A cloud-native multi-terminal intercommunication power plant industrial equipment management method and system

Abstract

The application belongs to the technical field of smart power plants and data middle platforms, and provides a cloud-native multi-terminal intercommunication power plant industrial equipment management method and system, specifically: in the smart power plant scene, a data middle platform and a data application terminal are included, and the data middle platform is configured with a load monitor; the load monitor is used to acquire a lag feature group in real time; the load pollution risk of each data service is calculated according to the lag feature group; and finally, the load pollution risk of each middle platform service is combined to determine the load abnormality of the base data middle platform. Through real-time monitoring of the data feedback quality of each middle platform service in the base data middle platform in the smart power plant scene, the risk of low reading efficiency in the process of providing middle platform services for the data application terminal by the base data middle platform is effectively quantified, the data pollution problem in the process of obtaining data services by the data application terminal is avoided, the stability of the data service is improved, and the risk of the data pollution problem to the data application terminal is reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of smart power plants and data middle platforms, and particularly relates to a cloud-native multi-end intercommunication power plant industrial equipment management method and system. BACKGROUND

[0002] With the rapid development of information technology, power plants are gradually transforming into intelligent smart power plants. A smart power plant integrates a base data middle platform and a data application end, which includes intelligent monitoring, data acquisition, power generation management, or energy efficiency management. The base data middle platform plays a centralized data service role in the smart power plant, providing the required data to the data application end to realize data sharing and integration of the smart power plant.

[0003] In the actual application of a smart power plant, the data application end obtains data services by calling the standardized interface of the data middle platform. In addition to the traditional basic functions of reading and storing, the data services also have middle platform functions such as interception, isolation, and preprocessing, which greatly reduce the risk of source data leakage through the data middle platform as a middle platform function. However, the process of the data application end obtaining the middle platform function services often has the problem of data pollution of the data application end. One of the reasons for this problem is the incompatibility of the collaborative working mode of multi-end intercommunication. The data format and interface design standards used by different systems themselves have differences, which makes the data services often face the risk of incompatibility, and thus the calling data obtained by the data application end has the risk of low reading efficiency, i.e., the timeliness of the feedback data does not meet the data request, which will cause the application data of the application end to be polluted and affect the accuracy of the execution results of the application processing program.

[0004] Currently, people's focus on data service acquisition is often concentrated on the interface adjustment process of data transmission, i.e., whether the data flow can be smoothly realized through the standardized interface. However, in the actual application process, the interface problem is not the only source of the low reading efficiency risk. Another important reason is that the data processing results fed back by the base data platform in the power plant have defects. These defects are often due to the high real-time requirement of power plant data processing. However, the cascading delay problem of multi-end intercommunication collaborative work amplifies the lag phenomenon of the feedback data, which has a strong correlation with the CPU occupancy and RAM occupancy in the server. When the service volume of individual middle platform services suddenly increases, this lag phenomenon will also affect other middle platform services running under the same server. Data with lag is non-requested data in real-time data application programs, and the transmission of non-requested data causes the reading efficiency risk of the data application end. In the data transmission process, the data service with defects is transmitted to the data application end, causing the quality pollution problem of the calling data. Therefore, there is an urgent need for a cloud-native multi-end intercommunication power plant industrial equipment management method and system. SUMMARY

[0005] The purpose of the present application is to propose a cloud-native multi-terminal interworking power plant industrial equipment management method and system to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0006] In order to achieve the above-mentioned purpose, according to an aspect of the present application, a cloud-native multi-terminal interworking power plant industrial equipment management method is provided, the method comprising the following steps:

[0007] In the smart power plant scene, a data middle platform and a data application terminal are included, and the data middle platform is configured with a load monitor; the lag feature group is obtained in real time through the load monitor; the load pollution risk of each middle platform service is calculated according to the lag feature group; and the base data middle platform load abnormality is determined in combination with the load pollution risk of each middle platform service.

[0008] Further, in the smart power plant scene, a data middle platform and a data application terminal are included, and the method of configuring the data middle platform with a load monitor is: the data middle platform provides several types of data services, the data application terminal obtains the data services by calling the standardized interface of the data middle platform, and the data request that is not directly read in the data service is defined as a middle platform service; the load monitor is a software layer load monitoring tool of the data middle platform.

[0009] Further, the method of obtaining the lag feature group in real time through the load monitor is: for the data request process of any next data application terminal under a middle platform service, the data in the data request of the data application terminal that needs to be obtained from the middle platform service is preset with a time stamp range, which is denoted as rq.tmk, and the time stamp range of the data actually sent by the middle platform service is denoted as st.tmk, and the load monitor monitors both: when st.tmk∈rq.tmk, the time domain of the data request result is defined as normal, otherwise the time domain of the data request result is overflowed; the data amount of the time domain overflow is denoted as overflow data amount; and the lag feature group is constructed according to the data request of the time domain overflow.

[0010] Further, the method of constructing the lag feature group according to the data request of the time domain overflow is: setting the data collection interval as DF, DF∈[60,180] seconds, and forming a data order value every interval time DF;

[0011] In the DF period, the percentage of the number of data requests of the time domain overflow in the total data request amount is denoted as overflow occurrence ratio, and the cumulative value of the overflow data amount is denoted as overflow cumulative value.

[0012] The binary group composed of the overflow occurrence ratio and the overflow cumulative value is denoted as the lag feature group.

[0013] Further, the method of calculating the load pollution risk of each middle platform service according to the lag feature group is:

[0014] The preset overflow occurrence threshold Ovth is 0.5, and the time point at which the hysteresis feature group is obtained each time is recorded as a measurement point;

[0015] For any middle station service, the overflow occurrence ratio is recorded as pto, and when pto> Ovth, the corresponding measurement point is recorded as a strong overflow point; define each measurement point between any strong overflow point and the first strong overflow point in the reverse time direction as an overflow interval, and the difference between the overflow cumulative value corresponding to any measurement point and the most distant measurement point in the overflow interval to which the measurement point belongs is the overflow difference value Ofd;

[0016] The principle of calculating and obtaining the overflow difference value is that the overflow difference value is a quantitative measure of data request processing delay, representing the performance fluctuation and load condition of data service when processing requests, reflecting an important index of data processing efficiency and delay characteristics of middle station service in a specific time period; the formation of the overflow difference value belongs to the difference quantization between any measurement point and the most distant measurement point in the overflow interval to which the measurement point belongs. This difference quantization makes full use of the time stamp monitoring angle of data request, deeply excavates the response characteristics of the system under high load, and constructs a dynamic monitoring model with the overflow difference value as the core by comprehensively considering the overlapping, processing delay and system load of data request, which can effectively capture the fluctuation trend in the data processing process, making it sensitive to the time domain change of data request. This sensitivity makes the model have better adaptability in high concurrency environment.

[0017] In any overflow interval, the overflow cumulative value corresponding to the measurement point with the minimum overflow occurrence ratio is obtained and recorded as the risk reference; the root mean square value of the risk reference of all middle station services at this measurement point is calculated and recorded as the reference level;

[0018] The ratio of the cumulative value of the overflow cumulative value in any overflow interval to the number of elements in the overflow cumulative value in the overflow interval that is greater than the corresponding reference level is the near risk level Neri;

[0019] The calculation method is as follows: Where k1 is an accumulation variable, nR is the number of elements in the overflow interval, OnR is the number of elements in the overflow interval whose overflow cumulative value is greater than the reference level, Ocv k1 is the overflow cumulative value of the k1th measurement point in the overflow interval corresponding to the measurement point;

[0020] According to the overflow interval, each sub-load pollution risk s.Losc is calculated:

[0021]

[0022] Where k2 is an accumulation variable, nR is the number of elements in the overflow interval, FnR is the number of negative overflow difference values in the overflow interval, and mid.Ofd is the median of the overflow difference values in the overflow interval.

[0023] The ratio of the sub-load pollution risk of the overflow interval to the number of elements in the overflow interval is taken as the load gradient, and the ratio of the load gradient of the current overflow interval to the average of the load gradients of each overflow interval except the current overflow interval is the load pollution risk;

[0024] Since the calculation of the load pollution risk is obtained by hierarchical processing according to the overflow interval of each measuring point, the risk of low reading efficiency in the calling data obtained by the data application scene data application end of the base data can be effectively quantified, but due to the excessive dependence on the distribution of the overflow occurrence ratio in the screening process of the strong overflow point, the sensitivity of the overflow cumulative value in the data analysis is reduced, and the problem of insufficient accuracy of the load pollution risk occurs, especially in the period when the strong overflow point occurs more densely, but the prior art cannot effectively compensate for this sensitivity decline phenomenon, in order to eliminate this influence, a more preferred scheme is proposed as follows.

[0025] Preferably, the method for calculating the load pollution risk of each middle station service according to the lag feature group is: the time when the lag feature group is obtained each time is recorded as a measuring point; for any middle station service, the median value of the overflow occurrence ratio of all measuring points is recorded as an overflow threshold value; if the overflow occurrence ratio of a measuring point is greater than the overflow threshold value and the overflow occurrence ratio of the measuring point is greater than that of the previous time, the measuring point is recorded as a marginal measuring point, otherwise it is a content measuring point;

[0026] The overflow cumulative value under all measuring points is normalized to form a cumulative normalization quantity, and the product of the overflow occurrence ratio of any measuring point and the cumulative normalization quantity is a lag module;

[0027] The minimum value of the overflow cumulative values of all marginal measuring points is taken as a marginal reference value, and the overflow critical condition of the measuring point is that the overflow cumulative value is greater than the marginal reference value; if there is a content measuring point that satisfies the overflow critical condition under the current middle station service, the average value of the overflow cumulative values of each content measuring point is calculated and recorded as an overflow critical threshold value; if there is no content measuring point that satisfies the overflow critical condition under any middle station service, the overflow critical threshold value is defined as the upper quartile of the overflow cumulative value of the content measuring point of the middle station service;

[0028] The corresponding measuring point whose overflow cumulative value is greater than the overflow critical threshold value is defined as a first critical point; if a first critical point is greater than the overflow cumulative values of the previous and subsequent first critical points, it is defined as a second critical point; the marginal interval is formed by the measuring points between any second critical point and the first second critical point in the reverse time direction;

[0029] The principle of calculating the overflow critical threshold is to use the trend of the overflow cumulative value, combine the marginal reference value and the quartile method, form an effective threshold setting mechanism, and search for the performance limit of the system under high load; if there is a content measurement point that meets the overflow critical condition, the critical threshold calculation program reveals the average performance of the system under the current load condition, which can effectively reflect the carrying capacity of the system under high load; the marginal reference value sets the lower limit for the evaluation of the overflow critical threshold, so that it can tolerate the minimum load state; in the case where the overflow critical condition is not met, the upper quartile is used to replace the threshold, ensuring the rationality and adaptability of the threshold, so that the system can be dynamically adjusted.

[0030] The marginal sub-interval is formed from any measurement point to the end point of its corresponding marginal interval. If the overflow occurrence ratio and the overflow cumulative value of a measurement point are both greater than those of the previous measurement point, the measurement point is defined as a sub-overflow measurement point, and the proportion of sub-overflow measurement points in the marginal sub-interval is the center amplification ratio Rgin; the derivation coefficient φ of the marginal interval is calculated according to the overflow occurrence ratio of the first critical point: φ = ln(∑ j2＝1 Rgin j2 × Spo j2 +1); where j2 is an accumulation variable, Spo j2 and Rgin j2 are the overflow occurrence ratio and the center amplification ratio of the j2th first critical point in the marginal interval, and ln() is the natural number e is the base number of the logarithmic function;

[0031] The calculation of the center amplification ratio is based on the dynamic monitoring of sub-overflow measurement points in the marginal sub-interval. The identification mechanism of sub-overflow measurement points in the marginal sub-interval ensures that the center amplification ratio only reflects abnormal data requests under high load conditions, making the center amplification ratio have good dynamic response capability and be able to reflect the changes of the system under different load conditions in real time. The center amplification ratio increases, indicating that the system is facing greater pressure and thus causing performance degradation or delay, so it is used as an early warning mechanism indicator to support the efficient operation of the system in complex environments.

[0032] The maximum value of all lag modules corresponds to the reference measurement point; the number of first critical points between any marginal interval and the reference measurement point is the reference weight Div;

[0033] The current load pollution risk Losc is calculated according to the derivation coefficient of the marginal interval and the reference weight:

[0034]

[0035] Where j1 is an accumulation variable, e is a natural constant, CT j1 and CB j1respectively, are the lag feature groups with the maximum and minimum lag modulus in the j1th marginal interval, Div j1 and SuDc j1 respectively, are the reference direction weight and the cumulative uniformity of the j1th marginal interval, the cumulative uniformity is the average of the overflow cumulative values in the marginal interval; min.SuDc represents the minimum value of all overflow cumulative values; GRLdx() is a slope function, and its return value is the slope between the two calling binary tuples.

[0036] Further, the method for judging the load abnormality of the base data center in combination with the load pollution risk of each middle station service is: if the load pollution risk at a moment is greater than that at the previous moment, it is defined that the middle station service has risk progression at the moment; if the z-score score corresponding to the maximum value of each load pollution risk at the same moment exceeds 3, it is considered that there is a sudden call at the moment;

[0037] the average value of each load pollution risk at the same moment is recorded as the risk set value at the moment, the first moment at which the risk set value appears a minimum value is searched in the reverse time direction from the current moment, each moment between the current moment and the moment is recorded as a reference point, and the ratio of the number of middle station services having risk progression at any reference point to the total number of middle station services at the reference point is recorded as the progression occurrence degree;

[0038] if the progression occurrence degree at the current moment is higher than 50%, and no sudden call occurs at each reference point at the current moment, it is judged that the load of the base data center is abnormal, and the server performance induced reading utility low risk occurs.

[0039] Preferably, when it is judged that the server performance induced reading utility low risk occurs, server resources are added to the base data center, the server resources including one or more of server nodes, CPUs, GPUs, RAM memories and bandwidths.

[0040] Preferably, in the present application, all undefined variables can be threshold values set by humans if not defined.

[0041] The present application also provides a cloud native multi-terminal interworking power plant industrial equipment management system, which comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to realize the steps in the cloud native multi-terminal interworking power plant industrial equipment management method, and the cloud native multi-terminal interworking power plant industrial equipment management system can run in desktop computers, notebook computers, palm computers and cloud data centers, and the executable system can include, but is not limited to, a processor, a memory, a server cluster, and the processor executes the computer program to run in the following system units:

[0042] The scenario building unit is used in smart power plant scenarios, including a data platform and a data application terminal, with the data platform configured with a load monitor;

[0043] The data acquisition unit is used to acquire hysteresis characteristic groups in real time through the load monitor;

[0044] The load pollution risk construction unit is used to calculate the load pollution risk of each data service based on the hysteresis characteristic group.

[0045] The data foundation resource monitoring unit is used to determine abnormal loads on the data foundation platform by combining the load pollution risk of various middleware services.

[0046] The beneficial effects of this invention are as follows: By real-time monitoring of the data feedback quality of each service platform in the data platform of the base in a smart power plant scenario, the risk of low read efficiency in the process of providing services to data application terminals is effectively quantified. Furthermore, anomalies in the timeliness of data obtained by each data application terminal from the data base are identified, and the server resource configuration strategy of the data platform is given early warning. Through these warnings and adjustments, data pollution problems are avoided during the data service acquisition process by data application terminals. This not only effectively ensures the reasonable allocation of server resources during data service provision by the data platform, improving the stability of data services, but also ensures the normal execution of various business processes or functions in the smart power plant that are highly sensitive to the timeliness of business data. Ultimately, this effectively improves the integration efficiency of the data platform and data application terminals in the smart power plant scenario and ensures the efficient operation of the entire smart power plant. Attached Figure Description

[0047] The above and other features of the present invention will become more apparent from the detailed description of the embodiments shown in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals denote the same or similar elements. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort. In the drawings:

[0048] Figure 1 The diagram shows a flowchart of a cloud-native multi-terminal interconnection method for managing industrial equipment in power plants.

[0049] Figure 2 The diagram shows the architecture of a cloud-native, multi-terminal, interconnected power plant industrial equipment management system. Detailed Implementation

[0050] The concept, specific structure and generated technical effects of the present application will be described clearly and completely in combination with embodiments and drawings to fully understand the purposes, schemes and effects of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0051] As Figure 1 shown is a flowchart of a power plant industrial equipment management method of cloud native multi-terminal interconnection, and the following will be described in combination with Figure 1 a power plant industrial equipment management method of cloud native multi-terminal interconnection according to an embodiment of the present application, the method comprising the following steps:

[0052] In the smart power plant scene, a data middle platform and a data application terminal are included, and the data middle platform is configured with a load monitor; the load monitor is used to acquire a lag feature group in real time; the load pollution risk of each middle platform service is calculated according to the lag feature group; and the base data middle platform load abnormality is determined in combination with the load pollution risk of each middle platform service.

[0053] Further, in the smart power plant scene, a data middle platform and a data application terminal are included, and the method of configuring the data middle platform with a load monitor is as follows: the data middle platform provides several types of data services, the data application terminal acquires the data services by calling the standardized interface of the data middle platform, and the data request that is not directly read in the data service is defined as a middle platform service; the load monitor is a software layer load monitoring tool of the data middle platform.

[0054] The data middle platform simultaneously runs several middle platform services, each middle platform service generates data transmission in the execution process, and the direction of the data transmission is from the data middle platform to the corresponding data application terminal; the load monitor is configured in the data middle platform, the load monitor is a software layer load monitoring tool, and is responsible for monitoring the data transmission information between the data middle platform and the data application terminal; the selection of the load monitor includes Prometheus, Grafana or New Relic; the middle platform service provided by the data middle platform needs to rely on server resources, and the server resources include cpu, bandwidth and RAM memory provided by several servers.

[0055] The data hub refers to a base data hub, which plays a centralized data service role in a smart power plant, is responsible for collecting, processing and storing data from other data application ends; the data application end is responsible for providing specific functions and operations, including intelligent monitoring and data collection application, power generation management application, energy efficiency management application, etc.; the data hub usually provides standardized interfaces including RESTful API or GraphQL API, and the data application end can obtain data services through these interfaces, including basic functions such as reading and storing, and middle platform functions such as interception, isolation and preprocessing; the transmission speed of the data obtained by the data application end through the standardized interface and the data transmitted by the data hub through the standardized interface is the same, and the data content read after format conversion is the same.

[0056] Further, the method of acquiring the lag feature group in real time through the load monitor is: for any data request process of a data application end under a middle platform service, the data required to be obtained from the middle platform service in the data request of the data application end is preset with a time stamp range, denoted as rq.tmk, and the time stamp range of the actual data sent by the middle platform service is denoted as st.tmk, and the load monitor monitors both: when st.tmk∈rq.tmk, the time domain of the data request result is defined as normal, otherwise the time domain of the data request result is overflow; the data amount of the time domain overflow is denoted as overflow data amount; the lag feature group is constructed according to the data request of the time domain overflow.

[0057] Each data request returns several records from the base data hub, each record has a time stamp, and the range of the time stamps corresponding to all the records under this data request is the time stamp range of the actual data sent by the middle platform service.

[0058] Further, the method of constructing the lag feature group according to the data request of the time domain overflow is: setting the data collection interval as DF, DF∈[60,180] seconds, and forming a data order value every interval time DF;

[0059] In the DF period, the percentage of the number of data requests of the time domain overflow in the total data request amount is denoted as the overflow occurrence ratio, and the cumulative value of the overflow data amount is denoted as the overflow cumulative value.

[0060] The binary tuple composed of the overflow occurrence ratio and the overflow cumulative value is denoted as the lag feature group.

[0061] In the data platform, several preset platform services are provided, each of which performs different data processing functions, including interception, isolation and preprocessing means in different preset data application environments, and data conversion means based on data models. Each data application end often needs to perform data requests for the same platform service in the data platform. These data requests have overlapping work tasks, but due to data isolation and different request parameters, the already processed data cannot be directly intercepted and used based on the timestamp. Since server resources are preset and allocated to each platform service, the more data requests occur at the same time, the greater the probability of lagging data.

[0062] Further, the method for calculating the load pollution risk of each platform service according to the lag feature group is:

[0063] The measurement point range is limited to the previous 24-72 hours of the current time;

[0064] The preset overflow occurrence threshold Ovth is 0.5, and the time when the lag feature group is obtained each time is recorded as a measurement point.

[0065] For any platform service, the overflow occurrence ratio is recorded as pto, and when pto> Ovth, the corresponding measurement point is recorded as a strong overflow point. The overflow interval is defined as the interval between any strong overflow point and the first strong overflow point in the reverse time direction. The difference between the overflow cumulative value corresponding to any measurement point and the most distant measurement point in the overflow interval is the overflow difference value Ofd. If the number of elements in the overflow interval is less than or equal to 30, it is excluded. By default, the current time is a strong overflow point. If the time interval between the current time and the strong overflow point searched in the reverse time direction is less than 30 minutes, the searched strong overflow point is ignored in the subsequent program.

[0066] Preferably, the preset overflow occurrence threshold Ovth has a first constraint condition that the number of strong overflow points is less than 20% of the total, and a second constraint condition that Ovth≥0.5. When a value that satisfies both the first constraint condition and the second constraint condition is searched, the minimum value among them is taken as the overflow occurrence threshold. Otherwise, the overflow occurrence threshold Ovth is set to 0.5.

[0067] The most distant measurement point in the overflow interval refers to the measurement point farthest from the current time.

[0068] In any overflow interval, the overflow cumulative value corresponding to the measurement point with the smallest overflow occurrence ratio is obtained and recorded as the risk reference. The root mean square value of the risk reference of all platform services at this measurement point is calculated and recorded as the reference level.

[0069] The ratio of the sum of overflow cumulative values in any overflow interval to the number of elements in the overflow cumulative value greater than the corresponding reference level in the overflow interval is the near risk level Neri.

[0070] The calculation method is: Wherein k1 is an accumulation variable, nR is the number of elements in the overflow interval, OnR is the number of elements in the overflow interval whose overflow cumulative value is greater than the reference level, Ocv k1 is the overflow cumulative value of the k1th measuring point in the overflow interval corresponding to the measuring point;

[0071] According to the overflow interval, each sub-load pollution risk s.Losc is calculated:

[0072]

[0073] Wherein k2 is an accumulation variable, nR is the number of elements in the overflow interval, FnR is the number of elements in the overflow interval whose overflow difference value is negative, mid.Ofd is the median value of the overflow difference value in the overflow interval; pto k2 is the overflow occurrence ratio of the k2th measuring point in the overflow interval, Ofd k2 is the overflow difference value of the k2th measuring point in the overflow interval, ln() is the logarithmic function with base e.

[0074] The ratio of the sub-load pollution risk of the overflow interval to the number of elements in the overflow interval is taken as the load gradient, and the ratio of the load gradient of the current overflow interval to the average of the load gradients of each overflow interval except the current overflow interval is taken as the load pollution risk;

[0075] The current measuring point refers to the nearest measuring point at the current time and having an overflow interval;

[0076] Preferably, the method for calculating the load pollution risk of each intermediate station service according to the lag feature group is: limiting the measuring point range to within 6-12 hours before the current time; the time when the lag feature group is obtained each time is recorded as the measuring point; for any intermediate station service, the median value of the overflow occurrence ratios of all measuring points is recorded as the overflow threshold value; if the overflow occurrence ratio of a measuring point is greater than the overflow threshold value and the overflow occurrence ratio of the measuring point is greater than that at the previous time, the measuring point is recorded as a marginal measuring point, otherwise as a content measuring point;

[0077] The overflow cumulative values of all measuring points are normalized to form a cumulative normalization quantity, and the product of the overflow occurrence ratio of any measuring point and the cumulative normalization quantity is a lag module;

[0078] The minimum value of the overflow cumulative values of all marginal measuring points is taken as a marginal reference value, and the overflow critical condition of the measuring point is that the overflow cumulative value is greater than the marginal reference value; if there is a content measuring point under the current intermediate station service that satisfies the overflow critical condition, the average value of the overflow cumulative values of each content measuring point is calculated and recorded as the overflow critical threshold value; if there is no content measuring point under any intermediate station service that satisfies the overflow critical condition, the overflow critical threshold value is defined as the upper quartile of the overflow cumulative values of the content measuring points of the intermediate station service.

[0079] A first critical point is defined as a corresponding measuring point whose overflow cumulative value is greater than the overflow critical threshold value; if a first critical point is greater than the overflow cumulative values of its previous and subsequent first critical points, it is defined as a second critical point; a marginal interval is formed by each measuring point between any second critical point and the first second critical point in the reverse time direction of the second critical point;

[0080] A marginal sub-interval is formed by any measuring point to the terminal measuring point of its corresponding marginal interval; if a measuring point is greater than the overflow occurrence proportion and the overflow cumulative value of its previous measuring point, such a measuring point is defined as a sub-overflow measuring point, and the proportion of sub-overflow measuring points in the marginal sub-interval is the central amplification proportion Rgin; the derivation coefficient φ of the marginal interval is calculated according to the overflow occurrence proportion of the first critical point: φ = ln(∑ j2＝1 Rgin j2 ×Spo j2 +1); in the formula, j2 is an accumulation variable, Spo j2 and Rgin j2 are the overflow occurrence proportion and the central amplification proportion of the j2th first critical point in the marginal interval, and ln() is a logarithmic function with the base number e;

[0081] The terminal measuring point of the marginal interval is the measuring point farthest from the current time in the marginal interval;

[0082] The reference measuring point is defined as the measuring point corresponding to the maximum value of all lag modules; the number of first critical points between any marginal interval and the reference measuring point is the reference direction weight Div; the measuring points between a marginal interval and the reference measuring point do not include the measuring points of the marginal interval itself;

[0083] The current load pollution risk Losc is calculated according to the derivation coefficient of the marginal interval and the reference direction weight:

[0084]

[0085] In the formula, j1 is an accumulation variable, e is a natural constant, CT j1 and CB j1 are the lag feature groups with the maximum value and the minimum value of the lag module in the j1th marginal interval, Div j1 and SuDc j1 are the reference direction weight and the cumulative uniformity of the j1th marginal interval, and the cumulative uniformity is the average value of the overflow cumulative values in the marginal interval; min.SuDc represents the minimum value of all overflow cumulative values; GRLdx() is a slope function, and its return value is the slope between the two calling binary tuples.

[0086] Further, the method for judging the load abnormality of the base data middle platform in combination with the load pollution risk of each middle platform service is: if the load pollution risk at a moment is greater than that at a previous moment, it is defined that the middle platform service has risk progression at the moment; if the maximum value of the load pollution risks at the same moment exceeds 3, it is considered that there is a sudden call at the moment;

[0087] The average value of the load pollution risks at the same moment is recorded as the risk set value at the moment, the first moment at which the risk set value appears a minimum value is searched in the reverse time direction from the current moment, each moment between the current moment and the moment is recorded as a reference point, and the ratio of the number of middle platform services having risk progression at any reference point to the total number of middle platform services at the reference point is recorded as the progression occurrence degree;

[0088] If the progression occurrence degree at the current moment is higher than 50%, and no sudden call occurs at each reference point at the current moment, it is judged that the base data middle platform has load abnormality, and the read efficiency is low due to the server performance.

[0089] Preferably, when it is judged that the read efficiency is low due to the server performance, server resources are added to the base data middle platform, and the server resources include one or more of server nodes, CPUs, GPUs, RAM memories and bandwidths.

[0090] The embodiment of the application provides a cloud native multi-terminal interworking power plant industrial equipment management system. Figure 2 As shown in the figure, the embodiment of the application is a cloud native multi-terminal interworking power plant industrial equipment management system structure diagram, the cloud native multi-terminal interworking power plant industrial equipment management system of the embodiment includes a processor, a memory and a computer program stored in the memory and executable on the processor, and the processor implements the steps in the cloud native multi-terminal interworking power plant industrial equipment management method embodiment when executing the computer program.

[0091] The system includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program running in the following system units:

[0092] The scene construction unit is configured to include a data middle platform and a data application terminal in the smart power plant scene, and the data middle platform is configured with a load monitor.

[0093] The data acquisition unit is configured to acquire a lag feature group in real time through the load monitor.

[0094] The load pollution risk construction unit is configured to calculate the load pollution risk of each data service according to the lag feature group.

[0095] The data base resource monitoring unit is used for determining the base data platform load abnormality in combination with the load pollution risk of each platform service.

[0096] The cloud-native multi-terminal interworking power plant industrial equipment management system can run in desktop computers, notebook computers, palm computers and cloud servers and other computing devices. The system that the cloud-native multi-terminal interworking power plant industrial equipment management system can run in can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the example is only an example of the cloud-native multi-terminal interworking power plant industrial equipment management system and does not constitute a limitation on the cloud-native multi-terminal interworking power plant industrial equipment management system, which can include more or fewer components, or combine certain components, or different components, for example, the cloud-native multi-terminal interworking power plant industrial equipment management system can also include input and output devices, network access devices, buses and the like.

[0097] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor, etc. The processor is the control center of the system that the cloud-native multi-terminal interworking power plant industrial equipment management system can run in, and connects each part of the entire system that the cloud-native multi-terminal interworking power plant industrial equipment management system can run in through various interfaces and lines.

[0098] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the cloud-native multi-terminal intercommunication power plant industrial equipment management system by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0099] Although the description of the present application has been quite detailed and particularly described with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present application. Furthermore, the present application is described above in embodiments that the inventors can foresee, and the purpose is to provide a useful description, and non-essential modifications to the present application that have not yet been foreseen can still represent equivalent modifications of the present application.

Claims

1. A cloud-native, multi-terminal interoperability method for managing industrial equipment in power plants, characterized in that: The method includes the following steps: in a smart power plant scenario, a data middle platform and a data application terminal are included; a load monitor is configured in the data middle platform; lag characteristic groups are obtained in real time through the load monitor; the load pollution risk of each middle platform service is calculated based on the lag characteristic groups; and the load anomaly of the base data middle platform is determined by combining the load pollution risk of each middle platform service. In the process of acquiring the lag feature group in real time through the load monitor, the percentage of data requests that cause time-domain overflow to the total number of data requests is recorded as the overflow occurrence ratio, and the cumulative value of the overflow data is recorded as the overflow cumulative value. The overflow occurrence ratio and the overflow cumulative value constitute the lag feature group. The method for calculating the load pollution risk of each middleware service based on the hysteresis feature group is as follows: the overflow occurrence threshold Ovth is preset to 0.5, and the time when the hysteresis feature group is obtained is recorded as the measurement point; for any middleware service, the overflow occurrence ratio is recorded as pto, and when pto>Ovth, the corresponding measurement point is recorded as a strong overflow point; the measurement points between any strong overflow point and the first strong overflow point in the reverse time direction are defined as the overflow interval, and the difference between any measurement point and the corresponding overflow cumulative value of the farthest measurement point in its overflow interval is the overflow difference value Ofd; In any overflow interval, obtain the cumulative overflow value corresponding to the measuring point with the smallest overflow occurrence ratio, and record it as the risk reference; calculate the root mean square value of the risk reference of all middleware services under this measuring point and record it as the reference level. The ratio of the sum of spillover accumulations in any spillover interval to the number of elements in that spillover accumulation interval that are greater than the corresponding reference level is the near-risk level, Neri. Where k1 is the cumulative variable, Ocv k1 The overflow accumulation is the sum of the k1th measurement point in the overflow interval corresponding to this measurement point, nR is the number of elements in the overflow interval, and OnR is the number of elements in the overflow interval whose overflow accumulation value is greater than the reference level; the pollution risk s.Losc of each sub-load is calculated based on the overflow interval. ； Where k2 is the cumulative variable, nR is the number of elements in the overflow interval, FnR is the number of negative overflow difference values ​​in the overflow interval, and mid.Ofd is the median value of the overflow difference values ​​in the overflow interval; The load gradient is the ratio of the sub-load contamination risk of the overflow interval to the number of elements in the overflow interval. The load contamination risk is the ratio of the load gradient of the current overflow interval to the average load gradient of all overflow intervals except the current overflow interval.

2. The cloud-native multi-terminal interconnected power plant industrial equipment management method according to claim 1, characterized in that, In the smart power plant scenario, there are data middleware and data application terminals. The method for configuring load monitors in the data middleware is as follows: the data middleware provides several types of data services, and the data application terminal obtains data services by calling the standardized interface of the data middleware. Data requests that are not directly read in the data services are defined as middleware services. Load monitors are software-level load monitoring tools for data middleware platforms.

3. The cloud-native multi-terminal interconnected power plant industrial equipment management method according to claim 1, characterized in that, The method for obtaining lag feature groups in real time through load monitoring is as follows: For any data request process of a data application terminal next to a middleware service, the data requested by the data application terminal from the middleware service has a preset timestamp range, denoted as rq.tmk, and the timestamp range of the data actually sent by the middleware service is denoted as st.tmk. The load monitor monitors both: when st.tmk∈rq.tmk, the time domain of the data request result is defined as normal; otherwise, the time domain of the data request result overflows. The amount of data that overflows in the time domain is denoted as the overflow data amount. Lag feature groups are constructed based on the data requests that overflow in the time domain.

4. The cloud-native multi-terminal interoperability power plant industrial equipment management method according to claim 3, characterized in that, The method for constructing a lag feature group based on data requests that have experienced time-domain overflow is as follows: set the data acquisition interval to DF, where DF ∈ [60, 180] seconds, and generate a data order value for each interval DF; during the DF period, the percentage of data requests that have experienced time-domain overflow to the total number of data requests is recorded as the overflow occurrence ratio, and the cumulative value of the overflow data is recorded as the overflow cumulative value; the tuple formed by the overflow occurrence ratio and the overflow cumulative value is recorded as the lag feature group.

5. The cloud-native multi-terminal interoperability power plant industrial equipment management method according to claim 1, characterized in that, The method for calculating the load pollution risk of each middleware service based on the hysteresis characteristic group is as follows: The time when the hysteresis characteristic group is obtained is recorded as a measurement point; for any middleware service, the median value of the overflow occurrence ratio of all measurement points is recorded as the overflow threshold; if the overflow occurrence ratio of a measurement point is greater than the overflow threshold and the overflow occurrence ratio of that measurement point is greater than its previous time point, then that measurement point is recorded as a marginal measurement point; otherwise, it is a content measurement point; the cumulative overflow values ​​under all measurement points are normalized to form a cumulative normalized value, and the product of the overflow occurrence ratio of any measurement point and the cumulative normalized value is the hysteresis modulus; the minimum value among the cumulative overflow values ​​of all marginal measurement points is taken as the marginal benchmark value, and the overflow critical condition of the measurement point is the overflow accumulation... If the product value is greater than the marginal baseline value, and there are content measurement points under the current middle platform service that meet the overflow critical condition, then calculate the average value of the overflow cumulative value of each content measurement point and record it as the overflow critical threshold; if there are no content measurement points that meet the overflow critical condition under any middle platform service, then define the overflow critical threshold as the upper quartile of the overflow cumulative value of the content measurement points of that middle platform service; define the corresponding measurement point whose overflow cumulative value is greater than the overflow critical threshold as the first critical point; if a first critical point is greater than the overflow cumulative value of both its previous and next first critical points, then define it as the second critical point; the marginal interval is formed by the measurement points between any second critical point and the first second critical point in the reverse time direction. The marginal sub-interval is formed by any measuring point and the end measuring point of its corresponding marginal interval. If a measuring point has a larger overflow occurrence ratio and overflow accumulation value than its predecessor measuring point, such a measuring point is defined as a sub-overflow measuring point. The proportion of sub-overflow measuring points in the marginal sub-interval is the central magnification ratio Rgin. The derivative coefficient of the marginal interval is calculated based on the overflow occurrence ratio of the first critical point. Define the measurement point corresponding to the maximum value among all hysteresis moduli as the benchmark measurement point; the number of the first critical points between any marginal interval and the benchmark measurement point is used as the benchmark weight Div; calculate the current load contamination risk based on the derivative coefficients of the marginal interval and the benchmark weight.

6. The cloud-native multi-terminal interoperability power plant industrial equipment management method according to claim 1, characterized in that, The method for determining the load anomaly of the base data middle platform by combining the load pollution risk of each middle platform service is as follows: if the load pollution risk at a certain moment is greater than that at the previous moment, it is defined that the middle platform service has a progressive risk at that moment; if the z-score corresponding to the maximum value of each load pollution risk at the same moment exceeds 3, it is considered that there is a sudden call at that moment. The average risk of each load pollution at the same moment is recorded as the risk set value at that moment. Starting from the current moment, the first moment when the risk set value reaches a minimum value is searched in reverse time. Each moment between that moment and the current moment is recorded as a reference point. The ratio of the number of middleware services with progressive risk at any reference point to the total number of middleware services at that reference point is recorded as the progressive occurrence degree. If the progressive occurrence degree at the current moment is higher than 50%, and no sudden calls occur at any reference point at the current moment, it is determined that the load of the base data middleware is abnormal, and the risk of low read efficiency induced by server performance occurs.

7. A cloud-native multi-terminal interoperability power plant industrial equipment management method according to claim 6, characterized in that, When it is determined that there is a risk of low read efficiency caused by server performance, server resources are added to the base data platform. Server resources include one or more of the following: server nodes, CPU, GPU, RAM, and bandwidth.

8. A cloud-native, multi-terminal, interconnected power plant industrial equipment management system, characterized in that, The cloud-native multi-terminal interconnected power plant industrial equipment management system includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the cloud-native multi-terminal interconnected power plant industrial equipment management method according to any one of claims 1-7. The cloud-native multi-terminal interconnected power plant industrial equipment management system runs on computing devices such as desktop computers, laptops, handheld computers, and cloud data centers.

Images