Enhanced layered fog architecture for IoT sensing and actuation as a service

The reduced service cost offered by Sensing and Actuation as a Service paradigm, particularly in Internet of Things (IoT) era, has encouraged many establishments to start without worrying about having their own infrastructure. Such a paradigm is typically managed by a centralized cloud service provider. Fog paradigm has emerged as a mini-cloud that if designed with care to assist the cloud, together will achieve better performance. This article introduces a layered fog architecture called Sensors and Actuator Layered Fog Services Delivery (SALFSD) for IoT ecosystems. The significance of SALFSD is being fault resistant; it dynamically reassigns tasks of the failed node to the nearest active node to maintain the network connection. Besides, SALFSD monitors end users pre-specified cases closer to the physical devices hired by end users to fasten generating the actuation commands. Such node may offload its monitoring responsibility to its parent node in case it is overloaded. SALFSD is evaluated using Yet Another Fog Simulator in different scenarios (numbers of users, sensors, actuators, and areas). A comparison was made for Sensing and Actuating as a Service (SAaaS) with/without layered fog, and layered fog with/without (failure reassignment, pre-specified cases in fog nodes, and offloading). The comparison was conducted in terms of computing/communication latencies and the number of missed messages for both observations and actuation commands. Results show that failure reassignment prevented losing messages and maintained network connectivity. Also, wisely selecting the monitoring fog node per end user pre-specified cases and the offloading scheme decreased actuation latency.

PACR: Position-Aware Protocol for Connectivity Restoration in Mobile Sensor Networks

Wireless Sensor Networks (WSNs) have gained global attention in recent times due to their vast applications in various fields. These networks can face the disruption of data transmission due to sensor node failures when placed in harsh, inaccessible, and adverse environments such as battlefields or monitoring in enemy territory. The specific tasks performed by the collaboration among the sensor nodes in WSNs by internode connectivity may be terminated. Besides this, due to the failure of sensor nodes, the area covered by the network may be limited, which can cause damage to the objectives for such a network, as there might be an unaware danger in the lost area. Connectivity is a big problem in mobile WSNs due to the mobility of nodes. Researchers have developed a lot of algorithms that are capable enough for connectivity problems, but they do not emphasize the loss of coverage. We try to fill these gaps by proposing the new hybrid algorithm PACR (Position-Aware protocol for Connectivity Restoration). The concept behind PACR is the same as a person who writes his will before death on a deathbed. In the same way, when the sensor energy is below the threshold, it is converted into a recovery coordinator and generates a recovery plan. This accelerates the recovery by decreasing the time needed for failure identification. For the recovery process, the neighbor’s nodes do not travel to the exact position of the failed node. Instead, they just move to the distance where they can build communication links with other nodes. This greatly prolongs the network lifetime. The simulation results show that PACR outperforms other techniques present in the literature.

Overhead of using spare nodes

With the increasing fault rate on high-end supercomputers, the topic of fault tolerance has been gathering attention. To cope with this situation, various fault-tolerance techniques are under investigation; these include user-level, algorithm-based fault-tolerance techniques and parallel execution environments that enable jobs to continue following node failure. Even with these techniques, some programs with static load balancing, such as stencil computation, may underperform after a failure recovery. Even when spare nodes are present, they are not always substituted for failed nodes in an effective way. This article considers the questions of how spare nodes should be allocated, how to substitute them for faulty nodes, and how much the communication performance is affected by such a substitution. The third question stems from the modification of the rank mapping by node substitutions, which can incur additional message collisions. In a stencil computation, rank mapping is done in a straightforward way on a Cartesian network without incurring any message collisions. However, once a substitution has occurred, the optimal node-rank mapping may be destroyed. Therefore, these questions must be answered in a way that minimizes the degradation of communication performance. In this article, several spare node allocation and failed node substitution methods will be proposed, analyzed, and compared in terms of communication performance following the substitution. The proposed substitution methods are named sliding methods. The sliding methods are analyzed by using our developed simulation program and evaluated by using the K computer, Blue Gene/Q (BG/Q), and TSUBAME 2.5. It will be shown that when failures occur, the stencil communication performance on the K and BG/Q can be slowed around 10 times depending on the number of node failures. The barrier performance on the K can be cut in half. On BG/Q, barrier performance can be slowed by a factor of 10. Further, it will also be shown that almost no such communication performance degradation can be seen on TSUBAME 2.5. This is because TSUBAME 2.5 has an Infiniband network connected with a FatTree topology, while the K computer and BG/Q have dedicated Cartesian networks. Thus, the communication performance degradation depends on network characteristics.

The Effective Healing Strategy against Localized Attacks on Interdependent Spatially Embedded Networks

Many real-world infrastructure networks, such as power grids and communication networks, always depend on each other by their functional components that share geographic proximity. A lot of works were devoted to revealing the vulnerability of interdependent spatially embedded networks (ISENs) when facing node failures and showed that the ISENs are susceptible to geographically localized attacks caused by natural disasters or terrorist attacks. How to take emergency methods to prevent large scale of cascading failures on interdependent infrastructures is a longstanding problem. Here, we propose an effective strategy for the healing of local structures using the connection profile of a failed node, called the healing strategy by prioritizing minimum degrees (HPMD), in which a new link between two active low-degree neighbors of a failed node is established during the cascading process. Afterwards, comparisons are made between HPMD and three healing strategies based on three metrics: random choice, degree centrality, and local centrality, respectively. Simulations are performed on the ISENs composed of two diluted square lattices with the same size under localized attacks. Results show that HPMD can significantly improve the robustness of the system by enhancing the connectivity of low-degree nodes, which prevent the diffusion of failures from low-degree nodes to moderate-degree nodes. In particular, HPMD can outperform other three strategies in the size of the giant component of networks, critical attack radius, and the number of iterative cascade steps for a given quota of newly added links, which means HPMD is more effective, more timely, and less costly. The high performance of HPMD indicates low-degree nodes should be placed on the top priority for effective healing to resist the cascading of failures in the ISENs, which is totally different from the traditional methods that usually take high-degree nodes as critical nodes in a single network. Furthermore, HPMD considers the distance between a pair of nodes to control the variation in the network structures, which is more applicable to spatial networks than previous methods.

TAPU: Test and pick up-based k-connectivity restoration algorithm for wireless sensor networks

A k-connected wireless sensor network remains connected if any k-1 arbitrary nodes stop working. The aim of movement-assisted k -connectivity restoration is to preserve the k -connectivity of a network by moving the nodes to the necessary positions after possible failures in nodes. This paper proposes an algorithm named TAPU for k-connectivity restoration that guarantees the optimal movement cost. Our algorithm improves the time and space complexities of the previous approach (MCCR) in both best and worst cases. In the proposed algorithm, the nodes are classified into safe and unsafe groups. Failures of safe nodes do not change the k value of the network while failures of unsafe nodes reduce the k value. After an unsafe node’s failure, the shortest path tree of the failed node is generated. Each node moves to its parent location in the tree starting from a safe node with the minimum moving cost to the root. TAPU has been implemented on simulation and testbed environments including Kobuki robots and Iris nodes. The measurements show that TAPU finds the optimum movement up to 79.5% faster with 50% lower memory usage than MCCR and with up to 59% lower cost than the greedy algorithms.

An efficient local cascade defense method in complex networks

Cascading failures in networked systems often lead to catastrophic consequence. Defending cascading failure propagation by employing local load redistribution method is an efficient way. Given initial load of every node, the key of improving network robustness against cascading failures is to maximally defend cascade propagation with minimum total extra capacity of all nodes. With finite total extra capacity of all nodes, we first discuss three general extra capacity distributions including degree-based distribution (DD), average distribution (AD) and random distribution (RD). To sufficiently use the total spare capacity (SC) of all neighboring nodes of a failed node, then we propose a novel SC-based local load redistribution mechanism to improve the cascade defense ability of network. We investigate the network robustness against cascading failures induced by a single node failure under the three extra capacity distributions in both scale-free networks and random networks. Compared with the degree-based (DB) local load redistribution method, our SC method achieves higher robustness under all of the three extra capacity distributions. The extensive simulation results can well confirm the effectiveness of the SC local load redistribution method.

Multiple Repair Localities with Distinct Erasure Tolerance

In distributed storage systems, codes with lower repair locality for each coordinate are much more desirable since they can reduce the disk I/O complexity for repairing a failed node. The ith coordinate of a linear code 𝒞 is said to have [Formula: see text] locality if there exist δi non-overlapping local repair sets of size no more than ri, where a local repair set of one coordinate is defined as the set of some other coordinates by which one can recover the value at this coordinate. In this paper, we consider linear codes with information [Formula: see text] locality, where there exists an information set I such that for each [Formula: see text], the ith coordinate has [Formula: see text] locality and [Formula: see text] and [Formula: see text]. We derive a lower bound on the codeword length n for any linear [n, k, d] code with information [Formula: see text] locality. Particularly, we indicate that some existing bounds can be deduced from our result by restrictions on parameters.

Average Bridge Consensus: Dealing With Active-Passive Sensors

In network average consensus problems, a failure, in which a node cannot provide the initial value, but can communicate with its neighbors gives rise to the bridge consensus problem. In its formulation, the failed node serves as a bridge which maintains the network communication connectivity, and its failure to provide the value does not impact the capability of the rest of the network nodes to reach a consensus. The proposed bridge consensus solution can deal with multiple failing nodes and large networks in a scalable manner. The solution properties are proven and illustrated by a numerical example.

Dynamic Update Mechanism in Wireless Sensor Networks

Many researches use diff environmental conditions or application requirements in WSN. In the default Deluge mechanism, it will recover a sensor node from an updating error by reloading the stored full image again or waiting for the host machine to retransmit the full image again. This strategy is easy to implement and intuitive, but replacing the current executing image by retransmitting a full image file again is resource-consuming. To avoid retransmitting the full image when performing recovery, at the time when diff-based updating procedures have been finished, sensor nodes using our recovery mechanisms will backup the received patch files (i.e. diff script) in flash memory. Our mechanisms would effectively utilize flash memory space to store several backup patch files. When recovery is needed, our mechanismswould incrementally recover a failed node by patching up the system with each of the backup patch files. In the design of our recovery mechanisms, the failed sensor node will first try its best to recover itself without the assistance of the host machine, in order to avoid affecting the operations of other normal nodes when performing recovery procedures. Thus, compared with the full image replacement strategy, our mechanisms can save many computing resources.

An Energy Efficient Simultaneous-Node Repositioning Algorithm for Mobile Sensor Networks

Recently, wireless sensor network (WSN) applications have seen an increase in interest. In search and rescue, battlefield reconnaissance, and some other such applications, so that a survey of the area of interest can be made collectively, a set of mobile nodes is deployed. Keeping the network nodes connected is vital for WSNs to be effective. The provision of connectivity can be made at the time of startup and can be maintained by carefully coordinating the nodes when they move. However, if a node suddenly fails, the network could be partitioned to cause communication problems. Recently, several methods that use the relocation of nodes for connectivity restoration have been proposed. However, these methods have the tendency to not consider the potential coverage loss in some locations. This paper addresses the concerns of both connectivity and coverage in an integrated way so that this gap can be filled. A novel algorithm for simultaneous-node repositioning is introduced. In this approach, each neighbour of the failed node, one by one, moves in for a certain amount of time to take the place of the failed node, after which it returns to its original location in the network. The effectiveness of this algorithm has been verified by the simulation results.