In Part I of this manifesto, we argue that to gain the operators' trust, researchers will have to pursue a more scientific approach towards NetAI than in the past that endeavors the development of explainable and generalizable learning models. In this paper, we go one step further and posit that this \"opening up of NetAI research\" will require that the largely self-assured hubris about NetAI gives way to a healthy dose humility. Rather than continuing to extol the virtues and \"magic\" of black-box models that largely obfuscate the critical role of the utilized data play in training these models, concerted research efforts will be needed to design NetAI-driven agents or systems that can be expected to perform well when deployed in production settings and are also required to exhibit strong robustness properties when faced with ambiguous situations and real-world uncertainties. We describe one such effort that is aimed at developing a new ML pipeline for generating trained models that strive to meet these expectations and requirements.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426409","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}
{"title":"Towards Future-Based Explanations for Deep RL Network Controllers","authors":"Sagar Patel, Sangeetha Abdu Jyothi, Nina Narodytska","doi":"10.1145/3626570.3626607","DOIUrl":"https://doi.org/10.1145/3626570.3626607","url":null,"abstract":"Lack of explainability is hindering the practical adoption of high-performance Deep Reinforcement Learning (DRL) controllers. Prior work focused on explaining the controller by identifying salient features of the controller's input. However, these feature-based methods focus solely on inputs and do not fully explain the controller's policy. In this paper, we put forward future-based explainers as an essential tool for providing insights into the controller's decision-making process and, thereby, facilitating the practical deployment of DRL controllers. We highlight two applications of futurebased explainers in the networking domain: online safety assurance and guided controller design. Finally, we provide a roadmap for the practical development and deployment of future-based explainers for DRL network controllers.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426413","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}
{"title":"Performance evaluation teaching in the age of cloud computing","authors":"Giuliano Casale","doi":"10.1145/3626570.3626588","DOIUrl":"https://doi.org/10.1145/3626570.3626588","url":null,"abstract":"Cloud computing has been one of the most significant developments in computer science of the last two decades, fostering sharp changes in performance engineering practices across the computing industry and, at the same time, profoundly steering research trends in academia. A distinctive trait of this paradigm is that cloud engineers can programmatically control application performance, raising an expectation for computing graduates who find employment in software and system development to have basic performance engineering skills. This, in my view, calls for a broader and deeper education on software and system performance topics as part of the computing curriculum, while at the same time requiring a rethink of the syllabus of a classic performance evaluation module. This abstract presents my personal experience in doing so, including a discussion on the educational strengths and weaknesses of performance engineering emerging from cloud computing practice.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426420","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}
{"title":"On Ultra-Sharp Queueing Bounds","authors":"Florin Ciucu, Sima Mehri, Amr Rizk","doi":"10.1145/3626570.3626581","DOIUrl":"https://doi.org/10.1145/3626570.3626581","url":null,"abstract":"Martingale-based techniques render sharp bounds in several queueing scenarios, but mainly in heavy-traffic and subject to the degree of burstiness. We present a related technique to render ultra-sharp bounds across all utilization levels and for various degrees of burstiness.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426570","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}
Ananda G. Maity, Joshua C. A. Casapao, Naphan Benchasattabuse, Michal Hajdusek, Rodney Van Meter, David Elkouss
{"title":"Noise estimation in an entanglement distillation protocol","authors":"Ananda G. Maity, Joshua C. A. Casapao, Naphan Benchasattabuse, Michal Hajdusek, Rodney Van Meter, David Elkouss","doi":"10.1145/3626570.3626594","DOIUrl":"https://doi.org/10.1145/3626570.3626594","url":null,"abstract":"Estimating noise processes is an essential step for practical quantum information processing. Standard estimation tools require consuming valuable quantum resources. Here we ask the question of whether the noise affecting entangled states can be learned solely from the measurement statistics obtained during a distillation protocol. As a first step, we consider states of the Werner form and find that the Werner parameter can be estimated efficiently from the measurement statistics of an idealized distillation protocol. Our proposed estimation method can find application in scenarios where distillation is an unavoidable step.","PeriodicalId":35745,"journal":{"name":"Performance Evaluation Review","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426412","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}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
