Power equipment control method and system based on computing power architecture

Abstract

The present disclosure provides a power equipment control method and system based on a computing power architecture, which relates to the field of power equipment control technology. The method includes: constructing a twin control platform for power equipment; constructing an algorithm database; performing algorithm analysis and evaluation according to preset dimensions, and constructing a multi-layer architecture of computing power; establishing a multi-layer mapping relationship between power equipment and computing power; comparing synchronous operation monitoring data with abnormalities, and locating abnormal data; using the location of abnormal data, performing abnormal-computing power level matching, determining matching computing power, and generating a computing power distribution execution strategy; determining a power equipment distribution control strategy, and sending it to a control platform to control the power equipment. The present disclosure can solve the technical problem in the prior art that the efficiency of power equipment control is low due to the situation that insufficient computing power or slow processing response is easily generated in power equipment control, thereby achieving the technical effect of improving the efficiency of power equipment control.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power equipment control, and in particular to a power equipment control method and system based on a computing power architecture. Background Art

[0002] There are different levels of algorithms in the computing power architecture. Some algorithms have fast processing speeds, while others have large computational workloads and slow speeds. The quality of the algorithm will affect the efficiency of the algorithm and even the program. If multiple algorithms are started at the same time for processing, it is easy to cause insufficient computing power or slow processing response of the program. At present, most of the existing power equipment controls are based on the control requirements to allocate algorithms and start them at the same time, resulting in insufficient computing power or slow processing response.

[0003] In summary, the prior art has a technical problem in which the efficiency of power equipment control is low due to insufficient computing power or slow processing response that is easily generated in power equipment control. Summary of the invention

[0004] The present disclosure provides a power equipment control method and system based on a computing power architecture, so as to solve the technical problem in the prior art that the power equipment control efficiency is low due to insufficient computing power or slow processing response that is easily generated in the power equipment control.

[0005] According to the first aspect of the present disclosure, a method for controlling power equipment based on a computing power architecture is provided, including: collecting connection control relationships of power equipment, and synchronously collecting operation monitoring data of power equipment, and constructing a power equipment twin control platform using digital twin technology; constructing an algorithm database based on the operation control requirements of power equipment; performing algorithm analysis and evaluation according to preset dimensions based on the algorithm database, and constructing a computing power multi-layer architecture; performing correlation analysis on operation control requirements between the algorithms in the computing power multi-layer architecture and the power equipment, and establishing a multi-layer mapping relationship between power equipment and computing power, including primary computing power and advanced computing power; extracting synchronous operation monitoring data through the power equipment twin control platform, comparing the synchronous operation monitoring data with abnormalities, and locating abnormal data; utilizing the location of abnormal data, performing abnormality-computing power level matching based on the multi-layer mapping relationship between power equipment and computing power, determining matching computing power, and generating a computing power distribution execution strategy; determining a power equipment distribution control strategy based on the computing power distribution execution strategy and abnormal data, and sending it to the control platform to control the power equipment.

[0006] According to the second aspect of the present disclosure, there is provided an electric power equipment control system based on a computing power architecture, including: an electric power equipment twin control platform construction module, the electric power equipment twin control platform construction module is used to collect connection control relationships of electric power equipment, and synchronously collect operation monitoring data of electric power equipment, and use digital twin technology to build an electric power equipment twin control platform; an algorithm database construction module, the algorithm database construction module is used to build an algorithm database based on the operation control requirements of electric power equipment; a computing power multi-layer architecture construction module, the computing power multi-layer architecture construction module is used to perform algorithm analysis and evaluation according to preset dimensions based on the algorithm database, and construct a computing power multi-layer architecture; a multi-layer mapping relationship establishment module, the multi-layer mapping relationship establishment module is used to compare the operation control requirements of the electric power equipment with the algorithms in the computing power multi-layer architecture A correlation analysis is performed to establish a multi-layer mapping relationship between power equipment and computing power, including primary computing power and advanced computing power; an abnormal data locating module is used to extract synchronous operation monitoring data through the power equipment twin control platform, compare the synchronous operation monitoring data with abnormalities, and locate abnormal data; a computing power distribution execution strategy generation module is used to utilize the location of abnormal data, based on the multi-layer mapping relationship between power equipment and computing power, to perform abnormality-computing power level matching, determine the matching computing power, and generate a computing power distribution execution strategy; a power equipment distribution control strategy acquisition module is used to determine the power equipment distribution control strategy according to the computing power distribution execution strategy and abnormal data, and send it to the control platform to control the power equipment.

[0007] One or more technical solutions provided in the present disclosure have at least the following technical effects or advantages: according to the method adopted in the present disclosure, by collecting the connection control relationship of the power equipment and synchronously collecting the operation monitoring data of the power equipment, a power equipment twin control platform is constructed using the digital twin technology; based on the operation control requirements of the power equipment, an algorithm database is constructed; according to the algorithm database, algorithm analysis and evaluation are performed according to preset dimensions to construct a multi-layer architecture of computing power; based on the algorithm in the multi-layer architecture of computing power and the power equipment, a correlation analysis of the operation control requirements is performed to establish a multi-layer mapping relationship between the power equipment and the computing power, including primary computing power and advanced computing power; through the power equipment The standby twin control platform extracts synchronous operation monitoring data, compares the synchronous operation monitoring data with anomalies, and locates abnormal data; utilizes the location of abnormal data, based on the multi-layer mapping relationship between power equipment and computing power, performs anomaly-computing power level matching, determines the matching computing power, and generates a computing power distribution execution strategy; determines the power equipment distribution control strategy based on the computing power distribution execution strategy and abnormal data, and sends it to the control platform to control the power equipment, which solves the technical problem in the prior art that the efficiency of power equipment control is low due to insufficient computing power or slow processing response in power equipment control, and achieves the technical effect of improving the efficiency of power equipment control.

[0008] It should be understood that the contents described in this section are not intended to indicate the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present disclosure or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a method for controlling electric power equipment based on a computing power architecture provided in an embodiment of the present disclosure;

[0011] Figure 2 A schematic diagram of a process for constructing an algorithm database in a power equipment control method based on a computing power architecture according to an embodiment of the present disclosure;

[0012] Figure 3 A schematic diagram of the structure of an electric power equipment control system based on a computing power architecture provided in an embodiment of the present disclosure.

[0013] Explanation of the accompanying drawings: power equipment twin control platform construction module 11, algorithm database construction module 12, computing power multi-layer architecture construction module 13, multi-layer mapping relationship establishment module 14, abnormal data locating module 15, computing power distribution execution strategy generation module 16, power equipment distributed control strategy acquisition module 17. DETAILED DESCRIPTION

[0014] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0015] Embodiment 1

[0016] The power equipment control method based on computing power architecture provided in the embodiment of the present disclosure is referred to Figure 1 and Figure 2 Illustratively, the method comprises:

[0017] The method provided in the embodiment of the present disclosure includes:

[0018] Collect the connection control relationship of power equipment, and simultaneously collect the operation monitoring data of power equipment, and use digital twin technology to build a twin control platform for power equipment;

[0019] Specifically, the connection control relationship of the power equipment is collected. Among them, the power equipment is composed of multiple electronic components, devices and electromechanical components. The electrical connection between any two electronic components, devices and electromechanical components is a connection. Multiple electronic components are connected according to the circuit diagram to complete the predetermined function. Further, the operation monitoring data of the power equipment is synchronously collected to obtain synchronous operation monitoring data. For example, the operation monitoring data of the power equipment includes equipment parameters such as temperature, vibration, and speed, as well as process parameters such as pressure, voltage, and current. Further, the digital twin is to integrate multidisciplinary and multi-scale simulation processes using data such as physical models, sensors, and operation history. The digital twin model is a mirror image of the physical object in the virtual space, reflecting the entire life cycle process of the physical object. Further, using digital twin technology, according to the connection control relationship and operation monitoring data of the power equipment, a digital twin model of the power equipment is constructed as a twin control platform for the power equipment.

[0020] Build an algorithm database based on the operation and control requirements of power equipment;

[0021] Specifically, according to the processing speed requirements, communication requirements, memory requirements, etc. of the power equipment, the operation control computing power requirements of the power equipment are obtained, and the operation control algorithm is determined. The correspondence between the power equipment control parameters and the operation control algorithm is established. Based on the historical power equipment control records, the abnormal fault data of multiple power equipment are extracted. According to the abnormal fault data, the reasons for the abnormal fault data that do not meet the operation processing requirements are obtained, and then the corresponding abnormal processing algorithm is determined. The abnormal fault data is classified, the abnormal fault type is obtained, and the correspondence between the abnormal fault type and the abnormal processing algorithm is established. According to the correspondence between the power equipment control parameters and the operation control algorithm, and the correspondence between the abnormal fault type and the abnormal processing algorithm, an algorithm database is constructed.

[0022] Perform algorithm analysis and evaluation according to preset dimensions based on the algorithm database to build a multi-layer computing architecture;

[0023] Specifically, extract the power equipment control requirements of each algorithm in terms of memory, communication, and energy consumption, determine the evaluation results of the algorithm's processing of the memory, communication, and energy consumption requirements in the power equipment control, and obtain the multi-dimensional evaluation coefficients of each algorithm in terms of memory, communication, and energy consumption. Obtain the abnormal fault type or power equipment control parameter corresponding to each algorithm in the algorithm database, and obtain the corresponding power equipment. Associate the power equipment with the corresponding algorithm to determine the corresponding algorithm information of the power equipment. According to the multi-dimensional evaluation coefficient of each algorithm, divide the computing power level of the corresponding algorithm of each power equipment. Combine multiple power equipment with the corresponding multiple algorithms, determine the multi-level algorithm information of each power equipment, and build a multi-layer computing power architecture based on the multi-level algorithm information of each power equipment.

[0024] Based on the algorithm in the multi-layer architecture of the computing power and the correlation analysis of the operation control requirements of the power equipment, a multi-layer mapping relationship between the power equipment and the computing power is established, including primary computing power and advanced computing power;

[0025] Specifically, according to the difficulty of operation control requirements, the algorithms and power equipment in the multi-layer architecture of computing power are divided into primary computing power, advanced computing power and corresponding power equipment. According to the division rules of primary computing power, advanced computing power and corresponding power equipment, a multi-layer mapping relationship between power equipment and computing power is established.

[0026] Extracting synchronous operation monitoring data through the power equipment twin control platform, comparing the synchronous operation monitoring data with abnormalities, and locating abnormal data;

[0027] Specifically, the operating data of the power equipment when it meets the operation control requirements is collected as the standard parameter characteristics. The corresponding relationship between the synchronous operation monitoring data and the standard parameter characteristics is obtained, and the synchronous operation monitoring data and the standard parameter characteristics with the corresponding relationship are used to perform operation control on the same operation control requirements. The synchronous operation monitoring data and the standard parameter characteristics of each corresponding relationship are accessed in turn, the comparison difference is obtained, and the abnormal parameters are determined. Abnormal power equipment is located based on the abnormal parameters, and abnormal power equipment and abnormal data are located.

[0028] By locating abnormal data and based on the multi-layer mapping relationship between power equipment and computing power, we can match the abnormality and computing power levels, determine the matching computing power, and generate a computing power distribution execution strategy.

[0029] Specifically, an abnormal assessment prediction of abnormal power equipment is performed based on the abnormality. The abnormal assessment level of the power equipment is obtained. According to the abnormal impact corresponding to the abnormal data, the equipment impact and the associated equipment impact analysis are performed on the abnormal power equipment to determine the risk coefficient of the abnormal equipment. In combination with the abnormal assessment level and the risk coefficient of the abnormal equipment, different computing powers are allocated, and abnormal-computing power level matching is performed to determine the matching computing power. Among them, the level of matching computing power is proportional to the abnormal assessment level and the risk coefficient of the abnormal equipment. When the abnormal assessment level and the risk coefficient of the abnormal equipment are higher, the level of matching computing power is higher. When the abnormal assessment level and the risk coefficient of the abnormal equipment are lower, the level of matching computing power is lower.

[0030] The power equipment distribution control strategy is determined according to the computing power distribution execution strategy and abnormal data, and is sent to the control platform to control the power equipment.

[0031] Specifically, according to the abnormal data, determine the abnormal power equipment corresponding to the abnormal data, determine the abnormal power equipment and its connection relationship. Perform correlation impact analysis on the abnormal power equipment and abnormal power-related equipment, and monitor the operation monitoring data of the abnormal power-related equipment. Compare the operation monitoring data of the abnormal power-related equipment with the algorithm database to obtain the impact of the abnormal equipment. Perform control node optimization to obtain the power equipment distribution control strategy and send it to the power equipment twin control platform to control the power equipment.

[0032] Among them, this embodiment can solve the technical problem in the prior art that the efficiency of power equipment control is low due to insufficient computing power or slow processing response in the power equipment control, thereby achieving the technical effect of improving the efficiency of power equipment control.

[0033] The method provided in the embodiment of the present disclosure also includes:

[0034] Obtain the operation control computing power requirements of the power equipment, determine the operation control algorithm, and establish the corresponding relationship between the power equipment control parameters and the operation control algorithm;

[0035] Extract the abnormal fault database of power equipment, analyze the operation and processing requirements based on the abnormal fault data, obtain the abnormal processing algorithm, and establish the corresponding relationship between the abnormal fault type and the abnormal processing algorithm;

[0036] The algorithm database is constructed based on the correspondence between the control parameters of the power equipment and the operation control algorithm, and the correspondence between the abnormal fault type and the abnormality processing algorithm.

[0037] Specifically, according to the processing speed requirements, communication requirements, memory requirements, etc. of the power equipment, the operation control computing power requirements of the power equipment are obtained, and the operation control algorithm is determined. Among them, when the computing power requirement is higher, an algorithm with a faster response speed and a higher degree of complexity is set to improve the efficiency of computing power utilization. When the computing power requirement is lower, a simpler and more elementary algorithm is set. Further, a correspondence between the control parameters of the power equipment and the operation control algorithm is established. Among them, for algorithms with faster response speeds and higher degrees of complexity, more parameter control changes are set for the control parameters of the power equipment, and for algorithms with simpler and more elementary degrees, fewer parameter control changes are set for the control parameters of the power equipment.

[0038] Furthermore, based on the historical power equipment control records, the abnormal fault data of multiple power equipment are extracted and combined to obtain the abnormal fault database of the power equipment. The operation processing requirements are analyzed according to the abnormal fault data to obtain the cause of the abnormal fault, that is, the cause of the abnormal fault data obtained by not meeting the operation processing requirements, and then determine the corresponding abnormal processing algorithm causing the abnormal fault cause. The abnormal fault data is classified, the abnormal fault type is obtained, and the corresponding relationship between the abnormal fault type and the abnormal processing algorithm is established. For example, when the operation processing requirement is to sum, the abnormal processing algorithm is obtained to apply the multiplication sign, and the abnormal fault data is obtained.

[0039] Furthermore, the correspondence between the control parameters of the power equipment and the operation control algorithm, and the correspondence between the abnormal fault type and the abnormal processing algorithm are added and an algorithm database is constructed, wherein the algorithm database is constructed to improve the efficiency of obtaining the control of the power equipment.

[0040] The method provided in the embodiment of the present disclosure also includes:

[0041] Analyze and evaluate each algorithm in the algorithm database according to the requirements of memory, communication, and energy consumption, and determine the evaluation coefficient of each dimension;

[0042] Based on the power equipment corresponding to each algorithm in the algorithm database, perform equipment correspondence analysis to determine the corresponding algorithm information of the power equipment;

[0043] According to the multi-dimensional evaluation coefficient of each algorithm, the corresponding algorithm of each power device is divided into computing power levels, the multi-level algorithm information of each power device is determined, and the computing power multi-layer architecture is constructed based on the multi-level algorithm information of each power device.

[0044] Specifically, according to the power equipment control requirements in the dimensions of memory, communication, and energy consumption of the power equipment, each algorithm in the algorithm database is analyzed and evaluated, the memory, communication, and energy consumption dimensional requirements of each algorithm are extracted, and the dimensional evaluation coefficients of the memory, communication, and energy consumption dimensions of each algorithm are determined. Among them, the dimensional evaluation coefficient is the evaluation result of the algorithm processing the memory, communication, and energy consumption requirements in the power equipment control. When the memory, communication, and energy consumption requirements are higher, the control of the power equipment through the algorithm reaches or is closer to the memory, communication, and energy consumption requirements, and the memory, communication, and energy consumption dimension evaluation coefficients of the algorithm are higher.

[0045] Furthermore, according to each algorithm in the algorithm database, the abnormal fault type or power equipment control parameter corresponding to the algorithm is obtained, and the corresponding power equipment is obtained according to the abnormal fault type or power equipment control parameter. The power equipment is analyzed for equipment correspondence, the power equipment is associated with the corresponding algorithm, and the corresponding algorithm information of the power equipment is determined.

[0046] Furthermore, according to the multi-dimensional evaluation coefficient of each algorithm, the corresponding algorithm of each power device is divided into computing power levels. Among them, the algorithm with a higher multi-dimensional evaluation coefficient is divided into a higher level of computing power corresponding to the algorithm. Furthermore, multiple power devices are combined with corresponding multiple algorithms to determine the multi-level algorithm information of each power device, and a multi-layer computing power architecture is constructed based on the multi-level algorithm information of each power device.

[0047] Among them, a multi-layer computing power architecture is built to improve the efficiency of power equipment control.

[0048] The method provided in the embodiment of the present disclosure also includes:

[0049] Collect normal operation data of each power equipment and construct a standard parameter feature set for each power equipment;

[0050] Using the synchronous operation monitoring data and the standard parameter feature set to perform multi-parameter same-direction traversal comparison to determine abnormal parameters;

[0051] Abnormal power equipment is located based on the abnormal parameters to locate abnormal power equipment and abnormal data.

[0052] Specifically, by obtaining the operation control requirements of the power equipment, the normal operation data of each power equipment is collected. The normal operation data is the operation data when the operation data of the power equipment meets the operation control requirements, that is, the standard parameter characteristics. Further, the standard parameter feature set of each power equipment is constructed based on the normal operation data combination.

[0053] Furthermore, the electric power equipment has multiple synchronous operation monitoring data and multiple standard parameter features. According to the operation control requirements of the electric power equipment, the correspondence between the synchronous operation monitoring data and the standard parameter features is obtained, and the synchronous operation monitoring data and the standard parameter features with the corresponding relationship are used to perform operation control on the same operation control requirements. Further, according to the correspondence between the synchronous operation monitoring data and the standard parameter features, the synchronous operation monitoring data and the standard parameter features of each corresponding relationship are accessed in turn to obtain the comparison difference and determine the abnormal parameters. Further, the abnormal electric power equipment is located based on the abnormal parameters, and the abnormal electric power equipment and abnormal data are located. Among them, obtaining abnormal data can improve the efficiency of subsequent computing power matching.

[0054] The method provided in the embodiment of the present disclosure also includes:

[0055] Determine an abnormal deviation value according to the abnormal data, perform an abnormal evaluation prediction of the abnormal power equipment based on the abnormal deviation value, and obtain an abnormal evaluation level of the power equipment;

[0056] Analyze the impact of abnormal power equipment and related equipment to determine the risk factor of abnormal equipment;

[0057] Based on the abnormality assessment level and the risk coefficient of the abnormal device, an abnormality-computing power level matching is performed to determine the matching computing power, wherein the level of the matching computing power is proportional to the abnormality assessment level and the risk coefficient of the abnormal device.

[0058] Specifically, the comparison difference is extracted according to the abnormal data as the abnormal deviation value. The abnormal evaluation prediction of the abnormal power equipment is performed based on the abnormal deviation value. The abnormal evaluation level of the power equipment is obtained. Among them, the larger the abnormal deviation value, the greater the abnormal impact caused by the abnormal deviation value, and the higher the abnormal evaluation level is obtained.

[0059] Furthermore, according to the abnormal impact corresponding to the abnormal deviation value, the equipment impact degree and the associated equipment impact degree of the abnormal power equipment are analyzed to determine the risk coefficient of the abnormal equipment. The higher the equipment impact degree and the associated equipment impact degree, the higher the risk of failure caused by the abnormal deviation value, and the higher the risk coefficient of the abnormal equipment.

[0060] Furthermore, different computing powers are allocated based on the abnormality assessment level and the risk coefficient of abnormal equipment, and abnormality-computing power level matching is performed to determine the matching computing power. Among them, the level of matching computing power is proportional to the abnormality assessment level and the risk coefficient of abnormal equipment. When the abnormality assessment level and the risk coefficient of abnormal equipment are higher, the level of matching computing power is higher. When the abnormality assessment level and the risk coefficient of abnormal equipment are lower, the level of matching computing power is lower.

[0061] Among them, the matching computing power is obtained for subsequent adjustment and control to improve the efficiency of power equipment control.

[0062] The method provided in the embodiment of the present disclosure also includes:

[0063] Setting weight values ​​of the abnormality assessment level and the risk coefficient of the abnormal equipment, and calculating and obtaining the fault risk coefficient based on the weight values, the abnormality assessment level and the risk coefficient of the abnormal equipment;

[0064] Perform a computing power response requirement analysis based on the fault risk coefficient to determine computing power accuracy requirements and computing power speed requirements;

[0065] The matching computing power is determined based on the computing power accuracy requirement, computing power speed requirement and the multi-level computing power matching corresponding to the abnormal power equipment.

[0066] Specifically, the weight values ​​of the abnormal assessment level and the risk coefficient of the abnormal equipment are set. Based on the product of the abnormal assessment level weight value and the abnormal assessment level, and the product of the risk coefficient weight value of the abnormal equipment and the risk coefficient of the abnormal equipment, the fault risk coefficient is obtained by summing up. The weight value is customized based on the actual situation by the counting personnel in this field, for example, 6:4.

[0067] Furthermore, the computing power response requirements are analyzed according to the fault risk coefficient to determine the computing power accuracy requirements and computing power speed requirements. Among them, when the fault risk coefficient is lower, it means that the fault has a lower impact on the operation and control of the power equipment, and the parameters obtained by allocating primary computing power for operation control are close to the parameters obtained by allocating advanced computing power for operation control, which means that the computing power accuracy and speed requirements are less correlated with abnormal power equipment with lower fault risk coefficients. Therefore, the lower the computing power accuracy requirements for its configuration, the lower the computing power speed requirements.

[0068] Furthermore, according to the computing power accuracy requirements and computing power speed requirements, the corresponding computing power accuracy and computing power speed are configured for the multi-level computing power corresponding to the abnormal power equipment to determine the matching computing power.

[0069] Among them, the matching computing power is determined to be used for monitoring and judging primary faults.

[0070] The method provided in the embodiment of the present disclosure also includes:

[0071] Determining abnormal power equipment and abnormal assessment level according to the abnormal data;

[0072] According to the abnormal power equipment, determine the power equipment connection relationship, perform correlation impact analysis on the abnormal power equipment, and obtain the impact of the abnormal equipment and the abnormal operation tolerance time;

[0073] Determine the time node for distributing computing power according to the computing power distribution execution strategy;

[0074] Based on the impact of the abnormal equipment, the abnormal operation tolerance time, and the distributed computing power time node, the control node is optimized to determine the power equipment distribution control strategy, which is used to control the power equipment in stages according to the control node.

[0075] Specifically, according to the abnormal data, the abnormal power equipment corresponding to the abnormal data is determined, and an abnormal evaluation prediction of the abnormal power equipment is performed to obtain an abnormal evaluation level.

[0076] Furthermore, according to the abnormal power equipment, matching is performed in the connection control relationship of the power equipment to determine the abnormal power equipment and its connection relationship. An analysis of the correlation influence of the abnormal power equipment and the abnormal power-related equipment is performed, and the operation monitoring data of the abnormal power-related equipment is monitored. The operation monitoring data of the abnormal power-related equipment is compared with the algorithm database to obtain the abnormal equipment impact and abnormal operation tolerance time. Among them, the abnormal operation tolerance time is the time to wait for the calculation results of the computing power of other power equipment. Furthermore, when the abnormal evaluation level is higher, in order to ensure the accuracy of the control, the power equipment with a lower abnormal equipment impact is first controlled and adjusted, and the computing power is recalculated, and the waiting time for the computing power calculation is generated.

[0077] Furthermore, according to the matching computing power of the computing power distribution execution strategy, the time period of computing power distribution is calculated. The initial allocation time node is set, and the distributed computing power time nodes are determined in sequence according to the time period of computing power distribution. Among them, the distributed computing power time node is the time interval node of the entire computing power distribution calculation.

[0078] Furthermore, based on the abnormal equipment impact, abnormal operation tolerance time, and distributed computing power time node, multiple power equipment distribution control strategies are obtained, and the control node optimization is performed. The obtained power equipment distribution control strategy is used to control the power equipment in stages according to the control node. Among them, the abnormal power equipment with a higher abnormal evaluation level and a higher abnormal equipment impact is controlled first, and then the abnormal power equipment with a higher abnormal evaluation level and a lower abnormal equipment impact is controlled.

[0079] Among them, the accuracy of power equipment control can be ensured by optimizing the distributed control strategy of power equipment.

[0080] Embodiment 2

[0081] Based on the same inventive concept as the power equipment control method based on computing power architecture in the aforementioned embodiment, reference is made to Figure 3 For illustration, the present disclosure also provides a power equipment control system based on a computing power architecture, the system comprising:

[0082] A power equipment twin control platform construction module 11, wherein the power equipment twin control platform construction module 11 is used to collect the connection control relationship of the power equipment, and simultaneously collect the operation monitoring data of the power equipment, and use the digital twin technology to build a power equipment twin control platform;

[0083] An algorithm database construction module 12, wherein the algorithm database construction module 12 is used to construct an algorithm database based on the operation control requirements of the power equipment;

[0084] A computing power multi-layer architecture construction module 13, wherein the computing power multi-layer architecture construction module 13 is used to perform algorithm analysis and evaluation according to the algorithm database according to preset dimensions to construct a computing power multi-layer architecture;

[0085] A multi-layer mapping relationship establishment module 14, which is used to perform a correlation analysis of operation control requirements on the power equipment based on the algorithm in the computing power multi-layer architecture and establish a multi-layer mapping relationship between the power equipment and the computing power, including primary computing power and advanced computing power;

[0086] An abnormal data locating module 15, the abnormal data locating module 15 is used to extract synchronous operation monitoring data through the power equipment twin control platform, compare the synchronous operation monitoring data with abnormalities, and locate abnormal data;

[0087] A computing power distribution execution strategy generation module 16, which is used to utilize the location of abnormal data, perform abnormality-computing power level matching based on the multi-layer mapping relationship between power equipment and computing power, determine the matching computing power, and generate a computing power distribution execution strategy;

[0088] The power equipment distribution control strategy acquisition module 17 is used to determine the power equipment distribution control strategy according to the computing power distribution execution strategy and abnormal data, and send it to the control platform to control the power equipment.

[0089] Furthermore, the system further comprises:

[0090] A corresponding relationship acquisition module, the corresponding relationship acquisition module is used to obtain the operation control computing power requirements of the power equipment, determine the operation control algorithm, and establish a corresponding relationship between the power equipment control parameters and the operation control algorithm;

[0091] An abnormality processing algorithm acquisition module, which is used to extract an abnormal fault database of power equipment, perform operation and processing requirement analysis based on abnormal fault data, obtain an abnormality processing algorithm, and establish a corresponding relationship between abnormal fault types and abnormality processing algorithms;

[0092] The algorithm database acquisition module is used to construct the algorithm database based on the corresponding relationship between the control parameters of the power equipment and the operation control algorithm, and the corresponding relationship between the abnormal fault type and the abnormal processing algorithm.

[0093] Furthermore, the system further comprises:

[0094] A module for obtaining evaluation coefficients of each dimension, wherein the module for obtaining evaluation coefficients of each dimension is used to analyze and evaluate each algorithm in the algorithm database according to the requirements of memory, communication, and energy consumption, and determine the evaluation coefficients of each dimension;

[0095] A corresponding algorithm information acquisition module for electric equipment, the corresponding algorithm information acquisition module for electric equipment is used to perform equipment correspondence analysis based on the electric equipment corresponding to each algorithm in the algorithm database, and determine the corresponding algorithm information of the electric equipment;

[0096] A computing power multi-layer architecture acquisition module is used to classify the computing power levels of the corresponding algorithms of each power device according to the multi-dimensional evaluation coefficients of each algorithm, determine the multi-level algorithm information of each power device, and construct the computing power multi-layer architecture based on the multi-level algorithm information of each power device.

[0097] Furthermore, the system further comprises:

[0098] A standard parameter feature set acquisition module, which is used to collect normal operation data of each power device and construct a standard parameter feature set of each power device;

[0099] An abnormal parameter acquisition module, the abnormal parameter acquisition module is used to perform a multi-parameter same-direction traversal comparison using the synchronous operation monitoring data and the standard parameter feature set to determine the abnormal parameters;

[0100] An abnormal power equipment locating module is used to locate abnormal power equipment based on the abnormal parameters, and locate abnormal power equipment and abnormal data.

[0101] Furthermore, the system further comprises:

[0102] An abnormality assessment level obtaining module, the abnormality assessment level obtaining module is used to determine an abnormal deviation value according to the abnormal data, perform abnormality assessment prediction of abnormal power equipment based on the abnormal deviation value, and obtain an abnormality assessment level of the power equipment;

[0103] A risk coefficient acquisition module, which is used to analyze the impact of abnormal power equipment and the impact of associated equipment to determine the risk coefficient of the abnormal equipment;

[0104] A matching computing power acquisition module is used to perform abnormality-computing power level matching based on the abnormality assessment level and the risk coefficient of the abnormal device, and determine the matching computing power, wherein the level of the matching computing power is proportional to the abnormality assessment level and the risk coefficient of the abnormal device.

[0105] Furthermore, the system further comprises:

[0106] A fault risk coefficient acquisition module, which is used to set weight values ​​of the abnormality assessment level and the risk coefficient of the abnormal equipment, and calculate and acquire the fault risk coefficient based on the weight value, the abnormality assessment level and the risk coefficient of the abnormal equipment;

[0107] A computing power accuracy requirement obtaining module, wherein the computing power accuracy requirement obtaining module is used to perform a computing power response requirement analysis according to the fault risk coefficient, and determine a computing power accuracy requirement and a computing power speed requirement;

[0108] A matching computing power acquisition module is used to determine the matching computing power based on the computing power accuracy requirement, computing power speed requirement and multi-level computing power matching corresponding to the abnormal power equipment.

[0109] Furthermore, the system further comprises:

[0110] An abnormal power equipment determination module, the abnormal power equipment determination module is used to determine abnormal power equipment and abnormality assessment level according to the abnormal data;

[0111] An abnormal operation tolerance time acquisition module, the abnormal operation tolerance time acquisition module is used to determine the connection relationship of the power equipment according to the abnormal power equipment, perform correlation impact analysis of the abnormal power equipment, and obtain the abnormal equipment impact and abnormal operation tolerance time;

[0112] A distributed computing power time node acquisition module, wherein the distributed computing power time node acquisition module is used to determine the distributed computing power time node according to the computing power distribution execution strategy;

[0113] A phased control module is used to optimize the control nodes based on the impact of the abnormal equipment, the abnormal operation tolerance time, and the distributed computing power time nodes, and determine the power equipment distribution control strategy. The power equipment distribution control strategy is used to control the power equipment in stages according to the control nodes.

[0114] The specific example of the power equipment control method based on the computing power architecture in the aforementioned embodiment 1 is also applicable to the power equipment control system based on the computing power architecture in this embodiment. Through the aforementioned detailed description of the power equipment control method based on the computing power architecture, those skilled in the art can clearly understand the power equipment control system based on the computing power architecture in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0115] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0116] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for controlling electric power equipment based on computing power architecture, characterized in that: include: Collect the connection control relationship of power equipment, and simultaneously collect the operation monitoring data of power equipment, and use digital twin technology to build a twin control platform for power equipment; Build an algorithm database based on the operation and control requirements of power equipment; Perform algorithm analysis and evaluation according to preset dimensions based on the algorithm database to build a multi-layer computing architecture; Based on the algorithm in the multi-layer architecture of computing power and the correlation analysis of the operation control requirements of the power equipment, a multi-layer mapping relationship between the power equipment and computing power is established, wherein the algorithm includes primary computing power and advanced computing power; Extracting synchronous operation monitoring data through the power equipment twin control platform, comparing the synchronous operation monitoring data with abnormalities, and locating abnormal data; By locating abnormal data and based on the multi-layer mapping relationship between power equipment and computing power, we can match the abnormality and computing power levels, determine the matching computing power, and generate a computing power distribution execution strategy. The power equipment distribution control strategy is determined according to the computing power distribution execution strategy and abnormal data, and is sent to the control platform to control the power equipment.

2. The method according to claim 1, characterized in that The algorithm database is constructed based on the operation control requirements of the power equipment, including: Obtain the operation control computing power requirements of the power equipment, determine the operation control algorithm, and establish the corresponding relationship between the power equipment control parameters and the operation control algorithm; Extract the abnormal fault database of power equipment, analyze the operation and processing requirements based on the abnormal fault data, obtain the abnormal processing algorithm, and establish the corresponding relationship between the abnormal fault type and the abnormal processing algorithm; The algorithm database is constructed based on the correspondence between the control parameters of the power equipment and the operation control algorithm, and the correspondence between the abnormal fault type and the abnormality processing algorithm.

3. The method according to claim 2, characterized in that According to the algorithm database, algorithm analysis and evaluation are performed according to preset dimensions to build a multi-layer computing power architecture, including: Analyze and evaluate each algorithm in the algorithm database according to the requirements of memory, communication, and energy consumption, and determine the evaluation coefficient of each dimension; Based on the power equipment corresponding to each algorithm in the algorithm database, perform equipment correspondence analysis to determine the corresponding algorithm information of the power equipment; According to the multi-dimensional evaluation coefficient of each algorithm, the corresponding algorithm of each power device is divided into computing power levels, the multi-level algorithm information of each power device is determined, and the computing power multi-layer architecture is constructed based on the multi-level algorithm information of each power device.

4. The method according to claim 1, characterized in that The synchronous operation monitoring data is extracted through the power equipment twin control platform, and the synchronous operation monitoring data is compared with abnormalities to locate abnormal data, including: Collect normal operation data of each power equipment and construct a standard parameter feature set for each power equipment; Using the synchronous operation monitoring data and the standard parameter feature set to perform multi-parameter same-direction traversal comparison to determine abnormal parameters; Abnormal power equipment is located based on the abnormal parameters to locate abnormal power equipment and abnormal data.

5. The method according to claim 4, characterized in that The method utilizes the location of abnormal data, performs abnormality-computing power level matching based on the multi-layer mapping relationship between power equipment and computing power, determines the matching computing power, and generates a computing power distribution execution strategy, including: Determine an abnormal deviation value according to the abnormal data, perform an abnormal evaluation prediction of the abnormal power equipment based on the abnormal deviation value, and obtain an abnormal evaluation level of the power equipment; Analyze the impact of abnormal power equipment and related equipment to determine the risk factor of abnormal equipment; Based on the abnormality assessment level and the risk coefficient of the abnormal device, an abnormality-computing power level matching is performed to determine the matching computing power, wherein the level of the matching computing power is proportional to the abnormality assessment level and the risk coefficient of the abnormal device.

6. The method according to claim 5, characterized in that Based on the abnormal assessment level and the risk factor of the abnormal device, an abnormality-computing power level matching is performed to determine the matching computing power, including: Setting weight values ​​of the abnormality assessment level and the risk coefficient of the abnormal equipment, and calculating and obtaining the fault risk coefficient based on the weight values, the abnormality assessment level and the risk coefficient of the abnormal equipment; Perform a computing power response requirement analysis based on the fault risk coefficient to determine computing power accuracy requirements and computing power speed requirements; The matching computing power is determined based on the computing power accuracy requirement, computing power speed requirement and the multi-level computing power matching corresponding to the abnormal power equipment.

7. The method according to claim 6, characterized in that Determining a power equipment distribution control strategy according to the computing power distribution execution strategy and abnormal data includes: Determining abnormal power equipment and abnormal assessment level according to the abnormal data; According to the abnormal power equipment, determine the power equipment connection relationship, perform correlation impact analysis on the abnormal power equipment, and obtain the impact of the abnormal equipment and the abnormal operation tolerance time; Determine the time node for distributing computing power according to the computing power distribution execution strategy; Based on the impact of the abnormal equipment, the abnormal operation tolerance time, and the distributed computing power time node, the control node is optimized to determine the power equipment distribution control strategy, which is used to control the power equipment in stages according to the control node.

8. A power equipment control system based on computing power architecture, characterized in that: A method for controlling a power device based on a computing power architecture according to any one of claims 1 to 7, the system comprising: A power equipment twin control platform construction module, which is used to collect the connection control relationship of the power equipment and synchronously collect the operation monitoring data of the power equipment, and use the digital twin technology to build a power equipment twin control platform; An algorithm database construction module, wherein the algorithm database construction module is used to construct an algorithm database based on the operation control requirements of the power equipment; A computing power multi-layer architecture construction module, wherein the computing power multi-layer architecture construction module is used to perform algorithm analysis and evaluation according to preset dimensions based on the algorithm database to construct a computing power multi-layer architecture; A multi-layer mapping relationship establishment module, the multi-layer mapping relationship establishment module is used to perform a correlation analysis of operation control requirements on the power equipment based on the algorithm in the computing power multi-layer architecture and establish a multi-layer mapping relationship between the power equipment and the computing power, wherein the algorithm includes primary computing power and advanced computing power; An abnormal data locating module, the abnormal data locating module is used to extract synchronous operation monitoring data through the power equipment twin control platform, compare the synchronous operation monitoring data with abnormalities, and locate abnormal data; A computing power distribution execution strategy generation module, wherein the computing power distribution execution strategy generation module is used to utilize the location of abnormal data, perform abnormality-computing power level matching based on the multi-layer mapping relationship between power equipment and computing power, determine the matching computing power, and generate a computing power distribution execution strategy; The power equipment distribution control strategy acquisition module is used to determine the power equipment distribution control strategy according to the computing power distribution execution strategy and abnormal data, and send it to the control platform to control the power equipment.

Images