Search for: All records

IoT devices used in various applications, such as monitoring agricultural soil moisture, or urban air quality assessment, are typically battery-operated and energy-constrained. We develop a lightweight and distributed cooperative sensing scheme that provides energy-efficient sensing of an area by reducing spatio-temporal overlaps in the coverage using a multi-sensor IoT network. Our “Sensing Together” solution includes two algorithms: Distributed Task Adaptation (DTA) and Distributed Block Scheduler (DBS), which coordinate the sensing operations of the IoT network through information shared using a distributed “token passing” protocol. DTA adapts the sensing rates from their “raw” values (optimized for each IoT device independently) to minimize spatial redundancy in coverage, while ensuring that a desired coverage threshold is met at all points in the covered area. DBS then schedules task execution times across all IoT devices in a distributed manner to minimize temporal overlap. On-device evaluation shows a small token size and execution times of less than 0.6s on average while simulations show average energy savings of 5% per IoT device under various weather conditions. Moreover, when devices had more significant coverage overlaps, energy savings exceeded 30% thanks to cooperative sensing. In simulations of larger networks, energy savings range on average between 3.34% and 38.53%, depending on weather conditions. Our solutions consistently demonstrate near-optimal performance under various scenarios, showcasing their capability to efficiently reduce temporal overlap during sensing task scheduling. 

Federated Learning (FL) typically involves a large-scale, distributed system with individual user devices/servers training models locally and then aggregating their model updates on a trusted central server. Existing systems for FL often use an always-on server for model aggregation, which can be inefficient in terms of resource utilization. They also may be inelastic in their resource management. This is particularly exacerbated when aggregating model updates at scale in a highly dynamic environment with varying numbers of heterogeneous user devices/servers. We present LIFL, a lightweight and elastic serverless cloud platform with fine-grained resource management for efficient FL aggregation at scale. LIFL is enhanced by a streamlined, event-driven serverless design that eliminates the individual, heavyweight message broker and replaces inefficient container-based sidecars with lightweight eBPF-based proxies. We leverage shared memory processing to achieve high-performance communication for hierarchical aggregation, which is commonly adopted to speed up FL aggregation at scale. We further introduce the locality-aware placement in LIFL to maximize the benefits of shared memory processing. LIFL precisely scales and carefully reuses the resources for hierarchical aggregation to achieve the highest degree of parallelism, while minimizing aggregation time and resource consumption. Our preliminary experimental results show that LIFL achieves significant improvement in resource efficiency and aggregation speed for supporting FL at scale, compared to existing serverful and serverless FL systems. 

Name-based publish/subscribe systems using Information-Centric Networking (ICN) principles can provide a flexible and efficient framework for communication in disaster situations. Efficient, secure dissemination of information can play a critical role in disaster management. But, secure and authenticated group communications that maintain confidentiality and integrity remain a challenge. In this paper, we design a flexible and efficient encryption framework SAFE that leverages graph-based naming frameworks for providing role-based communication among first responders. We study the suitability of message-oriented encryption where the sender leverages the name hierarchy, and compare it with a key-oriented encryption scheme that requires the receiver to utilize appropriate keys to decrypt based on the publisher-targeted name for the message. Both encryption schemas can be built with attribute-based encryption (ABE) or public key encryption (PKE) implementations. We find message-oriented encryption provides the needed flexibility for dynamic environments when communicating with members changes frequently. With message-oriented encryption, we further address key revocation and support for infrastructure-less environments in disaster situations and consider the tradeoff between flexibility and optimization for large relatively static communication groups. We evaluate both encryption schemas built on top of ABE and PKE. We examine the key generation time, ciphertext length, encryption, and decryption time, and see that SAFE's design is the most suitable for large and dynamically changing groups. 

Efficient and secure message dissemination plays an important role during a disaster environment. Name-based publish/subscribe systems, especially role-based names, using principles of Information-Centricity provide an efficient frame-work for communications among first responders. However, a challenge is maintaining confidentiality during communication. We have developed an encryption framework that leverages graph-based naming systems which provides role-based communication among first responders. Our framework is built on top of the dynamic role-based names and can be implemented using attribute-based encryption (ABE) or public key encryption (PKE). In this demo, we show the operations of our framework in a typical scenario of first responders using the application. 

Multi-sensor IoT devices can gather different types of data by executing different sensing activities or tasks. Therefore, IoT applications are also becoming more complex in order to process multiple data types and provide a targeted response to the monitored phenomena. However, IoT devices which are usually resource-constrained still face energy challenges since using each of these sensors has an energy cost. Therefore, energy-efficient solutions are needed to extend the device lifetime while balancing the sensing data requirements of the IoT application. Cooperative monitoring is one approach for managing energy and involves reducing the duplication of sensing tasks between neighboring IoT devices. Setting up cooperative monitoring is a scheduling problem and is challenging in a distributed environment with resource-constrained IoT devices. In this work, we present our Distributed Token and Tier-based task Scheduler (DTTS) for a multi-sensor IoT network. Our algorithm divides the monitoring period (5 min epochs) into a set of non-overlapping intervals called tiers and determines the start deadlines for the task at each IoT device. Then to minimize temporal sensing overlap, DTTS distributes task executions throughout the epoch and uses tokens to share minimal information between IoT devices. Tasks with earlier start deadlines are scheduled in earlier tiers while tasks with later start deadlines are scheduled in later tiers. Evaluating our algorithm against a simple round-robin scheduler shows that the DTTS algorithm always schedules tasks before their start deadline expires. 

Multi-sensor IoT devices enable the monitoring of different phenomena using a single device. Often deployed over large areas, these devices have to depend on batteries and renewable energy sources for power. Therefore, efficient energy management solutions that maximize device lifetime and information utility are important. We present SEMA, a smart energy management solution for IoT applications that uses a Model Predictive Control (MPC) approach to optimize IoT energy use and maximize information utility by dynamically determining task values to be used by the IoT device’s sensors. Our solution uses the current device battery state, predicted available solar energy over the short-term, and task energy and utility models to meet the device energy goals while providing sufficient monitoring data to the IoT applications. To avoid the need for executing the MPC optimization at a centralized sink (from which the task values are downloaded to the SEMA devices), we propose SEMA-Approximation (SEMA-A), which uses an efficient MPC Approximation that is simple enough to be run on the IoT device itself. SEMA-A decomposes the MPC optimization problem into two levels: an energy allocation problem across the time epochs, and task-dependent sensor scheduling problem, and finds efficient algorithms for solving both problems. Experimental results show that SEMA is able to adapt the task values based on the available energy, and that SEMA-A closely approximates SEMA in sensing performance. 

Timely delivery of the right information to the right first responders can help improve the outcomes of their efforts and save lives. With social media communications (Twitter, Facebook, etc.) being increasingly used to send and get information during disasters, forwarding them to the right first responders in a timely manner can be very helpful. We use Natural Language Processing and Machine Learning, to steer the social media posts to the most appropriate first responder.An important goal is to retrieve and deliver only the critical, actionable information to first responders in real-time. We examine the overall pipeline starting from retrieving tweets from the social media platforms, to their classification, and dissemination to first responders.We propose improvements in the area of data retrieval, relevance prediction and prioritizing information sent to the first responders by fusing NLP and ML classification techniques thus improving emergency response. We demonstrate the effectiveness of our proposed approach in retrieving and extracting 37,295 actionable tweets related to the IDA hurricane that occurred in the US in Aug.–Sep, 2021. 

In many scenarios, information must be disseminated over intermittently-connected environments when the network infrastructure becomes unavailable, e.g., during disasters where first responders need to send updates about critical tasks. If such updates pertain to a shared data set, dissemination consistency is important. This can be achieved through causal ordering and consensus. Popular consensus algorithms, e.g., Paxos, are most suited for connected environments. While some work has been done on designing consensus algorithms for intermittently-connected environments, such as the One-Third Rule (OTR) algorithm, there is still need to improve their efficiency and timely completion. We propose CoNICE, a framework to ensure consistent dissemination of updates among users in intermittently-connected, infrastructure-less environments. It achieves efficiency by exploiting hierarchical namespaces for faster convergence, and lower communication overhead. CoNICE provides three levels of consistency to users, namely replication, causality and agreement. It uses epidemic propagation to provide adequate replication ratios, and optimizes and extends Vector Clocks to provide causality. To ensure agreement, CoNICE extends OTR to also support long-term network fragmentation and decision invalidation scenarios; we define local and global consensus pertaining to within and across fragments respectively. We integrate CoNICE's consistency preservation with a naming schema that follows a topic hierarchy-based dissemination framework, to improve functionality and performance. Using the Heard-Of model formalism, we prove CoNICE's consensus to be correct. Our technique extends previously established proof methods for consensus in asynchronous environments. Performing city-scale simulation, we demonstrate CoNICE's scalability in achieving consistency in convergence time, utilization of network resources, and reduced energy consumption. 

Name-based pub/sub allows for efficient and timely delivery of information to interested subscribers. A challenge is assigning the right name to each piece of content, so that it reaches the most relevant recipients. An example scenario is the dissemination of social media posts to first responders during disasters. We present FLARE, a framework using federated active learning assisted by naming. FLARE integrates machine learning and name-based pub/sub for accurate timely delivery of textual information. In this demo, we show FLARE’s operation. 

During disasters, it is critical to deliver emergency information to appropriate first responders. Name-based information delivery provides efficient, timely dissemination of relevant content to first responder teams assigned to different incident response roles. People increasingly depend on social media for communicating vital information, using free-form text. Thus, a method that delivers these social media posts to the right first responders can significantly improve outcomes. In this paper, we propose FLARE, a framework using 'Social Media Engines' (SMEs) to map social media posts (SMPs), such as tweets, to the right names. SMEs perform natural language processing-based classification and exploit several machine learning capabilities, in an online real-time manner. To reduce the manual labeling effort required for learning during the disaster, we leverage active learning, complemented by dispatchers with specific domain-knowledge performing limited labeling. We also leverage federated learning across various public-safety departments with specialized knowledge to handle notifications related to their roles in a cooperative manner. We implement three different classifiers: for incident relevance, organization, and fine-grained role prediction. Each class is associated with a specific subset of the namespace graph. The novelty of our system is the integration of the namespace with federated active learning and inference procedures to identify and deliver vital SMPs to the right first responders in a distributed multi-organization environment, in real-time. Our experiments using real-world data, including tweets generated by citizens during the wildfires in California in 2018, show our approach outperforming both a simple keyword-based classification and several existing NLP-based classification techniques.