Search

Edge computing systems benefit from knowledge of short-term mobility from 5G technologies, as tasks offloaded from user devices can be placed at the edge to reduce their latencies. However, as devices move, they will need to offload their tasks to different edge servers, which may require migrating data from one edge server to another. In this paper, we introduce MoDEMS, a system architecture through which we provide a rigorous theoretical framework to study the challenges of such migrations to minimize the service provider cost and user latency. We show that this cost minimization problem can be expressed as an integer linear programming problem, which is challenging to solve due to resource constraints at the servers and unknown user mobility patterns. We show that finding the optimal migration plan is in general NP-hard, and we propose alternative heuristic solution algorithms. We finally validate our results with realistic user mobility traces.

As the importance of latency performance increases, a number of multi-bit feedback-based congestion control mechanisms have been proposed for explicit latency control in cellular networks. However, due to their reactive nature and limited access to the network queue, while latency reduction was possible, latency guarantee has not been achieved. Also, due to the need for end-host modifications, it was hard to commonly provide latency benefit to all connected devices. To this end, we propose a novel network-assisted congestion control, ECLAT, which can always bound the queuing delay within a delay-budget through ECN-based single-bit feedback while maintaining high link utilization for any device. To do so, ECLAT 1) calculates its target operating point for each flow, which is related to the maximum allowable cwnd to meet the delay-budget under time-varying cellular networks, and 2) determines its single-bit feedback policy to limit cwnd within the target operating point. Our extensive experiments in our testbed demonstrate that ECLAT is able to bound the queuing delays of multiple flows within their delay-budget and achieve high utilization even in the dynamic cellular network environment.

Multi-path TCP (MPTCP) has been standardized by IETF and being used in practice. However, the MPTCP performance analysis has been paid less attention than algorithm improvement, such as coupled congestion control between subflows. The existing analytical models lack consideration of both slow start and congestion avoidance phases. In this letter, we perform a full analysis to derive the MPTCP performance by considering both the phases in the network with shared bottleneck so that we can calculate data transfer latency as well as throughput for a given size of data. Via direct code execution on top of the NS-3 simulation, we show that the proposed analysis captures data transfer latency under packet losses due to buffer overflow.

Crop models are increasingly used to evaluate crop yields at regional/global scales. These applications require the integration and processing of very large data sets in order to explore the implications of land management options across spatially heterogeneous scales. These modeling involve the combination of large spatially explicit data sets for climate, biophysical and crop management variables as well as significant computational capacity for regional/global scale simulations. As a result, the application of crop models at regional/global scales is challenging due to the requirements for input data, calibration, validation and simulation setups appropriate for thousands to millions of spatial points. Not surprisingly, the implementation of these models across large areas using fine-scale grids can be limited by computational time requirements. To reduce the large computational load of an agroecosystem simulation process for regional and global scales, we developed an E PIC P arallel C omputing F ramework (EPCF) to facilitate regional/global gridded crop modeling. The EPCF can make full use of the CPU resources of the workstation through parallel processing. For future users, only a few lines of additional code modification are needed to convert the single process code to parallel computing code. Parallel processing in one machine makes it easy to handle the whole system without the overhead and expertise required for a distributed system. EPCF is a system that provides not only the ease of development but also cost-efficiency.

The United States is a world leader in the production of maize and other crops and the agricultural success of the country is directly linked to the intensive use of fertilizers and irrigation. However, even in advanced agricultural systems, soils can become degraded over time due to factors such as soil organic matter (SOM) loss and erosion. Here, we use a series of scenario‐based model analyses to show that about one‐third of current annual US. N fertilizer use in maize agriculture is used to compensate for the long‐term loss of soil fertility through erosion and organic matter loss. This leads to over a half billion dollars per year in extra fertilizer supply costs to US farmers. These results highlight the potential to reduce both the input costs and environmental impacts of agriculture through the restoration of SOM in agricultural soils.

In this paper, we propose SPARCLE, a novel scheduling system offering network-aware polynomial-time task assignment and resource allocation algorithms for stream processing applications in dispersed computing networks. In particular, we address two major challenges. The first one concerns the assignment of both computation and transport tasks comprising a stream processing application to computing nodes and communication links of the network, respectively, to maximize the application’s processing rate. The second one concerns the resource allocation of multiple stream processing applications to satisfy their requested QoS. Our experimental results on a real image stream processing application and extensive simulations show that SPARCLE can increase the application’s processing rate by 9 times and 3 times, compared to the cloud computing case and state-of-the-art algorithms, respectively.

This paper presents a new approach to memory disaggregation called FluidMem that leverages the userfault mechanism in Linux to achieve full memory disaggregation in software. FluidMem enables dynamic and transparent resizing of an unmodified Virtual Machine’s (VM’s) memory footprint in the cloud. As a result, a VM’s memory footprint can seamlessly scale over multiple machines or even be downsized to a near-zero footprint on a given server. FluidMem’s architecture provides flexibility to cloud operators to manage remote memory without requiring guest intervention, while also supporting paging out the entirety of a VM’s pages within its address space. FluidMem integrates with a remote memory backend in a modular way, easily supporting systems such as RAMCloud to harness remote memory. We demonstrate FluidMem outperforms an existing memory disaggregation approach based on network swap. Microbenchmarks are evaluated to characterize the latency of different components of the FluidMem architecture, and two memory-intensive applications are demonstrated using FluidMem, the Graph500 benchmark, and MongoDB. Additionally, we show FluidMem can flexibly and efficiently grow and shrink the memory footprint of a VM as defined by a cloud provider.

Today’s Internet must support applications with increasingly dynamic and heterogeneous connectivity requirements, such as video streaming and the Internet of Things. Yet current network management practices generally rely on pre-specified flow configurations, which cannot cover all possible scenarios. In this work, we instead propose a model-free learning approach to automatically optimize the policies for heterogeneous network flows. This approach is attractive as no existing comprehensive models quantify how different policy choices affect flow performance under dynamically changing network conditions. We extend multi-armed bandit frameworks to propose new online learning algorithms for protocol selection, addressing the challenge of policy configurations affecting the performance of multiple flows sharing the same network resources. This performance coupling limits the scalability and optimality of existing online learning algorithms. We theoretically prove that our algorithm achieves a sublinear regret and demonstrate its optimality and scalability through data-driven simulations.

The HTTP-based Adaptive Streaming (HAS) techniques are widely used in Internet video streaming services, including YouTube and Netflix. The Dynamic Adaptive Streaming over HTTP (DASH) is the latest international standard that facilitates the interoperability of different HAS techniques of various vendors. DASH specification defines the media presentation description (MPD), which describes a list of available content, URL addresses, and the segment format. The rate adaptation algorithms, however, are not part of the standard, and the details of the algorithms are left to vendors. As a result, there are many different algorithms adopted in both commercial and open source players while the detailed algorithms and their performance are barely understood. In this paper, we investigate the detailed operations of the different players by code level analysis and through reverse engineering. Specifically, we present the pseudo codes of 3 open source players and devise a method to obtain the detailed operation information, e.g., bitrate and buffer amount, of popular streaming players whose source codes are not publicly available. We conduct extensive experiments on our testbed and provide suggestions based on the behaviors of these players, including the repeated over-estimation of the available bandwidth, unfair bitrate selection when multiple players compete for the bandwidth, and insensitivity of Quick UDP Internet Connections (QUIC) protocol to the varying network bandwidth.

This paper presents a fully distributed scheduling framework called CASTLE (Client-side Adaptive Scheduler That minimizes Load and Energy), which jointly optimizes the spectral efficiency of cellular networks and battery consumption of smart devices. To do so, we focus on scenarios when many smart devices compete for cellular resources in the same base station: spreading out transmissions over time so that only a few devices transmit at once improves both spectral efficiency and battery consumption. To this end, we devise two novel features in CASTLE. First, we explicitly consider inter-cell interference for accurate cellular load estimation. Based on our observations, we exploit the RSRQ (Reference Signal Received Quality) and SINR as features in a machine learning algorithm to accurately estimate the cellular load. Second, we propose a fully distributed scheduling algorithm that coordinates transmissions between clients based on the locally estimated load level at each client. Our formulation for minimizing battery consumption at each device leads to an optimized backoff-based algorithm that fits practical environments. To evaluate these features, we prototype a complete LTE system testbed consisting of mobile devices, eNodeBs, EPC (Evolved Packet Core) and application servers. Our comprehensive experimental results show that CASTLE's load estimation is up to 91% accurate, and that CASTLE achieves higher spectral efficiency with less battery consumption, compared to existing centralized scheduling algorithms as well as a distributed CSMA-like protocol. Furthermore, we develop a light-weight SDK that can expedite the deployment of CASTLE into smart devices and evaluate it in a commercial LTE network.

Modern cell phones are required to receive and display alerts via the Wireless Emergency Alert (WEA) program, under the mandate of the Warning, Alert, and Response Act of 2006. These alerts include AMBER alerts, severe weather alerts, and (unblockable) Presidential Alerts, intended to inform the public of imminent threats. Recently, a test Presidential Alert was sent to all capable phones in the United States, prompting concerns about how the underlying WEA protocol could be misused or attacked. In this paper, we investigate the details of this system, and develop and demonstrate the first practical spoofing attack on Presidential Alerts, using both commercially available hardware as well as modified open source software. Our attack can be performed using a commercially-available software defined radio, and our modifications to the open source NextEPC and srsLTE software libraries. We find that with only four malicious portable base stations of a single Watt of transmit power each, almost all of a 50,000-seat stadium can be attacked with a 90% success rate. The true impact of such an attack would of course depend on the density of cell phones in range; fake alerts in crowded cities or stadiums could potentially result in cascades of panic. Fixing this problem will require a large collaborative effort between carriers, government stakeholders, and cell phone manufacturers. To seed this effort, we also discuss several defenses to address this threat in both the short and long term.

Emerging applications like virtual reality (VR), augmented reality (AR), and 360-degree video aim to exploit the unprecedentedly low latencies promised by technologies like the tactile Internet and mobile 5G networks. Yet these promises are still unrealized. In order to fulfill them, it is crucial to understand where packet delays happen, which impacts protocol performance such as throughput and latency. In this work, we empirically find that sender-side protocol stack delays can cause high end-to-end latencies, though existing solutions primarily address network delays. Unfortunately, however, current latency diagnosis tools cannot even distinguish between delays on network links and delays in the end hosts. To close this gap, we present ELEMENT, a latency diagnosis framework that decomposes end-to-end TCP latency into endhost and network delays, without requiring admin privileges at the sender or receiver. We validate that ELEMENT achieves more than 90% accuracy in delay estimation compared to the ground truth in different production networks. To demonstrate ELEMENT's potential impact on real-world applications, we implement a relatively simple user-level library that uses ELEMENT to minimize delays. For evaluation, we integrate ELEMENT with legacy TCP applications and show that it can reduce latency by up to 10 times while maintaining throughput and fairness. We finally demonstrate that ELEMENT can significantly reduce the latency of a virtual reality application that needs extremely low latencies and high throughput.