2. Thesis and Dissertations

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/1/10

Browse

Filters

2014 - 20203

Settings

Has files: YesSubject: search.filters.subject.Load Balancing

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Efficient Mining of Frequent Colossal Itemsets from High Dimensional Data
    (National Institute of Technology Karnataka, Surathkal, 2020) Vanahalli, Manjunath K.; Patil, Nagamma.
    The basic and major step of Association Rule Mining (ARM) is itemset mining. ARM and itemset mining have a great and vast range of applications. The conventional featured enumeration based itemset mining algorithms focus on mining frequent itemsets, frequent closed itemsets, and frequent maximal itemsets from transactional datasets. The transactional datasets consist of a smaller number of attributes (features) and a large number of rows (samples). The abundant data across a variety of domains, including bioinformatics has led to the formation of a new form of dataset known as high dimensional dataset, whose data characteristics are different from that of transactional datasets. The high dimensional datasets consist of a large number of features and a smaller number of rows. The amount of information that can be extracted from high dimensional datasets is potentially huge, but extraction of information from these datasets is a non-trivial task. The result of Frequent Itemset Mining (FIM) and Frequent Closed Itemset Mining (FCIM) algorithms include small and mid-sized itemsets, which do not enclose valuable and complete information for decision making. In applications dealing with high dimensional datasets such as bioinformatics, ARM gives greater importance to the large-sized itemsets known as colossal itemsets. The recent research focused on mining frequent colossal itemsets and frequent colossal closed itemsets, which are more influential in decision making and are significant for many applications, especially in the field of bioinformatics. The preprocessing technique of existing frequent colossal itemset mining and frequent colossal closed itemset mining algorithms fail to prune the complete set of insignificant features and rows. An Effective Improved Preprocessing (EIP) technique has been proposed to prune the complete set of insignificant features and rows, which confines an increase in the mining search space. The existing frequent colossal itemset mining algorithm mine limited set of frequent colossal itemsets leading to the generation of an incomplete set of association rules, which consequently affects the decision making. Frequent colossal itemset mining algorithm has been proposed to achieve better accuracy than existing algorithms in terms of mining number of frequent colossal itemsets from the high dimensional dataset. The existing algorithms for mining Frequent Colossal Closed Itemsets (FCCI) from the high dimensional dataset do not enclose an efficient pruning strategy and closeness checking method. To overcome the drawbacks of the existing works, an algorithm enclosed with efficient Rowset Cardinality Table (RCT) based closeness checking methodand pruning strategy has been proposed to efficiently mine FCCI from high dimensional dataset. The existing algorithms are inefficient in mining FCCI from the datasets consisting of a large number of features and rows, as they are inefficient in handling the changing characteristics of data subset during the mining process. The combination of different enumeration methods is required to efficiently handle different characteristics possessed by different datasets. A dynamic switching algorithm has been proposed to efficiently mine FCCI form the dataset consisting of a large number of features and rows. The dynamic switching algorithm efficiently handles the changing characteristics of the data subset during the mining process. The dynamic switching algorithm is enclosed with Itemset Support Table (IST) based closeness checking method and pruning strategy. The existing algorithms for mining FCCI from high dimensional datasets are sequential and computationally expensive. Distributed and parallel computing is a good strategy to overcome the inefficiency of the existing sequential algorithms. The inefficiency of the existing sequential algorithms has been overcome by proposing the parallel row enumerated algorithm to efficiently mine FCCI from the high dimensional dataset. Traversing the row enumerated tree is the best solution for mining FCCI from the high dimensional dataset. The intrinsic nature of the row enumerated tree is typically unbalanced, as the number of nodes in each row enumerated tree branch vary. The distributed and parallel algorithm with load balancing has been designed to address the inefficiency of existing works.
  • Thumbnail Image
    Item
    Bio-Inspired Quality of Service Aware Routing in Mobile Ad Hoc Networks
    (National Institute of Technology Karnataka, Surathkal, 2014) M, Kiran.; Reddy, G. Ram Mohana
    In recent years a lot of work has been done in an effort to incorporate Swarm Intelligence (SI) techniques in building an adaptive routing protocols for Mobile Ad Hoc Networks (MANETs). As centralized approach for routing in MANETs lack in scalability and fault-tolerance, SI techniques provide natural solutions through distributed approach to the adaptive routing for MANETs. The mobile nodes found in MANETs are capable of monitoring the network status as well as data processing. Thus the MANETs can be made Context Aware with the help of mobile nodes local monitoring capability. In this thesis work, a novel mobility aware bio inspired routing protocol for MANETs referred to as Mobility Aware Termite (MA-Termite) is proposed by inheriting the hill building nature of social inset Termite MA-Termite will find the reliable path between the source and destination node based on the stable nodes in terms of its mobility with the help of the local monitoring capability of nodes. Further, analytical model is also proposed for studying an asymptotic pheromone behavior of MA-Termite using two different parameters (decay rate and pheromone sensitivity) over both single and double links. The results depict how individual parameters are correlated and how they affect the global performance of MANETs. The best possible parameter values are determined for optimal performance for MA-Termite. Recently, several telecommunication applications of bio-inspired algorithms achieved remarkable success. In SI techniques, the captivating features of insects or mammals are correlated with the real world problems to find solutions. The natural question is whether it is possible to develop a new hybrid algorithm by combining the distinguishing features of these insects or mammals? In this regard, the salient features of mammals such as bats are combined with the proposed MA-Termite algorithm to come up with a new hybrid routing algorithm referred to as Bat-Termite for MANETs. Bat-Termite improved the backup route maintenance and also exhibited superior routing features such as quick route discovery, high robustness with efficient management of multiple routes and rapid route repair. One of the features of both MA-Termite and Bat-Termite algorithms is they always exclusively choose the highest pheromone link thus congests the highest pheromone link over a period of time. This undesirable behavior is referred to as stagnation. Further, MA-Termite lags in load balancing and fails to take the full benefit of multipath environment. One of the methods to avoid the stagnation problem is pheromone heuristic control. Thus, a novel heuristic hybrid Load Balanced Quality of Service (QoS) aware routing protocol referred to as Load BalancedBat-Termite (LB-Bat-Termite) is proposed for MANETs in order to solve the stagnation problem of both MA-Termite and hybrid Bat-Termite algorithms. The LB-Bat-Termite algorithm with its context awareness, QoS awareness and load balancing features exhibited considerable performance gain due to load balancing. LB-Bat-Termite produces additional control packets in order to maintain all possible paths to the destination node and thus mobile nodes spends most of its time in route maintenance than data transfer; hence causes performance degradation under high node density conditions. In prder to improve the scalability and to reduce the control packet overhead, a novel heuristic Load Balanced Termite based QoS aware routing protocol is referred to as Load Balanced-Termite (LB-Termite) is proposed for MANETs. LB-Termite exhibited considerable performance gain under both scalability and mobility factors. The proposed bio-inspired QoS aware routing algorithms in this thesis work could be used for applications such as university or campus settings, data sharing during lecturing or meeting or data sharing during virtual classrooms. The proposed algorithms for MANETs in this thesis namely MA-Termite, Bat-Termite, LB-Bat-Termite and LB-Termite are compared with the state-of-the-art bio-inspired (Simple Ant Routing Algorithm and Termite Algorithm) and non bio- inspired routing algorithms (Ad Hoc On demand Distance Vector Routing algorithm) for its performance evaluation and results are encouraging in terms of QoS parameters (Throughput, Total Packet Drops, End to End Delay and Control Packet Overhead).
  • Thumbnail Image
    Item
    Bio-Inspired QOS Aware Resources Allocation and Management at the Cloud Data Center
    (National Institute of Technology Karnataka, Surathkal, 2018) Domanal, Shridhar G; Reddy, G. Ram Mohana
    Cloud comprises of many hardware and software resources and managing these resources will play an important role in executing a clients request. Now-a-days clients from different parts of the world are demanding for various services at a rapid rate. In this present situation efficient load balancing algorithms will play an vital role in allocating the clients requests and also ensuring the usage of the resources in an intelligent way so that underutilization of the resources will not occur in the cloud environment. Clients demand for different cloud resources w.r.t Service Level Agreement (SLA) in a seamless manner, therefore resource allocation and management plays an important role in Infrastructure as a Service (IaaS) based cloud environment. Computing systems in the cloud environment heavily rely on virtualization technology and thus makes the servers feasible for independent applications. Further, virtualization process improves the power efficiency of the data centers (consolidation of physical machines (PMs)) and thereby enabling the assignment of multiple virtual machines (VMs) to a single physical PM. These VM instances can be procured in the form of On-Demand and Spot instances. Consequently, some of the PMs in the cloud data center can be turned off (sleep state) and resulting in low power consumption and thus making cloud data center more efficient. In this research work, the main focus is towards designing and development of efficient QoS aware load balancing and resources allocation/management algorithms using Bio-Inspired techniques which ensures fault tolerant task execution in heterogeneous cloud environment. Experimental results demonstrate that our proposed Bio-Inspired Load Balancing and QoS Aware Resources Allocation/Management algorithms outperforms peer research and benchmark algorithms in terms of efficient utilization of the cloud resources, improved reliability and reduced average response time.