Power data transmission scheduling method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a power data transmission scheduling method and device, equipment, a storage medium and a program product, and relates to the technical field of data transmission. By adopting the method, the transmission efficiency of the power data can be improved. The method comprises the steps of collecting a multi-source power data set, and performing normalization processing and abnormal value removal on the multi-source power data set to obtain a target power data set; performing dynamic slicing processing on the target power data set to segment the target power data set into a plurality of data slices, and scheduling the plurality of data slices to corresponding processing units by using a Hash algorithm; in the processing unit, data transmission dynamic queues are respectively constructed based on the plurality of data slices; and carrying out transmission scheduling on the data transmission dynamic queue by utilizing a dynamic perception queue scheduling algorithm, and carrying out storage optimization on the transmitted data.

Description

Technical Field

[0001] The present application relates to the technical field of data transmission, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for scheduling power data transmission. Background Art

[0002] In the modernization process of electrical equipment manufacturing, the level of intelligence and automation of the production process has been continuously improved, which has led to a surge in data volume and diversification of data types. These data cover all aspects from power frequency withstand voltage test to lightning impulse test, from mechanical property test to real-time video monitoring, and they play an irreplaceable role in monitoring the production process, predicting and controlling product quality. However, the massive amount and complexity of data have brought challenges to traditional data transmission methods.

[0003] Traditional data transmission methods often use a unified, static scheduling strategy, which is inadequate when faced with sudden increases in data volume or the diversity of data types. For example, equipment failures or abnormal fluctuations in process parameters during production require data management systems to respond quickly and adjust transmission strategies to ensure timely processing of critical data. Therefore, current data transmission methods have the problem of low data transmission efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a power data transmission scheduling method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0005] In a first aspect, the present application provides a method for scheduling power data transmission, comprising:

[0006] Collecting a multi-source power data set, normalizing and removing outliers on the multi-source power data set to obtain a target power data set;

[0007] Dynamically slice the target power data set to divide the target power data set into a plurality of data slices, and dispatch the plurality of data slices to corresponding processing units using a hash algorithm;

[0008] In the processing unit, based on the plurality of data slices, respectively construct data transmission dynamic queues;

[0009] The dynamic perception queue scheduling algorithm is used to schedule the data transmission dynamic queue and optimize the storage of the transmitted data.

[0010] In one embodiment, the normalizing and outlier removal of the multi-source power data set includes:

[0011] The multi-source power data set is input into a normalization processing model for zero-mean normalization processing to obtain a current data set that conforms to a standard normal distribution; an abnormal score is evaluated for each data point in the current data set using an isolation forest algorithm to obtain an abnormal score value corresponding to each data point; and according to the abnormal score value, abnormal data points in the current data set are identified and removed.

[0012] In one embodiment, constructing data transmission dynamic queues based on the plurality of data slices respectively includes:

[0013] Obtain the data flow and data priority of each data slice, and determine the queue status of each data slice according to the data flow and the data priority; generate a transmission strategy for the data transmission dynamic queue according to the queue status; and construct the data transmission dynamic queue containing multiple data slices based on the transmission strategy.

[0014] In one embodiment, the method of scheduling the plurality of data slices to corresponding processing units using a hash algorithm includes:

[0015] The hash value of each data slice is calculated by the hash algorithm, and a scheduling strategy for each data slice is generated according to the hash value; based on the scheduling strategy, each data slice is scheduled to the corresponding processing unit.

[0016] In one embodiment, the method further comprises:

[0017] A first predicted probability of a potential quality problem is calculated through a Bayesian probability calculation model according to a dynamic queue for data transmission; a second predicted probability of the potential quality problem is obtained, and a target predicted probability of the potential quality problem is obtained by performing a fusion calculation based on the first predicted probability and the second predicted probability; a target quality problem is identified among the potential quality problems based on the target predicted probability and a warning threshold, and a warning response is generated for the target quality problem.

[0018] In one embodiment, the method further comprises:

[0019] Obtain feedback data of the Bayesian probability calculation model, and generate optimized model parameters through a model parameter optimization model according to the feedback data; update the Bayesian probability calculation model according to the optimized model parameters to obtain an updated current Bayesian probability calculation model; the current Bayesian probability calculation model is used to replace the Bayesian probability calculation model.

[0020] In a second aspect, the present application also provides a power data transmission scheduling device, comprising:

[0021] A data processing module, used for collecting multi-source power data sets, normalizing and removing outliers on the multi-source power data sets, and obtaining a target power data set;

[0022] A data scheduling module, used for dynamically slicing the target power data set to divide the target power data set into a plurality of data slices, and scheduling the plurality of data slices to corresponding processing units by using a hash algorithm;

[0023] A queue construction module, used for respectively constructing data transmission dynamic queues in the processing unit based on the plurality of data slices;

[0024] The transmission scheduling module is used to utilize a dynamic perception queue scheduling algorithm to perform transmission scheduling on the data transmission dynamic queue and to optimize the storage of the transmitted data.

[0025] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0026] A multi-source power data set is collected, and the multi-source power data set is normalized and outliers are removed to obtain a target power data set; the target power data set is dynamically sliced ​​to divide the target power data set into multiple data slices, and the multiple data slices are scheduled to corresponding processing units using a hash algorithm; in the processing unit, data transmission dynamic queues are respectively constructed based on the multiple data slices; the data transmission dynamic queues are scheduled for transmission using a dynamic perception queue scheduling algorithm, and storage optimization is performed on the transmitted data.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0028] A multi-source power data set is collected, and the multi-source power data set is normalized and outliers are removed to obtain a target power data set; the target power data set is dynamically sliced ​​to divide the target power data set into multiple data slices, and the multiple data slices are scheduled to corresponding processing units using a hash algorithm; in the processing unit, data transmission dynamic queues are respectively constructed based on the multiple data slices; the data transmission dynamic queues are scheduled for transmission using a dynamic perception queue scheduling algorithm, and storage optimization is performed on the transmitted data.

[0029] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0030] A multi-source power data set is collected, and the multi-source power data set is normalized and outliers are removed to obtain a target power data set; the target power data set is dynamically sliced ​​to divide the target power data set into multiple data slices, and the multiple data slices are scheduled to corresponding processing units using a hash algorithm; in the processing unit, data transmission dynamic queues are respectively constructed based on the multiple data slices; the data transmission dynamic queues are scheduled for transmission using a dynamic perception queue scheduling algorithm, and storage optimization is performed on the transmitted data.

[0031] The above-mentioned power data transmission scheduling method, device, computer equipment, computer-readable storage medium and computer program product, by utilizing dynamic data slicing technology to dynamically slice the target power data set, can divide the power data into data slices suitable for transmission according to the data type and transmission requirements of the target power data set, thereby optimizing the power data transmission process and improving the power data transmission efficiency; then optimize the data slices through the hash algorithm to further ensure that the power data can be quickly and accurately transmitted to the corresponding processing unit, thereby enhancing the reliability and stability of power data transmission; finally, based on multiple data slices, dynamic data transmission queues are constructed respectively, and the dynamic data transmission dynamic queues are scheduled for transmission using a dynamic perception queue scheduling algorithm, thereby optimizing the data transmission process, and being able to quickly respond and adjust the data transmission strategy, so that it can cope with equipment failures or abnormal fluctuations in process parameters during the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 This is an application environment diagram of a power data transmission scheduling method in one embodiment;

[0034] Figure 2 A schematic diagram of a flow chart of a power data transmission scheduling method in one embodiment;

[0035] Figure 3 A schematic diagram of a process of building a dynamic queue in one embodiment;

[0036] Figure 4 A schematic diagram of a flow chart of a data transmission scheduling step in an embodiment;

[0037] Figure 5 A schematic diagram of a process of intelligent early warning steps in an embodiment;

[0038] Figure 6 It is a flowchart of a method for scheduling power data transmission in a specific embodiment;

[0039] Figure 7 is a structural block diagram of a power data transmission and scheduling device in one embodiment;

[0040] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] The power data transmission scheduling method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be integrated on the server or placed on the cloud or other network servers.

[0043] Specifically, the power data transmission scheduling method provided in the embodiment of the present application can be executed by a terminal.

[0044] Exemplarily, the terminal collects a multi-source power data set, normalizes and removes outliers on the multi-source power data set to obtain a target power data set; the terminal dynamically slices the target power data set to divide the target power data set into multiple data slices, and uses a hash algorithm to schedule the multiple data slices to corresponding processing units; the terminal constructs data transmission dynamic queues in the processing unit based on the multiple data slices; the terminal uses a dynamic perception queue scheduling algorithm to schedule the data transmission dynamic queues for transmission, and optimizes the storage of the transmitted data.

[0045] In such Figure 1 In the application environment shown, the terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0046] In one embodiment, Figure 2 As shown, a method for scheduling power data transmission is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0047] Step S201 : collecting a multi-source power data set, normalizing the multi-source power data set and removing outliers to obtain a target power data set.

[0048] The multi-source power data set includes but is not limited to test results, sensor readings, monitoring videos, etc.

[0049] Specifically, the terminal collects data in real time from multiple sources in the production process of electrical equipment, including test results, sensor readings, monitoring videos, etc. These data are the basis for realizing intelligent monitoring and quality problem prediction. The collection process can be as follows:

[0050]

[0051] In the above formula, Represents the collected data set, and di represents the i-th data source.

[0052] Then, the terminal normalizes the multi-source power data set and removes outliers. The specific processing process is as follows:

[0053]

[0054]

[0055] In the above formula, Represents the original data, represents the mean of the data, represents the standard deviation of the data, represents the normalized data, represents the preprocessed data and IQR represents the interquartile range, which is used for outlier detection and removal.

[0056] Step S202 , dynamically slice the target power data set to divide the target power data set into a plurality of data slices, and schedule the plurality of data slices to corresponding processing units using a hash algorithm.

[0057] Dynamic slicing can be the process of segmenting a data set according to certain rules or conditions for analysis, processing or storage. The purpose of data slicing is to extract a specific subset from a large data set in order to process or analyze the data more efficiently.

[0058] Specifically, the terminal uses dynamic data slicing technology to divide the target power data set into multiple data slices suitable for transmission according to data characteristics and transmission requirements. The data slicing formula is as follows:

[0059]

[0060] In the above formula, Indicates data slices, Indicates the slice size, Represents the preprocessed data.

[0061] Then, the terminal uses a hash algorithm to schedule multiple data slices to corresponding processing units.

[0062] Step S203: In the processing unit, dynamic data transmission queues are constructed based on the multiple data slices.

[0063] Among them, the data transmission dynamic queue can be a system for efficiently managing data packets or task queues during data transmission. It can dynamically adjust data queuing, transmission and scheduling strategies according to the network, system load and real-time status.

[0064] Specifically, in the processing unit, the terminal constructs dynamic data transmission queues based on multiple data slices, and dynamically adjusts the scheduling strategy according to data traffic and priority, such as Figure 3 As shown, the construction of dynamic queues takes into account the real-time and importance of data to optimize transmission efficiency. The calculation formula for queue construction is as follows:

[0065]

[0066] In the above formula, Indicates The queue status of data points, Indicates data slices, is a smoothing factor used to balance the weights of new and old data slices.

[0067] Step S204, using a dynamic perception queue scheduling algorithm, performs transmission scheduling on the data transmission dynamic queue, and performs storage optimization on the transmitted data.

[0068] Among them, the Dynamic-Aware Queue Scheduling Algorithm can be a scheduling algorithm used in real-time systems, network traffic management, task scheduling and distributed systems. The algorithm dynamically adjusts the queue scheduling strategy by real-time monitoring and sensing system status, load changes and other factors to optimize resource utilization, reduce latency, improve system throughput, and can cope with system load fluctuations and sudden traffic.

[0069] Specifically, Figure 4As shown in the figure, the terminal uses a dynamic perception queue scheduling algorithm to schedule the data transmission dynamic queue and optimize the storage of the transmitted data to ensure fast data retrieval and analysis. Storage optimization considers the access frequency and importance of data and adopts a hierarchical storage strategy. The specific calculation formula is as follows:

[0070]

[0071] In the above formula, Indicates the optimized storage solution. Represents a collection of data slices, Indicates the data access mode, Indicates the data retention time, It is a storage optimization function.

[0072] In the above-mentioned power data transmission scheduling method, by using dynamic data slicing technology to dynamically slice the target power data set, the power data can be divided into data slices suitable for transmission according to the data type and transmission requirements of the target power data set, thereby optimizing the transmission process of the power data and improving the transmission efficiency of the power data; the data slices are then optimized and scheduled by the hash algorithm, further ensuring that the power data can be quickly and accurately transmitted to the corresponding processing unit, thereby enhancing the reliability and stability of power data transmission; finally, data transmission dynamic queues are constructed based on multiple data slices, and the dynamic perception queue scheduling algorithm is used to schedule the data transmission dynamic queues, thereby optimizing the data transmission process, and being able to quickly respond and adjust the data transmission strategy, so that it can cope with equipment failures or abnormal fluctuations in process parameters during the production process.

[0073] In one embodiment, in the above step S201, normalization processing and outlier removal are performed on the multi-source power data set, which specifically includes the following steps:

[0074] The multi-source power data set is input into the normalization processing model for zero-mean standardization processing to obtain the current data set that conforms to the standard normal distribution; the anomaly score of each data point in the current data set is evaluated through the isolation forest algorithm to obtain the anomaly score value corresponding to each data point; according to the anomaly score value, the abnormal data points in the current data set are identified and removed.

[0075] Specifically, the terminal inputs the multi-source power data set into the normalization processing model for zero-mean normalization processing to obtain the current data set that conforms to the standard normal distribution; then the pre-processed data is analyzed in real time to identify abnormal patterns. In this embodiment, intelligent monitoring is implemented through the Isolation Forest algorithm, which "isolates" observations by randomly selecting features and randomly selecting feature values. If an observation is easy to isolate, then it is likely to be abnormal. Monitoring function of the isolation forest It can be expressed as the following calculation formula:

[0076]

[0077] In the above formula, Indicates abnormal indicators. represents the isolation forest monitoring function, Represents the preprocessed data. The Isolation Forest algorithm is implemented by constructing multiple isolation trees, each of which randomly selects a feature and feature value to isolate the data point. The depth of the isolation tree It can be used to measure the ease of isolation and thus evaluate the abnormal score of a data point, as calculated by the following formula:

[0078]

[0079] In the above formula, Isolate data points The average path length of the tree is is the number of samples in the data set. The lower the anomaly score value, the more likely the data point is an anomaly.

[0080] In one embodiment, in the above step S203, a data transmission dynamic queue is constructed based on multiple data slices, which specifically includes the following steps:

[0081] The data flow and data priority of each data slice are obtained, and the queue status of each data slice is determined according to the data flow and data priority; a transmission strategy of a data transmission dynamic queue is generated according to the queue status; based on the transmission strategy, a data transmission dynamic queue containing multiple data slices is constructed.

[0082] Among them, data traffic may refer to the amount or speed of data transmitted in the network, and data priority may refer to the fact that different types of data flows or applications in the network can be given different processing priorities according to their urgency or importance.

[0083] Specifically, the terminal obtains the data flow and data priority of each data slice, determines the queue status of each data slice according to the data flow and data priority; generates the transmission strategy of the data transmission dynamic queue according to the queue status, and dynamically adjusts the transmission strategy in real time according to the data flow and data priority; based on the adjusted current transmission strategy, constructs a data transmission dynamic queue containing multiple data slices, such as: real-time queue, batch queue, fixed queue and file queue, etc. The construction of the queue takes into account the real-time and importance of the data, which helps to improve the data transmission efficiency.

[0084] In one embodiment, in the above step S202, the multiple data slices are scheduled to the corresponding processing units using a hash algorithm, which specifically includes the following steps:

[0085] The hash value of each data slice is calculated by a hash algorithm, and a scheduling strategy for each data slice is generated according to the hash value; based on the scheduling strategy, each data slice is scheduled to the corresponding processing unit.

[0086] Specifically, the terminal calculates the hash value of each data slice through a hash algorithm, and the hash algorithm can be calculated as follows:

[0087]

[0088] In the above formula, Representing data slices The hash value of represents a hash function, is the number of processing units. The design of hash functions needs to consider the characteristics of data slices to achieve efficient data scheduling.

[0089] Then, the terminal generates a scheduling strategy for each data slice according to the hash value, and then schedules each data slice to the corresponding processing unit based on the scheduling strategy.

[0090] In this embodiment, by using a hash algorithm to schedule data slices, it can be ensured that data is transmitted to the corresponding processing unit quickly and accurately.

[0091] In one embodiment, the method of the present application further comprises the following steps:

[0092] The first prediction probability of potential quality problems is calculated through the Bayesian probability calculation model according to the data transmission dynamic queue; the second prediction probability of the potential quality problem is obtained, and the target prediction probability of the potential quality problem is obtained by performing a fusion calculation based on the first prediction probability and the second prediction probability; the target quality problem is identified among the potential quality problems according to the target prediction probability and the warning threshold, and a warning response is generated for the target quality problem.

[0093] The second predicted probability may be obtained by comprehensive evaluation based on the opinions of monitoring personnel, technical experts, and the knowledge and experience of suppliers.

[0094] Specifically, the terminal applies the Bayesian probability calculation model to calculate the probability of quality problems, and realizes real-time prediction and early warning of potential quality problems. The Bayesian probability calculation model is specifically calculated as follows:

[0095]

[0096] In the above formula, The given data Post-quality issues The probability of occurrence, It's a quality issue The data is observed in the case of The probability of It's a quality issue The prior probability of It’s data The marginal probability of .

[0097] Then, the terminal performs a fusion calculation based on the first prediction probability and the second prediction probability to obtain a target prediction probability of a potential quality problem. The fusion calculation mechanism can be expressed by the following calculation formula:

[0098]

[0099] In the above formula, is the final predicted probability of quality problems, is the probability obtained by the Bayesian prediction model, is the predicted probability provided by the expert system, is a weighting factor used to adjust the impact of the two prediction methods.

[0100] When the terminal detects that the target prediction probability exceeds the warning threshold, it identifies the target quality problem among the potential quality problems, automatically triggers the warning for the target quality problem and takes corresponding measures. The calculation formula of the abnormal response mechanism is as follows:

[0101]

[0102] In the above formula, Indicates early warning response, represents the final predicted probability of quality problems, Indicates the preset warning threshold. It is the warning trigger function.

[0103] In addition, the terminal can also monitor system performance in real time, including key indicators such as data transmission rate and prediction accuracy. Figure 5As shown, performance monitoring can be achieved through the following calculation formula:

[0104]

[0105] In the above formula, Indicates the system performance score, Indicates the data transmission rate, represents the prediction accuracy, Indicates the utilization of system resources. , and is the weight factor, which is used to adjust the impact of various indicators. is the performance evaluation function.

[0106] In one embodiment, the method of the present application further comprises the following steps:

[0107] Obtain feedback data of the Bayesian probability calculation model, and generate optimized model parameters through the model parameter optimization model according to the feedback data; update the Bayesian probability calculation model according to the optimized model parameters to obtain an updated current Bayesian probability calculation model; the current Bayesian probability calculation model is used to replace the Bayesian probability calculation model.

[0108] The feedback data of the Bayesian probability calculation model may be historical output data obtained by calculation and processing by the Bayesian probability calculation model.

[0109] Specifically, the terminal continuously improves the accuracy of quality problem prediction through data iteration and algorithm optimization. The algorithm optimization process can be expressed as the following calculation formula:

[0110]

[0111] In the above formula, and Represent the model parameters before and after optimization, is the learning rate, is the loss function, is the loss function with respect to the parameters gradient.

[0112] In addition, this embodiment also introduces an adaptive learning mechanism, so that the terminal can continuously optimize the performance of the Bayesian probability calculation model according to new data and feedback. The adaptive learning process can be expressed as the following calculation formula:

[0113]

[0114] In the above formula, represents the model parameters after adaptation, and Represent the new and old model parameters respectively, Indicates new data or feedback, is the learning rate, is an adaptive learning function.

[0115] In one embodiment, Figure 6 As shown, a method for scheduling power data transmission in a specific embodiment is provided, which specifically includes the following steps:

[0116] Step S601, collect a multi-source power data set, input the multi-source power data set into a normalization processing model for zero-mean normalization processing, and obtain a current data set that conforms to the standard normal distribution; evaluate the abnormal score of each data point in the current data set by the isolation forest algorithm to obtain the abnormal score value corresponding to each data point; identify and remove the abnormal data points in the current data set according to the abnormal score value to obtain the target power data set,

[0117] Step S602, dynamically slice the target power data set to divide the target power data set into multiple data slices, and calculate the hash value of each data slice through a hash algorithm, and generate a scheduling strategy for each data slice based on the hash value; based on the scheduling strategy, schedule each data slice to the corresponding processing unit.

[0118] Step S603, in the processing unit, obtain the data flow and data priority of each data slice, determine the queue status of each data slice according to the data flow and data priority; generate a transmission strategy for the data transmission dynamic queue according to the queue status; based on the transmission strategy, construct a data transmission dynamic queue containing multiple data slices.

[0119] Step S604, calculate the first predicted probability of potential quality problems through the Bayesian probability calculation model according to the data transmission dynamic queue; obtain the second predicted probability of the potential quality problem, and perform a fusion calculation based on the first predicted probability and the second predicted probability to obtain the target predicted probability of the potential quality problem; identify the target quality problem among the potential quality problems based on the target predicted probability and the warning threshold, and generate a warning response for the target quality problem.

[0120] Step S605, using a dynamic perception queue scheduling algorithm, performs transmission scheduling on the data transmission dynamic queue, and performs storage optimization on the transmitted data.

[0121] The beneficial effects brought by the above embodiments are as follows:

[0122] 1) Through experimental verification, it demonstrates high efficiency and accuracy in the production quality management of electrical equipment, has significant practical application value, and provides an intelligent solution for data management and quality control in the electrical equipment manufacturing industry.

[0123] 2) It can improve the efficiency of data transmission, reduce the incidence of quality problems, optimize the sampling strategy, and minimize costs. Experimental verification shows that the method of this application has significant effects in practical applications and has important practical application value for improving the intelligent level of production quality management of electrical equipment.

[0124] 3) Through intelligent monitoring technology, key data in the production process is collected and analyzed in real time to provide basic information for data transmission and quality problem prediction. The application of dynamic data slicing technology enables the system to slice the collected data in real time according to the data type and transmission requirements, thereby improving the efficiency of data transmission. The hash algorithm optimization scheduling ensures that the data can be transmitted to the corresponding processing unit quickly and accurately. The application of Bayes' theorem enables the system to calculate the probability of quality problems based on real-time data, and realize real-time prediction and early warning of potential quality problems in the production process. The introduction of the collaborative judgment mechanism combines the knowledge and experience of monitoring personnel, technical experts and suppliers to make collaborative judgments on quality problems, thereby improving the accuracy and reliability of predictions.

[0125] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0126] Based on the same inventive concept, the embodiment of the present application also provides a power data transmission scheduling device for implementing the power data transmission scheduling method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more power data transmission scheduling device embodiments provided below can refer to the limitations of the power data transmission scheduling method above, and will not be repeated here.

[0127] In an exemplary embodiment, Figure 7 As shown, a power data transmission scheduling device is provided, comprising:

[0128] The data processing module 701 is used to collect multi-source power data sets, perform normalization processing and outlier removal on the multi-source power data sets, and obtain a target power data set;

[0129] The data scheduling module 702 is used to dynamically slice the target power data set to divide the target power data set into multiple data slices, and schedule the multiple data slices to corresponding processing units using a hash algorithm;

[0130] A queue construction module 703 is used to construct data transmission dynamic queues in the processing unit based on multiple data slices;

[0131] The transmission scheduling module 704 is used to utilize a dynamic perception queue scheduling algorithm to perform transmission scheduling on the data transmission dynamic queue and to optimize the storage of the transmitted data.

[0132] In one embodiment, the data processing module 701 is also used to input the multi-source power data set into the normalization processing model for zero-mean normalization processing to obtain a current data set that conforms to the standard normal distribution; perform an abnormal score evaluation on each data point in the current data set through the isolation forest algorithm to obtain the abnormal score value corresponding to each data point; and identify and remove abnormal data points in the current data set based on the abnormal score value.

[0133] In one embodiment, the queue construction module 703 is also used to obtain the data flow and data priority of each data slice, determine the queue status of each data slice according to the data flow and data priority; generate a transmission strategy for the data transmission dynamic queue according to the queue status; and construct a data transmission dynamic queue containing multiple data slices based on the transmission strategy.

[0134] In one embodiment, the data scheduling module 702 is also used to calculate the hash value of each data slice through a hash algorithm, and generate a scheduling strategy for each data slice according to the hash value; based on the scheduling strategy, each data slice is scheduled to a corresponding processing unit.

[0135] In one embodiment, the electric power data transmission scheduling device also includes an early warning response module, which is used to calculate a first predicted probability of a potential quality problem through a Bayesian probability calculation model according to a dynamic data transmission queue; obtain a second predicted probability of the potential quality problem, and perform a fusion calculation based on the first predicted probability and the second predicted probability to obtain a target predicted probability of the potential quality problem; identify a target quality problem among the potential quality problems based on the target predicted probability and the early warning threshold, and generate an early warning response for the target quality problem.

[0136] In one embodiment, the power data transmission and scheduling device also includes a model updating module, which is used to obtain feedback data of the Bayesian probability calculation model, and generate optimized model parameters through the model parameter optimization model according to the feedback data; according to the optimized model parameters, the Bayesian probability calculation model is updated to obtain an updated current Bayesian probability calculation model; the current Bayesian probability calculation model is used to replace the Bayesian probability calculation model.

[0137] Each module in the above-mentioned power data transmission and dispatching device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0138] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for scheduling power data transmission is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0139] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0140] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0141] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0142] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0143] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0144] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0145] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0146] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for scheduling power data transmission, characterized in that: The method comprises: Collecting a multi-source power data set, normalizing and removing outliers on the multi-source power data set to obtain a target power data set; Dynamically slice the target power data set to divide the target power data set into a plurality of data slices, and dispatch the plurality of data slices to corresponding processing units using a hash algorithm; In the processing unit, based on the plurality of data slices, respectively construct data transmission dynamic queues; The dynamic perception queue scheduling algorithm is used to schedule the data transmission dynamic queue and optimize the storage of the transmitted data.

2. The method according to claim 1, characterized in that The normalizing and outlier removal of the multi-source power data set includes: Inputting the multi-source power data set into a normalization processing model for zero-mean normalization processing to obtain a current data set that conforms to a standard normal distribution; An abnormal score evaluation is performed on each data point in the current data set by using an isolation forest algorithm to obtain an abnormal score value corresponding to each data point; According to the anomaly score value, abnormal data points in the current data set are identified and removed.

3. The method according to claim 1, characterized in that The step of constructing a dynamic data transmission queue based on the plurality of data slices comprises: Acquire the data flow and data priority of each of the data slices, and determine the queue state of each of the data slices according to the data flow and the data priority; generating a transmission strategy for the data transmission dynamic queue according to the queue state; Based on the transmission strategy, the data transmission dynamic queue including the plurality of data slices is constructed.

4. The method according to claim 1, characterized in that: The method of scheduling the plurality of data slices to corresponding processing units by using a hash algorithm includes: Calculating a hash value of each of the data slices by using the hash algorithm, and generating a scheduling strategy for each of the data slices according to the hash value; Based on the scheduling strategy, each of the data slices is scheduled to the corresponding processing unit.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Calculate the first predicted probability of potential quality problems through a Bayesian probability calculation model according to the data transmission dynamic queue; Obtaining a second predicted probability of the potential quality problem, and performing a fusion calculation based on the first predicted probability and the second predicted probability to obtain a target predicted probability of the potential quality problem; According to the target prediction probability and the early warning threshold, a target quality problem is identified among the potential quality problems, and an early warning response for the target quality problem is generated.

6. The method according to claim 5, characterized in that The method further comprises: Acquiring feedback data of the Bayesian probability calculation model, and generating optimized model parameters through a model parameter optimization model according to the feedback data; The Bayesian probability calculation model is updated according to the optimized model parameters to obtain an updated current Bayesian probability calculation model; the current Bayesian probability calculation model is used to replace the Bayesian probability calculation model.

7. A power data transmission and scheduling device, characterized in that: The device comprises: A data processing module, used for collecting multi-source power data sets, normalizing and removing outliers on the multi-source power data sets, and obtaining a target power data set; A data scheduling module, used for dynamically slicing the target power data set to divide the target power data set into a plurality of data slices, and scheduling the plurality of data slices to corresponding processing units by using a hash algorithm; A queue construction module, used for respectively constructing data transmission dynamic queues in the processing unit based on the plurality of data slices; The transmission scheduling module is used to utilize a dynamic perception queue scheduling algorithm to perform transmission scheduling on the data transmission dynamic queue and to optimize the storage of the transmitted data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images