Search

Network resource reservation systems are being developed and deployed, driven by the demand and substantial benefits of providing performance predictability for modern distributed applications. However, existing systems suffer limitations: They either are inefficient in finding the optimal resource reservation, or cause private information (e.g., from the network infrastructure) to be exposed (e.g., to the user). In this paper, we design BoxOpt, a novel system that leverages efficient oracle construction techniques in optimization and learning theory to automatically, and swiftly learn the optimal resource reservations without exchanging any private information between the network and the user. In BoxOpt, we first model the simple reservation interface adopted in most reservation systems as a resource membership oracle. Second, we develop an efficient algorithm that constructs a resource separation oracle by a linear number of calls on resource membership oracle. Third, we develop a generic framework to construct a resource optimization oracle by iteratively calling the resource separation oracle, and then develop three novel, efficient algorithms under this generic framework, the best of which computes the optimal resource reservation by a linear number of calls on resource separation oracle. As such, BoxOpt can discover the optimal resource reservation with O(n2) calls on the resource membership oracle. We implement a prototype of BoxOpt with and demonstrate its efficiency and efficacy via extensive experiments using real network topology and a 7-day trace from a large operational federation network. Results show that (1) BoxOpt has a 100% correctness ratio by comparing with a state-of-the-art optimization solver, and (2) for 90% of requests, BoxOpt learns the optimal resource reservation within 10 seconds. [ABSTRACT FROM AUTHOR]

Multi-domain network resource reservation systems are being deployed, driven by the demand and substantial benefits of providing predictable network resources. However, a major lack of existing systems is their coarse granularity, due to the participating networks’ concern of revealing sensitive information, which can result in substantial inefficiencies. This paper presents Mercator, a novel multi-domain network resource discovery system to provide fine-grained, global network resource information, for collaborative sciences. The foundation of Mercator is a resource abstraction through algebraic-expression enumeration (i.e., linear inequalities/equations), as a compact representation of multiple properties of network resources (e.g., bandwidth, delay, and loss rate) in multi-domain networks. In addition, we develop an obfuscating protocol, to address the privacy concerns by ensuring that no participant can associate the algebraic expressions with the corresponding member networks. We also introduce a super-set projection technique to increase Mercator’s scalability. We implement a prototype Mercator and deploy it in a small federation network. We also evaluate the performance of Mercator through extensive experiments using real topologies and traces. Results show that Mercator 1) efficiently discovers available networking resources in collaborative networks on average four orders of magnitude faster, and allows fairer allocations of network resources; 2) preserves the member networks’ privacy with little overhead; and 3) scales to a collaborative network of 200 member networks. [ABSTRACT FROM AUTHOR]

Revealing an abstract view of the network is essential for the new paradigm of developing network-aware adaptive applications that can fully leverage the available computation and storage resources and achieve better business values. In this paper, we introduce ONV, a novel abstraction of flow-based on-demand network view. The ONV models network views as linear constraints on network-related variables in application-layer objective functions, and provides “equivalent” network views that allow applications to achieve the same optimal objectives as if they have the global information. We prove the lower bound for the number of links contained in an equivalent network view, and propose two algorithms to effectively calculate on-demand equivalent network views. We evaluate the efficacy and the efficiency of our algorithms extensively with real-world topologies. Evaluations demonstrate that the ONV can simplify the network up to 80% while maintaining an equivalent view of the network. Even for a large network with more than 25 000 links and a request containing 3000 flows, the result can be effectively computed in less than 1 min on a commodity server. [ABSTRACT FROM AUTHOR]

Collaborative robots are multirobot systems working together for the same industrial task such as robotic assembling. To achieve an efficient collaboration, robots require not only locally sensing the environmental data but also immediately sharing these data with neighbors. However, there exists a dilemma between the large amount of sensory data and the limited wireless bandwidth. In this paper, we study the problem of maximizing the throughput of sensory data sharing in collaborative robots. This data sharing is different from the transmissions in conventional mobile networks due to the real-time sharing requirement and the vicinity sharing pattern. Thus, existing adaptation methods cannot be applied directly. To maximize the throughput in dynamic environment, we propose a novel adaptation method AdaSharing based on control theory, which jointly adapts the combination of packet rate and transmission power according to the feedback of throughput. We implement AdaSharing in a nine-robot testbed, and conduct extensive experiments to verify its feasibility and effectiveness. Simulations based on ns-2 are further conducted to evaluate AdaSharing in large-scale scenarios. Both experiment and simulation results demonstrate that AdaSharing outperforms existing methods by improving the throughput up to 23%. [ABSTRACT FROM AUTHOR]

New-generation industries heavily rely on big data to improve their efficiency. Such big data are commonly collected by smart nodes and transmitted to the cloud via wireless. Due to the limited size of smart node, the shortage of energy is always a critical issue, and the wireless data transmission is extremely a big power consumer. Aiming to reduce the energy consumption in wireless, this article introduces a potential breach from data redundancy. If redundant data are no longer collected, a large amount of wireless transmissions can be cancelled and their energy saved. Motivated by this breach, this article proposes a compressive-sensing-based collection framework to minimize the amount of collection while guaranteeing data quality. This framework is verified by experiments and extensive realtrace- driven simulations. [ABSTRACT FROM PUBLISHER]

Real-time routing is a basic element of closed-loop, real-time sensing and control, but it is challenging due to dynamic, uncertain link/path delays. The probabilistic nature of link/path delays makes the basic problem of computing the probabilistic distribution of path delays NP-hard, yet quantifying probabilistic path delays is a basic element of real-time routing and may well have to be executed by resource-constrained devices in a distributed manner; the highly varying nature of link/path delays makes it necessary to adapt to in-situ delay conditions in real-time routing, but it has been observed that delay-based routing can lead to instability, estimation error, and low data delivery performance in general. To address these challenges, we propose the Multi-Timescale Estimation (MTE) method; by accurately estimating the mean and variance of per-packet transmission time and by adapting to fast-varying queueing in an accurate, agile manner, MTE enables accurate, agile, and efficient estimation of probabilistic path delay bounds in a distributed manner. Based on MTE, we propose the Multi-Timescale Adaptation (MTA) routing protocol; MTA integrates the stability of an ETX-based directed-acyclic-graph (DAG) with the agility of spatiotemporal data flow control within the DAG to ensure real-time data delivery in the presence of dynamics and uncertainties. We also address the challenges of implementing MTE and MTA in resource-constrained devices such as TelosB motes. We evaluate the performance of MTA using the NetEye and Indriya sensor network testbeds. We find that MTA significantly outperforms existing protocols, e.g., improving deadline success ratio by 89% and reducing transmission cost by a factor of 9.7 in the NetEye testbed. [ABSTRACT FROM PUBLISHER]

As sensornets are increasingly being deployed in mission-critical applications, it becomes imperative that we consider application QoS requirements in in-network processing (INP). Toward understanding the complexity of joint QoS and INP optimization, we study the problem of jointly optimizing packet packing (i.e., aggregating shorter packets into longer ones) and the timeliness of data delivery. We identify the conditions under which the problem is strong NP-hard, and we find that the problem complexity heavily depends on aggregation constraints (in particular, maximum packet size and reaggregation tolerance) instead of network and traffic properties. For cases when the problem is NP-hard, we show that there is no polynomial-time approximation scheme (PTAS); for cases when the problem can be solved in polynomial time, we design polynomial time, offline algorithms for finding the optimal packet packing schemes. To understand the impact of joint QoS and INP optimization on sensornet performance, we design a distributed, online protocol tPack that schedules packet transmissions to maximize the local utility of packet packing at each node. Using a testbed of 130 TelosB motes, we experimentally evaluate the properties of tPack. We find that jointly optimizing data delivery timeliness and packet packing and considering real-world aggregation constraints significantly improve network performance. Our findings shed light on the challenges, benefits, and solutions of joint QoS and INP optimization, and they also suggest open problems for future research. [ABSTRACT FROM PUBLISHER]