Showing papers presented at "Parallel and Distributed Computing: Applications and Technologies in 2016"

mePaaS: Mobile-Embedded Platform as a Service for Distributing Fog Computing to Edge Nodes

Abstract: The distant data centre-centric Internet of Things systems face the latency issue especially in the real-time-based applications. Recently, Fog Computing models have been introduced to overcome the latency issue by utilising the proximity-based computational resources. However, the increasing users of Fog Computing servers will cause bottleneck issues and consequently the latency issue arises again. This paper introduces the utilisation of Mist Computing (Mist) model, which exploits the computational and networking resources from the devices at the very edge of IoT networks. The proposed service-oriented mobile-embedded Platform as a Service framework enables the edge IoT devices to provide a platform that allows requesters to deploy and execute their own program models. The framework supports resource-aware autonomous service configuration that can manage the availability of the functions provided by the Mist node based on the dynamically changing hardware resource availability. Additionally, the framework also supports task distribution among a group of Mist nodes. The prototype has been tested and performance evaluated on the real world devices.

Pre-Impact Fall Detection Based on Wearable Device Using Dynamic Threshold Model

Abstract: Falling accidents, including slipping, tripping and falling, are the primary reason of injury related to death not only for elderly, but for young people or worker happening at workplace also. If falling accident can be early detected in pre-fall or critical fall phase, called pre-impact fall detection, it will be very useful such as conducting airbag inflation. Furthermore, various detection methods, with an uncomplicated threshold detection method, do maximizing the true positive prediction values but the lead-time, time before subject impacts to the floor, will likely increases the chance of false alarms. Consequently the researcher found that the using of adaptive threshold may reduce false alarms. In this paper, the dynamic threshold method, automatically adjustable threshold for pre-impact fall detection in wearable device, has been proposed and experimented. For our evaluation, 192 instances of several kinds of activity of daily living and falling, were captured. All activities were performed by 6 different young healthy volunteers, 4 males and 2 females, aged between 19 and 21. The several experiments were conducted for performance evaluation including sensitivity, specificity and accuracy measurements. The results of proposed method can detect the pre-impact fall from normal activities of daily living with 99.48% sensitivity, 95.31% specificity and 97.40% accuracy with 365.12 msec of lead time. The results confirm that our proposed method with automatically adjustable threshold based on motion history, is suitable for using in pre-impact fall detection system than fixed threshold based method.

ControllerSEPA: A Security-Enhancing SDN Controller Plug-in for OpenFlow Applications

Abstract: Software-defined networking (SDN), as a new network paradigm, has the advantage of centralizing control and global visibility over a network. However, security issues remain a major concern and prevent SDN from being widely adopted. One of the challenges is the prevention of malicious OpenFlow application (OF app) access to the SDN controller as it opens a programmable northbound interface for third party applications. In this paper, we address app-to-control security issues with focus on five main attack vectors: unauthorized access, illegal function calling, malicious rules injection, resources exhausting and manin-the-middle attack. Based on the identified threat models, we develop a light-weight plug-in, which is called ControllerSEPA, by using RESTful API to defend SDN controller against malicious OF apps. Specifically, ControllerSEPA can provide the services including OF app-based AAA control (unlike OpenDaylight and ONOS which offer user-based or role-based AAA control), rule conflict resolution, OF app isolation, fine-grained access control and encryption. Furthermore, we study the feasibility of deploying ControllerSEPA on five open source SDN controllers: OpenDaylight, ONOS, Floodlight, Ryu and POX. Results show that the deployment operates with very low complexity, and most of time the modification of source codes is unnecessary. In our implementations, the repacked services in ControllerSEPA create negligible latency (0.1% to 0.3%) and can provide more rich services to OF apps.

A Traffic Classification Method with Spectral Clustering in SDN

Abstract: Traffic classification is becoming one of the major applications in the data center networks with a lot of cloud services. Recent works about software defined networking (SDN) have found new ways to manage data center networks. However, with the imbalance of the elephant and mice flows is sharpening, the accuracy and efficiency of traffic classification have become more and more important in SDN management. To address this issue, in this paper, we propose a traffic classification method that can deal with the traffic classification in SDN. Our method is based on spectral clustering and Software-Defined Networking (SDN). We propose a real-time flow extraction and representation method by scanning the flow tables in SDN controller. Then we cluster the flow data with spectral analysis. Extensive experiments on different settings have been performed, showing that our method is good at traffic classification with high detection rates and low overhead.

Combining Re-Sampling with Twin Support Vector Machine for Imbalanced Data Classification

Abstract: Imbalanced datasets exist widely in real life. The identification of the minority class in imbalanced datasets tends to be the focus of classification. The twin support vector machine (TWSVM) as a variant of enhanced SVM provides an effective technique for data classification. In the paper, we propose to combine a re-sampling technique, which utilizes over-sampling and under-sampling to balance the training data, with TWSVM to deal with imbalanced data classification. Experimental results show that our proposed approach outperforms other state-of–art methods.

Spectrally Efficient Nonorthogonal Frequency Division Multiplexing with Index Modulation

Abstract: Spectrally Efficient Frequency Division Multiplexing (SEFDM) systems provide enhanced spectrum utilization compared with Orthogonal Frequency Division Multiplexing (OFDM) systems by relaxing the orthogonality condition among sub-carriers. However, in the SEFDM systems, the loss of orthogonality results in the inter-carrier-interference (ICI) thus reduces the transmission reliability. To alleviate the ICI and achieve better error performance, this paper proposes a novel SEFDM transmission scheme, called SEFDM with index modulation (SEFDM-IM). The index modulation, which was originally proposed for OFDM systems, performs an additional modulation besides conventional M-ary modulation by selecting the indices of the sub-carriers. Since a number of sub-carriers are switched off in index modulation, when the index modulation is applied in SEFDM systems, the ICI is reduced and better error performance can be obtained in comparison with the SEFDM systems using conventional Mary modulation. Simulation results confirm this conclusion that the joint applications of SEFDM and index modulation can effectively increase the transmission reliability.

Optimal Scheduling Algorithm of MapReduce Tasks Based on QoS in the Hybrid Cloud

Abstract: Research on MapReduce tasks scheduling method for the hybrid cloud environment to meet QoS is of great significance. Considering that traditional scheduling algorithms cannot fully maximize efficiency of the private cloud and minimize costs under the public cloud, this paper proposes a MapReduce task optimal scheduling algorithm named MROSA to meet deadline and cost constraints. Private cloud scheduling improves the Max-Min strategy, reducing job execution time. The algorithm improves the resource utilization of the private cloud and the QoS satisfaction. In order to minimize the public cloud cost, public cloud scheduling based on cost optimization selects the best public cloud resources according to the deadline. Experimental results show that the proposed algorithm in this paper has less job execution time, higher QoS satisfaction than the Fair scheduler and FIFO scheduler. It also has more cost savings and shorter job completion time than recent similar studies.

Implementation and Optimization of AES Algorithm on the Sunway TaihuLight

Abstract: With the rapid development of information technology, the security of massive amounts of digital data has attracted huge attention in recent years. In this paper, we provide an efficient parallel implementation of the Advanced Encryption Standard (AES) algorithm, a widely used symmetrical block encryption algorithm, based on the Sunway TaihuLight. The Sunway TaihuLight is a China's independently developed heterogeneous supercomputer with peak performance over 100 PFlops. We also optimize the parallel implementation of the AES algorithm based on the Sunway TaihuLight to achieve more optimized performance. The optimization of the parallel AES algorithm in a single SW26010 node is provided. Specifically, we expand the scale to 1024 nodes and achieve the throughput of about 63.91 GB/s (511.28 Gbits/s). Our parallel implementation of the AES algorithm has great parallel scalability and the speedup ratio can be very high with the number of nodes increasing.

Research on L-MVC Framework

Abstract: Model–View–Controller pattern has been adopted as an architecture for World Wide Web applications in major programming languages. Though, many commercial and noncommercial web frameworks are very popular and applied widely, they are not particularly suitable for small applications. In this paper, the principle and basic components of MVC pattern are analyzed. Another new very Lightweight MVC framework was created, written by PHP and deployed on Linux, and then was applied to an online paper submission system as a demonstration which aims to improve the code re-usability and maintainability of small applications.

Resource-Aware Virtual Network Parallel Embedding Based on Genetic Algorithm

Abstract: Embedding virtual network requests in an underlying physical infrastructure, the so-called virtual network embedding (VNE) problem, has attracted significant research interests already. A realistic scenario might entail embedding multiple VN requests (MVNE) that arrive simultaneously (batch arrivals). The existing heuristic MVNE approaches neither consider the coordination among multiple VNR embeddings nor embed all the arriving VNRs simultaneously considering the available physical resources. This paper considers the MVNE problem in the scenario where the available physical resources may not be sufficient to satisfy the physical resource demands of all the VNRs in the batch. We explore applying genetic algorithm (GA) to handle the MVNE problem. We propose an algorithm to decide which VNRs could be mapped together. Extensive simulations are carried out to evaluate the performance of the proposed algorithms in terms of the VN acceptance ratio and the long-term revenue of the service provider.

The Optimization of LRU Algorithm Based on Pre-Selection and Cache Prefetching of Files in Hybrid Cloud

Abstract: In recent years, the research on caching in cloud environment has become an important research topic, and it has profound meaning to research the cache replacement algorithm in hybrid Cloud. There aren't enough considerations on some aspects, such as the selection of pending cache files, the prefetching of pending cache files among different clouds and the cost of recovery of files. Considering those shortages, this paper proposes an optimized LRU algorithm based on pre-selection and cache prefetching of files. This algorithm determines whether the file is to meet the pre-selection and cache prefetching conditions before adding a cache file, and it implements the LRU cache replacement algorithm which is based on priority. The algorithm divides the cache into multiple priority queues, and uses the LRU cache replacement algorithm to select the replacement file in each queue. Then select the files in each priority and put them together, select the file to perform replacement operation which has minimum probability of being accessed again. Compared with three typical cache replacement algorithm GD-Size, LRU, LFU, experimental results show that the cache replacement algorithm in this paper not only effectively save cost, but also greatly enhance the byte hit rate, delay savings rate and cache hit rate.

An Optimization Algorithm for Heterogeneous Hadoop Clusters Based on Dynamic Load Balancing

Abstract: Hadoop is a popular cloud computing software, and its major component MapReduce can efficiently complete parallel computing in homogeneous environment. But in practical application heterogeneous cluster is a common phenomenon. In this case, it's prone to unbalance load. To solve this problem, a model of heterogeneous Hadoop cluster based on dynamic load balancing is proposed in this paper. This model starts from MapReduce and tracks node information in real time by using its monitoring module. A maximum node hit rate priority algorithm (MNHRPA) is designed and implemented in the paper, and it can achieve load balancing by dynamic adjustment of data allocation based on nodes' computing power and load. The experimental results show that the algorithm can effectively reduce tasks' completion time and achieve load balancing of the cluster compared with Hadoop's default algorithm.

Performance Improvement of Genetic Algorithm for Multiple Sequence Alignment

Abstract: The multiple sequence alignment (MSA) is considered one of the most important tasks in Bioinformatics. Nevertheless, with the growth in the amount of genomic data available, it is essential the results with biological significance and an acceptable execution time. Thus, many tools have been proposed with the focus in these two last requirements. Considering the tools, the MSA-GA is of them, which is based on Genetic Algorithms approach, and it is widely used to perform MSA, because its simpler approach and good results. However, the biological significance and execution time are two elements that work in opposite directions, because when more biological significance is desired, more execution time will be wasted, mainly considering the amount of genomic data produced by next generation sequencing recently. Therefore, the implementation of parallel programming can help to smooth this disadvantage. Thus, in the present work we developed a parallel version of the MSA-GA tool using multithread programming, in order to keep the good results produced by the tool and improving its execution time.

Performability Analysis for IaaS Cloud Data Center

Abstract: Cloud computing has been bringing fundamental changes to computing models in the past few years. Infrastructure as a Service (IaaS), a kind of basic cloud services, is provisioned to customers in the form of virtual machines (VMs). The increasing demands for IaaS cloud services require the performability analysis of cloud infrastructure. Analytic modeling is one of the effective evaluation approaches. This paper aims to develop a monolithic model, by using continuous time Markov chain (CTMC), for a IaaS CDC, which (1) consists of active and standby physical machines (PMs), (2) allows PM migration among active and standby PM pools, (3) all jobs are homogeneous, and (4) a running job could continue its running by using idle active PMs when the PM working for this job fails. Although a monolithic CTMC model for IaaS Cloud performability analysis may face largeness and stiffness problems, it could be used to verify the scalable approximate model. We present the details of state transition rules of the proposed model and the formula for computing metrics, including the immediate service probability, the mean response time and so on. Numerical analysis and simulations are carried out to verify the accuracy of the proposed model.

An Application Oriented Multi-Agent Based Approach to Dynamic Truck Scheduling at Cross-Dock

Abstract: Truck arrival management forms a very active stream of research and a crucial challenge for a cross-dock terminals. The study focuses on the truck congestion problem, which leads to a lower operation efficiency and a longer waiting time at the gate and at the yard. One of the operational measures to solve this problem is the truck appointment system. It is used to coordinate the major cross-dock planning activities and to regulate the arrival time of trucks at the cross-dock. When the trucker get an appointment time different to its preference time, then we are talking about a truck deviation time. Because the deviation will result in daily operations schedule, an optimization model for truck appointment was proposed in this paper. In the model, the truck deviation time was minimized subject to the constraints of resources availability including dock doors, yard zones, gate lanes, workforce and material handling systems. To solve the model, a method based multi-agent system to real-time truck scheduling, that take into account the uncertainty of arrival time as an operational characteristic, was designed. It ensures a negotiation among truck agents and resource agents. Lastly, a numerical experiments are provided to illustrate the validity of the model and to illustrate the working and benefit of our approach.

An Advanced Load Balancing Strategy for Cloud Environment

Abstract: The rapid development of cloud computing, bring great convenience to developers. Recently the resource management of the cloud platform has become a hot research topic, especially the load balancing problem in data center is very important for cloud provider. In this paper, a load balancing framework is proposed for cloud platform, it use the threshold window strategy and an advanced AR prediction model to reduce the migration of VMs. Experiments show that this method can effectively achieve load balancing, promote the utilization of the physical machines, and solve the frequent migration problem caused by high instantaneous peak values significantly.

Green-Aware Online Resource Allocation for Geo-Distributed Cloud Data Centers on Multi-Source Energy

Abstract: Huge energy consumption of large-scale cloud data centers damages the environment with excessive carbon emission. More and more data center operators are seeking to reduce carbon footprint via various types of renewable energy sources. However, the intermittent availability of renewable energy source makes it quite challenging to cooperate the dynamic workload arrivals. In this paper, we investigate how to coordinate multi-type renewable energy (e.g. wind power and solar power) in order to reduce the long-term energy cost with spatio-temporal diversity of electricity price for geo-distributed cloud data centers under the constraints of service level agreement (SLA) and carbon footprints. To tackle the randomness of workload arrival, dynamic electricity price change and renewable energy generation, we first formulate the minimizing energy cost problem into a constrained stochastic optimization problem. Then, based on Lyapunov optimization technique, we design an online control algorithm which can work without long-term future system information for solving the problem. Finally, we evaluate the effectiveness of the algorithm with extensive simulations based on real-world workload traces, electricity price and historic climate data.

Performance and Portability Studies with OpenACC Accelerated Version of GTC-P

Abstract: Accelerator-based heterogeneous computing is of paramount importance to High Performance Computing. The increasing complexity of the cluster architectures requires more generic, high-level programming models. OpenACC is a directive-based parallel programming model, which provides performance on and portability across a wide variety of platforms, including GPU, multicore CPU, and many-core processors. GTC-P is a discovery-science-capable real-world application code based on the Particle-In-Cell (PIC) algorithm that is well-established in the HPC area. Several native versions of GTC-P have been developed for supercomputers on TOP500 with different architectures, including Titan, Mira, etc. Motivated by the state-of-art portability, we implemented the first OpenACC version of GTC-P and evaluated its performance portability across NVIDIA GPUs, Intel x86 and OpenPOWER CPUs. In this paper, we also proposed two key optimization methods for OpenACC implementation of PIC algorithm on multicore CPU and GPU including removing atomic operation and taking advantage of shared memory. OpenACC shows both impressive productivity and performance in a perspective of portability and scalability. The OpenACC version achieves more than 90% performance compared with the native versions with only about 300 LOC.

Improved Data Streams Classification with Fast Unsupervised Feature Selection

Abstract: Data streams classification poses three major challenges, namely, infinite length, concept-drift, and featureevolution. The first two issues have been widely studied. However, most existing data stream classification techniques ignore the last one. DXMiner [17], the first model which addresses featureevolution by using the past labeled instances to select the top ranked features based on a scores computed by a formula. This semi-supervised feature selection method depends on the quality of the past classification and neglects the possible correlation among different features, thus unable to produce an optimal feature subset which deteriorates the accuracy of classification. Multi-Cluster Feature Selection (MCFS) [5] proposed for static data classification and clustering applies unsupervised feature selection to address the feature-evolution problem, but suffers from the high computational cost in feature selection. In this paper, we apply MCFS in the DXMiner framework to handle each window of data in a data stream for dynamic data stream-classification. With unsupervised feature selection, our method produces the optimal feature subset and hence improves DXMiner on the classification accuracy. We further improve the time complexity of the feature selection process in MCFS by using the locality sensitive hashing forest (LSH Forest) [4]. The empirical results indicate that our approach outperforms stateof-the-art streams classification techniques in classifying real-life data streams.

On Routing of Multiple Concurrent User Requests in Multi-Radio Multi-Channel Wireless Mesh Networks

Abstract: Multiple-radio multiple-channel (MRMC) wireless mesh networks (WMNs) generally serve as wireless backbones for ubiquitous Internet access. These networks often face a challenge to satisfy multiple user traffic requests simultaneously between different source-destination pairs with different data transfer requirements. We construct analytical network models and formulate such multi-pair routing as a rigorous optimization problem. We design a cooperative routing and scheduling algorithm with channel assignment, in which, a primary path is built upon the selection of appropriate link patterns. The performance of the proposed algorithm is illustrated by simulation-based combinatorial experiments.

A Survey of Challenging Issues and Approaches in Mobile Cloud Computing

Abstract: Recently, the exploitation of cloud resources for augmenting mobile devices leads to the emergence of a new research area called Mobile Cloud Computing (MCC). In this work, we present a survey and taxonomy for MCC architecture, characteristics, and open research issues aim to explore deep research in this area. We present a taxonomy based on the key issues while highlighting the specific concerns in MCC, and discuss related approaches taken to tackle these issues. Furthermore, the direction for future work is discussed.

A Dynamic Migration Method for Big Data in Cloud

Abstract: Big data applications store data sets through sharing data center under the Cloud computing environment, but the need of data set in big data applications is dynamic change over time. In face of multiple data centers, such applications meet new challenges in data migration which mainly include how to how to reduce the number of network access, how to reduce the overall time consumption, and how to improve the efficiency by the time of balancing the global load in the migration process. Facing these challenges, we first build the problem model and descript the dynamic migration method, then solve the global time consumption of data migration, the number of network access and global load balancing these three parameters. Finally, do the cloud computing simulation experiment under the Cloudsim experiment platform. The result shows that the proposed method makes the task completion time reduced by 10% and the data transmission time accounts for the roportion of the total time is reduced. When the amount of data sets is increase, the proportion can reduces to 50% or less. Network access number lower than Zipf and reached stable, in global load, the variance of the node's store space closed to zero.

Accurate Evaluation of Bivariate Polynomials

Abstract: Polynomials are widely used in scientific computing and engineering. In this paper, we present an accurate and fast compensated algorithm to evaluate bivariate polynomials with floating-point coefficients. This algorithm is applying error free transformations to the bivariate Horner scheme and sum the final decomposition accurately. We also prove the proposed algorithm's accuracy with forward error analysis that the accuracy of the computed result is similar to the result computed by the bivariate Horner scheme in twice the working precision. Numerical experiments illustrate the behavior and it has higher efficiency than the bivariate Horner scheme implemented in double-double library.

An Improved Molecular Computing Model of Modular-Multiplication over Finite Field GF(2n)

Abstract: With the rapid development of DNA computing, there are some questions worth study that how to implement the arithmetic operations used in cryptosystem based on DNA computing models. This paper proposes an improved DNA computing model to calculate modular-multiplication over finite field GF(2n). Comparing to related works, both assembly time complexity and space complexity are more optimal. The computation tiles performing 4 different functions assemble into the seed configuration with inputs to figure out the result. It is given that how the computation tiles be bitwise coded and how assembly rules work. The assembly time complexity is Θ(n) and the space complexity is Θ(n2). This model requires 148 types of computation tiles and 8 types of boundary tiles.

Affine Correction Based Image Watermarking Robust to Geometric Attacks

Abstract: How to resist combined geometric attacks effectively while maintain a high embedding capacity is still a challenging task for the digital watermarking research. An affine correction based algorithm is proposed in this paper, which can resist combined geometric attacks and keep a higher watermark embedding capacity. The SURF algorithm and the RANSAC algorithm are used to extract, match and select feature points from the attacked image and the original image. Then, the least square algorithm is used to estimate the affine matrix of the geometric attacks according to the relationship between the matched feature points. The attacks are corrected based on the estimated affine matrix. A fine correction step is included to improve the precision of the watermark detection. To resist the cropping attacks, the watermark information is encoded with LT-coding. The encoded watermark is embedded in the DWT-DCT composite domain of the image. Experimental results show that the proposed algorithm not only has a high embedding capacity, but also is robust to many kinds of geometric attacks.

NUMA-BTDM: A Thread Mapping Algorithm for Balanced Data Locality on NUMA Systems

Abstract: Optimizing for Non-Uniform Memory Access (NUMA) systems could be considered inappropriate because hardware architecture aware optimizations are not portable. On the contrary, this paper supports the idea that developing NUMA aware optimizations improves performance and energy consumption on NUMA systems and that these optimizations may be considered portable when they are non static. This paper introduces NUMA Balanced Thread and Data Mapping (BTDM), an extension of PThreads4w API [1]. NUMA-BTDM employs balanced data locality concept, improving thread and data mapping for NUMA systems. The purpose is to combine task parallelism with balanced data locality in order to obtain both better performance and reduced energy consumption on NUMA systems at run-time. The implementation of NUMA-BTDM targets homogeneous architectures based on the energy model with constant energy consumption or on the energy model in which each core is powered from a separate source (architectures on which parallel execution may reduce energy consumption compared to serial execution).

An Improved Task Scheduling Algorithm Based on Cache Locality and Data Locality in Hadoop

Abstract: The optimization of task scheduling in Hadoop environment is an important research topic. The result of task scheduling affects the system performance and resource utilization. The existing task scheduling algorithm is lack of consideration at the cache level, which makes the performance of the task greatly affected. Therefore, this paper proposes an improved task scheduling algorithm based on cache locality and data locality. Firstly section matrix and weighted bipartite graph are constructed according to the relation between resources and tasks. Then the bipartite graph matching is used to realize map task scheduling for optimizing the local cache and data locality and reducing the data transmission amount during task execution process. The experimental results show that the proposed algorithm can effectively improve the data locality and system performance, which is better than other two algorithms.

Comparison on Network Simulation Techniques

Abstract: Network simulation is an important technique for verifying new algorithms, analyzing network performance and deploying the practical networks. Different network simulation softwares are applied for different scenarios. In this paper, their performance in different applications are discussed in detail. Three kinds of main network simulation softwares are introduced in this paper: OPNET, Network Simulator (NS) and Objective Modular Network Testbed in C++ (OMNeT++). NS is widely used in network research. How to apply NS in network traffic analysis is discussed in this paper.

Performance Optimization for In-Memory File Systems on NUMA Machines

Abstract: The growing demand for high-performance data processing stimulates the development of in-memory file systems, which exploit the advanced features of emerging non-volatile memory techniques for achieving high-speed file accesses. Existing in-memory file systems, however, are all designed for the systems with uniformed memory accesses. Their performance is poor on Non-Uniform Memory Access (NUMA) machines as they do not consider the asymmetric memory access speed and the architecture of multiple nodes. In this paper, we propose a new design of NUMA-aware in-memory file systems. We propose a distributed file system layout for leveraging the loads of in-memory file accesses on different nodes, a thread-file binding algorithm and a buffer assignment technique for increasing local memory accesses during run-time. Based on the proposed techniques, we implement a functional NUMA-aware in-memory file system, HydraFS, in Linux kernel. Extensive experiments are conducted with the standard benchmark. The experimental results show that HydraFS significantly outperforms typical existing in-memory file systems, including EXT4-DAX, PMFS, and SIMFS.

An Improved Particle Swarm Optimization Algorithm Based on Cauchy Operator and 3-Opt for TSP

Abstract: An improved particle swarm optimization (PSO) algorithm based on self-adaptive excellence coefficients, Cauchy operator and 3-opt, called SCLPSO, is proposed in this paper in order to deal with the issues such as premature convergence and low accuracy of the basic discrete PSO when applied to traveling salesman problem (TSP). To improve the optimization ability and convergence speed of the algorithm, each edge is assigned a self-adaptive excellence coefficient based on the principle of roulette selection, which can be adjusted dynamically according to the process of searching for the solutions. To gain better global search ability of the basic discrete PSO, the Cauchy distribution density function is used to regulate the inertia weight so as to improve the diversity of the population. Furthermore, the 3-opt local search technique is utilized to increase the accuracy and convergence speed of the algorithm. Through simulation experiments with MATLAB, the performance of the proposed algorithm is evaluated on several classical examples taken from the TSPLIB. The experimental results indicate that the proposed SCLPSO algorithm performs better in terms of accuracy and convergence speed compared with several other algorithms, and thus is a potential intelligence algorithm for solving TSP.