Search for: All records

The growing disparity between food supply and demand requires innovative Digital Agriculture (DA) systems to increase farm sustainability and profitability. However, current systems suffer from problems of complexity stemming from the challenge of integrating diverse, often non-interoperable hardware and software components. In order to tackle these complexities to increase farm efficiency and understand the tradeoffs of these new DA innovations we developed Realtime Optimization and Management System (ROAM), which is a decision-support system developed to find a Pareto optimal architectural design to build DA systems. To find the Pareto optimal solution, we employed the Rhodium Multi-Objective Evolutionary Algorithm (MOEA), which systematically evaluates the trade-offs in DA system designs. Based on data from five live deployments at Cornell University, each DA design can be analyzed based on user defined objectives and evaluated under uncertain farming environments with ROAM. Paired with this, we develop a web interface that allows users to define personalized decision spaces and visualize decision tradeoffs. To help validate ROAM, it was deployed to a commercial farm where the user was recommended a DA architecture design method to increase farm efficiency. ROAM allows users to quickly make key decisions in designing their DA systems to increase farm profitability. 

Circuit-switched technologies have long been proposed for handling high-throughput traffic in datacenter networks, but recent developments in nanosecond-scale reconfiguration have created the enticing possibility of handling low-latency traffic as well. The novel Oblivious Reconfigurable Network (ORN) design paradigm promises to deliver on this possibility. Prior work in ORN designs achieved latencies that scale linearly with system size, making them unsuitable for large-scale deployments. Recent theoretical work showed that ORNs can achieve far better latency scaling, proposing theoretical ORN designs that are Pareto optimal in latency and throughput. In this work, we bridge multiple gaps between theory and practice to develop Shale, the first ORN capable of providing low-latency networking at datacenter scale while still guaranteeing high throughput. By interleaving multiple Pareto optimal schedules in parallel, both latency- and throughput-sensitive flows can achieve optimal performance. To achieve the theoretical low latencies in practice, we design a new congestion control mechanism which is best suited to the characteristics of Shale. In datacenter-scale packet simulations, our design compares favorably with both an in-network congestion mitigation strategy, modern receiver-driven protocols such as NDP, and an idealized analog for sender-driven protocols. We implement an FPGA-based prototype of Shale, achieving orders of magnitude better resource scaling than existing ORN proposals. Finally, we extend our congestion control solution to handle node and link failures. 

In a landmark 1981 paper, Valiant and Brebner gave birth to the study of oblivious routing and, simultaneously, introduced its most powerful and ubiquitous method: Valiant load balancing (VLB). By routing messages through a randomly sampled intermediate node, VLB lengthens routing paths by a factor of two but gains the crucial property of obliviousness: it balances load in a completely decentralized manner, with no global knowledge of the communication pattern. Forty years later, with datacenters handling workloads whose communication pattern varies too rapidly to allow centralized coordination, oblivious routing is as relevant as ever, and VLB continues to take center stage as a widely used — and in some settings, provably optimal — way to balance load in the network obliviously to the traffic demands. However, the ability of the network to rapidly reconfigure its interconnection topology gives rise to new possibilities. In this work we revisit the question of whether VLB remains optimal in the novel setting of reconfigurable networks. Prior work showed that VLB achieves the optimal tradeoff between latency and guaranteed throughput. In this work we show that a strictly superior latency-throughput tradeoff is achievable when the throughput bound is relaxed to hold with high probability. The same improved tradeoff is also achievable with guaranteed throughput under time-stationary demands, provided the latency bound is relaxed to hold with high probability and that the network is allowed to be semi-oblivious, using an oblivious (randomized) connection schedule but demand-aware routing. We prove that the latter result is not achievable by any fully-oblivious reconfigurable network design, marking a rare case in which semi-oblivious routing has a provable asymptotic advantage over oblivious routing. Our results are enabled by a novel oblivious routing scheme that improves VLB by stretching routing paths the minimum possible amount — an additive stretch of 1 rather than a multiplicative stretch of 2 — yet still manages to balance load with high probability when either the traffic demand matrix or the network’s interconnection schedule are shuffled by a uniformly random permutation. To analyze our routing scheme we prove an exponential tail bound which may be of independent interest, concerning the distribution of values of a bilinear form on an orbit of a permutation group action. 

This paper explores how conceptions of societal impact are produced and performed during academic computer science research, by leveraging critical technical practice while building a digital agriculture networking platform. Our findings reveal how everyday practices of envisioning and building infrastructure require working across disciplinary and institutional seams, leading us as computer scientists to continuously reconceptualize the intended societal impact. By self-reflectively analyzing how we accrue resources for projects, produce research systems, write about them, and maintain alignments with stakeholders, we demonstrate that this seam work produces shifting simulacra of societal impact around which the system’s success is narrated. HCI researchers frequently suggest that technical systems’ impact could be improved by motivating computer scientists to consider impact in system-building. Our findings show that institutional and disciplinary structures significantly shape how computer scientists can enact societal impact in their work. This work suggests opportunities for structural interventions to shape the impact of computing systems. 

Edge computing is a distributed computing paradigm that moves data-intensive applications and services (e.g., AI) closer to the data source. The rapid growth of edge endpoints connected to the Internet today poses several challenges in scalable application life cycle management. That is, managing data and workloads on several thousand, up to millions of edge endpoints, challenged by limited connectivity, resource constraints, network and edge endpoint failures. In this work, we present EdgeRDV, a new edge abstraction that builds on the idea of rendezvous nodes to manage edge workloads at scale. The EdgeRDV architecture is comprised of a central cloud management endpoint (or cloud hub), a central gateway for each edge site (or edge hub), redundant gateways (or rendezvous nodes), and edge endpoints. Beyond its scalable architecture, EdgeRDV presents new techniques and algorithms that address single points of failures and provide adjustable levels of resilience and cost-effectiveness in edge network deployments. We conducted preliminary experiments to evaluate EdgeRDV, through simulations, and our results show that EdgeRDV requires one to three orders of magnitude fewer intermediate nodes compared to relay structures, can gracefully adapt to failures, and requires a constant number of messages during failure recovery in edge sites with up to 667K+ edge endpoints. 

This work is an experience with a deployed networked system for digital agriculture (or DA). Digital agriculture is the use of data-driven techniques towards a sustainable increase in farm productivity and efficiency. DA systems are expected to be overlaid on existing rural infrastructures, which are known to be less robust. While existing DA approaches partially address several infrastructure issues, challenges related to data aggregation, data analytics, and fault tolerance remain open. In this work, we present the design of Comosum, an extensible, reconfigurable, and fault-tolerant architecture of hardware, software, and distributed cloud abstractions to sense, analyze, and actuate on different farm types. FarmBIOS is an implementation of the Comosum architecture. We analyze FarmBIOS by leveraging various applications, deployment experiences, and network differences between urban and rural farms. This includes, for instance, an edge analytics application achieving 86% accuracy in vineyard disease detection. An eighteen-month deployment of FarmBIOS highlights Comosum’s fault tolerance. It was fault tolerant to intermittent network outages that lasted for several days during many periods of the deployment. We introduce active digital twins to cope with the unreliability of the underlying base systems. 

The growing disparity between food supply and demand requires innovative Digital Agriculture (DA) systems to increase farm sustainability and profitability. However, current systems suffer from problems of complexity. To increase farm efficiency and understand the tradeoffs of these new DA innovations we developed ROAM, which is a decision support system developed to find a Pareto optimal architectural design to build DA systems. Based on data from five live deployments at Cornell University, each DA design can be analyzed based on user defined metrics and evaluated under uncertain farming environments with ROAM. Paired with this, we develop a web interface that allows users to define personalized decision spaces and to visualize decision tradeoffs. To help validate ROAM, it was deployed to a commercial farm where the user was recommended a method to increase farm efficiency. ROAM allows users to quickly make key decisions in designing their DA systems to increase farm profitability. 

Rural infrastructure is known to be more prone to breakdown than urban infrastructure. This paper explores how the fragility of rural infrastructure is reproduced through the process of engineering design. Building on values in design, we examine how eventual use is anticipated by engineering researchers building on emerging infrastructure for digital agriculture (DA). Our approach combines critically reflective technical systems-building with interviews with other practitioners to understand and address moments early in the design process where the eventual effects of DA systems may be being built-in. Our findings contrast researchers’ visions of seamless farming technologies with the seamful realities of their work to produce them. We trace how, when anticipating future use, the seams that researchers themselves experience disappear, other seams are hidden from view by institutional support, and seams end users may face are too distant to be in sight. We develop suggestions for the design of these technologies grounded in a more artful management of seamfulness and seamlessness during the process of design and development. 

Oblivious routing has a long history in both the theory and practice of networking. In this work we initiate the formal study of oblivious routing in the context of reconfigurable networks, a new architecture that has recently come to the fore in datacenter networking. These networks allow a rapidly changing bounded-degree pattern of interconnections between nodes, but the network topology and the selection of routing paths must both be oblivious to the traffic demand matrix. Our focus is on the trade-off between maximizing throughput and minimizing latency in these networks. For every constant throughput rate, we characterize (up to a constant factor) the minimum latency achievable by an oblivious reconfigurable network design that satisfies the given throughput guarantee. The trade-off between these two objectives turns out to be surprisingly subtle: the curve depicting it has an unexpected scalloped shape reflecting the fact that load-balancing becomes more difficult when the average length of routing paths is not an integer because equalizing all the path lengths is not possible. The proof of our lower bound uses LP duality to verify that Valiant load balancing is the most efficient oblivious routing scheme when used in combination with an optimally-designed reconfigurable network topology. The proof of our upper bound uses an algebraic construction in which the network nodes are identified with vectors over a finite field, the network topology is described by either the elementary basis or a sequence of Vandermonde matrices, and routing paths are constructed by selecting columns of these matrices to yield the appropriate mixture of path lengths within the shortest possible time interval.