Power supply dispatching abnormity detection system and method

Abstract

The invention relates to the technical field of electric power, and provides a power supply dispatching anomaly detection system and method.The power supply dispatching anomaly detection system comprises a master control terminal, a data acquisition and monitoring module, a power supply dispatching anomaly detection module and a power supply dispatching anomaly detection module, the data processing and analyzing module is configured to process and analyze the parameter data by using a deep learning algorithm and identify abnormal conditions possibly existing in the power system; the exception detection and identification module is configured to detect and identify the exception condition by using a data mining technology and judge the type and severity of the exception condition; and the risk assessment and processing suggestion module is configured to perform risk assessment on the power system according to the detection result of the abnormal condition and provide corresponding processing suggestions. According to the invention, anomaly detection and processing can be carried out on the power system accurately, quickly and reliably, and the operation level and safety of the power system are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power technology, and in particular to a power supply scheduling anomaly detection system and method. Background Art

[0002] The power system is an electric energy production and consumption system consisting of power plants, power transmission and transformation lines, power distribution stations and power consumption. Its function is to convert primary energy in nature into electric energy through power generation devices, and then supply electric energy to various users through transmission, transformation and distribution. To achieve this function, the power system also has corresponding information and control systems at various links and levels to measure, regulate, control, protect, communicate and dispatch the production process of electric energy to ensure that users obtain safe and high-quality electric energy.

[0003] The existing technologies have the following shortcomings in the detection and processing of power system anomalies: 1. Dependence on manual intervention: Traditional power system monitoring and processing often require manual intervention, which places high demands on the operators of the power system and is prone to missed detections or misjudgments. 2. Lack of intelligence: Traditional power systems lack intelligent technical support and are unable to conduct in-depth analysis and intelligent processing of data, resulting in limitations and deficiencies in the processing solutions. 3. Insufficient data analysis capabilities: Traditional anomaly detection systems have limited processing capabilities for large amounts of data, and are unable to effectively mine the potential information and patterns in the data, making it difficult to make accurate predictions and decisions. 4. Slow response of the power system: Traditional power systems have a slow detection and response speed to abnormal situations, and are unable to promptly discover and handle potential problems, affecting the safety and stability of the power system. Summary of the invention

[0004] The purpose of the embodiments of the present disclosure is to provide a power supply scheduling anomaly detection system and method, so as to at least solve the technical problems existing in the prior art, such as the low level of intelligence in power system anomaly detection and processing, insufficient data analysis capabilities, resulting in low accuracy and efficiency of anomaly detection results, and slow detection and response speed of the power system to abnormal situations, affecting the safety and stability of the power system.

[0005] In order to solve the above technical problems, the embodiments of the present disclosure adopt the following technical solutions:

[0006] In a first aspect, an embodiment of the present disclosure provides a power supply scheduling abnormality detection system, including a main control terminal, and:

[0007] A data acquisition and monitoring module configured to acquire parameter data of the power system;

[0008] A data processing and analysis module, configured to process and analyze the parameter data using a deep learning algorithm to identify possible abnormal conditions in the power system;

[0009] An abnormality detection and identification module, configured to detect and identify the abnormal situation using data mining technology, and determine the type and severity of the abnormal situation;

[0010] The risk assessment and processing suggestion module is configured to perform risk assessment on the power system according to the detection result of the abnormal situation and provide corresponding processing suggestions.

[0011] In some embodiments, the parameter data of the power system includes at least one of power load data, power market data, power quality data, power grid security assessment data, and energy consumption and analysis data.

[0012] In some embodiments, the treatment recommendations include equipment maintenance plans and / or load adjustment plans.

[0013] In some embodiments, the data processing and analysis module includes:

[0014] A sparse computing module, configured to perform computational analysis on the parameter data using the characteristics of sparse matrices and sparse vectors;

[0015] A quantized network module, configured to quantize network weights and activations to a low bit width;

[0016] A mixed precision computing module, configured to use numerical representations of different precisions in the network, wherein the numerical representations of different precisions include half-precision floating point numbers and single-precision floating point numbers;

[0017] The delayed scheduling and asynchronous computing module is configured to optimize the scheduling order of computing tasks and perform asynchronous computing.

[0018] In some embodiments, the mixed precision computing module and the delay scheduling and asynchronous computing module have higher priority than the sparse computing module and the quantization network module.

[0019] In some embodiments, the anomaly detection and identification module includes:

[0020] Isolation Forest Algorithm module, configured to build randomly split trees to locate a few outliers;

[0021] a local anomaly factor module configured to utilize a density-based anomaly detection algorithm to find anomaly data in a data set having different densities relative to neighboring data points of the anomaly point;

[0022] an integrated anomaly detection module configured to detect and identify anomalies of the power system in combination with a plurality of anomaly detection algorithms or models;

[0023] The multi-scale anomaly detection module is configured to combine data features of different scales to identify abnormal conditions of the power system at different granularities.

[0024] In some embodiments, the power supply scheduling anomaly detection system further includes a real-time monitoring and feedback module connected to the main control terminal.

[0025] The real-time monitoring and feedback module is configured to monitor the operating status of the power system in real time and provide real-time feedback to the operator of the power system through a visual interface, wherein the real-time feedback includes abnormal conditions of the power system and / or the processing suggestions.

[0026] In a second aspect, an embodiment of the present disclosure provides a power supply scheduling anomaly detection method, which is applied to a power supply scheduling anomaly detection system. The power supply scheduling anomaly detection system includes a main control terminal, and a data acquisition and monitoring module, a data processing and analysis module, an anomaly detection and identification module, and a risk assessment and processing suggestion module respectively connected to the main control terminal. The method includes:

[0027] Collect parameter data of the power system through the data acquisition and monitoring module;

[0028] Processing and analyzing the parameter data using a deep learning algorithm through the data processing and analysis module to identify abnormal conditions that may exist in the power system;

[0029] The abnormal situation is detected and identified by the abnormality detection and identification module using data mining technology to determine the type and severity of the abnormal situation;

[0030] Through the risk assessment and processing suggestion module, risk assessment of the power system is performed according to the detection result of the abnormal situation, and corresponding processing suggestions are provided.

[0031] In some embodiments, the data processing and analysis module includes a sparse computing module, a quantized network module, a mixed precision computing module, and a delay scheduling and asynchronous computing module. The parameter data is processed and analyzed by the data processing and analysis module using a deep learning algorithm, including:

[0032] The sparse computing module uses the characteristics of sparse matrices and sparse vectors to perform calculation and analysis on the parameter data;

[0033] Quantizing the network weights and activation values ​​to a low bit width through the quantization network module;

[0034] By means of the mixed precision computing module, numerical representations of different precisions are used in the network, wherein the numerical representations of different precisions include half-precision floating point numbers and single-precision floating point numbers;

[0035] The delay scheduling and asynchronous computing module is used to optimize the scheduling order of computing tasks and perform asynchronous computing.

[0036] In some embodiments, the anomaly detection and identification module includes an isolation forest algorithm module, a local anomaly factor module, an integrated anomaly detection module, and a multi-scale anomaly detection module. The anomaly detection and identification module uses data mining technology to detect and identify the anomaly, and determines the type and severity of the anomaly, including:

[0037] The isolation forest algorithm module constructs a randomly segmented tree to locate a small number of outliers for high-dimensional data and large-scale data sets;

[0038] Using the local anomaly factor module, a density-based anomaly detection algorithm is used to find abnormal data in a data set having different densities relative to neighboring data points of the abnormal point;

[0039] Detecting and identifying abnormal conditions of the power system by combining a plurality of abnormality detection algorithms or models through the integrated abnormality detection module;

[0040] Through the multi-scale anomaly detection module, data features of different scales are combined to identify abnormal conditions of the power system at different granularities.

[0041] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned power supply scheduling anomaly detection method when executing the computer program on the memory.

[0042] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned power supply scheduling abnormality detection method is implemented.

[0043] The embodiment of the present disclosure provides a power supply scheduling anomaly detection system and method. A main control terminal and a data acquisition and monitoring module, a data processing and analysis module, an anomaly detection and identification module, and a risk assessment and processing suggestion module are respectively connected to the main control terminal. The parameter data of the power system are collected through the data acquisition and monitoring module; the parameter data are processed and analyzed by the data processing and analysis module using a deep learning algorithm to identify the abnormal conditions that may exist in the power system; the abnormal conditions are detected and identified by the anomaly detection and identification module using data mining technology to determine the type and severity of the abnormal conditions; the risk assessment and processing suggestion module is used to conduct a risk assessment on the power system according to the detection result of the abnormal conditions, and provide corresponding processing suggestions. The artificial intelligence algorithm and big data technology are introduced into the power supply scheduling anomaly detection system, which can automatically monitor and intelligently analyze the power system, improve the efficiency and reliability of the operation of the power supply scheduling anomaly detection system, make the abnormality detection and processing of the power system more accurate, fast and reliable, and improve the operation level and safety of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in 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 described below are only some embodiments recorded in the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 It is a structural schematic diagram of a power supply scheduling anomaly detection system according to an embodiment of the present disclosure;

[0046] Figure 2 The present invention is a flowchart of a method for detecting abnormal power supply scheduling according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] Various aspects and features of the present disclosure are described herein with reference to the drawings.

[0048] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present disclosure will occur to those skilled in the art.

[0049] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the general description of the present disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the present disclosure.

[0050] These and other characteristics of the present disclosure will become apparent from the following description of a preferred form of embodiment given as a non-limiting example, with reference to the accompanying drawings.

[0051] It should also be understood that, although the present disclosure has been described with reference to some specific examples, those skilled in the art will be able to realize many other equivalent forms of the present disclosure that have the features described in the claims and are therefore within the scope of protection defined thereby.

[0052] The above and other aspects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0053] Specific embodiments of the present disclosure are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments claimed are merely examples of the present disclosure, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid obscuring the present disclosure with unnecessary or redundant details. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of ways with substantially any suitable detailed structure.

[0054] This specification may use the phrases "in one embodiment," "in another embodiment," "in a further embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present disclosure.

[0055] Embodiment 1

[0056] Figure 1 The schematic diagram of the structure of the power supply scheduling abnormality detection system according to the embodiment of the present disclosure is shown as follows: Figure 1 As shown, a power supply scheduling anomaly detection system provided by an embodiment of the present disclosure includes a main control terminal 10, and:

[0057] A data acquisition and monitoring module 20, configured to collect parameter data of the power system;

[0058] A data processing and analysis module 30 is configured to process and analyze the parameter data using a deep learning algorithm to identify abnormal conditions that may exist in the power system;

[0059] The abnormality detection and identification module 40 is configured to detect and identify the abnormal situation using data mining technology to determine the type and severity of the abnormal situation;

[0060] The risk assessment and processing suggestion module 50 is configured to perform risk assessment on the power system according to the detection result of the abnormal situation and provide corresponding processing suggestions.

[0061] Among them, the main control terminal is the main controller of each module, and the main control terminal can be a server, etc. The data acquisition and monitoring module 20 collects various parameter data of the power system in real time through sensors, and transmits the collected parameter data to the data processing and analysis module 30 for processing. The parameter data of the power system can be the overall parameter data of the power system, or the parameter data of the power equipment and facilities in the power system. The power equipment and facilities include generators, excitation systems, distribution systems, speed regulators, transmission lines, loads, etc.

[0062] Preferably, the parameter data of the power system includes at least one of power load data, power market data, power quality data, power grid security assessment data, and energy consumption and analysis data. The power load data includes at least one of current, voltage, power, and frequency information. The parameter data of the power system may also be other parameters when the power system is running, and the specific type thereof is not specifically limited in this disclosure.

[0063] The data processing and analysis module 30 uses a deep learning algorithm to process and analyze the collected parameter data to identify possible abnormal conditions in the power system, such as equipment failure and load abnormality. The deep learning algorithm can be one or more of the algorithms such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN), etc., which can perform a comprehensive and in-depth analysis of the collected parameter data, extract the corresponding data features, and achieve high-precision prediction and classification by continuously optimizing the model, thereby accurately identifying possible abnormal conditions in the power system.

[0064] The abnormal detection and identification module 40 uses data mining technology to deeply mine and process possible abnormal situations, accurately detect and identify the type and severity of each abnormal situation. The risk assessment and processing suggestion module 50 performs risk assessment on the overall operation or local operation of the power system according to the detection results of the abnormal situation detected and identified by the abnormal detection and identification module 40, and provides corresponding processing suggestions to help the operators of the power system (such as operators) make decisions quickly. For example, when a certain device fails, the impact on other devices and the overall operation of the power system is judged according to the fault condition of the device. When the degree of failure of the device is low, it only needs to be shut down for repair or replacement, and other devices can still maintain normal operation; when the degree of failure of the device is serious and may affect the operation safety of the entire power system, the entire power system is controlled to stop running, the faulty device only needs to be repaired or replaced, and other devices that are easily affected by the faulty device are inspected and repaired to determine whether there may be safety hazards, so as to ensure the safe and reliable operation of the entire power system.

[0065] Optionally, the processing suggestion includes an equipment maintenance plan and / or a load adjustment plan. The processing suggestion is determined according to the type, severity, and cause of the abnormal situation, etc. The specific type of the processing suggestion is not specifically limited in this disclosure.

[0066] The power supply dispatching anomaly detection system provided by the embodiment of the present disclosure is provided with a main control terminal and a data acquisition and monitoring module 20, a data processing and analysis module 30, an anomaly detection and identification module 40, and a risk assessment and processing suggestion module 50 respectively connected to the main control terminal. The parameter data of the power system is collected by the data acquisition and monitoring module 20; the parameter data is processed and analyzed by the data processing and analysis module 30 using a deep learning algorithm to identify the abnormal conditions that may exist in the power system; the abnormal conditions are detected and identified by the data mining technology by the anomaly detection and identification module 40 to determine the type and severity of the abnormal conditions; the risk assessment and processing suggestion module 50 is used to conduct a risk assessment on the power system according to the detection result of the abnormal conditions, and provide corresponding processing suggestions, and introduce artificial intelligence algorithms and big data technologies (including data acquisition, storage, processing, analysis and mining, etc.) into the power supply dispatching anomaly detection system, so as to automatically monitor and intelligently analyze the power system, improve the efficiency and reliability of the operation of the power supply dispatching anomaly detection system, make the abnormal detection and processing of the power system more accurate, fast and reliable, and improve the operation level and safety of the power system.

[0067] In some embodiments, the data processing and analysis module 30 includes:

[0068] A sparse computing module, configured to perform computational analysis on the parameter data using the characteristics of sparse matrices and sparse vectors;

[0069] A quantized network module, configured to quantize network weights and activations to a low bit width;

[0070] A mixed precision computing module, configured to use numerical representations of different precisions in the network, wherein the numerical representations of different precisions include half-precision floating point numbers and single-precision floating point numbers;

[0071] The delayed scheduling and asynchronous computing module is configured to optimize the scheduling order of computing tasks and perform asynchronous computing.

[0072] In this embodiment, when the parameter data is analyzed and processed using a deep learning algorithm, the analysis and processing is performed through a quantized neural network. The sparse computing module can utilize the characteristics of sparse matrices and sparse vectors to avoid calculating all the collected parameter data, which is particularly effective when processing large data sets, and can greatly reduce the amount of calculation and improve data processing and analysis efficiency.

[0073] Bit width refers to the width of data processed in a computer system, that is, the number of data bits that can be processed or transmitted at one time (quantization accuracy). The quantized network module can quantize network weights and activation values ​​to a smaller number of bits, such as binary or ternary, to reduce computational complexity and storage requirements.

[0074] The mixed precision computing module uses numerical representations of different precisions in the network, and uses both half-precision and single-precision floating-point numbers to fully utilize the capabilities of the hardware and improve the accuracy of the calculation results. The delayed scheduling and asynchronous computing module reduces the overall computing time by optimizing the scheduling order of computing tasks and performing asynchronous computing.

[0075] By analyzing and processing the parameter data of the power system through the above-mentioned sparse computing module, quantized network module, mixed precision computing module, delay scheduling and asynchronous computing module, the data processing efficiency and the accuracy of the data results can be improved.

[0076] Furthermore, the mixed precision calculation module and the delay scheduling and asynchronous calculation module have higher priority than the sparse calculation module and the quantized network module. Since the sparse calculation module will reduce the amount of data processing, some data may be lost; and the quantized network module can significantly reduce the storage and calculation amount of the power supply scheduling anomaly detection system by quantizing the network weights and activation values ​​to a low bit width, reducing the computational complexity and storage requirements, but may lose a certain amount of accuracy, such as making it impossible to clarify the correlation between some complex data (for example, considering some data with strong correlation to have less correlation). Therefore, in this embodiment, the priority of the mixed precision calculation module and the delay scheduling and asynchronous calculation module is set to be higher than the sparse calculation module and the quantized network module, so as to make full use of the capabilities of the hardware to obtain more accurate results, and improve the computing efficiency by optimizing the overall computing task sequence and performing asynchronous computing.

[0077] In some embodiments, the anomaly detection and identification module 40 includes:

[0078] Isolation Forest Algorithm module, configured to build randomly split trees to locate a few outliers;

[0079] a local anomaly factor module configured to utilize a density-based anomaly detection algorithm to find anomaly data in a data set having different densities relative to neighboring data points of the anomaly point;

[0080] an integrated anomaly detection module configured to detect and identify anomalies of the power system in combination with a plurality of anomaly detection algorithms or models;

[0081] The multi-scale anomaly detection module is configured to combine data features of different scales to identify abnormal conditions of the power system at different granularities.

[0082] The isolation forest algorithm module quickly locates a small number of abnormal points by constructing randomly segmented trees for processing high-dimensional data and large-scale data sets; the local anomaly factor module uses a density-based anomaly detection method to discover abnormal data in a data set with different densities relative to the neighboring data points of the abnormal point, thereby improving the anomaly detection range and thus improving the accuracy of anomaly detection; the integrated anomaly detection module combines the prediction results of multiple anomaly detection algorithms or models to comprehensively detect and identify the abnormal conditions of the power system, thereby improving the accuracy and robustness of anomaly detection; the multi-scale anomaly detection module combines data features of different scales to identify abnormal conditions of the power system at different granularities, thereby improving the sensitivity and accuracy of anomaly detection.

[0083] In some embodiments, the power supply scheduling anomaly detection system also includes a real-time monitoring and feedback module 60 connected to the main control terminal 10, and the real-time monitoring and feedback module 60 is configured to monitor the operating status of the power system in real time and provide real-time feedback to the operator of the power system through a visual interface, wherein the real-time feedback includes the abnormal situation of the power system and / or the processing suggestions.

[0084] When real-time feedback is provided to the operators of the power system through the real-time monitoring and feedback module 60, not only can the detection results of abnormal conditions of the power system be provided in a timely manner, but also corresponding processing solutions can be recommended according to the severity and type of the abnormal conditions, thereby improving the detection and response speed of the power system to abnormal conditions, facilitating the timely discovery and handling of potential power system problems, improving the operating efficiency and reliability of the power supply scheduling abnormality system, and ensuring the safety and stability of the power system operation.

[0085] In this embodiment, a visual interface may be provided on the main control terminal 10 to facilitate the operators of the power system to intuitively understand the operation status of the power system and perform subsequent operations and management.

[0086] Embodiment 2

[0087] Figure 2 A flow chart of a method for detecting abnormal power supply scheduling according to an embodiment of the present disclosure is shown. Figure 2 As shown, the embodiment of the present disclosure provides a power supply scheduling anomaly detection method, which is applied to the power supply scheduling anomaly detection system of the above embodiment. The power supply scheduling anomaly detection system includes a main control terminal 10, and a data acquisition and monitoring module 20, a data processing and analysis module 30, an anomaly detection and identification module 40, and a risk assessment and processing suggestion module 50 respectively connected to the main control terminal 10. The method includes:

[0088] S101: Collecting parameter data of the power system through the data acquisition and monitoring module 20;

[0089] S102: Processing and analyzing the parameter data by using a deep learning algorithm through the data processing and analysis module 30 to identify abnormal conditions that may exist in the power system;

[0090] S103: The abnormality detection and identification module 40 uses data mining technology to detect and identify the abnormal situation, and determines the type and severity of the abnormal situation;

[0091] S104: Through the risk assessment and processing suggestion module 50, risk assessment is performed on the power system according to the detection result of the abnormal situation, and corresponding processing suggestions are provided.

[0092] In some embodiments, the parameter data of the power system includes at least one of power load data, power market data, power quality data, power grid security assessment data, and energy consumption and analysis data.

[0093] In some embodiments, the treatment recommendations include equipment maintenance plans and / or load adjustment plans.

[0094] In some embodiments, the data processing and analysis module 30 includes a sparse computing module, a quantized network module, a mixed precision computing module, and a delay scheduling and asynchronous computing module.

[0095] In step S102, the parameter data is processed and analyzed by the data processing and analysis module 30 using a deep learning algorithm, including:

[0096] S1021: performing calculation and analysis on the parameter data by using the characteristics of sparse matrices and sparse vectors through the sparse calculation module;

[0097] S1022: quantizing the network weights and activation values ​​to a low bit width through the quantization network module;

[0098] S1023: Using the mixed precision computing module to represent numerical values ​​of different precisions in the network, wherein the numerical values ​​of different precisions include half-precision floating point numbers and single-precision floating point numbers;

[0099] S1024: Optimize the scheduling order of computing tasks and perform asynchronous computing through the delay scheduling and asynchronous computing module.

[0100] In some embodiments, the mixed precision computing module and the delay scheduling and asynchronous computing module have higher priority than the sparse computing module and the quantization network module.

[0101] In some embodiments, the anomaly detection and identification module 40 includes an isolation forest algorithm module, a local anomaly factor module, an integrated anomaly detection module, and a multi-scale anomaly detection module.

[0102] In step S103, the abnormal situation is detected and identified by the abnormality detection and identification module using data mining technology to determine the type and severity of the abnormal situation, including:

[0103] S1031: constructing a randomly segmented tree through the isolation forest algorithm module to locate a small number of outliers, so as to be used for high-dimensional data and large-scale data sets;

[0104] S1032: Using the local anomaly factor module, using a density-based anomaly detection algorithm to find abnormal data in a data set having different densities relative to neighboring data points of the abnormal point;

[0105] S1033: Detecting and identifying abnormal conditions of the power system by combining the integrated abnormality detection module with a plurality of abnormality detection algorithms or models;

[0106] S1034: Combining data features of different scales through the multi-scale anomaly detection module to identify abnormal conditions of the power system at different granularities.

[0107] In some embodiments, the power supply scheduling anomaly detection system further includes a real-time monitoring and feedback module connected to the main control terminal, and the method further includes:

[0108] The real-time monitoring and feedback module monitors the operating status of the power system in real time, and provides real-time feedback to the operators of the power system through a visual interface, wherein the real-time feedback includes abnormal conditions of the power system and / or the processing suggestions.

[0109] The above-mentioned visualization interface is provided on the main control terminal 10, so that the operators of the power system can intuitively understand the operation status of the power system and perform subsequent operations and management.

[0110] The power supply scheduling anomaly detection method for cable online monitoring equipment provided in the embodiment of the present disclosure corresponds to the power supply scheduling anomaly detection system in the above-mentioned embodiment. Any optional items in the embodiment of the power supply scheduling anomaly detection system are also applicable to the embodiment of the power supply scheduling anomaly detection method, which will not be repeated here.

[0111] Embodiment 3

[0112] An embodiment of the present disclosure further provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned power supply scheduling abnormality detection method when executing the computer program on the memory.

[0113] In some embodiments, the processor executing the computer program may be a processing device including one or more general-purpose processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, the processor may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor running other instruction sets, or a processor running a combination of instruction sets. The processor may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a system on a chip (SoC), etc.

[0114] The memory may be a read-only memory (ROM), a random access memory (RAM), a phase-change random access memory (PRAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), an electrically erasable programmable read-only memory (EEPROM), other types of random access memory (RAM), a flash disk or other form of flash memory, a cache, a register, a static memory, a compact disk read-only memory (CD-ROM), a digital versatile disk (DVD) or other optical storage, a cassette or other magnetic storage device, or any other possible non-temporary medium used to store information or instructions that can be accessed by a computer device.

[0115] The electronic devices of the embodiments of the present disclosure may include but are not limited to fixed terminal devices such as servers, desktop computers, digital TVs, etc., and mobile terminal devices such as vehicle-mounted devices (such as head-up display devices), handheld devices (such as mobile phones, tablet computers, etc.), wearable devices (such as smart watches, smart bracelets, etc.), etc.

[0116] Embodiment 4

[0117] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned power supply scheduling abnormality detection method is implemented.

[0118] The computer-readable storage medium of the disclosed embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0119] In the embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any storage medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device or device. The program code contained on the storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0120] The computer programs of the embodiments of the present disclosure may be organized into one or more computer executable components or modules. Any number and combination of such components or modules may be used to implement the various aspects of the present disclosure. For example, the various aspects of the present disclosure are not limited to the specific computer executable instructions or specific components or modules shown in the drawings and described herein. Other embodiments may include different computer executable instructions or components with more or less functions than those shown and described herein.

[0121] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example of the energy acquisition device described in the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0123] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] In addition, the features of the embodiments shown in the drawings of the present disclosure or the various embodiments mentioned in this specification are not necessarily understood as independent embodiments from each other. Instead, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the drawings.

[0125] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A power supply scheduling anomaly detection system, characterized in that: It includes a main control terminal, and the following components respectively connected to the main control terminal: A data acquisition and monitoring module configured to acquire parameter data of the power system; A data processing and analysis module, configured to process and analyze the parameter data using a deep learning algorithm to identify possible abnormal conditions in the power system; An abnormality detection and identification module, configured to detect and identify the abnormal situation using data mining technology, and determine the type and severity of the abnormal situation; The risk assessment and processing suggestion module is configured to perform risk assessment on the power system according to the detection result of the abnormal situation and provide corresponding processing suggestions.

2. The power supply scheduling anomaly detection system according to claim 1, characterized in that: The parameter data of the power system includes at least one of power load data, power market data, power quality data, power grid security assessment data, and energy consumption and analysis data.

3. The power supply scheduling anomaly detection system according to claim 2, characterized in that: The treatment suggestions include equipment maintenance plans and / or load adjustment plans.

4. The power supply scheduling anomaly detection system according to claim 1, characterized in that: The data processing and analysis module includes: A sparse computing module, configured to perform computational analysis on the parameter data using the characteristics of sparse matrices and sparse vectors; A quantized network module, configured to quantize network weights and activations to a low bit width; A mixed precision computing module, configured to use numerical representations of different precisions in the network, wherein the numerical representations of different precisions include half-precision floating point numbers and single-precision floating point numbers; The delayed scheduling and asynchronous computing module is configured to optimize the scheduling order of computing tasks and perform asynchronous computing.

5. The power supply scheduling anomaly detection system according to claim 4, characterized in that: The mixed precision computing module and the delay scheduling and asynchronous computing module have higher priority than the sparse computing module and the quantization network module.

6. The power supply scheduling anomaly detection system according to claim 1, characterized in that: The anomaly detection and identification module includes: Isolation Forest Algorithm module, configured to build randomly split trees to locate a small number of outliers; a local anomaly factor module configured to utilize a density-based anomaly detection algorithm to find anomaly data in a data set having different densities relative to neighboring data points of the anomaly point; an integrated anomaly detection module configured to detect and identify anomalies of the power system in combination with a plurality of anomaly detection algorithms or models; The multi-scale anomaly detection module is configured to combine data features of different scales to identify abnormal conditions of the power system at different granularities.

7. The power supply scheduling anomaly detection system according to claim 1, characterized in that: The power supply scheduling abnormality detection system also includes a real-time monitoring and feedback module connected to the main control terminal, The real-time monitoring and feedback module is configured to monitor the operating status of the power system in real time and provide real-time feedback to the operator of the power system through a visual interface, wherein the real-time feedback includes abnormal conditions of the power system and / or the processing suggestions.

8. A method for detecting abnormality in power supply scheduling, characterized in that: Applied to a power supply dispatching anomaly detection system, the power supply dispatching anomaly detection system includes a main control terminal, and a data acquisition and monitoring module, a data processing and analysis module, an anomaly detection and identification module, and a risk assessment and processing suggestion module respectively connected to the main control terminal. The method includes: Collect parameter data of the power system through the data acquisition and monitoring module; Processing and analyzing the parameter data using a deep learning algorithm through the data processing and analysis module to identify abnormal conditions that may exist in the power system; The abnormal situation is detected and identified by the abnormality detection and identification module using data mining technology to determine the type and severity of the abnormal situation; Through the risk assessment and processing suggestion module, risk assessment of the power system is performed according to the detection result of the abnormal situation, and corresponding processing suggestions are provided.

9. The power supply scheduling anomaly detection method according to claim 8, characterized in that: The data processing and analysis module includes a sparse computing module, a quantized network module, a mixed precision computing module, and a delay scheduling and asynchronous computing module. The parameter data is processed and analyzed by using a deep learning algorithm through the data processing and analysis module, including: The sparse computing module uses the characteristics of sparse matrices and sparse vectors to perform calculation and analysis on the parameter data; Quantizing the network weights and activation values ​​to a low bit width through the quantization network module; By means of the mixed precision computing module, numerical representations of different precisions are used in the network, wherein the numerical representations of different precisions include half-precision floating point numbers and single-precision floating point numbers; The delay scheduling and asynchronous computing module is used to optimize the scheduling order of computing tasks and perform asynchronous computing.

10. The power supply scheduling abnormality detection method according to claim 8, characterized in that: The anomaly detection and identification module includes an isolation forest algorithm module, a local anomaly factor module, an integrated anomaly detection module, and a multi-scale anomaly detection module. The anomaly detection and identification module uses data mining technology to detect and identify the anomaly and determine the type and severity of the anomaly, including: The isolation forest algorithm module constructs a randomly segmented tree to locate a small number of outliers for high-dimensional data and large-scale data sets; Using the local anomaly factor module, a density-based anomaly detection algorithm is used to find abnormal data in a data set having different densities relative to neighboring data points of the abnormal point; Detecting and identifying abnormal conditions of the power system by combining a plurality of abnormality detection algorithms or models through the integrated abnormality detection module; Through the multi-scale anomaly detection module, data features of different scales are combined to identify abnormal conditions of the power system at different granularities.

Images