Fuzzy rule based checkpointing arrangement for fault tolerance in Mobile Grids
01 Aug 2014-pp 289-293
TL;DR: A Fuzzy Rule based system (FRS) is used to construct an efficient checkpointing arrangement for MoGs to increase the probability of recovery of checkpointed data subsequent to a failure; thereby allowing a distributed application to complete its execution successfully on the MoG.
Abstract: Mobile Grids (MoGs) are an emerging sphere in distributed computing and are expected to become a crucial part of computational Grids in future. Apart from allowing a convenient user access to the Grid, mobile hosts can act as valuable computing resources in the Grid. However, mobile hosts have limitations of resources such as stable storage, wireless bandwidth, battery power etc. and are also subject to mobility and frequent disconnections. Therefore, a fault tolerance scheme is essential if the computing power of mobile hosts has to be used effectively in the grids. This paper presents a checkpointing based fault tolerance technique for Mobile Grid computing systems. A Fuzzy Rule based system (FRS) is used to construct an efficient checkpointing arrangement for MoGs. With FRS, superior nodes, i.e., having sufficient resources, are selected as Checkpoint Storage Nodes (CSNs) and other mobile hosts transfer their checkpointed data to one of the selected neighboring CSN. The objective of FRS is to increase the probability of recovery of checkpointed data subsequent to a failure; thereby allowing a distributed application to complete its execution successfully on the MoG. Simulations show FRS's better recovery probabilities in comparison to a random checkpointing arrangement.
Citations
More filters
01 Apr 2019
TL;DR: A checkpointing based failure handling technique is proposed which will improve arrangement reliability and failure recovery time for the MG network and is tested on a grid of ubiquitously available Android-based mobile phones.
Abstract: A mobile grid (MG) consists of interconnected mobile devices which are used for high performance computing. Fault tolerance is an important property of mobile computational grid systems for achieving superior arrangement reliability and faster recovery from failures. Since the failure of the resources affects task execution fatally, fault tolerance service is essential to achieve QoS requirement in MG. The faults which occur in MG are link failure, node failure, task failure, limited bandwidth etc. Detecting these failures can help in better utilisation of the resources and timely notification to the user in a MG environment. These failures result in loss of computational results and data. Many algorithms or techniques were proposed for failure handling in traditional grids. The authors propose a checkpointing based failure handling technique which will improve arrangement reliability and failure recovery time for the MG network. Experimentation was conducted by creating a grid of ubiquitously available Android-based mobile phones.
12 citations
Journal Article•
TL;DR: A proxy-based coordinated checkpointing scheme for the mobile to Grid middleware, Mobile Access to Grid Infrastructure (MAGi), which makes it efficient to rollback to the latest consistent global snapshot, without direct involvement of the mobile hosts, which results in less processing and storage overhead on mobile device as compared to existing schemes.
Abstract: Mobile Grid is an emerging and prospering field of distributed computing where mobile devices are enjoying the benefits of Grid. Challenges faced by mobile Grid are unpredictable network quality, lower trust, limited resources (battery power, network bandwidth, storage, processing power, etc) and extended periods of disconnections which may result in lost of the work done by these devices. We, therefore, need a proper fault tolerance scheme for these mobile hosts. A major issue is the appropriate handling of failures with minimal processing and storage overhead on mobile hosts. To meet these goals, we propose a proxy-based coordinated checkpointing scheme for our mobile to Grid middleware, Mobile Access to Grid Infrastructure (MAGi). In this scheme mobile hosts seamlessly store checkpoints on their respective proxies running on the middleware. Together with the central coordinator component, these proxies act as a centralized checkpointing store. This approach makes it efficient to rollback to the latest consistent global snapshot, without direct involvement of the mobile hosts, which results in less processing and storage overhead on mobile device as compared to existing schemes.
5 citations
TL;DR: A Fuzzy Rule based system is used to construct and select efficient static sensor nodes having adequate resources as Check Point Storage Nodes (CPSNs), thereby allowing a distributed application to complete its execution successfully.
Abstract: A WSN consists of a large number of limited computation and storage capability wireless sensor nodes, which communicate wirelessly. These sensor nodes typical communicate in short range and collaborate to accomplish the network function. To increase the range of sensing and with the advent of MEMS, mobile sensors and sinks is the technology the world is moving to. This paper presents a network of mobile sensors and a sink. A mobile sink is selected as check-point to have the recoverability of the network. A Fuzzy Rule based system (FRS) is used to construct and select efficient static sensor nodes having adequate resources as Check Point Storage Nodes (CPSNs). The objective of FRS is to increase the probability of recovery of check-pointed data subsequent to a failure, thereby allowing a distributed application to complete its execution successfully. Simulations show FRS's better recovery probabilities in comparison to a random check-pointing arrangement.
2 citations
01 Nov 2018
TL;DR: This research paper focuses on designing routing model using mobile agent paradigm and attempts to find more optimal path by considering multiple QoS parameters like stability, delay, congestion and energy of the node.
Abstract: A, Mobile ad-hoc network (MANET) is collection of mobile devices that desire to communicate in the lack of any fixed infrastructure so, in this environment every mobile nodes works as a router in itself. In this type of wireless network, any node can leave or join network at any movement. Besides it this type of networks have some other challenging characteristics as regularly changing topology, high mobility, narrow bandwidth. Conventional routing protocols focused on finding shortest path rather than Quality of Service path. Link breakage is the main reason of high mobility as well as lack of energy of wireless nodes. In the lack of resources, traffic density leads to congestion. So, the performance of routing protocol degrades in this type of networks. But it is not so easy task to take multiple QoS parameters for finding optimal route. Mobile software agent technology with unique features like mobility, autonomous, intelligent and adaptability can solve this problem. This research paper focuses on designing routing model using mobile agent paradigm. The proposed model attempts to find more optimal path by considering multiple QoS parameters like stability, delay, congestion and energy of the node. Simulation is done using Matlab simulator & the simulation output shows that our proposed model is more reliable than traditional hop by hop AODV for finding the route from source node to destination node.
2 citations
TL;DR: This paper creates a MG comprising of Wi-Fi Direct connected Android smartphones and proposes an efficient resource allocation model (ERAM) which provides resource allocation with failure handling and performs well with respect to application completion time, % battery consumption and recovery time from failure in comparison with existing techniques.
Abstract: Mobile grid (MG) is emergi ng as a new computing paradigm due to the ubiquitous availability of mobile devices. With the advancement in the capability of these devices, computationally intensive tasks can be executed using a peer-to-peer grid of such devices. MG can provide an edifice to execute parallel computationally intensive tasks. Key challenges that crop up while computing on a MG are resource constrained environment, inefficient resource allocation, high failure probability, etc. As a result, selection of appropriate nodes for task execution becomes critical for successful execution of the application. In this paper, we propose an efficient resource allocation model (ERAM) which provides resource allocation with failure handling. We created a MG comprising of Wi-Fi Direct connected Android smartphones. Different scenarios are considered for the purpose of experimentation. Our approach performs well with respect to application completion time, % battery consumption and recovery time from failure in comparison with existing techniques.
1 citations
References
More filters
TL;DR: This survey covers rollback-recovery techniques that do not require special language constructs and distinguishes between checkpoint-based and log-based protocols, which rely solely on checkpointing for system state restoration.
Abstract: This survey covers rollback-recovery techniques that do not require special language constructs. In the first part of the survey we classify rollback-recovery protocols into checkpoint-based and log-based.Checkpoint-based protocols rely solely on checkpointing for system state restoration. Checkpointing can be coordinated, uncoordinated, or communication-induced. Log-based protocols combine checkpointing with logging of nondeterministic events, encoded in tuples called determinants. Depending on how determinants are logged, log-based protocols can be pessimistic, optimistic, or causal. Throughout the survey, we highlight the research issues that are at the core of rollback-recovery and present the solutions that currently address them. We also compare the performance of different rollback-recovery protocols with respect to a series of desirable properties and discuss the issues that arise in the practical implementations of these protocols.
1,772 citations
TL;DR: A synchronous snapshot collection algorithm for mobile systems that neither forces every node to take a local snapshot, nor blocks the underlying computation during snapshot collection, and a minimal rollback/recovery algorithm in which the computation at a node is rolled back only if it depends on operations that have been undone due to the failure of node(s).
Abstract: A mobile computing system consists of mobile and stationary nodes, connected to each other by a communication network. The presence of mobile nodes in the system places constraints on the permissible energy consumption and available communication bandwidth. To minimize the lost computation during recovery from node failures, periodic collection of a consistent snapshot of the system (checkpoint) is required. Locating mobile nodes contributes to the checkpointing and recovery costs. Synchronous snapshot collection algorithms, designed for static networks, either force every node in the system to take a new local snapshot, or block the underlying computation during snapshot collection. Hence, they are not suitable for mobile computing systems. If nodes take their local checkpoints independently in an uncoordinated manner, each node may have to store multiple local checkpoints in stable storage. This is not suitable for mobile nodes as they have small memory. This paper presents a synchronous snapshot collection algorithm for mobile systems that neither forces every node to take a local snapshot, nor blocks the underlying computation during snapshot collection. If a node initiates snapshot collection, local snapshots of only those nodes that have directly or transitively affected the initiator since their last snapshots need to be taken. We prove that the global snapshot collection terminates within a finite time of its invocation and the collected global snapshot is consistent. We also propose a minimal rollback/recovery algorithm in which the computation at a node is rolled back only if it depends on operations that have been undone due to the failure of node(s). Both the algorithms have low communication and storage overheads and meet the low energy consumption and low bandwidth constraints of mobile computing systems.
213 citations
TL;DR: The concept of "mutable checkpoint," which is neither a tentative checkpoint nor a permanent checkpoint, is introduced to design efficient checkpointing algorithms for mobile computing systems and it is proved that there does not exist a nonblocking algorithm which forces only a minimum number of processes to take their checkpoints.
Abstract: Mobile computing raises many new issues such as lack of stable storage, low bandwidth of wireless channel, high mobility, and limited battery life. These new issues make traditional checkpointing algorithms unsuitable. Coordinated checkpointing is an attractive approach for transparently adding fault tolerance to distributed applications since it avoids domino effects and minimizes the stable storage requirement. However, it suffers from high overhead associated with the checkpointing process in mobile computing systems. Two approaches have been used to reduce the overhead: First is to minimize the number of synchronization messages and the number of checkpoints; the other is to make the checkpointing process nonblocking. These two approaches were orthogonal previously until the Prakash-Singhal algorithm combined them. However, we found that this algorithm may result in an inconsistency in some situations and we proved that there does not exist a nonblocking algorithm which forces only a minimum number of processes to take their checkpoints. In this paper; we introduce the concept of "mutable checkpoint," which is neither a tentative checkpoint nor a permanent checkpoint, to design efficient checkpointing algorithms for mobile computing systems. Mutable checkpoints can be saved anywhere, e.g., the main memory or local disk of MHs. In this way, taking a mutable checkpoint avoids the overhead of transferring large amounts of data to the stable storage at MSSs over the wireless network. We present techniques to minimize the number of mutable checkpoints. Simulation results show that the overhead of taking mutable checkpoints is negligible. Based on mutable checkpoints, our nonblocking algorithm avoids the avalanche effect and forces only a minimum number of processes to take their checkpoints on the stable storage.
152 citations
TL;DR: This paper presents a survey of the current state of wireless grid computing, including a discussion of the cooperation between wired and wireless grids including ways in which wireless grids extend the capabilities of existing wired grids.
Abstract: Wireless Grid computing extends the traditional Grid computing paradigm to include a diverse collection of mobile devices enabled to communicate using radio frequency, infrared, optical and other wireless mechanisms. Among the devices coming into use in wireless grid implementations are tiny sensors, Radio Frequency Identification tags (RFID). Personal Digital Assistants (PDAs) and paging devices, cellular phones, hand-held or wearable computers, laptop computers and special purpose computers embedded into many modern appliances [8, 26, 29]. Though many of these devices were initially developed to serve a specific, autonomous purpose, their potential for cooperation through the sharing of resources and capabilities, and the massive amounts of resources available due to their numbers, is quickly leading to applications resembling traditional Grid computing.
This paper presents a survey of the current state of wireless grid computing. This includes a discussion of the cooperation between wired and wireless grids including ways in which wireless grids extend the capabilities of existing wired grids. It also discusses many of the new capabilities and resources available to wireless grid devices and a sampling of several applications of these new resources. It provides a sampling of many current research endeavors in the wireless grid arena and an examination of a number of the potential challenges resulting from the unique characteristics of wireless grid devices.
76 citations
"Fuzzy rule based checkpointing arra..." refers background in this paper
...As a consequence, a new computing paradigm, the Mobile Grid (MoG), has emerged where mobile devices are being integrated into the grid as service recipients and as service providers as well [1-5]....
[...]
...Grid computing systems utilize network connected computers to construct large-scale, distributed systems for handling complex commercial and scientific problems [1, 2]....
[...]
01 May 1999
TL;DR: This paper introduces the concept of "mutable checkpoint," which is neither a tentative checkpoint nor a permanent checkpoint, to design efficient checkpointing algorithms for mobile computing systems and presents techniques to minimize the number of mutable checkpoints.
Abstract: Mobile computing raises many new issues such as lack of stable storage, low bandwidth of wireless channel, high mobility, and limited battery life. These new issues make traditional checkpointing algorithms unsuitable. Coordinated checkpointing is an attractive approach for transparently adding fault tolerance to distributed applications since it avoids domino effects and minimizes the stable storage requirement. However, it suffers from high overhead associated with the checkpointing process in mobile computing systems. Two approaches have been used to reduce the overhead: First is to minimize the number of synchronization messages and the number of checkpoints; the other is to make the checkpointing process nonblocking. These two approaches were orthogonal previously until the Prakash-Singhal algorithm (28) combined them. However, we (8) found that this algorithm may result in an inconsistency in some situations and we proved that there does not exist a nonblocking algorithm which forces only a minimum number of processes to take their checkpoints. In this paper, we introduce the concept of "mutable checkpoint," which is neither a tentative checkpoint nor a permanent checkpoint, to design efficient checkpointing algorithms for mobile computing systems. Mutable checkpoints can be saved anywhere, e.g., the main memory or local disk of MHs. In this way, taking a mutable checkpoint avoids the overhead of transferring large amounts of data to the stable storage at MSSs over the wireless network. We present techniques to minimize the number of mutable checkpoints. Simulation results show that the overhead of taking mutable checkpoints is negligible. Based on mutable checkpoints, our nonblocking algorithm avoids the avalanche effect and forces only a minimum number of processes to take their checkpoints on the stable storage.
68 citations