Time synchronization of devices in Internet-of-Things (IoT) networks is one of the challenging problems and a pre-requisite for the design of low-latency applications. Although many existing solutions have tried to address this problem, almost all solutions assume all the devices (nodes) in the network are faultless. Furthermore, these solutions exchange a large number of messages to achieve synchronization, leading to significant communication and energy overhead. To address these short-comings, we propose C-sync, a clustering-based decentralized time synchronization protocol that provides resilience against several types of faults with energy-efficient communication. C-sync achieves scalability by introducing multiple reference nodes in the network that restrict the maximum number of hops any node can have to its time source. The protocol is designed with a modular structure on the Contiki platform to allow application transitions. We evaluate C-sync on a real testbed that comprises over 40 Tmote Sky hardware nodes distributed across different levels in a building and show through experiments the fault resilience, energy efficiency, and scalability of the protocol. C-sync detects and isolates faults to a cluster and recovers quickly. The evaluation makes a qualitative comparison with state-of-the-art protocols and a quantitative comparison with a class of decentralized protocols (derived from GTSP) that provide synchronization with no/limited fault-tolerance. Results also show a reduction of 56.12% and 75.75% in power consumption in the worst-case and best-case scenarios, respectively, compared to GTSP, while achieving similar accuracy.

With rapid advancements in the Internet of Things (IoT) paradigm, electrical devices in the near future is expected to have IoT capabilities. This enables fine-grained tracking of individual energy consumption data of such devices, offering location-independent per-device billing. Thus, it is more fine-grained than the location-based metering of state-of-the-art infrastructure, which traditionally aggregates on a building or household level, defining the entity to be billed. However, such in-device energy metering is susceptible to manipulation and fraud. As a remedy, we propose a decentralized metering architecture that enables devices with IoT capabilities to measure their own energy consumption. In this architecture, the device-level consumption is additionally reported to a system-level aggregator that verifies distributed information and provides secure data storage using Blockchain, preventing data manipulation by untrusted entities. Using evaluations on an experimental testbed, we show that the proposed architecture supports device mobility and enables location-independent monitoring of energy consumption.

Maintaining peer-to-peer connectivity with low energy overhead is a key requirement for several emerging Internet of Things (IoT) applications. It is also desirable to develop such connectivity solutions for non-static network topologies, so that resilience to device failures can be fully realized. De-centralized clustering has emerged as a promising technique to address this critical challenge. Clustering of nodes around cluster heads (CHs) provides an energy-efficient two-tier framework for peer-to-peer communication. At the same time, decentralization ensures that the framework can quickly adapt to a dynamically changing network topology. Although some decentralized clustering solutions have been proposed in the literature, they either lack guarantees on connectivity or incur significant energy overhead to maintain the clusters. In this paper, we present Decentralized Connected Resilient IoT Clustering (DeCoRIC), an energy-efficient clustering scheme that is self-organizing and resilient to network changes while guaranteeing connectivity. Using experiments implemented on the Contiki simulator, we show that our clustering scheme adapts itself to node faults in a time-bound manner. Our experiments show that DeCoRIC achieves 100% connectivity among all nodes while improving the power efficiency of nodes in the system compared to the state-of-the-art techniques BEEM and LEACH by up to 110% and 70%, respectively. The improved power efficiency also translates to longer lifetime before first node death with a best-case of 109% longer than BEEM and 42% longer than LEACH.

Time synchronization is paramount for communication in Internet of Things (IoT) networks. Existing synchronization protocols in the IoT are designed to be accurate, energy-efficient and scalable with absolute trust on the time source(s). If a byzantine node becomes a time source, it can cause synchronization errors with false time, leading to system mal-functions or network crashes. In this paper, we introduce C-Sync: a clustering time synchronization protocol for decentralized IoT networks that incorporates resilience against byzantine nodes. We show that C-sync achieves a worst-case synchronization accuracy of a few tens of microseconds (µs).

Different scheduling algorithms for mixed criticality systems have been recently proposed. The common denominator of these algorithms is to discard low critical tasks whenever high critical tasks are in lack of computation resources. This is achieved upon a switch of the scheduling mode from Normal to Critical. We distinguish two main categories of the algorithms: system-level mode switch and task-level mode switch. System-level mode algorithms allow low criticality (LC) tasks to execute only in normal mode. Task-level mode switch algorithms enable to switch the mode of an individual high criticality task (HC), from low (LO) to high (HI), to obtain priority over all LC tasks. This paper investigates an online scheduling algorithm for mixed-criticality systems that supports dynamic mode switches for both task level and system level. When a HC task job overruns its LC budget, then only that particular job is switched to HI mode. If the job cannot be accommodated, then the system switches to Critical mode. To accommodate for resource availability of the HC jobs, the LC tasks are degraded by stretching their periods until the Critical mode exhibiting job complete its execution. The stretching will be carried out until the resource availability is met. We have mechanized and implemented the proposed algorithm using Uppaal. To study the efficiency of our scheduling algorithm, we examine a case study and compare our results to the state of the art algorithms.

Mixed-criticality (MC) systems are composed of tasks with varying criticality co-hosted on a single shared platform. In conventional MC systems, upon criticality change, the lower criticality tasks are penalized to guarantee resources for the higher criticality ones. However, in practice, penalizing lower criticality tasks have adverse effects and hence, the system is often under-utilized. In this paper, we consider the problem of reservation-based scheduling of mixed-criticality systems on a homogeneous multiprocessor platform to guarantee full service to the lower criticality tasks when one of the processors switches to the critical state. We explore the semi-partitioned scheduling model for dual-criticality systems in which the low criticality tasks executing on a processor are migrated to another processor upon mode switch to improve the service offered to them in the high criticality mode. We present the scheduling strategy of the proposed algorithm and derive its utilization bound. To evaluate the proposed algorithm, we use randomly generated task sets to compare the schedulability performance of the algorithm with the existing algorithms. Our results show that the proposed algorithm improves both schedulability and low criticality support when compared to existing algorithms for implicit-deadline task systems.

Owing to growing complexity and scale, safety-critical real-time systems are generally designed using the concept of mixed-criticality, wherein applications with different criticality or importance levels are hosted on the same hardware platform. To guarantee non-interference between these applications, the hardware resources, in particular the processor, are statically partitioned among them. To overcome the inefficiencies in resource utilization of such a static scheme, the concept of mixed-criticality real-time scheduling has emerged as a promising solution. Although there are several studies on such scheduling strategies for uniprocessor platforms, the problem of efficient scheduling for the multiprocessor case has largely remained open. In this work, we design a fluid-model based mixed-criticality scheduling algorithm for multiprocessors, in which multiple tasks are allowed to execute on the same processor simultaneously. We derive an exact schedulability test for this algorithm, and also present an optimal strategy for assigning the fractional execution rates to tasks. Since fluid-model based scheduling is not implementable on real hardware, we also present a transformation algorithm from fluid-schedule to a non-fluid one. We also show through experimental evaluation that the designed algorithms outperform existing scheduling algorithms in terms of their ability to schedule a variety of task systems.

Mixed-Criticality (MC) systems consolidate multiple functionalities with different criticalities onto a single hardware platform. Such systems improve the overall resource utilization while guaranteeing resources to critical tasks. In this paper, we focus on the problem of partitioned multiprocessor MC scheduling, in particular the problem of designing efficient partitioning strategies. We develop two new partitioning strategies based on the principle of evenly distributing the difference between total high-critical utilization and total low-critical utilization for the critical tasks among all processors. By balancing this difference, we are able to reduce the pessimism in uniprocessor MC schedulability tests that are applied on each processor, thus improving overall schedulability. To evaluate the schedulability performance of the proposed strategies, we compare them against existing partitioned algorithms using extensive experiments. We show that the proposed strategies are effective with both dynamic-priority Earliest Deadline First with Virtual Deadlines (EDF-VD) and fixed-priority Adaptive Mixed-Criticality (AMC) algorithms. Specifically, our results show that the proposed strategies improve schedulability by as much as 28.1% and 36.2% for implicit and constrained-deadline task systems respectively.