22 results about "Workload prediction" patented technology

The present invention provides a method for optimizing cooling resources in a data center based on workload prediction and a system thereof. The method includes the steps of: continuously collecting data in real-time from a plurality of sensors distributed across various sections of the data center; predicting future workload demands and corresponding cooling requirements over time and space in each section of the data center using historical and real-time collected data; determining whether to allocate the predicted workload demand to a section that meets the corresponding cooling requirements or to adjust the cooling resources to achieve the required cooling levels, whichever results in more optimized energy usage; and dynamically adjusting the cooling resources in each section of the data center based on real-time and predicted workload demands over time to minimize energy consumption and operational costs, thereby ensuring optimal cooling without over-provisioning.

The specification provides a workload prediction method, device, medium and computer system in a cloud computing service, the method comprising: in response to a first trigger event, obtaining first time series data corresponding to system state data in a first time period; based on the first time series data, performing a first prediction for a future first time domain range to obtain a first prediction result; in response to a second trigger event, obtaining second time series data corresponding to system state data in a second time period; based on the second time series data, performing a second prediction for a future second time domain range to obtain a second prediction result; evaluating the accuracy of the first prediction result to obtain an evaluation result; and determining a target prediction result of the workload according to the evaluation result, the first prediction result and the second prediction result.

The invention relates to the technical field of cloud computing, and provides a cloud resource workload prediction method based on multi-scale self-adaption in a computing network environment, and the method comprises the steps: carrying out the data collection of a workload sequence of a cloud data center through employing a sample division method based on a sliding window, and obtaining the cloud workload data of different time scales; carrying out noise reduction processing on the cloud working load data by adopting an adaptive threshold noise reduction method based on wavelet multi-scale decomposition, and carrying out Fourier transform to extract frequency domain features; carrying out sample division on the processed cloud working load data by adopting an adaptive mode clustering algorithm, and outputting a mode data set; adopting a Mixup data enhancement method based on mode driving to generate a mixed sample, adding the mixed sample into the mode data set, and constructing an enhanced mode data set; and obtaining a cloud resource workload prediction result by adopting a similarity alignment dynamic integrated prediction method. Finally, an ablation experiment proves that the method has higher prediction precision.

A method for incentivizing contact center agents with scheduling perks that includes: receiving a workload forecast and staffing plan for a current shift; receiving a service level target; receiving types of scheduling perks; performing a selection routine for determining a select scheduling perk for offering to a select agent; and sending a scheduling perk offer via electronic communication to the select agent. The selection routine may include: selecting a proposed scheduling perks and a proposed agent; modifying the staffing plan to create a proposed staffing plan that reflects the proposed scheduling perk; predicting a proposed forecasted target adherence using the modified staffing plan; determining whether the proposed forecasted target adherence satisfies a threshold defined by an acceptable forecasted target adherence and, if so, deeming the proposed scheduling perk as select scheduling perk and proposed agent as select agent.

The application provides a kind of self-supervision multi-scale cloud workload prediction method and system in the technical field of cloud computing resource management, method includes: step S1, the time series data of each physical machine workload in cloud environment is collected;Step S2, each time series data is subjected to data enhancement operation to obtain enhanced sequence data;Step S3, based on multi-scale patch embedding layer and scale perception layer, multi-scale encoder is constructed;Step S4, based on enhanced sequence data, the self-supervision training of multi-scale encoder is carried out;Step S5, in multi-scale encoder, prediction head is added, and the adapter of specific scale is introduced, obtain preset quantity of labeled data, based on each labeled data, the adapter parameters of prediction head and adapter are fine-tuned, and then cloud workload prediction model is constructed;Step S6, based on cloud workload prediction model, workload prediction is carried out.The application has the advantages that in the case of labeled data scarcity, the workload prediction accuracy is greatly improved.

The application discloses a server energy efficiency dynamic optimization method based on workload prediction and a deep learning model, relates to the cross field of server energy efficiency optimization and deep learning technology, and comprises the following steps: collecting server multi-source data, performing space-time alignment on the server multi-source data, extracting causal characteristics, constructing a standardized data set, constructing a time series graph convolution network, combining a multi-head attention mechanism, outputting a probabilistic load prediction interval, constructing an energy efficiency objective function based on a Lyapunov optimization framework, quantifying performance loss and temperature drift, and outputting multi-agent optimization constraints, defining a multi-reinforcement learning agent, outputting a collaborative adjustment instruction through a counterfactual baseline algorithm, constructing a digital twin shadow model to deduce energy efficiency, combining a meta-learning fine-tuning model, forming a closed-loop optimization of physical and digital double verification, realizing dynamic and accurate optimization of server energy efficiency, and adapting to multiple computing power scenes.

Techniques for multi-layered prediction of computing workloads are disclosed. A system identifies a level of granularity associated with a request for predicting the computing workload of a particular entity. The system obtains attribute data for computing resources at the identified level of granularity. The system determines whether computing resources not specified in the request should be included in the workload prediction. The system applies a time series prediction model to time series data obtained from the computing resources associated with the request. The system presents one or more workload predictions for the computing workload associated with the request.

The application relates to a cloud service workload prediction method and system based on a convolution enhanced Transformer, which comprises the following steps: collecting cloud server workload data and preprocessing the cloud server workload data to decompose the cloud server workload data into a trend component and a residual component; constructing a workload prediction model, training the workload prediction model by using the trend component and the residual component, and obtaining a trained workload prediction model; predicting the cloud server workload by using the trained workload prediction model to obtain a workload prediction value; predicting the trend component by using a trend information capturing module to obtain a prediction result of the trend component; predicting the residual component by using a convolution enhanced Transformer encoder module to obtain a prediction result of the residual component; and fusing the prediction result of the trend component and the prediction result of the residual component by using a feature fusion module to obtain a final workload prediction value.

The application belongs to the technical field of intelligent transportation, and discloses a driver workload prediction method based on multiple physiological signals under multiple auditory disturbances, which is created by combining three music rhythms (none, slow and fast), two navigation modes (high frequency and low frequency) and three traffic scenes (regular road, school road and construction site road), collects multi-modal data including skin electricity signal EDA, electrocardiogram signal ECG, electroencephalogram signal EEG, driving behavior characteristics and subjective workload evaluation, and the data is used to build a workload prediction model, and a stacking model is adopted, and the stacking model integrates multiple machine learning models to improve the prediction performance.

This invention provides a method, apparatus, and medium for predicting serverless user workloads. The method includes: collecting historical data from a serverless architecture, wherein the historical data includes performance monitoring data as an independent variable and the number of jobs waiting to be executed as a dependent variable; extracting root cause features, time-division features, differential features, and interaction features based on the performance monitoring data and the number of jobs waiting to be executed; training a preset workload model using the performance monitoring data, root cause features, time-division features, differential features, and interaction features as a training dataset to obtain a trained workload model; and using the trained workload model to predict serverless user workloads. This method, apparatus, and medium can solve the problem that existing workload prediction methods, due to the use of single features for prediction, are prone to weak data feature extraction and large prediction deviations.

This application can be applied to fields such as resource allocation, fintech, and smart healthcare. It discloses a resource allocation method and apparatus, storage medium, and computer equipment based on dynamic control. The method includes: acquiring the resource budget plan and project execution data of the target project; calculating and predicting resource demand based on the project execution data using a preset project resource prediction model; if the resource budget plan covers the predicted resource demand, calculating a resource idle matrix and matrix score based on the resource budget plan and the predicted resource demand; determining a first budget adjustment plan for the resource budget plan based on the matrix score; if the resource budget plan does not cover the predicted resource demand, acquiring multiple project nodes of the target project and the expected targets of each project node; calculating the predicted workload value based on the expected node targets using a preset workload prediction model; and determining a second budget adjustment plan for the resource budget plan based on the predicted workload value of each project node.

The application provides a workload prediction method for cloud-native applications and related equipment. The method comprises: performing tree-shaped aggregation processing on operation and maintenance time series data based on the internal data weight of the obtained operation and maintenance time series data to obtain an operation and maintenance time series data aggregation tree; calculating the correlation coefficient of each vector in the operation and maintenance time series data aggregation tree, and obtaining a characteristic time series data vector corresponding to the operation and maintenance time series data aggregation tree based on the correlation coefficient; and performing prediction on the characteristic time series data vector by using an information extraction network with introduced residual connection to obtain a prediction result corresponding to the operation and maintenance time series data. In the embodiment of the application, residual connection is introduced in the main encoder, so that even if the network depth is stacked, the output layer can directly obtain more input information, thereby maintaining the stability of model training. The generated adversarial network is introduced, the gradient is updated based on the optimal transmission distance for each iteration of the value function network, and then the weight is cut, thereby effectively solving the problem of long sequence state gradient explosion.

The invention provides a workload prediction method and device based on job information perception and time difference, and relates to the technical field of computing resource management, and the method comprises the steps: obtaining historical workload data of target equipment in a preset time period and job information related to a workload; extracting a time difference feature of the historical workload data, and fusing the time difference feature with the job information to generate a job load fusion feature; and inputting the job load fusion feature into a pre-trained conditional denoising diffusion model to obtain a job load prediction result of a future time period output by the conditional denoising diffusion model. According to the work load prediction method and device based on work information perception and time difference provided by the invention, the work information and the multi-order time difference feature are fused into the guide condition, and the generation capability of the condition de-noising diffusion model is utilized, so that high-robustness and high-precision probability prediction of work load mutation in a complex computing environment is realized.

Methods and systems for managing operation of a deployment comprising data processing systems are disclosed. The operation may be managed by optimizing data processing systems task allocation based on at least future workload predictions of the data processing systems. The at least future workload predictions may be generated by a trained inference model (e.g., a convolution neural network, a temporal graph network, etc.). A data processing system may be selected to perform the task by using the at least future workload predictions to minimize an objective function. The data processing system having a future workload prediction of the at least future workload predictions that minimizes the objective function may be selected. Once the data processing system has been selected, the task may be performed by the data processing system.

According to some embodiments, methods and systems can be associated with a cloud computing environment. A workload prediction framework can receive observed workload information associated with a database (e.g., a database as a service (“DBaaS”)) in the cloud computing environment. Based on the observed workload information, a statement arrival rate (“SAR”) prediction can be generated. Further, a host variable assignment prediction can be generated based on the observed workload information. The workload prediction framework can then automatically create a workload prediction for the database using the SAR prediction and the host variable assignment prediction. A physical database design advisor (e.g., a table partition advisor) can receive the workload prediction and, in response to the workload prediction, automatically generate a recommended physical layout for the database (e.g., using a cost model, a current physical layout, and an objective function).

The application belongs to the technical field of intelligent transportation, and discloses a driver workload evaluation method based on galvanic skin signal under multiple auditory interferences, different driving scenes are investigated to study the comprehensive influence of navigation frequency and music rhythm on driver workload, a double-index method is adopted to combine subjective evaluation and galvanic skin signal, the SCL distribution of the galvanic skin signal and the subjective evaluation score show strong and consistent correlation, which provides a solid foundation for the galvanic skin signal as the main physiological index of the workload prediction model, and makes the driver workload prediction based on the galvanic skin signal under multiple auditory interferences more accurate.

A model-as-a-service (MaaS) platform includes a multimodal model instance that is executed by dedicated groups of processing resources allocated to support different modality-specific processing pipelines. The MaaS platform further includes an intelligence layer that tracks modality-specific token utilization over time; generates a modality-specific workload prediction for the multimodal model instance based on the tracked data; and generates a modality-specific latency prediction based on the modality-specific workload prediction. The MaaS platform further includes a resource allocation component that uses the modality-specific latency prediction to dynamically reallocate the processing resources among the dedicated groups supporting the different modality-specific processing pipelines.

The invention relates to the technical field of data center heat dissipation, and provides a data center heat dissipation method and device based on workload prediction and electronic equipment, and the method comprises the steps: predicting the node-level workload distribution of a data center in a future time period according to historical and real-time workload data through employing a load prediction model; utilizing the cooling capacity prediction model to predict a cooling capacity demand in a future time period, and determining a business migration strategy and an optimal operation parameter; the service migration strategy is used for optimizing load distribution and cold energy supply efficiency of the data center by adjusting service distribution; the optimal operation parameters are used for achieving dynamic matching of the cooling capacity and the required cooling capacity of each refrigeration unit; and executing the service migration strategy, and adjusting the operation of the data center refrigeration system according to the optimal operation parameters. Accurate load prediction can be achieved, service distribution adjustment is matched, the refrigeration efficiency can be improved, energy consumption is reduced, the reliability and stability of the data center are improved, and normal operation of the data center is guaranteed.

The invention provides an end-to-end service level adaptive cloud data center resource collaborative optimization method. The method is characterized by comprising the following steps of: predicting a workload based on historical task data; under the constraint of global SLA violation budget, dynamic violation budget allocation and resource quota calculation are carried out on each application type based on dynamic planning; calculating the effective capacity of the virtual machine based on a historical utilization rate and a security margin factor, and supplying a security excess allocation virtual machine; a virtual machine-to-physical machine placement step based on an anti-affinity principle; and a double-layer load balancing task scheduling step based on deep reinforcement learning. According to the method, workload prediction, SLA violation budget allocation, resource supply and placement and online task scheduling are unified in one framework, and the problem of global sub-optimization caused by isolated optimization of a resource configuration layer and a scheduling layer is avoided.

The invention discloses a medical scheduling system and method based on machine learning and a large language model, and relates to the technical field of medical management and artificial intelligence application, and the method comprises the steps: precisely predicting a future human resource demand through a time sequence prediction model in combination with department historical business data and multi-dimensional feature data; generating a basic scheduling draft according to a personnel skill-post matching rule; personal attribute data of medical staff and a hospital management rule base are integrated, a big language model simulates a qualification manager to carry out multi-objective optimization, and a final scheduling table conforming to constraints is generated; and finally, iteratively optimizing the model through user feedback. The system correspondingly comprises a workload prediction module, a basic scheduling generation module, a multi-dimensional constraint information management module, a large language model optimization engine module, a user interaction and presentation module and a model iteration module, can automatically obtain data, intelligently process complex constraints and improve scheduling accuracy, compliance and humanization level, and is suitable for scheduling management of various medical institutions.

A model-as-a-service (MaaS) platform includes a multimodal model instance that is executed by dedicated groups of processing resources allocated to support different modality-specific processing pipelines. The MaaS platform further includes an intelligence layer that tracks modality-specific token utilization over time; generates a modality-specific workload prediction for the multimodal model instance based on the tracked data; and generates a modality-specific latency prediction based on the modality-specific workload prediction. The MaaS platform further includes a resource allocation component that uses the modality-specific latency prediction to dynamically reallocate the processing resources among the dedicated groups supporting the different modality-specific processing pipelines.

This application provides a load forecasting method, electronic device, storage medium, and program product, relating to the field of air logistics. The load forecasting method includes: acquiring ticket information for multiple target tickets, including flow information; determining the expected departure flights matched to each target ticket based on its flow information; and calculating the expected load data for each expected departure flight based on the ticket information of the target tickets matched to that expected departure flight. This load forecasting method achieves coordination between pallet / container loading and weighing and flight loading, pre-loading flights based on the expected load data, avoiding overloading and rework of pallets / containers and frequent changes to release schedules; reducing the risk of inconsistent release information; and reducing delays caused by temporary refueling and temporary cargo hauling, thus saving fuel costs.