Search

Fernando Corbato is best known for his work developing time-sharing operating systems. Early in his career, Corbato had a key role in the development of both the Compatible Time-Sharing System (CTSS) and Multics at the Massachusetts Institute of Technology in the 1960s. In 1990, Corbato received the Turing Award "for his pioneering work in organizing the concepts and leading the development of the general-purpose, large-scale, time-sharing and resource-sharing computer systems," and he was made a fellow of the Computer History Museum (CHM) in 2012. This interview is the first in a two-part Annals series based on an oral history conducted by Steven Webber for the CHM in February 2006.

Round Robin scheduling algorithm is the widely used scheduling algorithm in multitasking. It ensures fairness and starvation free execution of processes. It performs optimally for time sharing systems, but because of its larger waiting time, turnaround time and greater number of context switches it is not suitable for soft real time systems. The main objective of this paper is to develop a way in which the Round Robin algorithm can be modified for implementation in real time and embedded systems by minimizing its average waiting time, average turnaround time and context switching rate. The paper discusses a fuzzy based CPU scheduling algorithm. A set of fuzzy rules is defined. Each process is assigned a new priority based on its externally defined priority, relative remaining CPU burst time and relative waiting time. General Terms Algorithms, CPU scheduling

In operating system is an important issue, Allocates processor time to processes, to be fair. We presented in This paper proposed methods to reduce Average waiting time, average response time, Switch Counts process, through the design of a time sharing non-exclusive scheduling algorithm based on the round Robin and determined accurate time quantum . Among the proposed approaches, weight harmonic- dynamic weight and Subtraction Method are achieved better and more accurate results.

Comparing today's control rooms or cockpits to those of about 30 years ago clearly shows huge differences in hard- and software, making changes in psychological requirements more than reasonable. To identify changes in ability requirements for operators in future aviation is of some concern when learning about solutions envisaged with large scale programs like NextGen or SESAR. However, as systems evolve step by step and sometimes without much notice, it might be that in retrospect requirement changes are assessed as being only of minor magnitude, whereas prospective ratings tend to over-interpret changes as they might be perceived as endangering one's competence and routines. In this study, it is reported what more than 300 air traffic controllers and pilots described as perceived changes in ability requirements when comparing today's aircraft or system with the one they have been trained for initially. Results were showing different pictures for the professions compared; however operational monitoring, information ordering, selective attention, time sharing and vigilance were always among the requirements with the highest perceived changes since initial training. Results will help to increase the understanding of past changes in ability requirements as perceived by job incumbents.

Electric vehicle time-sharing is for the users’ travel and distance which is short, and for improving the efficiency of the traffic. Based on questionnaire suevey, interview and the Analytic Hierarchy Process (AHP), this paper constructed an analysis model of three hierachies (vehicles, operators and transaction) to identify the difference between several business models, so as to evaluate the innovation of electric vehicle time-sharing rental business model. At last, suggetions and measurements are provided to improve electric vehicle time-sharing rental.

The use of low power PV string inverters, up to a few kW, has been gaining popularity for small scale applications. In this paper a new transformerless PV string inverter is proposed. This inverter makes use of the inversion stage as an unfolding inverter for high output voltages, and a high switching frequency inverter at low voltages and low current, thus achieving a highly efficient operation. The control of the system is performed by a MPC scheme, which allows the use of a reduced dc-link capacitor. Simulations are presented for a 750VDc 5.6kW 220V rms PV string inverter, showing good results for the proposed inverter and control. Compared with a classical two stage inverter, the proposed PV string inverter presents up to 0.8% higher efficiency for high power operating points, with a maximum simulated efficiency of 96.9%.

Heterogeneous computing platforms including both processors and field programmable gate arrays (FPGAs) represent an attractive solution for balancing software flexibility with high performance and energy efficiency of custom hardware modules. Furthermore, the dynamic partial reconfiguration (DPR) capabilities of modern FPGAs allow virtualizing the available area to support several hardware modules in time sharing, hence making them even more attractive. Such a feature is exploited by the FRED framework, recently proposed to support the development of real-time applications upon such platforms. This paper presents an implementation of the FRED framework for the Linux operating system over the Zynq-7000 platform produced by Xilinx. Design solutions for managing hardware accelerators are first discussed. Then, a software architecture for Linux is presented, which comprises (i) support for shared-memory communication with hardware accelerators, (ii) an improved driver to handle the FPGA reconfiguration and (iii) a scheduler for requests of hardware acceleration. The proposed solution allows exploiting the enormous number of software systems available for Linux (such as drivers, libraries, communication stacks, etc.) and the typical programming flexibility of software, while relying on predictable hardware acceleration of heavy computations.

Sharing the Autonomous Vehicles (AV) has the potential to be the ultimate solution for overcoming the cost problem of these type of vehicles to fundamentally change the transportation systems. AVs enable the time sharing services where AV owners share their AVs at the times they don't need them. Such sharing could reduce the cost by enabling the owner to share the cost of the vehicle with other users. However, these services raise a severe privacy concern as the shared location and route data of the users are considered highly private and sensitive. In this paper we propose a privacy- preserving time-sharing scheme for AVs. Our approach enables the owner and the requester to perform a privacy-preserving matching on their transportation needs over the server without disclosing their routes to the server. To do so we use a set of Points of Interest (POI) locations as intermediate destinations in travel paths. Only if the matching is conflict-free and efficient, the owner and the requester share the details of the routes. We also show the accuracy of the proposed approach through extensive simulations on real data. It is shown that our enhanced POI selection scheme, with consideration of the traffic information and patterns in the area, outperforms the baseline scheme where the POIs are chosen randomly. Furthermore, it shows that our scheme achieves high accuracy in terms of resulting in false negatives compared to the ground truth.

This paper proposes a measurement-based method to estimate application (APP) specific EMI on a device running a time-sharing multi-tasking operating system (OS). The proposed method includes a near-field measurement technique for APP-specific EMI and an algorithm which can estimate system EMI with any different APPs execution sequences. Because of the task-scheduling feature, the execution order of APPs inside a system is dependent on various factors. Thus, the EMI estimation of such system may be complex. In this paper, the proposed method selects an OS and two APPs as a case study. The OS used in this paper is an open-source OS for robotic control with a commercial microcontroller. The measurement results show good agreements in the different execution orders of these 2 APPs. From 40MHz (system clock rate) up to 1GHz, the maximum difference is 4 dB within the range. This method can be used to estimate near field EMI of a complex HW/SW system.

Heterogeneous system-on-chips (SoC) that include both general-purpose processors and field programmable gate arrays (FPGAs) are emerging as very promising platforms to develop modern cyber-physical systems, combining the typical flexibility enabled by software with the speedup achievable by custom hardware accelerators. Furthermore, the dynamic partial reconfiguration (DPR) capabilities of modern FPGAs make such platforms even more attractive, offering the possibility of virtualizing the FPGA area to support several hardware accelerators in time sharing. However, heterogeneous platforms originate considerable challenges in the design and development process of applications, especially if timing and energy constraints are concerned. The FRED framework has been recently proposed to support the development of real-time applications upon such platforms, using a static slotted-based partitioning of the FPGA area to ensure predictable delays when managing custom hardware accelerators by DPR. This paper addresses the problem of designing a suitable FPGA partitioning to support the execution of a real-time application within the FRED framework. The problem is formulated as a mixed-integer linear program that is in charge of (i) designing the size of the slots (in terms of FPGA resources), (ii) allocating hardware tasks to the slots, and (iii) selecting which hardware tasks must be statically allocated to the FPGA, while ensuring bounded worst-case response times on the tasks.

It is generally accepted that future supercomputing workloads will consist of application compositions made up of coupled simulations as well as in-situ analytics. While these components have commonly been deployed using a space-shared configuration to minimize cross-workload interference, it is likely that not all the workload components will require the full processing capacity of the CPU cores they are running on. For instance, an analytics workload often does not need to run continuously and is not generally considered to have the same priority as simulation codes. In a space-shared configuration, this arrangement would lead to wasted resources due to periodically idle CPUs, which are generally unusable by traditional bulk synchronous parallel (BSP) applications. As a result, many have started to reconsider task based runtimes owing to their ability to dynamically utilize available CPU resources. While the dynamic behavior of task-based runtimes had historically been targeted at application induced load imbalances, the same basic situation arises due to the asymmetric performance resulting from time sharing a CPU with other workloads. Many have assumed that task based runtimes would be able to adapt easily to these new environments without significant modifications. In this paper, we present a preliminary set of experiments that measured how well asynchronous task-based runtimes are able to respond to load imbalances caused by the asymmetric performance of time shared CPUs. Our work focuses on a set of experiments using benchmarks running on both Charm++ and HPX-5 in the presence of a competing workload. The results show that while these runtimes are better suited at handling the scenarios than traditional runtimes, they are not yet capable of effectively addressing anything other than a fairly minimal level of CPU contention.

A bi-level multi-objective environmental economic dispatch model with wind farms is established based on decomposition coordination principle and users’ side resources. Considering the level of system load and users’ satisfaction degree, a multi-objective optimization mathematical model was established to determine fitting load of the system and time sharing price. Considering the randomness of wind power output, a multi-objective environmental economic dispatch model is established to determine the generation plan. A hybrid universal gravitation algorithm and tabu search algorithm is proposed to solve the model. The optimal scheduling scheme is determined by the method of approximate ideal solution based on entropy weight. Simulation results show that: Considering the influence of resources of source side in the scheduling process not only can improve load level of the system operation, the satisfaction of using electricity and absorptive capacity of wind power, but also can effectively in reduce the generation costs and pollution emissions.

This paper proposed an enhanced control method for multiple-input converters (MICs). Previously, the control design represents a major difficulty in MIC designs, primarily because MICs are naturally multiple-input-multiple-output (MIMO) control systems. As a result, a complex MIMO controller is generally required for an MIC. The proposed control design approach stands out from conventional ones due to its easiness especially for relatively complicated topologies. The proposed control scheme uses a demultiplexing stage in the loop to simplify the MIC control design. Consequently, the system to be controlled becomes a much simplified single-input-single-output system. Simulated and experimental results show that the proposed scheme is superior in its simplicity and compatibility with common control concepts such as bode diagram, crossover frequency, and phase margin. Simulated and experimental results are presented in this paper to verify the analysis.

Thread based programs are known to increase the efficiency of complex operations. Threading eases a load of GUI thread (main thread) thus improving the performance of the system. Keeping the above features of threading in mind, the present study focusses on multi-threaded based quick sort and is compared with sequential quick sort. Multithreading quick sort has shown greater efficiency over sequential quick sort and the results are validated using various performance metrics like % idle time, % maximum frequency, % processor utility, % processor time and total execution time.

Digital 3D models and their visualizations are increasingly being used in many fields of research, engineering design and humanities. They enable people to see objects in perspectives not available in 2D images. It would be useful if a group of people in a classroom, laboratory or across distances can collaboratively discuss their observations drawn using 3D models. We describe a simple system that allows a group of people to share in real-time their views of a 3D model using their devices ranging from mobile phones to large video walls. We evaluated the system performance and usability with 3D models of digitized cultural heritage objects.

International audience; Lattice codes used under the Compute-and-Forward paradigm suggest an alternative strategy for the standard Gaussian multiple-access channel (MAC). It has been proven that decoding an integer linear combination of the transmitted codewords enables higher data rates compared to decoding the messages individually. Recent work of Gasptar et al. proposed a new multiple access channel technique that they called Compute-and-Forward Multiple Access Channel (CFMA). The authors proved that, in the case of a two-user MAC and without time sharing, the entire capacity region is achieved using CFMA and a single-user decoder for signal to noise ratios above 1 + √ 2. Throughout this paper, we will work within the Compute-and-Forward framework. The strategy relies on lattice codes, here we will construct lattices using a multi-level coding based construction called construction D. To decode the lattice points, a multi-stage decoder (MSD) should be implemented at the receiver part. In this paper, we propose a new decoding strategy that helps to perform the standard MSD algorithm in a less complex way. The new technique is called Binary Subchannel Decomposition (BSCD). Since, we make use of MSD, we need at each level of the decoder to compute soft-inputs: Log-Likelihood ratios. However the calculations are very complex since we must compute infinite sums of exponentials at each stage. Hereinafter we give efficient LLR approximation for multi-stage decoders. Simulation results about the performance of BSCD are included and compared to the performance of the standard multi-stage decoder.

Computer science is a field that keeps evolving at a very fast pace, requiring everyone in this industry to keep up to date on the latest technological advancements. In recent history, this industry has welcomed new technologies such as distributed computing, parallel processing, virtualization, cloud computing, and, most recently, the Internet of Things (IoT). Each technology paves the way for the next and helps to build a strong foundation for others. For example, virtualization revolutionized and built the basis for cloud computing. It has been common practice to use computers with maximum resource utilization from the beginning when computers were invented, whether via time sharing, multitasking, or the recent virtualization trends.

Several techniques have been proposed to improve the performance of Parallel Discrete Event Simulation platforms relying on the Time Warp (optimistic) synchronization protocol. Among them we can mention optimized approaches for state restore, as well as techniques for load balancing or (dynamically) controlling the speculation degree, the latter being specifically targeted at reducing the incidence of causality errors leading to waste of computation. However, in state-of-the-art Time Warp systems, events’ processing is not preemptable, which may prevent the possibility to promptly react to the injection of higher priority (say, lower timestamp) events. Delaying the processing of these events may, in turn, give rise to higher incidence of incorrect speculation. In this article, we present the design and realization of a fine-grain time-sharing Time Warp system, to be run on multi-core Linux machines, which makes systematic use of event preemption in order to dynamically reassign the CPU to higher priority events/tasks. Our proposal is based on a truly dual mode execution, application versus platform, which includes a timer-interrupt-based support for bringing control back to platform mode for possible CPU reassignment according to very fine grain periods. The latter facility is offered by an ad-hoc timer-interrupt management module for Linux, which we release, together with the overall time-sharing support, within the open source ROOT-Sim platform. An experimental assessment based on the classical PHOLD benchmark and two real-world models is presented, which shows how our proposal effectively leads to the reduction of the incidence of causality errors, especially when running with higher degrees of parallelism.

On-line evolution of robot controllers allows robots to adapt while they perform their proper tasks. In our investigations, robots contain their own self-sufficient evolutionary algorithm (known as the encapsulated approach) where individual solutions are evaluated by means of a time sharing scheme: an individual controller is given the run of the robot for some amount of time and fitness corresponds to the robot’s task performance during that period. In this paper, we propose and provide a detailed analysis of two on-the-fly control schemes to set the evaluation time in highly dynamic scenarios with completely different tasks. One scheme, called the roulette-wheel selection scheme, stochastically selects evaluation time from promising intervals similar to multi-armed bandit schemes. The other scheme, named Heuristic-Rule (H-Rule), tweaks the evaluation time using specific heuristics. Our experiments show that H-Rule gives stable performance in different scenarios and can serve as a viable alternative to pre-selected optimal evaluation time.

The author reflects on his career in the computing world, specifically his work in early time-sharing system development, and the almost accidental steps that put him in touch with some of the technical giants of the industry in Berkeley and then led to his years at Norsk Data in Norway. He explains how his contribution to ND with regard to operating system technology contributed significantly to the company's astonishing growth.

We characterize the Pareto boundary of the achiev- able rate region of the two-user symmetric Gaussian interference channel when transmitters control their transmission power and receivers have successive interference cancelation capability. By identifying the shape of achievable rate region according to the strength of interference channels, we find combinations of decod- ing and power allocation strategies achieving the Pareto boundary. We also characterize the Pareto boundary of the achievable rate region when time sharing is additionally considered. Index Terms—Interference channel, achievable rate region, Pareto boundary, successive interference cancelation.

In the early 1960s, the time-sharing computer at the System Development Corporation had several messaging commands through which remotely logged in users communicated with one another and with the system operator. These commands were used for system operation and for sending information to remote users. They also permitted collaborative work such as joint debugging of multi-author programs, an activity now associated with the Internet. These capabilities appear to be the earliest documented implementation of text messaging and were in use before electronic mail was developed for time-sharing systems.

Graphics processing units (GPUs) are extensively used as accelerators across multiple application domains, ranging from general purpose applications to neural networks, and cryptocurrency mining. The initial utilization paradigm for GPUs was one application accessing all the resources of the GPU. In recent years, time sharing is broadly used among applications of a GPU, nevertheless, spatial sharing is not fully explored. When concurrent applications share the computational resources of a GPU, performance can be improved by eliminating idle resources. Additionally, the incorporation of GPUs in embedded and mobile devices increases the demand for power efficient computation due to battery limitations. In this article, we present an allocation methodology for streaming multiprocessors (SMs). The presented methodology works for two concurrent applications on a GPU and determines an allocation scheme that will provide power efficient application execution, combined with improved GPU performance. Experimental results show that the developed methodology yields higher throughput while achieving improved power efficiency, compared to other SM power-aware and performance-aware policies. If the presented methodology is adopted, it will lead to higher performance of applications that are concurrently executing on a GPU. This will lead to a faster and more efficient acceleration of execution, even for devices with restrained energy sources.

MIM Tegalampel is one of primary school in Klaten Regency which is pioneering the special program of the Science Olympiad (OSN). The purpose of this community service program is to provide knowledge and skills to teachers of MIM Tegalampel so they can identify the types of OSN material, apply several mastery strategies for OSN material, as well as solve OSN problems quickly and accurately. The method used is the method of enrichment, demonstration and try out. The evaluation of the implementation of this community service consisted of an initial evaluation in the form of a pre-test, the final evaluation in the form of a post-test, as well as an evaluation of the implementation. Based on the result of the workshop for teachers of MIM Tegalampel, it can be concluded that in general the participants considered the workshop scheduling to be appropriate, time sharing was appropriate, the balance between theory and practice was also appropriate. Participants considered most of the expectations and objectives of the workshop had been fulfilled. The evaluation result showed that participants had increased skills in identifying the types of OSN material. There was also an increase in the skills of participants in completing OSN problems. In addition, participants can apply several mastery strategies for OSN material.

10019 Background: As tumor and germline genomic data from pediatric cancer patients is scarce in existing genomic databases, there is an urgent need for more comprehensive datasets. Such data will allow us to fully assess the actionable pediatric cancer genome, facilitate biomarker discovery, and identify new clinical associations. Methods: We sequenced 1002 tumor/normal pairs as part of a real-time clinical genomics service including whole genome, exome and transcriptome for 775 and exome/transcriptome for 227 samples. Tumor types were representative of the common and rare diseases treated at our institution (37% hematological, 31% brain and 32% solid tumors). A multidisciplinary team assessed every case, and after clinical reporting was complete, genomics data and basic clinical information (primary diagnosis, age, sex, ethnicity, primary/relapse/metastasis status), was made securely available online through St. Jude Cloud (www.stjude.cloud). Results: Based on analysis of 253 initial cases from the Genomes for Kids study, our multi-platform sequencing approach uncovered diagnostic, prognostic and/or therapeutically relevant findings in 78% of patients. We estimate 11-16% of clinically-relevant gene mutations could be missed by less comprehensive sequencing approaches. One quarter of patients had a potentially druggable mutation. This surprisingly high proportion was driven, in part, by BRAF fused low-grade gliomas and diverse JAK/STAT pathway alterations in B-Cell acute lymphoblastic leukemias. Whole genome/transcriptome sequencing allowed us to detect rare and novel gene fusions in 8% of cases and facilitated discovery of a new recurrent fusion gene in pediatric melanoma. All data is available online for others to mine and it is likely that additional clinically-relevant mutations can be uncovered. Conclusions: These data demonstrate the value of incorporating comprehensive sequencing into clinical diagnostics and patient care. We endeavor to make this large and richly annotated dataset available to others in real time rather than holding it back for months or years until publication. We anticipate adding approximately 500 additional cases per year at regular intervals, and as the resource grows, expect users to identify new targetable alterations that may be incorporated into patient care.

Fluorescent magnetic nanoparticles (f-MNPs) show potential as magnetic labels for detection of biomarkers, with their magnetic properties enhancing biomolecular interaction with external magnetic manipulation and fluorescence enabling optical detection of individual nanometer particles. These features translate into improvements in speed of detection, sensitivity, and low cost when both fluorescent and magnetic properties are utilized for biomarker detection. Specifically, f-MNPs show tremendous potential for developing smartphone based real-time diagnostic systems for monitoring potentially infectious diseases in remote areas, which is important for public healthcare to prevent epidemics, where rapid and sensitive medical diagnostic protocols designed to not only detect biomarkers but also to enable real-time information sharing are critical. We describe a new approach to biosensing by combining the advantages of magnetic and optical detection f-MNPs with the fluorescent imaging capabilities of CCD cameras of smartphones and the information sharing with cloud computing technology. Our protocol is designed to not only provide rapid sensing but also enable real-time sharing of medical diagnostics information between healthcare professionals and remote patients. As a feasibility study, we demonstrate the use of f-MNPs functionalized with prostate specific antigen (PSA) which is detected via the interactions of f-MNPs with the antibody coated silicon oxide surface. Images of 'dry samples' were obtained with a smartphone and analysed remotely with dedicated image processing programs on a cloud computer. Our approach enabled the detection of 100 pg ml−1 PSA in less than 60 s, which is an order of magnitude lower than the sensitivity required for clinical detection of PSA in public healthcare.

The problem of optimal channel sensing in heterogeneous cognitive networks is considered to maximize the system throughput performance. The characteristics of an optimal operating sensing point maximizing the overall system rate are investigated under several rate criteria including the sum rate, the minimum of the primary and secondary rates, and the secondary rate with a guaranteed primary rate. Under the sum rate criterion, it is shown that the loss by imperfect sensing is no greater than half of the sum rate achieved by the perfect time sharing approach in a two user case if the sensing point is optimally designed.

Cataloged from PDF version of article. In this correspondence, we study the convexity properties for the problem of detecting the presence of a signal emitted from a power constrained transmitter in the presence of additive Gaussian noise under the Neyman-Pearson (NP) framework. It is proved that the detection probability corresponding to the α-level likelihood ratio test (LRT) is either strictly concave or has two inflection points such that the function is strictly concave, strictly convex, and finally strictly concave with respect to increasing values of the signal power. In addition, the analysis is extended from scalar observations to multidimensional colored Gaussian noise corrupted signals. Based on the convexity results, optimal and near-optimal time sharing strategies are proposed for average/peak power constrained transmitters and jammers. Numerical methods with global convergence are also provided to obtain the parameters for the proposed strategies. © 1991-2012 IEEE

This paper explores the feasibility of active clamping techniques in isolated time-sharing (TS) multiple-input converters (MICs). Additional losses caused by energy transfer from the leakage inductance in the isolating coupled-inductor into the input switches are addressed with a common active clamping leg for all input legs. An active clamping technique is applied to isolated TS-MIC to minimize the additional switching losses and voltage stresses on input legs. This paper also conducts an operational analysis of an isolated time-sharing dual-input single-ended primary-inductor converter (I-TS-DI-SEPIC) with the discussed active clamping technique. Zero-voltage switching can be achieved on the first-turned-on input leg and the active clamping leg with a proper driving strategy and well-chosen circuit parameter settings. Discussions on the effect of the active clamping technique to an MIC and the components stresses of the I-TS-DI-SEPIC with the active clamping technique have also been made to assist in the design of TS-MICs. Prototypes of the I-TS-DI-SEPIC with the active clamping technique have been built to demonstrate the performance in the application of split-phase dc distribution systems. Converter efficiency and voltage stresses are experimentally verified, showing that the active clamping technique achieves noticeable efficiency gains and component stress reduction.

This account of the evolution of time-shared microcomputers, often overlooked members of the microcomputer industry, looks at articles and advertisements that appeared in Byte magazine from 1977 to 1983. The author's quantitative and qualitative analysis reveals that time-shared microcomputers attempted to combine the best aspects of microcomputer and mini-computer/mainframe technologies and, for a time, were a considerable, important part of the microcomputer industry.

© 2016 IEEE. HPC facilities typically use batch scheduling to space-share jobs. In this paper we revisit time-sharing using a trace of over 2.4 million jobs obtained during 20 months of operation of a modern petascale supercomputer. Our simulations show that batch scheduling produces skewed distributions with much larger slowdowns for shorter-running, larger jobs, whereas time-sharing produces more uniform slowdowns. Consequently, for applications that strong scale, the turnaround time does not scale with batch scheduling, but it does with time-sharing, resulting in turnarounds that are orders of magnitude better at the largest scales. We also show that time-sharing can confer additional benefits in noisy systems and with modern programming practices. Future Exascale HPC systems are expected to exhibit billion-way heterogeneous parallelism and poor performance predictability. As many applications will run in strong scaling, how resource allocation policies affect the experience of supercomputer users has once again become a timely subject.

Throughput of the system in multiprogramming and time sharing systems mainly depends on the careful scheduling of the CPU and other I/O devices. CPU scheduling should control the waiting time, response time, turnaround time, and number of context switches. One of the most extensively used scheduling algorithms is shortest next remaining time first (SRTF), which gives the reduced amount of average waiting time. But this algorithm suffers from some drawbacks. One such is that, every upcoming process if selected for execution, causes a context switch even though it is slightly shorter than the currently running process. As the number of such situations increases, the number of context switches increases, causing the reduction in performance of the system. In this paper, we modify the traditional SRTF to intelligent SRTF, by changing the decision of the preemption, to decrease the number of context switches. The main idea of our proposed algorithm is to make a context switch only if the next process plus context switch over head is shorter than the currently running process. By this we can reduce the number of context switches and thereby the performance of the system is improved.

Differential power processing (DPP) has demonstrated its significant advantage of high system efficiency for photovoltaic (PV) applications especially in mismatch conditions. In this paper, a sub-module DPP based PV optimizer using a self-adjusted time-sharing maximum power point tracking (MPPT) control strategy is proposed, which can achieve fast and accurate tracking of all sub-modules' maximum power points (MPPs) with only one MPPT controller, facilitating system integration and largely reducing system cost and conversion loss. The effectiveness of the proposed solution is verified by both simulation and experiments.

With limited experiment devices and high arrival rate of requests, it is difficult for a remote control laboratory to satisfy all experiment requests within short period of time. This paper proposes a general device sharing scheme based on concurrent time-sharing to solve such problem in embedded experiments scenario. It has been verified that, under certain preconditions, such approach is feasible and effective to enhance the utilization rate of experiment devices, thus increasing the quality of services of remote control laboratory.

Laser tracker as a three-dimensional measuring instrument has been widely used in industrial measurement. To further improve the measurement accuracy of the laser tracker, the multi-station and time-sharing measurement is adopted. This method is based on GPS principle, and only distance is involved in the measurement to avoid the impact of error caused by angle measurement on the overall measurement accuracy. Taking the detection of motion accuracy in machine tool by multi-station and time-sharing measurement for example, the factors affecting the measurement accuracy are analyzed in-depth, such as time-sharing measurement, measurement layout, the error of instrument, etc. The results will provide a basis for further improve the accuracy of this method.

In time-sharing measurement method, system self-calibration is very important to improve detection accuracy. In traditional time-sharing measurement method, system self-calibration is finished by lots of targets coordination from NC machine moving. This self-calibration method not only needs complex motion trajectory but also increases repeatability errors. In this paper, a new system self-calibration method is proposed. Before detecting NC machine, the cat's eye is fitted on a standard component which has very high accuracy to move according to advanced setting trajectory. The laser tracker is in four different station respectively. System self-calibration is finished by targets coordination from the standard component. Because the standard component has very high accuracy, the system self-calibration accuracy is very higher too. By theoretical deviation and experiment, it is proved that the new self-calibration method is very important to improve detection accuracy.

Cloud computing promises high performance and cost-efficiency, however, most cloud infrastructures operate at low utilization which greatly adhere cost effectiveness. Previous works focus on seeking efficient virtual machine (VM) consolidation strategies to increase the utilization of virtual resources in production environment, while overlooking the under-utilization of backup virtual resources. We propose a heuristic time sharing policy derived from the restless multi-armed bandit problem. The proposed policy achieves increasing backup virtual resources utilization while providing high availability. The experiment results show that the traditional 1:1 backup provision can be extended to 1:M (M>>1) between the backup VM and the service VMs, and the utilization of backup VMs can be enhanced significantly.

Next-generation applications increasingly rely on in situ analytics to guide computation, reduce the amount of I/O performed, and perform other important tasks. Scheduling where and when to run analytics is challenging, however. This paper quantifies the costs and benefits of different approaches to scheduling applications and analytics on nodes in large-scale applications, including space sharing, uncoordinated time sharing, and gang scheduled time sharing.