Search results for: distributed%20data%20mining
1987 The Primitive Code-Level Design Patterns for Distributed Programming
Authors: Bing Li
Abstract:
The primitive code-level design patterns (PDP) are the rudimentary programming elements to develop any distributed systems in the generic distributed programming environment, GreatFree. The PDP works with the primitive distributed application programming interfaces (PDA), the distributed modeling, and the distributed concurrency for scaling-up. They not only hide developers from underlying technical details but also support sufficient adaptability to a variety of distributed computing environments. Programming with them, the simplest distributed system, the lightweight messaging two-node client/server (TNCS) system, is constructed rapidly with straightforward and repeatable behaviors, copy-paste-replace (CPR). As any distributed systems are made up of the simplest ones, those PDAs, as well as the PDP, are generic for distributed programming.Keywords: primitive APIs, primitive code-level design patterns, generic distributed programming, distributed systems, highly patterned development environment, messaging
Procedia PDF Downloads 1811986 A Survey on Concurrency Control Methods in Distributed Database
Authors: Seyed Mohsen Jameii
Abstract:
In the last years, remarkable improvements have been made in the ability of distributed database systems performance. A distributed database is composed of some sites which are connected to each other through network connections. In this system, if good harmonization is not made between different transactions, it may result in database incoherence. Nowadays, because of the complexity of many sites and their connection methods, it is difficult to extend different models in distributed database serially. The principle goal of concurrency control in distributed database is to ensure not interfering in accessibility of common database by different sites. Different concurrency control algorithms have been suggested to use in distributed database systems. In this paper, some available methods have been introduced and compared for concurrency control in distributed database.Keywords: distributed database, two phase locking protocol, transaction, concurrency
Procedia PDF Downloads 3441985 A Preliminary Conceptual Scale to Discretize the Distributed Manufacturing Continuum
Authors: Ijaz Ul Haq, Fiorenzo Franceschini
Abstract:
The distributed manufacturing methodology brings a new concept of decentralized manufacturing operations close to the proximity of end users. A preliminary scale, to measure distributed capacity and evaluate positioning of firms, is developed in this research. In the first part of the paper, a literature review has been performed which highlights the explorative nature of the studies conducted to present definitions and classifications due to novelty of this topic. From literature, five dimensions of distributed manufacturing development stages have been identified: localization, manufacturing technologies, customization and personalization, digitalization and democratization of design. Based on these determinants a conceptual scale is proposed to measure the status of distributed manufacturing of a generic firm. A multiple case study is then conducted in two steps to test the conceptual scale and to identify the corresponding level of distributed potential in each case study firm.Keywords: distributed manufacturing, distributed capacity, localized production, ordinal scale
Procedia PDF Downloads 1591984 Optimizing Communications Overhead in Heterogeneous Distributed Data Streams
Authors: Rashi Bhalla, Russel Pears, M. Asif Naeem
Abstract:
In this 'Information Explosion Era' analyzing data 'a critical commodity' and mining knowledge from vertically distributed data stream incurs huge communication cost. However, an effort to decrease the communication in the distributed environment has an adverse influence on the classification accuracy; therefore, a research challenge lies in maintaining a balance between transmission cost and accuracy. This paper proposes a method based on Bayesian inference to reduce the communication volume in a heterogeneous distributed environment while retaining prediction accuracy. Our experimental evaluation reveals that a significant reduction in communication can be achieved across a diverse range of dataset types.Keywords: big data, bayesian inference, distributed data stream mining, heterogeneous-distributed data
Procedia PDF Downloads 1551983 Method of Successive Approximations for Modeling of Distributed Systems
Authors: A. Torokhti
Abstract:
A new method of mathematical modeling of the distributed nonlinear system is developed. The system is represented by a combination of the set of spatially distributed sensors and the fusion center. Its mathematical model is obtained from the iterative procedure that converges to the model which is optimal in the sense of minimizing an associated cost function.Keywords: mathematical modeling, non-linear system, spatially distributed sensors, fusion center
Procedia PDF Downloads 3751982 Optimal Sizing and Placement of Distributed Generators for Profit Maximization Using Firefly Algorithm
Authors: Engy Adel Mohamed, Yasser Gamal-Eldin Hegazy
Abstract:
This paper presents a firefly based algorithm for optimal sizing and allocation of distributed generators for profit maximization. Distributed generators in the proposed algorithm are of photovoltaic and combined heat and power technologies. Combined heat and power distributed generators are modeled as voltage controlled nodes while photovoltaic distributed generators are modeled as constant power nodes. The proposed algorithm is implemented in MATLAB environment and tested the unbalanced IEEE 37-node feeder. The results show the effectiveness of the proposed algorithm in optimal selection of distributed generators size and site in order to maximize the total system profit.Keywords: distributed generators, firefly algorithm, IEEE 37-node feeder, profit maximization
Procedia PDF Downloads 4311981 Sensitivity Analysis for 14 Bus Systems in a Distribution Network with Distributed Generators
Authors: Lakshya Bhat, Anubhav Shrivastava, Shiva Rudraswamy
Abstract:
There has been a formidable interest in the area of Distributed Generation in recent times. A wide number of loads are addressed by Distributed Generators and have better efficiency too. The major disadvantage in Distributed Generation is voltage control- is highlighted in this paper. The paper addresses voltage control at buses in IEEE 14 Bus system by regulating reactive power. An analysis is carried out by selecting the most optimum location in placing the Distributed Generators through load flow analysis and seeing where the voltage profile rises. MATLAB programming is used for simulation of voltage profile in the respective buses after introduction of DG’s. A tolerance limit of +/-5% of the base value has to be maintained. To maintain the tolerance limit, 3 methods are used. Sensitivity analysis of 3 methods for voltage control is carried out to determine the priority among the methods.Keywords: distributed generators, distributed system, reactive power, voltage control, sensitivity analysis
Procedia PDF Downloads 6961980 Distributed Leadership: An Alternative at Higher Education Institutions in Turkey
Authors: Sakine Sincer
Abstract:
In today’s world, which takes further steps towards globalization each and every day, societies and cultures are re-shaped while the demands of the changing world are described once more. In this atmosphere, where the speed of change sometimes reaches a terrifying point, it is possible to state that effective leaders are needed more than ever in order to meet the above-stated needs and demands. The question of what effective leadership is keeping its importance on the agenda. Most of the answers to this question has mostly focused on the approach of distributed leadership recently. This study aims at analyzing the applicability of distributed leadership, which is accepted to be an example of effective leadership that can meet the needs of global world, which is changing more and more rapidly nowadays, at higher education institutions in Turkey. Within the framework of this study, first of all, the historical development of distributed leadership is addressed, and then a theoretical framework is drawn for this approach by means of underlying what distributed leadership is and is not. After that, different points of view about the approach are laid out within the borders of opinions expressed by Gronn and Spillane, who are accepted to be the most famous advocators of distributed leadership. Then, exemplar practices of distributed leadership are included in the study before drawing attention to the strengths and weaknesses of this approach. Lastly, the applicability of distributed leadership at higher education institutions in Turkey is analyzed. This study is carried out with the method of literature review by resorting to first- and second-hand sources on distributed leadership.Keywords: globalization, school leadership, distributed leadership, higher education, management
Procedia PDF Downloads 4001979 An Experimental Testbed Using Virtual Containers for Distributed Systems
Authors: Parth Patel, Ying Zhu
Abstract:
Distributed systems have become ubiquitous, and they continue their growth through a range of services. With advances in resource virtualization technology such as Virtual Machines (VM) and software containers, developers no longer require high-end servers to test and develop distributed software. Even in commercial production, virtualization has streamlined the process of rapid deployment and service management. This paper introduces a distributed systems testbed that utilizes virtualization to enable distributed systems development on commodity computers. The testbed can be used to develop new services, implement theoretical distributed systems concepts for understanding, and experiment with virtual network topologies. We show its versatility through two case studies that utilize the testbed for implementing a theoretical algorithm and developing our own methodology to find high-risk edges. The results of using the testbed for these use cases have proven the effectiveness and versatility of this testbed across a range of scenarios.Keywords: distributed systems, experimental testbed, peer-to-peer networks, virtual container technology
Procedia PDF Downloads 1391978 A Novel Probablistic Strategy for Modeling Photovoltaic Based Distributed Generators
Authors: Engy A. Mohamed, Y. G. Hegazy
Abstract:
This paper presents a novel algorithm for modeling photovoltaic based distributed generators for the purpose of optimal planning of distribution networks. The proposed algorithm utilizes sequential Monte Carlo method in order to accurately consider the stochastic nature of photovoltaic based distributed generators. The proposed algorithm is implemented in MATLAB environment and the results obtained are presented and discussed.Keywords: comulative distribution function, distributed generation, Monte Carlo
Procedia PDF Downloads 5781977 Advanced Simulation and Enhancement for Distributed and Energy Efficient Scheduling for IEEE802.11s Wireless Enhanced Distributed Channel Access Networks
Authors: Fisayo G. Ojo, Shamala K. Subramaniam, Zuriati Ahmad Zukarnain
Abstract:
As technology is advancing and wireless applications are becoming dependable sources, while the physical layer of the applications are been embedded into tiny layer, so the more the problem on energy efficiency and consumption. This paper reviews works done in recent years in wireless applications and distributed computing, we discovered that applications are becoming dependable, and resource allocation sharing with other applications in distributed computing. Applications embedded in distributed system are suffering from power stability and efficiency. In the reviews, we also prove that discrete event simulation has been left behind untouched and not been adapted into distributed system as a simulation technique in scheduling of each event that took place in the development of distributed computing applications. We shed more lights on some researcher proposed techniques and results in our reviews to prove the unsatisfactory results, and to show that more work still have to be done on issues of energy efficiency in wireless applications, and congestion in distributed computing.Keywords: discrete event simulation (DES), distributed computing, energy efficiency (EE), internet of things (IOT), quality of service (QOS), user equipment (UE), wireless mesh network (WMN), wireless sensor network (wsn), worldwide interoperability for microwave access x (WiMAX)
Procedia PDF Downloads 1841976 Coordinated Voltage Control in Radial Distribution System with Distributed Generators Using Sensitivity Analysis
Authors: Anubhav Shrivastava Shivarudraswamy, Bhat Lakshya
Abstract:
Distributed generation has indeed become a major area of interest in recent years. Distributed generation can address a large number of loads in a power line and hence has better efficiency over the conventional methods. However, there are certain drawbacks associated with it, an increase in voltage being the major one. This paper addresses the voltage control at the buses for an IEEE 30 bus system by regulating reactive power. For carrying out the analysis, the suitable location for placing distributed generators (DG) is identified through load flow analysis and seeing where the voltage profile is dipping. MATLAB programming is used to regulate the voltage at all buses within +/- 5% of the base value even after the introduction of DGs. Three methods for regulation of voltage are discussed. A sensitivity based analysis is then carried out to determine the priority among the various methods listed in the paper.Keywords: distributed generators, distributed system, reactive power, voltage control, sensitivity analysis
Procedia PDF Downloads 6511975 Artificial Intelligence and Distributed System Computing: Application and Practice in Real Life
Authors: Lai Junzhe, Wang Lihao, Burra Venkata Durga Kumar
Abstract:
In recent years, due to today's global technological advances, big data and artificial intelligence technologies have been widely used in various industries and fields, playing an important role in reducing costs and increasing efficiency. Among them, artificial intelligence has derived another branch in its own continuous progress and the continuous development of computer personnel, namely distributed artificial intelligence computing systems. Distributed AI is a method for solving complex learning, decision-making, and planning problems, characterized by the ability to take advantage of large-scale computation and the spatial distribution of resources, and accordingly, it can handle problems with large data sets. Nowadays, distributed AI is widely used in military, medical, and human daily life and brings great convenience and efficient operation to life. In this paper, we will discuss three areas of distributed AI computing systems in vision processing, blockchain, and smart home to introduce the performance of distributed systems and the role of AI in distributed systems.Keywords: distributed system, artificial intelligence, blockchain, IoT, visual information processing, smart home
Procedia PDF Downloads 1041974 Business-Intelligence Mining of Large Decentralized Multimedia Datasets with a Distributed Multi-Agent System
Authors: Karima Qayumi, Alex Norta
Abstract:
The rapid generation of high volume and a broad variety of data from the application of new technologies pose challenges for the generation of business-intelligence. Most organizations and business owners need to extract data from multiple sources and apply analytical methods for the purposes of developing their business. Therefore, the recently decentralized data management environment is relying on a distributed computing paradigm. While data are stored in highly distributed systems, the implementation of distributed data-mining techniques is a challenge. The aim of this technique is to gather knowledge from every domain and all the datasets stemming from distributed resources. As agent technologies offer significant contributions for managing the complexity of distributed systems, we consider this for next-generation data-mining processes. To demonstrate agent-based business intelligence operations, we use agent-oriented modeling techniques to develop a new artifact for mining massive datasets.Keywords: agent-oriented modeling (AOM), business intelligence model (BIM), distributed data mining (DDM), multi-agent system (MAS)
Procedia PDF Downloads 4241973 Big Data Analysis with Rhipe
Authors: Byung Ho Jung, Ji Eun Shin, Dong Hoon Lim
Abstract:
Rhipe that integrates R and Hadoop environment made it possible to process and analyze massive amounts of data using a distributed processing environment. In this paper, we implemented multiple regression analysis using Rhipe with various data sizes of actual data. Experimental results for comparing the performance of our Rhipe with stats and biglm packages available on bigmemory, showed that our Rhipe was more fast than other packages owing to paralleling processing with increasing the number of map tasks as the size of data increases. We also compared the computing speeds of pseudo-distributed and fully-distributed modes for configuring Hadoop cluster. The results showed that fully-distributed mode was faster than pseudo-distributed mode, and computing speeds of fully-distributed mode were faster as the number of data nodes increases.Keywords: big data, Hadoop, Parallel regression analysis, R, Rhipe
Procedia PDF Downloads 4931972 Performance Evaluation of Distributed and Co-Located MIMO LTE Physical Layer Using Wireless Open-Access Research Platform
Authors: Ishak Suleiman, Ahmad Kamsani Samingan, Yeoh Chun Yeow, Abdul Aziz Bin Abdul Rahman
Abstract:
In this paper, we evaluate the benefits of distributed 4x4 MIMO LTE downlink systems compared to that of the co-located 4x4 MIMO LTE downlink system. The performance evaluation was carried out experimentally by using Wireless Open-Access Research Platform (WARP), where the comparison between the 4x4 MIMO LTE transmission downlink system in distributed and co-located techniques was examined. The measured Error Vector Magnitude (EVM) results showed that the distributed technique achieved better system performance compared to the co-located arrangement.Keywords: multiple-input-multiple-output (MIMO), distributed MIMO, co-located MIMO, LTE
Procedia PDF Downloads 4121971 Sensitivity Analysis for 14 Bus Systems in a Distribution Network with Distribution Generators
Authors: Lakshya Bhat, Anubhav Shrivastava, Shivarudraswamy
Abstract:
There has been a formidable interest in the area of Distributed Generation in recent times. A wide number of loads are addressed by Distributed Generators and have better efficiency too. The major disadvantage in Distributed Generation is voltage control- is highlighted in this paper. The paper addresses voltage control at buses in IEEE 14 Bus system by regulating reactive power. An analysis is carried out by selecting the most optimum location in placing the Distributed Generators through load flow analysis and seeing where the voltage profile rises. Matlab programming is used for simulation of voltage profile in the respective buses after introduction of DG’s. A tolerance limit of +/-5% of the base value has to be maintained.To maintain the tolerance limit , 3 methods are used. Sensitivity analysis of 3 methods for voltage control is carried out to determine the priority among the methods.Keywords: distributed generators, distributed system, reactive power, voltage control, sensitivity analysis
Procedia PDF Downloads 5811970 Coordinated Voltage Control in a Radial Distribution System
Authors: Shivarudraswamy, Anubhav Shrivastava, Lakshya Bhat
Abstract:
Distributed generation has indeed become a major area of interest in recent years. Distributed Generation can address large number of loads in a power line and hence has better efficiency over the conventional methods. However there are certain drawbacks associated with it, increase in voltage being the major one. This paper addresses the voltage control at the buses for an IEEE 30 bus system by regulating reactive power. For carrying out the analysis, the suitable location for placing distributed generators (DG) is identified through load flow analysis and seeing where the voltage profile is dipping. MATLAB programming is used to regulate the voltage at all buses within +/-5% of the base value even after the introduction of DG’s. Three methods for regulation of voltage are discussed. A sensitivity based analysis is later carried out to determine the priority among the various methods listed in the paper.Keywords: distributed generators, distributed system, reactive power, voltage control
Procedia PDF Downloads 4891969 A Novel Microcontroller Based Islanding Protection of Distributed Generation Systems
Authors: Saeid Jalilzadeh, Majid Pakdel
Abstract:
The customer demand for better power quality and higher reliability has forced the power industry to use distributed generations (DGs) such as wind power and photo voltaic arrays. Islanding is a phenomenon occurs when a power grid becomes electrically isolated from the power system and the distribution system is energized by distributed generators. It is necessary to disconnect all distributed generators immediately after islanding occurrence. Therefore a DG system should have the capability to detect islanding phenomena. In this paper, a novel micro controller based relay for anti-islanding protection of a typical DG system is proposed. The simulation results using Proteus software verify the proper operation and effectiveness of the proposed protective relay.Keywords: islanding, distributed generation (DG), protective relay, micro controller, proteus software
Procedia PDF Downloads 5701968 Exploring Employee Experiences of Distributed Leadership in Consultancy SMEs
Authors: Mohamed Haffar, Ramdane Djebarni, Russell Evans
Abstract:
Despite a growth in literature on distributed leadership, the majority of studies are centred on large public organisations particularly within the health and education sectors. The purpose of this study is to fill the gap in the literature by exploring employee experiences of distributed leadership within two commercial consultancy SME businesses in the UK and USA. The aim of the study informed an exploratory method of research to gather qualitative data drawn from semi-structured interviews involving a sample of employees in each organisation. A series of broad, open questions were used to explore the employees’ experiences; evidence of distributed leadership; and extant barriers and practices in each organisation. Whilst some of our findings aligned with patterns and practices in the existing literature, it importantly discovered some emergent themes that have not previously been recognised in the previous studies. Our investigation identified that whilst distributed leadership was in evidence in both organisations, the interviewees’ experience reported that it was sporadic and inconsistent. Moreover, non-client focused projects were reported to be less important and distributed leadership was found to be inconsistent or non-existent.Keywords: consultancy, distributed leadership, owner-manager, SME, entrepreneur
Procedia PDF Downloads 1171967 Determination of Frequency Relay Setting during Distributed Generators Islanding
Authors: Tarek Kandil, Ameen Ali
Abstract:
Distributed generation (DG) has recently gained a lot of momentum in power industry due to market deregulation and environmental concerns. One of the most technical challenges facing DGs is islanding of distributed generators. The current industry practice is to disconnect all distributed generators immediately after the occurrence of islands within 200 to 350 ms after loss of main supply. To achieve such goal, each DG must be equipped with an islanding detection device. Frequency relays are one of the most commonly used loss of mains detection method. However, distribution utilities may be faced with concerns related to false operation of these frequency relays due to improper settings. The commercially available frequency relays are considering standard tight setting. This paper investigates some factors related to relays internal algorithm that contribute to their different operating responses. Further, the relay operation in the presence of multiple distributed at the same network is analyzed. Finally, the relay setting can be accurately determined based on these investigation and analysis.Keywords: frequency relay, distributed generation, islanding detection, relay setting
Procedia PDF Downloads 5291966 Attempt to Reuse Used-PCs as Distributed Storage
Authors: Toshiya Kawato, Shin-ichi Motomura, Masayuki Higashino, Takao Kawamura
Abstract:
Storage for storing data is indispensable. If a storage capacity becomes insufficient, we can increase its capacity by adding new disks. It is, however, difficult to add a new disk when a budget is not enough. On the other hand, there are many unused idle resources such as used personal computers despite those use value. In order to solve those problems, used personal computers can be reused as storage. In this paper, we attempt to reuse used-PCs as a distributed storage. First, we list up the characteristics of used-PCs and design a storage system that utilizes its characteristics. Next, we experimentally implement an auto-construction system that automatically constructs a distributed storage environment in used-PCs.Keywords: distributed storage, used personal computer, idle resource, auto construction
Procedia PDF Downloads 2461965 Condition Monitoring of Railway Earthworks using Distributed Rayleigh Sensing
Authors: Andrew Hall, Paul Clarkson
Abstract:
Climate change is predicted to increase the number of extreme weather events intensifying the strain on Railway Earthworks. This paper describes the use of Distributed Rayleigh Sensing to monitor low frequency activity on a vulnerable earthworks sectionprone to landslides alongside a railway line in Northern Spain. The vulnerable slope is instrumented with conventional slope stability sensors allowing an assessment to be conducted of the application of Distributed Rayleigh Sensing as an earthwork condition monitoring tool to enhance the resilience of railway networks.Keywords: condition monitoring, railway earthworks, distributed rayleigh sensing, climate change
Procedia PDF Downloads 1961964 Selection of Relevant Servers in Distributed Information Retrieval System
Authors: Benhamouda Sara, Guezouli Larbi
Abstract:
Nowadays, the dissemination of information touches the distributed world, where selecting the relevant servers to a user request is an important problem in distributed information retrieval. During the last decade, several research studies on this issue have been launched to find optimal solutions and many approaches of collection selection have been proposed. In this paper, we propose a new collection selection approach that takes into consideration the number of documents in a collection that contains terms of the query and the weights of those terms in these documents. We tested our method and our studies show that this technique can compete with other state-of-the-art algorithms that we choose to test the performance of our approach.Keywords: distributed information retrieval, relevance, server selection, collection selection
Procedia PDF Downloads 3011963 The Fusion of Blockchain and AI in Supply Chain Finance: Scalability in Distributed Systems
Authors: Wu You, Burra Venkata Durga Kumar
Abstract:
This study examines the promising potential of integrating Blockchain and Artificial Intelligence (AI) technologies to scalability in Distributed Systems within the field of supply chain finance. The finance industry is continually confronted with scalability challenges in its Distributed Systems, particularly within the supply chain finance sector, impacting efficiency and security. Blockchain, with its inherent attributes of high scalability and secure distributed ledger system, coupled with AI's strengths in optimizing data processing and decision-making, holds the key to innovating the industry's approach to these issues. This study elucidates the synergistic interplay between Blockchain and AI, detailing how their fusion can drive a significant transformation in the supply chain finance sector's Distributed Systems. It offers specific use-cases within this field to illustrate the practical implications and potential benefits of this technological convergence. The study also discusses future possibilities and current challenges in implementing this groundbreaking approach within the context of supply chain finance. It concludes that the intersection of Blockchain and AI could ignite a new epoch of enhanced efficiency, security, and transparency in the Distributed Systems of supply chain finance within the financial industry.Keywords: blockchain, artificial intelligence (AI), scaled distributed systems, supply chain finance, efficiency and security
Procedia PDF Downloads 841962 A Hybrid Distributed Algorithm for Solving Job Shop Scheduling Problem
Authors: Aydin Teymourifar, Gurkan Ozturk
Abstract:
In this paper, a distributed hybrid algorithm is proposed for solving the job shop scheduling problem. The suggested method executes different artificial neural networks, heuristics and meta-heuristics simultaneously on more than one machine. The neural networks are used to control the constraints of the problem while the meta-heuristics search the global space and the heuristics are used to prevent the premature convergence. To attain an efficient distributed intelligent method for solving big and distributed job shop scheduling problems, Apache Spark and Hadoop frameworks are used. In the algorithm implementation and design steps, new approaches are applied. Comparison between the proposed algorithm and other efficient algorithms from the literature shows its efficiency, which is able to solve large size problems in short time.Keywords: distributed algorithms, Apache Spark, Hadoop, job shop scheduling, neural network
Procedia PDF Downloads 3821961 A New Distributed Computing Environment Based On Mobile Agents for Massively Parallel Applications
Authors: Fatéma Zahra Benchara, Mohamed Youssfi, Omar Bouattane, Hassan Ouajji, Mohamed Ouadi Bensalah
Abstract:
In this paper, we propose a new distributed environment for High Performance Computing (HPC) based on mobile agents. It allows us to perform parallel programs execution as distributed one over a flexible grid constituted by a cooperative mobile agent team works. The distributed program to be performed is encapsulated on team leader agent which deploys its team workers as Agent Virtual Processing Unit (AVPU). Each AVPU is asked to perform its assigned tasks and provides the computational results which make the data and team works tasks management difficult for the team leader agent and that influence the performance computing. In this work we focused on the implementation of the Mobile Provider Agent (MPA) in order to manage the distribution of data and instructions and to ensure a load balancing model. It grants also some interesting mechanisms to manage the others computing challenges thanks to the mobile agents several skills.Keywords: image processing, distributed environment, mobile agents, parallel and distributed computing
Procedia PDF Downloads 3991960 Distributed System Computing Resource Scheduling Algorithm Based on Deep Reinforcement Learning
Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar
Abstract:
As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling, and proposes the challenges and improvement directions for DRL-based resource scheduling algorithms.Keywords: resource scheduling, deep reinforcement learning, distributed system, artificial intelligence
Procedia PDF Downloads 1021959 Application of the Discrete Rationalized Haar Transform to Distributed Parameter System
Authors: Joon-Hoon Park
Abstract:
In this paper the rationalized Haar transform is applied for distributed parameter system identification and estimation. A distributed parameter system is a dynamical and mathematical model described by a partial differential equation. And system identification concerns the problem of determining mathematical models from observed data. The Haar function has some disadvantages of calculation because it contains irrational numbers, for these reasons the rationalized Haar function that has only rational numbers. The algorithm adopted in this paper is based on the transform and operational matrix of the rationalized Haar function. This approach provides more convenient and efficient computational results.Keywords: distributed parameter system, rationalized Haar transform, operational matrix, system identification
Procedia PDF Downloads 5021958 Parallel Querying of Distributed Ontologies with Shared Vocabulary
Authors: Sharjeel Aslam, Vassil Vassilev, Karim Ouazzane
Abstract:
Ontologies and various semantic repositories became a convenient approach for implementing model-driven architectures of distributed systems on the Web. SPARQL is the standard query language for querying such. However, although SPARQL is well-established standard for querying semantic repositories in RDF and OWL format and there are commonly used APIs which supports it, like Jena for Java, its parallel option is not incorporated in them. This article presents a complete framework consisting of an object algebra for parallel RDF and an index-based implementation of the parallel query engine capable of dealing with the distributed RDF ontologies which share common vocabulary. It has been implemented in Java, and for validation of the algorithms has been applied to the problem of organizing virtual exhibitions on the Web.Keywords: distributed ontologies, parallel querying, semantic indexing, shared vocabulary, SPARQL
Procedia PDF Downloads 196