855 results about "Running time" patented technology

The invention discloses a cloud computing parallel task optimization scheduling method based on a priority dependency graph, which mainly solves the problem of parallel task scheduling in a cloud computing environment, and constructs the priority dependency graph (PDG) of cloud computing tasks by analyzing the dependency relationship and priority among the cloud computing tasks, so as to optimize the scheduling of the parallel tasks in the cloud computing environment. Nodes in the PDG represent cloud computing tasks, edges in the PDG represent dependency relationships among the tasks, the load condition of each computing node is continuously monitored on the basis of the PDG, the tasks are distributed to the most suitable nodes in combination with task priorities and the dependency relationships in the PDG, and if the load of a certain node is too high or the task running time exceeds the expectation, the tasks are distributed to the most suitable nodes. And automatically adjusting the resource allocation of the task. According to the method, the dependency and the priority among the tasks can be more accurately captured, so that the scheduling strategy is dynamically adjusted, the optimal arrangement of task execution is realized, the execution efficiency of the tasks is improved, and the overall resource utilization rate is maximized.

The invention relates to a calculation-storage stream joint scheduling optimization method and system based on DDQN and a heuristic strategy, and belongs to the technical field of distributed calculation and intelligent scheduling. The calculation-storage stream joint scheduling optimization method comprises the following steps: (1) defining a calculation stream and a storage stream; (2) workflow scheduling and execution: when the workflow is triggered, a scheduler evaluates the executable states of the tasks one by one according to the dependency relationship between the tasks and a scheduling strategy, and submits the executable tasks to a task executor; the task executor is responsible for executing the tasks on the working nodes and ensuring that the tasks are completed according to a preset sequence and priority; (3) collecting a DAG structure, queue information and an operation number; (4) task operation time and resource use prediction based on historical operation data; (5) scheduling optimization based on DDQN and a heuristic strategy; and (6) acquiring and storing scheduling information. The task execution efficiency and the resource utilization rate of the system are remarkably improved.

The invention relates to the technical field of industrial park intelligent monitoring, and particularly discloses a data acquisition and monitoring control method based on an intelligent industrial park, which comprises the following steps: acquiring key state data of equipment in real time, including operation time, operation temperature and operation power; an advanced signal processing algorithm is used for calculating an operation temperature abnormal index and an operation power abnormal index, the system can comprehensively evaluate the state of equipment and accurately judge whether slight or serious abnormal conditions exist or not based on detailed data analysis results, and the system can not only give out instant early warning notifications but also give out alarm information according to the serious abnormal conditions. According to the method, a machine learning model is adopted to predict the future operation state of the equipment, the equipment state abnormal coefficient in each future monitoring period is predicted based on the equipment state data in the current period, and classification and dynamic regulation and control of the equipment state are carried out according to a preset threshold value.

Apparatuses, systems, and techniques to generate a memory allocation plan for a set of tensors. In at least one embodiment, tensor data corresponding to the set of tensors is stored into memory locations at run time based, at least in part, on the memory allocation plan generated at a compile time.

Solutions for optimizing job runtimes via prediction-based token allocation includes receiving training data comprising historical run data, the historical run data comprising job characteristics, runtime results, and a token count for each of a plurality of prior jobs, and the job characteristics comprising an intermediate representation and job graph data; based at least on the training data, training a token estimator, the token estimator comprising a machine learning (ML) model; receiving job characteristics for a user-submitted job; based at least on the received job characteristics, generating, with the token estimator, token prediction data for the user-submitted job; selecting a token count for the user-submitted job, based at least on the token prediction data; identifying the selected token count to an execution environment; and executing, with the execution environment, the user-submitted job in accordance with the selected token count.

A method and system for predicting remaining thermal runtime in an electronic device is disclosed. The method involves obtaining the device's current processor power consumption and temperature sensor reading, selecting a predefined function relating temperature and time at that power level, determining the position of the current temperature on the function, calculating the time position for a shutdown temperature, and determining the time difference to estimate remaining runtime. In some examples, the functions are quadratic curves fitted to empirical time-temperature data collected at different processor power levels. In one embodiment, the prediction is implemented in augmented reality glasses and continuously adjusted using updated power and temperature data. The runtime prediction enables the device to warn the user prior to shutdown and perform graceful shutdown procedures. By accounting for diverse operating conditions, the method provides an accurate estimate of remaining time before the device reaches critical temperatures.

The invention relates to the technical field of data acquisition, in particular to an AOP-based user behavior data acquisition method. The method comprises the following steps: firstly, identifying user behavior related code features by statically analyzing Java source codes of an application program, and constructing a feature template library; during a compiling period, according to a template library identification target method, embedding a point burying instruction by utilizing a byte code enhancement technology, and constructing a monitoring section framework; and during running, dynamically adjusting an execution strategy according to the running state of the application program by virtue of a dynamic rule engine. Meanwhile, an annular buffer area is adopted to asynchronously process user behavior data streams, cache data are managed in a sub-generation mode, and asynchronous processing is triggered when a threshold value is exceeded. The method also constructs an adaptive thread pool model based on a hierarchical thread pool architecture, distributes tasks according to data value weights, monitors the task backlog rate of a high-priority sub-pool, adjusts the sampling frequency or acquisition dimension when the task backlog rate exceeds a threshold value, forms adaptive closed-loop control, and effectively acquires and processes user behavior data.

The present invention provides a multi-device collaborative control method and system for a digital workshop based on the Internet of Things, which relates to the technical field of data processing. The method includes: obtaining the status information of the first device during the execution of the processing task; generating a status change event when the process progress reaches a preset completion threshold or the running time exceeds a preset running time threshold; organizing various status change events into a queue in chronological order to generate a to-be-scheduled event stream; determining the target status change event associated with the second device; instructing the second device to execute the subsequent operation task, and calibrating the execution start time based on the trigger time to generate a second device action record; matching the second device action record with the target status change event, and comparing its recorded time with the trigger time. If the time deviation exceeds the tolerance interval, adjustment instruction data is generated; gradually correcting the control cycle of the second device. The present invention improves the autonomy and accuracy of multi-device collaborative control.

The invention relates to the technical field of flexible job shop scheduling in intelligent manufacturing and production scheduling, in particular to a flexible job shop scheduling optimization method for solving and adjusting resource constraints. Comprising the steps of initializing parameters and randomly generating an initial population; sequentially using a crossover operator and a mutation operator to evolve the current population; executing a hybrid decoding strategy on the current population; sorting the individuals in the current population from small to large according to the maximum completion time to form an elite population, and updating the elite population through question specific local search; and judging whether an evolution condition is met or not, if so, executing CP-based mathematical evolution, and outputting a final solution when the running time reaches the total running time. The method has the positive effects of reducing the resource waiting time, improving the machine utilization rate and improving the resource utilization efficiency and the scheduling performance of the whole workshop production.

The invention discloses a circulating pump control method based on a PLC, and relates to the technical field of circulating pump control, and the method comprises the steps: collecting key working condition data of a circulating pump, calculating a flow instantaneous deviation value, inputting the deviation and the real-time key working condition data into a lightweight digital twinborn model embedded in the PLC, and predicting flow output under an ideal working condition. Comparing with an actual value to obtain a deviation factor, correcting a current PID parameter based on the deviation factor, and calculating a target output frequency in combination with the flow deviation; and the PLC dispatches the current optimal pump set and the corresponding frequency in combination with the target output frequency and the health index and the operation duration of each pump, soft start-stop control is executed, and the selected pump sets are stably started one by one. The problems of response lag and extensive dispatching of a traditional control method are solved, and the intelligent control level and engineering adaptability of the circulating pump control method are remarkably improved.

The invention discloses an electrical equipment operation data monitoring management system and method, and relates to the technical field of electrical equipment management. According to the electrical equipment operation data monitoring management method, operation state time sequence data of electrical equipment is obtained based on a set time period, and an operation time sequence change index and an operation time sequence characteristic index of the electrical equipment are analyzed; and performing evaluation analysis on the operation time sequence change index and the operation time sequence characteristic index of the electrical equipment to obtain an operation health evaluation index of the electrical equipment, and taking a preset management measure. The change rate is calculated based on the difference between the operation value and the parameter value, the operation time sequence change index of the electrical equipment is obtained, when the equipment is in the early stage of degradation, the parameters of the equipment possibly do not exceed the alarm threshold value, but the change trend is abnormal, and the hidden risk can be recognized in advance by incorporating the trend information into an evaluation system.

A system can determine to combine a first function that executes in a first container and a second function that executes in a second container in a third container. The system can determine a first runtime of the first function based on a first container configuration of the first container. The system can determine a second runtime of the second function based on a second container configuration of the second container. The system can deploy the third container that comprises the first function matched to the first runtime and the second function matched to the second runtime. The system can direct a first call to the first function to the third container. The system can direct a second call to the second function to the third container.

The invention provides a computing power evaluation method and device, equipment, a medium and a program product. The method comprises the following steps: dividing the running time of target equipment into a plurality of sub-time regions; collecting performance data of the target equipment in each sub-time region; calculating a performance evaluation value of each sub-time region based on the performance data in each sub-time region; the performance evaluation values comprise a processor performance evaluation value, a memory performance evaluation value and a storage performance evaluation value; collecting system monitoring data of the target equipment in each sub-time region; based on the system monitoring data of the target equipment in each sub-time region, calculating an infrastructure comprehensive quality evaluation value of each sub-time region; and based on the infrastructure comprehensive quality evaluation value, the processor performance evaluation value, the memory performance evaluation value and the storage performance evaluation value in each sub-time region, calculating a comprehensive calculation power evaluation value of the target equipment in the operation time. By adopting the method provided by the embodiment of the invention, the accuracy of the computing power evaluation method can be improved.

The invention provides a method and device for vehicle thermal management and a computer readable storage medium. The method comprises the following steps: according to vehicle navigation data and / or a vehicle driving state, judging whether a vehicle driving mode meets the requirement of a thermal management mode or not; when it is judged that the vehicle running mode meets the requirement of the heat management mode, the environment temperature and the upper temperature limit and the lower temperature limit of a heat management component in the heat management mode are obtained, and the remaining running distance and / or the remaining running time from the vehicle to the destination are / is estimated; and performing thermal management on the thermal management part of the vehicle according to the acquired environment temperature, the temperature upper limit and the temperature lower limit of the thermal management part and the estimated residual driving distance and / or the residual driving time.

The invention provides an automobile air conditioner control method and device, a storage medium and an automobile air conditioner. The automobile air conditioner control method comprises the following steps of obtaining current environment temperature outside an automobile and current heating accumulation operation time of the air conditioner; and determining whether an air outlet and / or an airinlet of the air conditioner are covered with ice and snow or not according to the current environment temperature outside the automobile and the current heating accumulation operation time. The scheme provided by the invention can be used for solving the problem that due to the fact that the air outlet and / or the air inlet of the automobile air conditioner are covered with ice and snow, the problem that the heating effect of the air conditioner is reduced is solved.

The invention discloses a method and a system for detecting and diagnosing abnormal calling of timers of a linux system. The method comprises the following steps of: respectively acquiring running time and calling times of a callback function of each timer; matching and calling a kernel function operated by the timer according to the callback function; if both the callback function and the kernel function for calling the timer to run are within the kernel code range of the module required for running the test scene, the timer call is invalid call; if the running time and the calling frequency of the callback function both meet the judgment rule of the abnormal high-frequency calling, the timer calling is the abnormal high-frequency calling; and if the timer call is invalid call or abnormal high-frequency call, obtaining call times of each category in a kernel function running by calling the timer, determining an abnormal category according to the call times, and diagnosing a reason for abnormal call of the timer according to information of the abnormal category. According to the method, abnormal calling can be directly judged, the cause of abnormal calling can be indicated, and the detection and diagnosis efficiency is improved.

The invention provides a shared cache management method and electronic equipment, and relates to the technical field of electronic equipment control. According to the method, the running frequency points of the processor and the shared cache can be matched, so that the processor can obtain data from the shared cache in time, and the running speed of the application is ensured. The method comprises the following steps: in response to a first event, setting a running frequency point of a shared cache as a first frequency point based on a focus application, user operation information, performance information of each processing core and thread running information; wherein the focus application is the application operated by the user for the last time, the user operation information comprises the type and the number of times of the operation acting on the focus application by the user within the preset time, and the performance information of each processing core is used for reflecting the shared cache missing rate of the processing core; the thread running information is used for reflecting running time proportions of the plurality of thread groups on the N processing cores, and each thread group comprises one or more threads running on the electronic equipment.

The invention relates to the technical field of rail transit, in particular to a multi-signal train control system simulation evaluation method, system and device and a medium. A plurality of evaluation functions are integrated, and the evaluation range covers a plurality of key dimensions of train operation. Train operation efficiency and safety abnormity evaluation are closely associated and coordinated, and a complete and systematized evaluation architecture is constructed. The running situation of the train is comprehensively grasped by comprehensively considering running efficiency indexes such as morning and evening points, tracking intervals, energy consumption and key section train occupied time and safety abnormity indexes such as train allowable speed sudden change, abnormal braking, section abnormal parking, abnormal access handling and motor temperature rise alarm. Based on fusion and deep analysis of multi-source data, real-time changes of train states, such as real-time power consumption, traction operation time and the like of a train in a specific area, are comprehensively analyzed, and a powerful basis is provided for formulating an optimization strategy.

The application provides an air conditioner control method and system based on carrierless communication, and a storage medium. The method comprises the following steps: after the air conditioner is powered on, when it is detected that the intelligent control running time reaches two cycles, the user usage habit self-learning is entered, so as to intelligently control the air conditioner based on the self-learning result; whether the intelligent control running time reaches one cycle is detected in real time, if yes, the parameter correction is performed according to the user usage habit of the previous cycle, so as to obtain a new user usage habit, and intelligently control the air conditioner based on the new user usage habit; otherwise, the air conditioner is intelligently controlled based on the user usage habit of the current cycle; whether the current user usage habit meets the preset requirement is judged every preset cycle, so as to correct the control parameter corresponding to the user usage habit according to the judgment result. The application can continuously update the parameter according to the change of the user usage habit, and is more intelligent.

The invention discloses a heterogeneous resource scheduling method for deep learning jobs and a related device, and relates to the field of resource scheduling. Packaging the deep learning jobs needing to be packaged in the plurality of deep learning jobs into job pairs in pairs, and obtaining a to-be-scheduled job set composed of the job pairs and / or single deep learning jobs not needing to be packaged; according to the respective resource demand data of the plurality of deep learning jobs and the number of idle resources of the target server cluster, predicting respective running durations of each job object in the job set to be scheduled on the GPU and the NPU, and according to the respective running durations of each job object on the GPU and the NPU, scheduling the plurality of deep learning jobs in the job set to be scheduled. And carrying out resource scheduling on the to-be-scheduled job set by adopting a round scheduling mechanism on the target server cluster. According to the method and the device, the aim of heterogeneous resource scheduling of the deep learning task across the GPU and the NPU is fulfilled based on the preset adaptive class.

Estimated and actual processor runtimes improve computer functioning in fairly sharing computing resources. Today's computers and cloud-based services serve many users and many software applications sharing CPU resources. An operating system thus implements a scheduling policy that fairly allocates CPU time. A scheduler thread implements the scheduling policy based on estimated processor runtimes, and actual processor runtimes, associated with tasks. The operating system may maintain running tallies or totals for a user / group / organization based on credits (e.g., the estimated processor runtimes) and / or on penalties (e.g., the actual processor runtimes). The scheduler thread may select tasks for worker threads based on the credits and / or the penalties, thus ensuring that no user / group / organization unfairly consumes CPU time.

A system analyzes a set of static source code to identify source code segments that may be implemented using parallel multi-thread processing at run-time. The system determines whether source code segments meet multi-threading criteria, including lacking operational data dependencies and having particular run time or computing resource consumption characteristics. Based on determining that the source code meets multi-threading criteria, the system modifies the static source code to utilize parallel multi-thread processing at run-time. The system generates a recommendation for a user based on the source code modification.

The invention relates to an intelligent CTU goods shelf and an anti-shake control method and device thereof and a terminal. The method comprises the steps that a goods placing instruction for controlling operation of the intelligent CTU goods shelf is obtained, and a telescopic structure is controlled to clamp a goods shelf body according to the goods placing instruction; the goods placing instruction comprises the initial speed, the final speed and the maximum acceleration of the operation of the intelligent CTU goods shelf; processing the initial speed, the final speed and the maximum acceleration to obtain a speed curve; and according to the speed curve, the extending running speed and running time of the pallet fork in the goods shelf body are controlled, and a goods release instruction that the pallet fork in the goods shelf body extends in place is obtained. According to the method, a telescopic structure is controlled to clamp a goods shelf body to stabilize the goods shelf body of the intelligent CTU goods shelf according to a goods placing instruction, and then the extending running speed and running time of a pallet fork in the goods shelf body are controlled through a speed curve, so that the pallet fork in the goods shelf body extends in place; therefore, the intelligent CTU shelf doubly reduces the impact force generated when the pallet fork stretches out and draws back.

The invention discloses a computing power resource measurement method for a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The method comprises the steps that on each device of a client side, the hardware type of each device is obtained, and the hardware type of each device is a CPU chip or a GPU chip; deploying a plurality of reference models and a data set corresponding to each reference model on each piece of equipment; and when each device calls a function corresponding to each reference model. The method solves the problems that in the prior art, a weighted measurement mode based on resource attributes cannot reflect the computing power condition in real use of computing power resources although a calculation mode is simple and efficient, and a time test mode based on an artificial intelligence reference model cannot visually reflect the computing power condition although running time results are ranked. And the calculation power value evaluation of the intelligent equipment is not accurate.

The invention relates to the technical field of electronic equipment, and discloses a process control method, electronic equipment and a readable storage medium. According to the electronic equipment, when the foreground event is detected, the time for allowing all the process queues to run in the single scheduling period allocated by the processor to different process queues can be adjusted in time. For example, the first process queue comprises the to-be-run processes related to the foreground application, and the second process queue comprises the to-be-run processes related to the background application, so that the time allocated to the first process queue is increased, more to-be-run processes related to the foreground application can have enough running time, and foreground jamming is reduced. And moreover, the time allocated to the second process queue is shortened, the to-be-run processes related to the background application are suppressed, and the situation that the processes occupy too much resources during running, and consequently the background load is too large can be avoided.

A computing device comprising at least one processing module carrying multiple execution units each with a local memory unit; and a local network of the processing module linking at least some of the execution units to each other by respective communication paths; wherein the execution units are configured to execute a binary code segment at least temporarily stored in their respective associated local memory unit and derived from a computer executable program code application containing application code sections; and wherein at least one of the execution units is designated for executing a binary code segment as an assigned binary code segment based on a pre-determined runtime schedule with fixed time slots during which the execution unit is granted exclusive access to at least one of the communication paths when executing the assigned binary code segment in line with a pre-defined running order of the application code sections.

Systems and methods for providing dynamic network slicing resource reselection for wireless communication are described. User equipments (UEs) may determine that network slicing resources utilized with respect to one or more applications are to be changed in run time, such as for more efficient operation in light of a change in power mode, throughput mode, latency mode, etc. A message indicating a cause for reselection of a current packet data unit (PDU) session association with an application may be provided to a UE route selection policy (URSP) manager. The URSP manager may reevaluate a current PDU session association with the application to determine if it is a best match with the cause. If no, a switch to a new PDU session association with the application may be made. If yes, the current PDU session association with the application may be maintained. Other aspects and features are also claimed and described.

A computer-implemented method for upgrading and / or updating at least one service on a computer-implemented system, configured to: a. deploy at least one update version of the at least one service which needs to be updated or be upgraded on the system while maintaining the current version of the service on the system,; b. deploy and operate a monitoring module for protocolling communications among the plurality of services and for analysing dependencies among applications of the services with respect to their running times; c. determine process states of each at least one service which are suitable for updating and / or upgrading the service; d. disable the control of the current version of the service within the current technical application at a time slot of the identified time slots; and e. enable the control of the deployed update version of the service within the current technical application.

The invention provides a windshield control method and device with a memory function, and the method comprises the steps: controlling a windshield to move to a first locked-rotor point through time, and enabling the first locked-rotor point to be a positioning point at which a motor stops due to physical blocking when the windshield is driven by the motor to move to a first mechanical limit position; controlling the windshield to unidirectionally move to a target position only along the first direction, and recording the motor operation time T from the first locked-rotor point to the target position; storing the running time T; and when a position calling instruction is received, the windshield is controlled to move to the first locked-rotor point and then runs for the time T in the first direction to reach the target position. The technical scheme of the invention is a solution for realizing the grading controller with the memory function at low cost.

The invention provides an SMP architecture real-time operating system CPU occupancy rate statistical method, electronic equipment and a medium, and the method does not depend on redundant external hardware equipment, does not need to independently create a statistical task occupying CPU running time, and utilizes a timer generating Tick interruption in an operating system to calculate the CPU occupancy rate of the operating system. Through the scheduler-level high-precision statistics of the operation time of the observed task and the calibration of the total operation time of the CPU, the operation time of the observed task and the total operation time of the CPU are displayed in an accurate granularity, and the CPU occupancy rate of the strong real-time task can be accurately measured. By applying the technical scheme provided by the invention, the technical problem of measurement distortion of the CPU occupancy rate of the strong real-time task in the prior art is solved.