Search for: All records

The limited and highly variable resource dynamics of underserved communities, each with their own unique needs and values, underscore the need to integrate a context-aware approach when designing for these settings. Context-aware computing has long been a fundamental aspect of ubiquitous and pervasive systems, yet its application in Information and Communication Technologies for Development (ICT4D) remains limited. Existing context-aware approaches are predominantly designed for resource-rich environments and privileged communities, often failing to account for the unique constraints and dynamics of underserved populations. In this paper, we advocate for a paradigm shift in ICT system and service design to serve not only the privileged but also the underserved. Through the lens of two real-world case studies, we illustrate the contextual challenges faced by underserved communities and validate the design goals of our proposed framework by grounding them in real-world constraints, needs, and potential outcomes. Drawing upon existing literature and insights from the case studies, we first redefine context in ICT4D as a dynamic interplay of situated location, community needs, and limited resources, emphasizing a community-centered perspective. Building upon this definition, we conceptualize a more community-context-aware ICT4D design and propose enabling technologies for integrating community-in-the-loop methodologies, efficient resource allocation mechanisms, and context-aware service resiliency and adaptability strategies to enhance ICT services in resource-limited settings. By introducing a more context-aware approach to ICT4D, this paper aims to foster inclusivity, mitigate information inequity, and contribute to bridging the digital divide. Our work lays the foundation for future research on inclusive, resource-efficient, and community-driven context-aware ICT solutions. 

Geo-distributed Edge sites are expected to cater to the stringent demands of situation-aware applications like collaborative autonomous vehicles and drone swarms. While clients of such applications benefit from having network-proximal compute resources, an Edge site has limited resources compared to the traditional Cloud. Moreover, the load experienced by an Edge site depends on a client's mobility pattern, which may often be unpredictable. The Function-as-a-Service (FaaS) paradigm is poised aptly to handle the ephemeral nature of workload demand at Edge sites. In FaaS, applications are decomposed into containerized functions enabling fine-grained resource management. However, spatio-temporal variations in client mobility can still lead to rapid saturation of resources beyond the capacity of an Edge site.To address this challenge, we develop FEO (Federated Edge Orchestrator), a resource allocation scheme across the geodistributed Edge infrastructure for FaaS. FEO employs a novel federated policy to offload function invocations to peer sites with spare resource capacity without the need to frequently share knowledge about available capacities among participating sites. Detailed experiments show that FEO's approach can reduce a site's P99 latency by almost 3x, while maintaining application service level objectives at all other sites. 

Real-time video analytics typically require video frames to be processed by a query to identify objects or activities of interest while adhering to an end-to-end frame processing latency constraint. This imposes a continuous and heavy load on backend compute and network infrastructure. Video data has inherent redundancy and does not always contain an object of interest for a given query. We leverage this property of video streams to propose a lightweight Load Shedder that can be deployed on edge servers or on inexpensive edge devices co-located with cameras. The proposed Load Shedder uses pixel-level color-based features to calculate a utility score for each ingress video frame and a minimum utility threshold to select interesting frames to send for query processing. Dropping unnecessary frames enables the video analytics query in the backend to meet the end-to-end latency constraint with fewer compute and network resources. To guarantee a bounded end-to-end latency at runtime, we introduce a control loop that monitors the backend load and dynamically adjusts the utility threshold. Performance evaluations show that the proposed Load Shedder selects a large portion of frames containing each object of interest while meeting the end-to-end frame processing latency constraint. Furthermore, it does not impose a significant latency overhead when running on edge devices with modest compute resources. 

The accuracy of radar tracks depends strongly on the variances of the measurements, and those variances are inversely proportional to the signal-to-noise (SNR) produced the hardware and signal processor. The signal processor uses matched filter processing, and the efficiency of that depends on knowledge of the kinematics of the target. In particular, the matched filter performance depends heavily on range rate and range acceleration. Traditionally, the predicted state of the target from the track filter is used for matched filter processing, but the predicted kinematic state can have rather large errors, and those errors result in match filter loss. This loss can be very large for maneuvering (i.e., accelerating) targets. In this paper, an expected-maximization (EM) approach is taken to jointly address signal processing and tracking. The signal processor maximizes the SNR using the predicted state and produces measurements. The state estimator ( e.g., Kalman filter) uses those measurements to produce expected values of the kinematic state (i.e. the nuisance parameters). The signal processor then maximizes the SNR using the new state estimates. This process continues until the maximum likelihood values of the measurements are achieved. In this paper, the Interacting Multiple Model (IMM) estimator is introduced for the tracking function better address sudden maneuvers. The EM-Based approach to join signal processing and tracking are presented along with a discussion of the real-time computing. Monte Carlo simulation results are given to illustrate a 6 dB improvement in SNR and enhanced tracks for a maneuvering target. 

Overcoming the inherent challenges.