Search results for: distributed%20computing
1957 Optimal Planning of Dispatchable Distributed Generators for Power Loss Reduction in Unbalanced Distribution Networks
Authors: Mahmoud M. Othman, Y. G. Hegazy, A. Y. Abdelaziz
Abstract:
This paper proposes a novel heuristic algorithm that aims to determine the best size and location of distributed generators in unbalanced distribution networks. The proposed heuristic algorithm can deal with the planning cases where power loss is to be optimized without violating the system practical constraints. The distributed generation units in the proposed algorithm is modeled as voltage controlled node with the flexibility to be converted to constant power factor node in case of reactive power limit violation. The proposed algorithm is implemented in MATLAB and tested on the IEEE 37 -node feeder. The results obtained show the effectiveness of the proposed algorithm.Keywords: distributed generation, heuristic approach, optimization, planning
Procedia PDF Downloads 5141956 Merging of Results in Distributed Information Retrieval Systems
Authors: Larbi Guezouli, Imane Azzouz
Abstract:
This work is located in the domain of distributed information retrieval ‘DIR’. A simplified view of the DIR requires a multi-search in a set of collections, which forces the system to analyze results found in these collections, and merge results back before sending them to the user in a single list. Our work is to find a fusion method based on the relevance score of each result received from collections and the relevance of the local search engine of each collection.Keywords: information retrieval, distributed IR systems, merging results, datamining
Procedia PDF Downloads 3291955 Technical and Economic Environment in the Polish Power System as the Basis for Distributed Generation and Renewable Energy Sources Development
Authors: Pawel Sowa, Joachim Bargiel, Bogdan Mol, Katarzyna Luszcz
Abstract:
The article raises the issue of the development of local renewable energy sources and the production of distributed energy in context of improving the reliability of the Polish Power System and the beneficial impact on local and national energy security. The paper refers to the current problems of local governments in the process of investment in the area of distributed energy projects, and discusses the issues of the future role and cooperation within the local power plants and distributed energy. Attention is paid to the local communities the chance to raise their own resources and management of energy fuels (biomass, wind, gas mining) and improving the local energy balance. The material presented takes the issue of the development of the energy potential of municipalities and future cooperation with professional energy. As an example, practical solutions used in one of the communes in Silesia.Keywords: distributed generation, mini centers energy, renewable energy sources, reliability of supply of rural commune
Procedia PDF Downloads 5941954 Screen Method of Distributed Cooperative Navigation Factors for Unmanned Aerial Vehicle Swarm
Authors: Can Zhang, Qun Li, Yonglin Lei, Zhi Zhu, Dong Guo
Abstract:
Aiming at the problem of factor screen in distributed collaborative navigation of dense UAV swarm, an efficient distributed collaborative navigation factor screen method is proposed. The method considered the balance between computing load and positioning accuracy. The proposed algorithm utilized the factor graph model to implement a distributed collaborative navigation algorithm. The GNSS information of the UAV itself and the ranging information between the UAVs are used as the positioning factors. In this distributed scheme, a local factor graph is established for each UAV. The positioning factors of nodes with good geometric position distribution and small variance are selected to participate in the navigation calculation. To demonstrate and verify the proposed methods, the simulation and experiments in different scenarios are performed in this research. Simulation results show that the proposed scheme achieves a good balance between the computing load and positioning accuracy in the distributed cooperative navigation calculation of UAV swarm. This proposed algorithm has important theoretical and practical value for both industry and academic areas.Keywords: screen method, cooperative positioning system, UAV swarm, factor graph, cooperative navigation
Procedia PDF Downloads 701953 MULTI-FLGANs: Multi-Distributed Adversarial Networks for Non-Independent and Identically Distributed Distribution
Authors: Akash Amalan, Rui Wang, Yanqi Qiao, Emmanouil Panaousis, Kaitai Liang
Abstract:
Federated learning is an emerging concept in the domain of distributed machine learning. This concept has enabled General Adversarial Networks (GANs) to benefit from the rich distributed training data while preserving privacy. However, in a non-IID setting, current federated GAN architectures are unstable, struggling to learn the distinct features, and vulnerable to mode collapse. In this paper, we propose an architecture MULTI-FLGAN to solve the problem of low-quality images, mode collapse, and instability for non-IID datasets. Our results show that MULTI-FLGAN is four times as stable and performant (i.e., high inception score) on average over 20 clients compared to baseline FLGAN.Keywords: federated learning, generative adversarial network, inference attack, non-IID data distribution
Procedia PDF Downloads 1501952 ROOP: Translating Sequential Code Fragments to Distributed Code Fragments Using Deep Reinforcement Learning
Authors: Arun Sanjel, Greg Speegle
Abstract:
Every second, massive amounts of data are generated, and Data Intensive Scalable Computing (DISC) frameworks have evolved into effective tools for analyzing such massive amounts of data. Since the underlying architecture of these distributed computing platforms is often new to users, building a DISC application can often be time-consuming and prone to errors. The automated conversion of a sequential program to a DISC program will consequently significantly improve productivity. However, synthesizing a user’s intended program from an input specification is complex, with several important applications, such as distributed program synthesizing and code refactoring. Existing works such as Tyro and Casper rely entirely on deductive synthesis techniques or similar program synthesis approaches. Our approach is to develop a data-driven synthesis technique to identify sequential components and translate them to equivalent distributed operations. We emphasize using reinforcement learning and unit testing as feedback mechanisms to achieve our objectives.Keywords: program synthesis, distributed computing, reinforcement learning, unit testing, DISC
Procedia PDF Downloads 931951 The Impacts of Local Decision Making on Customisation Process Speed across Distributed Boundaries
Authors: Abdulrahman M. Qahtani, Gary. B. Wills, Andy. M. Gravell
Abstract:
Communicating and managing customers’ requirements in software development projects play a vital role in the software development process. While it is difficult to do so locally, it is even more difficult to communicate these requirements over distributed boundaries and to convey them to multiple distribution customers. This paper discusses the communication of multiple distribution customers’ requirements in the context of customised software products. The main purpose is to understand the challenges of communicating and managing customisation requirements across distributed boundaries. We propose a model for Communicating Customisation Requirements of Multi-Clients in a Distributed Domain (CCRD). Thereafter, we evaluate that model by presenting the findings of a case study conducted with a company with customisation projects for 18 distributed customers. Then, we compare the outputs of the real case process and the outputs of the CCRD model using simulation methods. Our conjecture is that the CCRD model can reduce the challenge of communication requirements over distributed organisational boundaries, and the delay in decision making and in the entire customisation process time.Keywords: customisation software products, global software engineering, local decision making, requirement engineering, simulation model
Procedia PDF Downloads 4211950 Distribution Network Optimization by Optimal Placement of Photovoltaic-Based Distributed Generation: A Case Study of the Nigerian Power System
Authors: Edafe Lucky Okotie, Emmanuel Osawaru Omosigho
Abstract:
This paper examines the impacts of the introduction of distributed energy generation (DEG) technology into the Nigerian power system as an alternative means of energy generation at distribution ends using Otovwodo 15 MVA, 33/11kV injection substation as a case study. The overall idea is to increase the generated energy in the system, improve the voltage profile and reduce system losses. A photovoltaic-based distributed energy generator (PV-DEG) was considered and was optimally placed in the network using Genetic Algorithm (GA) in Mat. Lab/Simulink environment. The results of simulation obtained shows that the dynamic performance of the network was optimized with DEG-grid integration.Keywords: distributed energy generation (DEG), genetic algorithm (GA), power quality, total load demand, voltage profile
Procedia PDF Downloads 761949 The Impact of Distributed Epistemologies on Software Engineering
Authors: Thomas Smith
Abstract:
Many hackers worldwide would agree that, had it not been for linear-time theory, the refinement of Byzantine fault tolerance might never have occurred. After years of significant research into extreme programming, we validate the refinement of simulated annealing. Maw, our new framework for unstable theory, is the solution to all of these issues.Keywords: distributed, software engineering, DNS, DHCP
Procedia PDF Downloads 3471948 Distributed Multi-Agent Based Approach on Intelligent Transportation Network
Authors: Xiao Yihong, Yu Kexin, Burra Venkata Durga Kumar
Abstract:
With the accelerating process of urbanization, the problem of urban road congestion is becoming more and more serious. Intelligent transportation system combining distributed and artificial intelligence has become a research hotspot. As the core development direction of the intelligent transportation system, Cooperative Intelligent Transportation System (C-ITS) integrates advanced information technology and communication methods and realizes the integration of humans, vehicle, roadside infrastructure, and other elements through the multi-agent distributed system. By analyzing the system architecture and technical characteristics of C-ITS, the report proposes a distributed multi-agent C-ITS. The system consists of Roadside Sub-system, Vehicle Sub-system, and Personal Sub-system. At the same time, we explore the scalability of the C-ITS and put forward incorporating local rewards in the centralized training decentralized execution paradigm, hoping to add a scalable value decomposition method. In addition, we also suggest introducing blockchain to improve the safety of the traffic information transmission process. The system is expected to improve vehicle capacity and traffic safety.Keywords: distributed system, artificial intelligence, multi-agent, cooperative intelligent transportation system
Procedia PDF Downloads 2091947 Implementation of Distributed Randomized Algorithms for Resilient Peer-to-Peer Networks
Authors: Richard Tanaka, Ying Zhu
Abstract:
This paper studies a few randomized algorithms in application-layer peer-to-peer networks. The significant gain in scalability and resilience that peer-to-peer networks provide has made them widely used and adopted in many real-world distributed systems and applications. The unique properties of peer-to-peer networks make them particularly suitable for randomized algorithms such as random walks and gossip algorithms. Instead of simulations of peer-to-peer networks, we leverage the Docker virtual container technology to develop implementations of the peer-to-peer networks and these distributed randomized algorithms running on top of them. We can thus analyze their behaviour and performance in realistic settings. We further consider the problem of identifying high-risk bottleneck links in the network with the objective of improving the resilience and reliability of peer-to-peer networks. We propose a randomized algorithm to solve this problem and evaluate its performance by simulations.Keywords: distributed randomized algorithms, peer-to-peer networks, virtual container technology, resilient networks
Procedia PDF Downloads 2041946 Sync Consensus Algorithm: Trying to Reach an Agreement at Full Speed
Authors: Yuri Zinchenko
Abstract:
Recently, distributed storage systems have been used more and more in various aspects of everyday life. They provide such necessary properties as Scalability, Fault Tolerance, Durability, and others. At the same time, not only reliable but also fast data storage remains one of the most pressing issues in this area. That brings us to the consensus algorithm as one of the most important components that has a great impact on the functionality of a distributed system. This paper is the result of an analysis of several well-known consensus algorithms, such as Paxos and Raft. The algorithm it offers, called Sync, promotes, but does not insist on simultaneous writing to the nodes (which positively affects the overall writing speed) and tries to minimize the system's inactive time. This allows nodes to reach agreement on the system state in a shorter period, which is a critical factor for distributed systems. Also when developing Sync, a lot of attention was paid to such criteria as simplicity and intuitiveness, the importance of which is difficult to overestimate.Keywords: sync, consensus algorithm, distributed system, leader-based, synchronization.
Procedia PDF Downloads 541945 DOS and DDOS Attacks
Authors: Amin Hamrahi, Niloofar Moghaddam
Abstract:
Denial of Service is for denial-of-service attack, a type of attack on a network that is designed to bring the network to its knees by flooding it with useless traffic. Denial of Service (DoS) attacks have become a major threat to current computer networks. Many recent DoS attacks were launched via a large number of distributed attacking hosts in the Internet. These attacks are called distributed denial of service (DDoS) attacks. To have a better understanding on DoS attacks, this article provides an overview on existing DoS and DDoS attacks and major defense technologies in the Internet.Keywords: denial of service, distributed denial of service, traffic, flooding
Procedia PDF Downloads 3851944 Model-Free Distributed Control of Dynamical Systems
Authors: Javad Khazaei, Rick Blum
Abstract:
Distributed control is an efficient and flexible approach for coordination of multi-agent systems. One of the main challenges in designing a distributed controller is identifying the governing dynamics of the dynamical systems. Data-driven system identification is currently undergoing a revolution. With the availability of high-fidelity measurements and historical data, model-free identification of dynamical systems can facilitate the control design without tedious modeling of high-dimensional and/or nonlinear systems. This paper develops a distributed control design using consensus theory for linear and nonlinear dynamical systems using sparse identification of system dynamics. Compared with existing consensus designs that heavily rely on knowing the detailed system dynamics, the proposed model-free design can accurately capture the dynamics of the system with available measurements and input data and provide guaranteed performance in consensus and tracking problems. Heterogeneous damped oscillators are chosen as examples of dynamical system for validation purposes.Keywords: consensus tracking, distributed control, model-free control, sparse identification of dynamical systems
Procedia PDF Downloads 2611943 Considering the Reliability of Measurements Issue in Distributed Adaptive Estimation Algorithms
Authors: Wael M. Bazzi, Amir Rastegarnia, Azam Khalili
Abstract:
In this paper we consider the issue of reliability of measurements in distributed adaptive estimation problem. To this aim, we assume a sensor network with different observation noise variance among the sensors and propose new estimation method based on incremental distributed least mean-square (IDLMS) algorithm. The proposed method contains two phases: I) Estimation of each sensors observation noise variance, and II) Estimation of the desired parameter using the estimated observation variances. To deal with the reliability of measurements, in the second phase of the proposed algorithm, the step-size parameter is adjusted for each sensor according to its observation noise variance. As our simulation results show, the proposed algorithm considerably improves the performance of the IDLMS algorithm in the same condition.Keywords: adaptive filter, distributed estimation, sensor network, IDLMS algorithm
Procedia PDF Downloads 6251942 Impact of Series Reactive Compensation on Increasing a Distribution Network Distributed Generation Hosting Capacity
Authors: Moataz Ammar, Ahdab Elmorshedy
Abstract:
The distributed generation hosting capacity of a distribution network is typically limited at a given connection point by the upper voltage limit that can be violated due to the injection of active power into the distribution network. The upper voltage limit violation concern becomes more important as the network equivalent resistance increases with respect to its equivalent reactance. This paper investigates the impact of modifying the distribution network equivalent reactance at the point of connection such that the upper voltage limit is violated at a higher distributed generation penetration, than it would without the addition of series reactive compensation. The results show that series reactive compensation proves efficient in certain situations (based on the ratio of equivalent network reactance to equivalent network resistance at the point of connection). As opposed to the conventional case of capacitive compensation of a distribution network to reduce voltage drop, inductive compensation is seen to be more appropriate for alleviation of distributed-generation-induced voltage rise.Keywords: distributed generation, distribution networks, series compensation, voltage rise
Procedia PDF Downloads 3901941 Analysis of Importance of Culture in Distributed Design Based on the Case Study at the University of Strathclyde
Authors: Zixuan Yang
Abstract:
This paper presents an analysis of the necessary consideration culture in distributed design through a thorough literature review and case study. The literature review has identified that the need for understanding cultural differences in product design and user evaluations is highlighted by analyzing cross-cultural influences; culture plays a significant role in distributed work, particularly in establishing team cohesion, trust, and credibility early in the project. By applying approaches of Geert Hofstede's dimensions and Fukuyama's trust analysis, a case study of a global design project, i.e., multicultural distributed teamwork solving the problem in terms of reducing the risk of deep vein thrombosis, showcases cultural dynamics, emphasizing trust-building and decision-making. The lessons learned emphasized the importance of cultural awareness, adaptability, and the utilization of scientific theories to enable effective cross-cultural collaborations in global design, providing valuable insights into navigating cultural diversity within design practices.Keywords: culture, distributed design, global design, Geert Hofstede's dimensions, Fukuyama's trust analysis
Procedia PDF Downloads 591940 A Fast Parallel and Distributed Type-2 Fuzzy Algorithm Based on Cooperative Mobile Agents Model for High Performance Image Processing
Authors: Fatéma Zahra Benchara, Mohamed Youssfi, Omar Bouattane, Hassan Ouajji, Mohamed Ouadi Bensalah
Abstract:
The aim of this paper is to present a distributed implementation of the Type-2 Fuzzy algorithm in a parallel and distributed computing environment based on mobile agents. The proposed algorithm is assigned to be implemented on a SPMD (Single Program Multiple Data) architecture which is based on cooperative mobile agents as AVPE (Agent Virtual Processing Element) model in order to improve the processing resources needed for performing the big data image segmentation. In this work we focused on the application of this algorithm in order to process the big data MRI (Magnetic Resonance Images) image of size (n x m). It is encapsulated on the Mobile agent team leader in order to be split into (m x n) pixels one per AVPE. Each AVPE perform and exchange the segmentation results and maintain asynchronous communication with their team leader until the convergence of this algorithm. Some interesting experimental results are obtained in terms of accuracy and efficiency analysis of the proposed implementation, thanks to the mobile agents several interesting skills introduced in this distributed computational model.Keywords: distributed type-2 fuzzy algorithm, image processing, mobile agents, parallel and distributed computing
Procedia PDF Downloads 4191939 Genetic Algorithm Based Node Fault Detection and Recovery in Distributed Sensor Networks
Authors: N. Nalini, Lokesh B. Bhajantri
Abstract:
In Distributed Sensor Networks, the sensor nodes are prone to failure due to energy depletion and some other reasons. In this regard, fault tolerance of network is essential in distributed sensor environment. Energy efficiency, network or topology control and fault-tolerance are the most important issues in the development of next-generation Distributed Sensor Networks (DSNs). This paper proposes a node fault detection and recovery using Genetic Algorithm (GA) in DSN when some of the sensor nodes are faulty. The main objective of this work is to provide fault tolerance mechanism which is energy efficient and responsive to network using GA, which is used to detect the faulty nodes in the network based on the energy depletion of node and link failure between nodes. The proposed fault detection model is used to detect faults at node level and network level faults (link failure and packet error). Finally, the performance parameters for the proposed scheme are evaluated.Keywords: distributed sensor networks, genetic algorithm, fault detection and recovery, information technology
Procedia PDF Downloads 4481938 Throughput of Point Coordination Function (PCF)
Authors: Faisel Eltuhami Alzaalik, Omar Imhemed Alramli, Ahmed Mohamed Elaieb
Abstract:
The IEEE 802.11 defines two modes of MAC, distributed coordination function (DCF) and point coordination function (PCF) mode. The first sub-layer of the MAC is the distributed coordination function (DCF). A contention algorithm is used via DCF to provide access to all traffic. The point coordination function (PCF) is the second sub-layer used to provide contention-free service. PCF is upper DCF and it uses features of DCF to establish guarantee access of its users. Some papers and researches that have been published in this technology were reviewed in this paper, as well as talking briefly about the distributed coordination function (DCF) technology. The simulation of the PCF function have been applied by using a simulation program called network simulator (NS2) and have been found out the throughput of a transmitter system by using this function.Keywords: DCF, PCF, throughput, NS2
Procedia PDF Downloads 5701937 The Quotation-Based Algorithm for Distributed Decision Making
Authors: Gennady P. Ginkul, Sergey Yu. Soloviov
Abstract:
The article proposes to use so-called "quotation-based algorithm" for simulation of decision making process in distributed expert systems and multi-agent systems. The idea was adopted from the techniques for group decision-making. It is based on the assumption that one expert system to perform its logical inference may use rules from another expert system. The application of the algorithm was demonstrated on the example in which the consolidated decision is the decision that requires minimal quotation.Keywords: backward chaining inference, distributed expert systems, group decision making, multi-agent systems
Procedia PDF Downloads 3681936 Design of a 28-nm CMOS 2.9-64.9-GHz Broadband Distributed Amplifier with Floating Ground CPW
Authors: Tian-Wei Huang, Wei-Ting Bai, Yu-Tung Cheng, Jeng-Han Tsai
Abstract:
In this paper, a 1-stage 6-section conventional distributed amplifier (CDA) structure distributed power amplifier (DPA) fabricated in a 28-nm HPC+ 1P9M CMOS process is proposed. The transistor size selection is introduced to achieve broadband power matching and thus remains a high flatness output power and power added efficiency (PAE) within the bandwidth. With the inductive peaking technique, the high-frequency pole appears and the high-frequency gain is increased; the gain flatness becomes better as well. The inductive elements used to form an artificial transmission line are built up with a floating ground coplanar waveguide plane (CPWFG) rather than a microstrip line, coplanar waveguide (CPW), or spiral inductor to get better performance. The DPA achieves 12.6 dB peak gain at 52.5 GHz with 2.9 to 64.9 GHz 3-dB bandwidth. The Psat is 11.4 dBm with PAEMAX of 10.6 % at 25 GHz. The output 1-dB compression point power is 9.8 dBm.Keywords: distributed power amplifier (DPA), gain bandwidth (GBW), floating ground CPW, inductive peaking, 28-nm, CMOS, 5G.
Procedia PDF Downloads 721935 Concept, Modules and Objectives of the Syllabus Course: Small Power Plants and Renewable Energy Sources
Authors: Rade M. Ciric, Nikola L. J. Rajakovic
Abstract:
This paper presents a curriculum of the subject small power plants and renewable energy sources, dealing with the concept of distributed generation, renewable energy sources, hydropower, wind farms, geothermal power plants, cogeneration plants, biogas plants of agriculture and animal origin, solar power and fuel cells. The course is taught the manner of connecting small power plants to the grid, the impact of small generators on the distribution system, as well as economic, environmental and legal aspects of operation of distributed generators.Keywords: distributed generation, renewable energy sources, energy policy, curriculum
Procedia PDF Downloads 3521934 HPPDFIM-HD: Transaction Distortion and Connected Perturbation Approach for Hierarchical Privacy Preserving Distributed Frequent Itemset Mining over Horizontally-Partitioned Dataset
Authors: Fuad Ali Mohammed Al-Yarimi
Abstract:
Many algorithms have been proposed to provide privacy preserving in data mining. These protocols are based on two main approaches named as: the perturbation approach and the Cryptographic approach. The first one is based on perturbation of the valuable information while the second one uses cryptographic techniques. The perturbation approach is much more efficient with reduced accuracy while the cryptographic approach can provide solutions with perfect accuracy. However, the cryptographic approach is a much slower method and requires considerable computation and communication overhead. In this paper, a new scalable protocol is proposed which combines the advantages of the perturbation and distortion along with cryptographic approach to perform privacy preserving in distributed frequent itemset mining on horizontally distributed data. Both the privacy and performance characteristics of the proposed protocol are studied empirically.Keywords: anonymity data, data mining, distributed frequent itemset mining, gaussian perturbation, perturbation approach, privacy preserving data mining
Procedia PDF Downloads 4991933 Relay Mining: Verifiable Multi-Tenant Distributed Rate Limiting
Authors: Daniel Olshansky, Ramiro Rodrıguez Colmeiro
Abstract:
Relay Mining presents a scalable solution employing probabilistic mechanisms and crypto-economic incentives to estimate RPC volume usage, facilitating decentralized multitenant rate limiting. Network traffic from individual applications can be concurrently serviced by multiple RPC service providers, with costs, rewards, and rate limiting governed by a native cryptocurrency on a distributed ledger. Building upon established research in token bucket algorithms and distributed rate-limiting penalty models, our approach harnesses a feedback loop control mechanism to adjust the difficulty of mining relay rewards, dynamically scaling with network usage growth. By leveraging crypto-economic incentives, we reduce coordination overhead costs and introduce a mechanism for providing RPC services that are both geopolitically and geographically distributed.Keywords: remote procedure call, crypto-economic, commit-reveal, decentralization, scalability, blockchain, rate limiting, token bucket
Procedia PDF Downloads 501932 A Query Optimization Strategy for Autonomous Distributed Database Systems
Authors: Dina K. Badawy, Dina M. Ibrahim, Alsayed A. Sallam
Abstract:
Distributed database is a collection of logically related databases that cooperate in a transparent manner. Query processing uses a communication network for transmitting data between sites. It refers to one of the challenges in the database world. The development of sophisticated query optimization technology is the reason for the commercial success of database systems, which complexity and cost increase with increasing number of relations in the query. Mariposa, query trading and query trading with processing task-trading strategies developed for autonomous distributed database systems, but they cause high optimization cost because of involvement of all nodes in generating an optimal plan. In this paper, we proposed a modification on the autonomous strategy K-QTPT that make the seller’s nodes with the lowest cost have gradually high priorities to reduce the optimization time. We implement our proposed strategy and present the results and analysis based on those results.Keywords: autonomous strategies, distributed database systems, high priority, query optimization
Procedia PDF Downloads 5171931 Researching Apache Hama: A Pure BSP Computing Framework
Authors: Kamran Siddique, Yangwoo Kim, Zahid Akhtar
Abstract:
In recent years, the technological advancements have led to a deluge of data from distinctive domains and the need for development of solutions based on parallel and distributed computing has still long way to go. That is why, the research and development of massive computing frameworks is continuously growing. At this particular stage, highlighting a potential research area along with key insights could be an asset for researchers in the field. Therefore, this paper explores one of the emerging distributed computing frameworks, Apache Hama. It is a Top Level Project under the Apache Software Foundation, based on Bulk Synchronous Processing (BSP). We present an unbiased and critical interrogation session about Apache Hama and conclude research directions in order to assist interested researchers.Keywords: apache hama, bulk synchronous parallel, BSP, distributed computing
Procedia PDF Downloads 2431930 Research on Control Strategy of Differential Drive Assisted Steering of Distributed Drive Electric Vehicle
Authors: J. Liu, Z. P. Yu, L. Xiong, Y. Feng, J. He
Abstract:
According to the independence, accuracy and controllability of the driving/braking torque of the distributed drive electric vehicle, a control strategy of differential drive assisted steering was designed. Firstly, the assisted curve under different speed and steering wheel torque was developed and the differential torques were distributed to the right and left front wheels. Then the steering return ability assisted control algorithm was designed. At last, the joint simulation was conducted by CarSim/Simulink. The result indicated: the differential drive assisted steering algorithm could provide enough steering drive-assisted under low speed and improve the steering portability. Along with the increase of the speed, the provided steering drive-assisted decreased. With the control algorithm, the steering stiffness of the steering system increased along with the increase of the speed, which ensures the driver’s road feeling. The control algorithm of differential drive assisted steering could avoid the understeer under low speed effectively.Keywords: differential assisted steering, control strategy, distributed drive electric vehicle, driving/braking torque
Procedia PDF Downloads 4731929 The AI Arena: A Framework for Distributed Multi-Agent Reinforcement Learning
Authors: Edward W. Staley, Corban G. Rivera, Ashley J. Llorens
Abstract:
Advances in reinforcement learning (RL) have resulted in recent breakthroughs in the application of artificial intelligence (AI) across many different domains. An emerging landscape of development environments is making powerful RL techniques more accessible for a growing community of researchers. However, most existing frameworks do not directly address the problem of learning in complex operating environments, such as dense urban settings or defense-related scenarios, that incorporate distributed, heterogeneous teams of agents. To help enable AI research for this important class of applications, we introduce the AI Arena: a scalable framework with flexible abstractions for distributed multi-agent reinforcement learning. The AI Arena extends the OpenAI Gym interface to allow greater flexibility in learning control policies across multiple agents with heterogeneous learning strategies and localized views of the environment. To illustrate the utility of our framework, we present experimental results that demonstrate performance gains due to a distributed multi-agent learning approach over commonly-used RL techniques in several different learning environments.Keywords: reinforcement learning, multi-agent, deep learning, artificial intelligence
Procedia PDF Downloads 1501928 Distributed Perceptually Important Point Identification for Time Series Data Mining
Authors: Tak-Chung Fu, Ying-Kit Hung, Fu-Lai Chung
Abstract:
In the field of time series data mining, the concept of the Perceptually Important Point (PIP) identification process is first introduced in 2001. This process originally works for financial time series pattern matching and it is then found suitable for time series dimensionality reduction and representation. Its strength is on preserving the overall shape of the time series by identifying the salient points in it. With the rise of Big Data, time series data contributes a major proportion, especially on the data which generates by sensors in the Internet of Things (IoT) environment. According to the nature of PIP identification and the successful cases, it is worth to further explore the opportunity to apply PIP in time series ‘Big Data’. However, the performance of PIP identification is always considered as the limitation when dealing with ‘Big’ time series data. In this paper, two distributed versions of PIP identification based on the Specialized Binary (SB) Tree are proposed. The proposed approaches solve the bottleneck when running the PIP identification process in a standalone computer. Improvement in term of speed is obtained by the distributed versions.Keywords: distributed computing, performance analysis, Perceptually Important Point identification, time series data mining
Procedia PDF Downloads 424