arXiv subjects

Yogesh Simmhan

Publications and source records attributed to Yogesh Simmhan.

At least 73 records · Page 4Linked to original sources

arXiv2021

Heuristic Algorithms for Co-scheduling of Edge Analytics and Routes for UAV Fleet Missions

Unmanned Aerial Vehicles (UAVs) or drones are increasingly used for urban applications like traffic monitoring and construction surveys. Autonomous navigation allows drones to visit waypoints and accomplish activities as part of their mission. A common activity is to hover and observe a location using on-board cameras. Advances in Deep Neural Networks (DNNs) allow such videos to be analyzed for automated decision making. UAVs also host edge computing capability for on-board inferencing by such DNNs. To this end, for a fleet of drones, we propose a novel Mission Scheduling Problem (MSP) that co-schedules the flight routes to visit and record video at waypoints, and their subsequent on-board edge analytics. The proposed schedule maximizes the utility from the activities while meeting activity deadlines as well as energy and computing constraints. We first prove that MSP is NP-hard and then optimally solve it by formulating a mixed integer linear programming (MILP) problem. Next, we design two efficient heuristic algorithms, JSC and VRC, that provide fast sub-optimal solutions. Evaluation of these three schedulers using real drone traces demonstrate utility-runtime trade-offs under diverse workloads.

cs.RO↗

arXiv2020

GoCoronaGo: Privacy Respecting Contact Tracing for COVID-19 Management

The COVID-19 pandemic is imposing enormous global challenges in managing the spread of the virus. A key pillar to mitigation is contact tracing, which complements testing and isolation. Digital apps for contact tracing using Bluetooth technology available in smartphones have gained prevalence globally. In this article, we discuss various capabilities of such digital contact tracing, and its implication on community safety and individual privacy, among others. We further describe the GoCoronaGo institutional contact tracing app that we have developed, and the conscious and sometimes contrarian design choices we have made. We offer a detailed overview of the app, backend platform and analytics, and our early experiences with deploying the app to over 1000 users within the Indian Institute of Science campus in Bangalore. We also highlight research opportunities and open challenges for digital contact tracing and analytics over temporal networks constructed from them.

cs.CY↗

arXiv2020

A Distributed Path Query Engine for Temporal Property Graphs

Property graphs are a common form of linked data, with path queries used to traverse and explore them for enterprise transactions and mining. Temporal property graphs are a recent variant where time is a first-class entity to be queried over, and their properties and structure vary over time. These are seen in social, telecom, transit and epidemic networks. However, current graph databases and query engines have limited support for temporal relations among graph entities, no support for time-varying entities and/or do not scale on distributed resources. We address this gap by extending a linear path query model over property graphs to include intuitive temporal predicates and aggregation operators over temporal graphs. We design a distributed execution model for these temporal path queries using the interval-centric computing model, and develop a novel cost model to select an efficient execution plan from several. We perform detailed experiments of our Granite distributed query engine using both static and dynamic temporal property graphs as large as 52M vertices, 218M edges and 325M properties, and a 1600-query workload, derived from the LDBC benchmark. We often offer sub-second query latencies on a commodity cluster, which is 149x-1140x faster compared to industry-leading Neo4J shared-memory graph database and the JanusGraph / Spark distributed graph query engine. Granite also completes 100% of the queries for all graphs, compared to only 32-92% workload completion by the baseline systems. Further, our cost model selects a query plan that is within 10% of the optimal execution time in 90% of the cases. Despite the irregular nature of graph processing, we exhibit a weak-scaling efficiency >= 60% on 8 nodes and >= 40% on 16 nodes, for most query workloads.

cs.DC↗

arXiv2020

A Scalable Platform for Distributed Object Tracking across a Many-camera Network

Advances in deep neural networks (DNN) and computer vision (CV) algorithms have made it feasible to extract meaningful insights from large-scale deployments of urban cameras. Tracking an object of interest across the camera network in near real-time is a canonical problem. However, current tracking platforms have two key limitations: 1) They are monolithic, proprietary and lack the ability to rapidly incorporate sophisticated tracking models; and 2) They are less responsive to dynamism across wide-area computing resources that include edge, fog and cloud abstractions. We address these gaps using Anveshak, a runtime platform for composing and coordinating distributed tracking applications. It provides a domain-specific dataflow programming model to intuitively compose a tracking application, supporting contemporary CV advances like query fusion and re-identification, and enabling dynamic scoping of the camera network's search space to avoid wasted computation. We also offer tunable batching and data-dropping strategies for dataflow blocks deployed on distributed resources to respond to network and compute variability. These balance the tracking accuracy, its real-time performance and the active camera-set size. We illustrate the concise expressiveness of the programming model for $4$ tracking applications. Our detailed experiments for a network of 1000 camera-feeds on modest resources exhibit the tunable scalability, performance and quality trade-offs enabled by our dynamic tracking, batching and dropping strategies.

cs.DC↗

arXiv2019

Characterizing IoT Data and its Quality for Use

The Internet of Things (IoT) is a cyber physical social system that encompasses science, enterprise and societal domains. Data is the most important commodity in IoT, enabling the "smarts" through analytics and decision making. IoT environments can generate and consume vast amounts of data. But managing this data effectively and gaining meaningful insights from it requires us to understand its characteristics. Traditional scientific, enterprise and big data management approaches may not be adequate, and have to evolve. Further, these characteristics and the physical deployment environments also impact the quality of the data for use. In this paper, we offer a taxonomy of IoT data characteristics, along with data quality considerations, that are constructed from the ground-up based on the diverse IoT domains and applications we review. We emphasize on the essential features, rather than a vast array of attributes. We also indicate factors that influence the data quality. Such a review is of value to IoT managers, data handlers and application composers in managing and making meaningful use of data, and for big data platform developers to offer meaningful solutions to address these considerations.

cs.OH↗

arXiv2019

ElfStore: A Resilient Data Storage Service for Federated Edge and Fog Resources

Edge and fog computing have grown popular as IoT deployments become wide-spread. While application composition and scheduling on such resources are being explored, there exists a gap in a distributed data storage service on the edge and fog layer, instead depending solely on the cloud for data persistence. Such a service should reliably store and manage data on fog and edge devices, even in the presence of failures, and offer transparent discovery and access to data for use by edge computing applications. Here, we present Elfstore, a first-of-its-kind edge-local federated store for streams of data blocks. It uses reliable fog devices as a super-peer overlay to monitor the edge resources, offers federated metadata indexing using Bloom filters, locates data within 2-hops, and maintains approximate global statistics about the reliability and storage capacity of edges. Edges host the actual data blocks, and we use a unique differential replication scheme to select edges on which to replicate blocks, to guarantee a minimum reliability and to balance storage utilization. Our experiments on two IoT virtual deployments with 20 and 272 devices show that ElfStore has low overheads, is bound only by the network bandwidth, has scalable performance, and offers tunable resilience.

cs.DC↗

arXiv2019

Distributed Algorithms for Subgraph-Centric Graph Platforms

Graph analytics for large scale graphs has gained interest in recent years. Many graph algorithms have been designed for vertex-centric distributed graph processing frameworks to operate on large graphs with 100 M vertices and edges, using commodity clusters and Clouds. Subgraph-centric programming models have shown additional performance benefits than vertex-centric models. But direct mapping of vertex-centric and shared-memory algorithms to subgraph-centric frameworks are either not possible, or lead to inefficient algorithms. In this paper, we present three subgraph-centric distributed graph algorithms for triangle counting, clustering and minimum spanning forest, using variations of shared and vertex-centric models. These augment existing subgraph-centric algorithms that exist in literature, and allow a broader evaluation of these three classes of graph processing algorithms and platforms.

cs.DC↗

arXiv2019

Characterizing Application Scheduling on Edge, Fog and Cloud Computing Resources

Cloud computing has grown to become a popular distributed computing service offered by commercial providers. More recently, Edge and Fog computing resources have emerged on the wide-area network as part of Internet of Things (IoT) deployments. These three resource abstraction layers are complementary, and provide distinctive benefits. Scheduling applications on clouds has been an active area of research, with workflow and dataflow models serving as a flexible abstraction to specify applications for execution. However, the application programming and scheduling models for edge and fog are still maturing, and can benefit from learnings on cloud resources. At the same time, there is also value in using these resources cohesively for application execution. In this article, we present a taxonomy of concepts essential for specifying and solving the problem of scheduling applications on edge, for and cloud computing resources. We first characterize the resource capabilities and limitations of these infrastructure, and design a taxonomy of application models, Quality of Service (QoS) constraints and goals, and scheduling techniques, based on a literature review. We also tabulate key research prototypes and papers using this taxonomy. This survey benefits developers and researchers on these distributed resources in designing and categorizing their applications, selecting the relevant computing abstraction(s), and developing or selecting the appropriate scheduling algorithm. It also highlights gaps in literature where open problems remain.

cs.DC↗

arXiv2019

A Partition-centric Distributed Algorithm for Identifying Euler Circuits in Large Graphs

Finding the Eulerian circuit in graphs is a classic problem, but inadequately explored for parallel computation. With such cycles finding use in neuroscience and Internet of Things for large graphs, designing a distributed algorithm for finding the Euler circuit is important. Existing parallel algorithms are impractical for commodity clusters and Clouds. We propose a novel partition-centric algorithm to find the Euler circuit, over large graphs partitioned across distributed machines and executed iteratively using a Bulk Synchronous Parallel (BSP) model. The algorithm finds partial paths and cycles within each partition, and refines these into longer paths by recursively merging the partitions. We describe the algorithm, analyze its complexity, validate it on Apache Spark for large graphs, and offer experimental results. We also identify memory bottlenecks in the algorithm and propose an enhanced design to address it.

cs.DC↗

arXiv2018

Toward SATVAM: An IoT Network for Air Quality Monitoring

Air pollution is ranked as the second most serious risk for public health in India after malnutrition. The lack of spatially and temporally distributed air quality information prevents a scientific study on its impact on human health and on the national economy. In this paper, we present our initial efforts toward SATVAM, Streaming Analytics over Temporal Variables for Air quality Monitoring, that aims to address this gap. We introduce the multi-disciplinary, multi-institutional project and some of the key IoT technologies used. These cut across hardware integration of gas sensors with a wireless mote packaging, design of the wireless sensor network using 6LoWPAN and RPL, and integration with a cloud backend for data acquisition and analysis. The outcome of our initial deployment will inform an improved design that will enable affordable and manageable monitoring at the city scale. This should lead to data-driven policies for urban air quality management.

cs.NI↗

arXiv2018

A Manifesto for Future Generation Cloud Computing: Research Directions for the Next Decade

The Cloud computing paradigm has revolutionised the computer science horizon during the past decade and has enabled the emergence of computing as the fifth utility. It has captured significant attention of academia, industries, and government bodies. Now, it has emerged as the backbone of modern economy by offering subscription-based services anytime, anywhere following a pay-as-you-go model. This has instigated (1) shorter establishment times for start-ups, (2) creation of scalable global enterprise applications, (3) better cost-to-value associativity for scientific and high performance computing applications, and (4) different invocation/execution models for pervasive and ubiquitous applications. The recent technological developments and paradigms such as serverless computing, software-defined networking, Internet of Things, and processing at network edge are creating new opportunities for Cloud computing. However, they are also posing several new challenges and creating the need for new approaches and research strategies, as well as the re-evaluation of the models that were developed to address issues such as scalability, elasticity, reliability, security, sustainability, and application models. The proposed manifesto addresses them by identifying the major open challenges in Cloud computing, emerging trends, and impact areas. It then offers research directions for the next decade, thus helping in the realisation of Future Generation Cloud Computing.

cs.DC↗

arXiv2018

VIoLET: A Large-scale Virtual Environment for Internet of Things

IoT deployments have been growing manifold, encompassing sensors, networks, edge, fog and cloud resources. Despite the intense interest from researchers and practitioners, most do not have access to large-scale IoT testbeds for validation. Simulation environments that allow analytical modeling are a poor substitute for evaluating software platforms or application workloads in realistic computing environments. Here, we propose VIoLET, a virtual environment for defining and launching large-scale IoT deployments within cloud VMs. It offers a declarative model to specify container-based compute resources that match the performance of the native edge, fog and cloud devices using Docker. These can be inter-connected by complex topologies on which private/public networks, and bandwidth and latency rules are enforced. Users can configure synthetic sensors for data generation on these devices as well. We validate VIoLET for deployments with > 400 devices and > 1500 device-cores, and show that the virtual IoT environment closely matches the expected compute and network performance at modest costs. This fills an important gap between IoT simulators and real deployments.

cs.DC↗

arXiv2018

Towards a Data-driven IoT Software Architecture for Smart City Utilities

The Internet of Things (IoT) is emerging as the next big wave of digital presence for billions of devices on the Internet. Smart Cities are practical manifestation of IoT, with the goal of efficient, reliable and safe delivery of city utilities like water, power and transport to residents, through their intelligent management. A data-driven IoT Software Platform is essential for realizing manageable and sustainable Smart Utilities, and for novel applications to be developed upon them. Here, we propose such a service-oriented software architecture to address two key operational activities in a Smart Utility -- the IoT fabric for resource management, and the data and application platform for decision making. Our design uses open web standards and evolving network protocols, Cloud and edge resources, and streaming Big Data platforms. We motivate our design requirements using the smart water management domain; some of these requirements are unique to developing nations. We also validate the architecture within a campus-scale IoT testbed at the Indian Institute of Science (IISc), Bangalore, and present our experiences. Our architecture is scalable to a township or city, while also generalizable to other Smart Utility domains. Our experiences serves as a template for other similar efforts, particularly in emerging markets, and highlights the gaps and opportunities for a data-driven IoT Software architecture for smart cities.

cs.DC↗

arXiv2018

Adaptive Energy-aware Scheduling of Dynamic Event Analytics across Edge and Cloud Resources

The growing deployment of sensors as part of Internet of Things (IoT) is generating thousands of event streams. Complex Event Processing (CEP) queries offer a useful paradigm for rapid decision-making over such data sources. While often centralized in the Cloud, the deployment of capable edge devices on the field motivates the need for cooperative event analytics that span Edge and Cloud computing. Here, we identify a novel problem of query placement on edge and Cloud resources for dynamically arriving and departing analytic dataflows. We define this as an optimization problem to minimize the total makespan for all event analytics, while meeting energy and compute constraints of the resources. We propose 4 adaptive heuristics and 3 rebalancing strategies for such dynamic dataflows, and validate them using detailed simulations for 100 - 1000 edge devices and VMs. The results show that our heuristics offer O(seconds) planning time, give a valid and high quality solution in all cases, and reduce the number of query migrations. Furthermore, rebalance strategies when applied in these heuristics have significantly reduced the makespan by around 20 - 25%.

cs.DC↗

arXiv2017

Big Data and Fog Computing

Fog computing serves as a computing layer that sits between the edge devices and the cloud in the network topology. They have more compute capacity than the edge but much less so than cloud data centers. They typically have high uptime and always-on Internet connectivity. Applications that make use of the fog can avoid the network performance limitation of cloud computing while being less resource constrained than edge computing. As a result, they offer a useful balance of the current paradigms. This article explores various aspects of fog computing in the context of big data.

cs.DC↗

arXiv2017

Distributed Scheduling of Event Analytics across Edge and Cloud

Internet of Things (IoT) domains generate large volumes of high velocity event streams from sensors, which need to be analyzed with low latency to drive decisions. Complex Event Processing (CEP) is a Big Data technique to enable such analytics, and is traditionally performed on Cloud Virtual Machines (VM). Leveraging captive IoT edge resources in combination with Cloud VMs can offer better performance, flexibility and monetary costs for CEP. Here, we formulate an optimization problem for energy-aware placement of CEP queries, composed as an analytics dataflow, across a collection of edge and Cloud resources, with the goal of minimizing the end-to-end latency for the dataflow. We propose a Genetic Algorithm (GA) meta-heuristic to solve this problem, and compare it against a brute-force optimal algorithm (BF). We perform detailed real-world benchmarks on the compute, network and energy capacity of edge and Cloud resources. These results are used to define a realistic and comprehensive simulation study that validates the BF and GA solutions for 45 diverse CEP dataflows, LAN and WAN setup, and different edge resource availability. We compare the GA and BF solutions against random and Cloud-only baselines for different configurations, for a total of 1764 simulation runs. Our study shows that GA is within 97% of the optimal BF solution that takes hours, maps dataflows with 4 - 50 queries in 1 - 26 secs, and only fails to offer a feasible solution <= 20% of the time.

cs.DC↗

arXiv2017

Toward Reliable and Rapid Elasticity for Streaming Dataflows on Clouds

The pervasive availability of streaming data is driving interest in distributed Fast Data platforms for streaming applications. Such latency-sensitive applications need to respond to dynamism in the input rates and task behavior using scale-in and -out on elastic Cloud resources. Platforms like Apache Storm do not provide robust capabilities for responding to such dynamism and for rapid task migration across VMs. We propose several dataflow checkpoint and migration approaches that allow a running streaming dataflow to migrate, without any loss of in-flight messages or their internal tasks states, while reducing the time to recover and stabilize. We implement and evaluate these migration strategies on Apache Storm using micro and application dataflows for scaling in and out on up to 2-21 Azure VMs. Our results show that we can migrate dataflows of large sizes within 50 sec, in comparison to Storm's default approach that takes over $100~sec$. We also find that our approaches stabilize the application much earlier and there is no failure and re-processing of messages.

cs.DC↗

arXiv2017

Collaborative Reuse of Streaming Dataflows in IoT Applications

Distributed Stream Processing Systems (DSPS) like Apache Storm and Spark Streaming enable composition of continuous dataflows that execute persistently over data streams. They are used by Internet of Things (IoT) applications to analyze sensor data from Smart City cyber-infrastructure, and make active utility management decisions. As the ecosystem of such IoT applications that leverage shared urban sensor streams continue to grow, applications will perform duplicate pre-processing and analytics tasks. This offers the opportunity to collaboratively reuse the outputs of overlapping dataflows, thereby improving the resource efficiency. In this paper, we propose \emph{dataflow reuse algorithms} that given a submitted dataflow, identifies the intersection of reusable tasks and streams from a collection of running dataflows to form a \emph{merged dataflow}. Similar algorithms to unmerge dataflows when they are removed are also proposed. We implement these algorithms for the popular Apache Storm DSPS, and validate their performance and resource savings for 35 synthetic dataflows based on public OPMW workflows with diverse arrival and departure distributions, and on 21 real IoT dataflows from RIoTBench.

cs.DC↗