Panoramic transparency and risk closed-loop control method and system for power grid production command center
Through multi-scale analysis and wavelet transformation, multi-dimensional data modeling, dynamic scoring and Bayesian optimization, the shortcomings of data processing and risk management in the power grid production process are solved, and comprehensive monitoring and fine management of the power grid production process are realized. It has improved the scientificity and effectiveness of risk identification and system control.
Patent Information
- Application Number
- CN202410966008.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-29
AI Technical Summary
The existing data standardization processing methods are insufficient in the power grid production process, and the multi-scale characteristics of the data and the weight of historical data cannot be fully considered, resulting in insufficient accuracy and robustness of the data processing results; the risk identification and management methods are based on linear analysis and cannot be used. Effectively capture dynamic changes and nonlinear characteristics of risk events, resulting in low timeliness and accuracy of risk warnings; dynamic monitoring and control methods lack comprehensive analysis of multi-source data and multi-dimensional data modeling, making it difficult to realize the entire process of power grid production comprehensive monitoring and fine management.
Using multi-scale analysis and wavelet transformation to standardize real-time data, build a multi-dimensional data model, identify and prevent false acceptance and false listing projects through dynamic scoring and Bayesian optimization, combine information entropy to perform closed-loop control, dynamically manage risks, and use pull Grande optimizes and adjusts system management strategies.
Improve the accuracy and robustness of data processing, identify potential risk events in advance, improve the timeliness and accuracy of risk identification, enhance the safety and management efficiency of the system, and improve the management and control of the power grid production process. ability.
Smart Images

Figure CN119051248A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power system management, and in particular to a panoramic transparency and risk closed-loop control method for a power grid production command center. Background Art
[0002] With the continuous development of power systems and the advancement of intelligentization, data management and risk control in the production process of power grids have become important issues that need to be solved urgently. Modern power system management relies on big data analysis and real-time monitoring technology. By collecting and processing a large amount of production data, it can reflect the operation status of the power grid in real time and provide support for dispatching and decision-making. In recent years, the application of mathematical tools such as multi-scale analysis, complex network theory, nonlinear dynamics, Bayesian inference, information entropy and optimization algorithms in power systems has gradually increased. These methods provide new ideas and means for power grid data processing and risk management. However, although these technologies have made significant progress in their respective fields, there are still many challenges in data standardization processing, risk identification and management, dynamic monitoring and control in the production process of power grids. The application of existing technologies in processing multi-dimensional data fusion, multi-scale data analysis, real-time risk warning and closed-loop control is not perfect enough and cannot fully meet the complex and changeable needs of the power grid production process.
[0003] The existing technologies mainly face the following deficiencies. First, data standardization processing methods are mainly based on simple mean and standard deviation processing, which fails to fully consider the multi-scale characteristics of data and the weight of historical data, resulting in insufficient accuracy and robustness of data processing results. Second, in terms of risk identification and management, traditional methods are mostly based on linear analysis and static evaluation, which cannot effectively capture the dynamic changes and nonlinear characteristics of risk events, resulting in low timeliness and accuracy of risk warnings. Third, existing dynamic monitoring and control methods are mostly based on a single data source, lacking comprehensive analysis of multi-source data and multi-dimensional data modeling, making it difficult to achieve comprehensive monitoring and fine management of the entire power grid production process. In addition, the application of closed-loop control and feedback mechanisms is also relatively limited, and information theory tools such as information entropy have not been fully utilized to evaluate the complexity and uncertainty of feedback data, resulting in the scientificity and effectiveness of system control strategies to be improved. Summary of the invention
[0004] In view of the above-mentioned problems, the present invention is proposed.
[0005] Therefore, the technical problem solved by the present invention is: the existing risk closed-loop control method has insufficient accuracy, insufficient refinement, and limited effectiveness, and how to achieve optimization of comprehensive monitoring and refined management of the entire power grid production process.
[0006] To solve the above technical problems, the present invention provides the following technical solutions: a panoramic transparency and risk closed-loop control method for a power grid production command center, including collecting data and performing standardized processing and transparent management of real-time data in the power grid production process; dynamically analyzing risk events in the production process, identifying and preventing false acceptance and fictitious items; performing closed-loop control on the collected data, continuously monitoring and dynamically managing risks.
[0007] As a preferred solution of the panoramic transparency and risk closed-loop control method of the power grid production command center described in the present invention, wherein: the data collection and standardized processing and transparent management of real-time data in the power grid production process include multi-scale analysis, obtaining real-time power load data, equipment operation status data, and environmental monitoring data from various sensors and monitoring equipment, collecting power load, equipment temperature, equipment vibration, ambient temperature and humidity, processing the mean and standard deviation of various types of original data, and introducing time frequency factors and historical data weights to eliminate the dimensional influence of the data, so that data of different scales can be compared on the same basis, and multi-scale analysis of standardized data is performed through wavelet transform, scale parameters and translation parameters are adjusted, and data are analyzed at different time scales to reveal structures and patterns at different time resolutions. The multi-scale analysis is expressed as:
[0008]
[0009] Among them, S i is the standardized data, D i are various raw data, μ D is the data mean, σ D is the data standard deviation, t is the time variable, ω is the time frequency factor, h is the historical data factor, α is the historical data weight, W(t,a) is the data after wavelet transformation, ψ is the mother wavelet function, a is the scale parameter, and b is the translation parameter.
[0010] As a preferred solution of the panoramic transparency and risk closed-loop control method of the power grid production command center described in the present invention, the data collection and standardized processing and transparent management of real-time data in the power grid production process also include multi-dimensional data modeling, by integrating data sources and weighting data with different weights, building a multi-dimensional data model, and building and analyzing the relationship network between data, calculating the degree distribution of nodes in the network, and adjusting the node relationship through periodic weights and sensitivity factors, reflecting the abnormal conditions and trends in the data in real time, expressed as:
[0011]
[0012]
[0013] Among them, Mk is a multidimensional data model, w i is the data weight, λ i is the decay factor, T is the time interval, P(k) is the node degree distribution, k i is the degree of the i-th node, A i is the abnormality measure of the i-th node, is the average degree of all nodes in the network, max(M k ) is the maximum value in the multidimensional data model result. If the abnormality measure A of the node i A value higher than all nodes indicates that the node's degree deviates from the average level and there are high outliers in the multidimensional data model, indicating unusual activities or problems.
[0014] As a preferred solution of the panoramic transparency and risk closed-loop control method of the power grid production command center described in the present invention, the dynamic analysis of risk events in the production process includes dynamic analysis of risk events, identifying current high-risk nodes and potential risk events through a dynamic scoring method, and converting information into quantitative risk scores. The current risk score reflects the abnormal situation of each node in the system at the current moment. Combining the current risk score, historical risk score and the rate of change of the risk score, a prediction model is constructed. Through the time series prediction model, the risk score is further analyzed and predicted to determine the future risk trend, which is expressed as:
[0015]
[0016] Among them, R j Score the j-th risk event, β j is the attenuation factor of the risk event, θ j is the time offset of the risk event, P q is the qth risk prediction value, α1 is the current risk score coefficient, γ1 is the historical risk score coefficient, δ1 is the time derivative coefficient, and Δt is the time interval.
[0017] As a preferred solution of the panoramic transparency and risk closed-loop control method of the power grid production command center described in the present invention, wherein: the identification and prevention of false acceptance and false listing of items includes risk prevention, and the selection of risk prevention measures is performed based on the weighted sum of multiple risk prediction values, and the observation data probability under different preventive measures conditions and the prior probability of the preventive measures are combined. In the Bayesian optimization model, the optimal preventive measures are selected by maximizing the product of the observation data probability and the prior probability, which is expressed as:
[0018]
[0019]
[0020] Among them, Vs is the intensity of preventive measures, ω q is the weight of the precautionary measures, is the optimal preventive measure intensity, P(D|V) is the probability of observation data under the condition of preventive measure V, D i is the observed data, μ V,i is the mean of the observed data under the preventive measure V, σ i is the standard deviation of the observed data, P(V) is the prior probability of the preventive measures, μ V is the prior mean of the precautionary measures, σ V is the a priori standard deviation of the precautionary measure and Z is the normalization constant.
[0021] As a preferred solution of the panoramic transparency and risk closed-loop control method of the power grid production command center described in the present invention, the closed-loop control of the collected data includes information entropy, and the closed-loop control model constructs a control quantity that reflects the dynamic changes of risks by performing time-weighted integration on the intensity of preventive measures, and adjusts the control measures of the system in real time in combination with historical data. By calculating the probability distribution of the occurrence of events, the degree of system uncertainty is quantified, and the closed-loop control feedback is combined with the control quantity and information entropy for normalization, which is expressed as:
[0022]
[0023] Among them, C t is the closed-loop control quantity, γ is the attenuation factor, H is the information entropy, p i is the probability of event i occurring, F c is the closed-loop control feedback value, H max is the maximum information entropy.
[0024] As a preferred solution of the panoramic transparency and risk closed-loop control method of the power grid production command center described in the present invention, the continuous monitoring and dynamic management of risks includes dynamic management, which dynamically adjusts and optimizes the system management strategy by combining closed-loop control feedback and optimal control theory, and finds the optimal solution under preset constraints through the Lagrangian optimization control method, which is expressed as:
[0025]
[0026] Among them, G d To dynamically manage model values, α t To dynamically manage weights, is the Lagrangian function, f(x) is the objective function, λ1 is the Lagrangian multiplier, g i (x) is the constraint condition, b i is the constraint value.
[0027] Another object of the present invention is to provide a panoramic transparency and risk closed-loop control system for a power grid production command center, which can perform closed-loop control on collected data through a closed-loop control module, continuously monitor and dynamically manage risks, and solve the current problem of not fully utilizing information theory tools to evaluate the complexity and uncertainty of feedback data.
[0028] As a preferred solution for the panoramic transparency and risk closed-loop control system of the power grid production command center described in the present invention, it includes: a standardized modeling module, an analysis and prevention module, and a closed-loop control module; the standardized modeling module is used to collect data and perform standardized processing and transparent management of real-time data in the power grid production process; the analysis and prevention module is used to dynamically analyze risk events in the production process, identify and prevent false acceptance and fictitious items; the closed-loop control module is used to perform closed-loop control of the collected data, continuously monitor and dynamically manage risks.
[0029] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that the processor executes the computer program to implement a method for panoramic transparency and risk closed-loop control of a power grid production command center.
[0030] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for implementing panoramic transparency and risk closed-loop control of a power grid production command center are implemented.
[0031] Beneficial effects of the present invention: The panoramic transparency and risk closed-loop control method of the power grid production command center provided by the present invention improves the accuracy and robustness of data processing through standardized processing and multi-scale analysis, integrates multi-source data through multi-dimensional data modeling, and enhances the overall grasp of the power grid production process. The dynamic analysis and prediction methods identify the development trend of potential risk events in advance, improve the timeliness and accuracy of risk identification, and dynamically evaluate and prevent risks through the Bayesian inference method, thereby enhancing the scientificity and accuracy of risk management and improving the security of the system. The complexity and uncertainty of feedback data are evaluated through information entropy, which improves the scientificity and effectiveness of the system control strategy and the management efficiency of the system. The management strategy is comprehensively optimized and adjusted through the Lagrangian optimization method, which significantly improves the management and control capabilities of the power grid production process and improves the overall benefits of the system. The present invention achieves better results in terms of accuracy, security and management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
[0033] Figure 1 An overall flow chart of the panoramic transparency and risk closed-loop control method of the power grid production command center provided in the first embodiment of the present invention.
[0034] Figure 2 An overall module diagram of a panoramic transparency and risk closed-loop control system for a power grid production command center provided in the third embodiment of the present invention. DETAILED DESCRIPTION
[0035] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0036] Example 1
[0037] Reference Figure 1 , which is an embodiment of the present invention, provides a panoramic transparency and risk closed-loop control method for a power grid production command center, including:
[0038] S1: Collect data and perform standardized processing and transparent management of real-time data in the power grid production process.
[0039] Furthermore, data is collected and real-time data in the power grid production process is standardized and transparently managed, including multi-scale analysis.
[0040] It should be noted that real-time power load data, equipment operation status data, and environmental monitoring data are obtained from various sensors and monitoring equipment. Power load, equipment temperature, equipment vibration, ambient temperature, and humidity are collected. The mean and standard deviation of various raw data are processed, and time frequency factors and historical data weights are introduced to eliminate the dimensional influence of the data so that data of different scales can be compared on the same basis. Multi-scale analysis is performed on standardized data through wavelet transform, and scale parameters and translation parameters are adjusted. Data are analyzed at different time scales to reveal structures and patterns at different time resolutions. Multi-scale analysis is expressed as:
[0041]
[0042]
[0043] Among them, S i is the standardized data, D i are various raw data, μ D is the data mean, σ D is the data standard deviation, t is the time variable, ω is the time frequency factor, h is the historical data factor, α is the historical data weight, W(t,a) is the data after wavelet transformation, ψ is the mother wavelet function, a is the scale parameter, and b is the translation parameter.
[0044] Furthermore, data collection and standardized processing and transparent management of real-time data in the power grid production process also include multi-dimensional data modeling.
[0045] It should be noted that by integrating data sources and weighting data with different weights, a multi-dimensional data model is constructed, and a relationship network between data is constructed and analyzed. The degree distribution of nodes in the network is calculated, and the node relationship is adjusted through periodic weights and sensitivity factors. The abnormal conditions and trends in the data are reflected in real time, which is expressed as:
[0046]
[0047] Among them, M k is a multidimensional data model, w i is the data weight, λ i is the decay factor, T is the time interval, P(k) is the node degree distribution, k i is the degree of the i-th node, A i is the abnormality measure of the i-th node, is the average degree of all nodes in the network, max(M k ) is the maximum value in the multidimensional data model result. If the abnormality measure A of the node i A value higher than all nodes indicates that the node's degree deviates from the average level and there are high outliers in the multidimensional data model, indicating unusual activities or problems.
[0048] S2: Dynamically analyze risk events in the production process to identify and prevent false acceptance and fictitious items.
[0049] Furthermore, dynamic analysis of risk events in the production process includes dynamic analysis of risk events.
[0050] It should be noted that the current high-risk nodes and potential risk events are identified through the dynamic scoring method, and the information is converted into a quantitative risk score. The current risk score reflects the abnormal situation of each node in the system at the current moment. Combining the current risk score, historical risk score and the rate of change of the risk score, a prediction model is constructed. Through the time series prediction model, the risk score is further analyzed and predicted to determine the future risk trend, which is expressed as:
[0051]
[0052] Among them, R j Score the j-th risk event, β j is the attenuation factor of the risk event, θ j is the time offset of the risk event, P q is the qth risk prediction value, α1 is the current risk score coefficient, γ1 is the historical risk score coefficient, δ1 is the time derivative coefficient, and Δt is the time interval.
[0053] Going further, identifying and preventing false acceptances and fictitious items includes risk prevention.
[0054] It should be noted that the selection of risk prevention measures is based on the weighted sum of multiple risk prediction values, combined with the observed data probability under different preventive measures and the prior probability of the preventive measures. In the Bayesian optimization model, the optimal preventive measures are selected by maximizing the product of the observed data probability and the prior probability, which is expressed as:
[0055]
[0056] Among them, V s is the intensity of preventive measures, ω q is the weight of the precautionary measures, is the optimal preventive measure intensity, P(D|V) is the probability of observation data under the condition of preventive measure V, D i is the observed data, μ V,i is the mean of the observed data under the preventive measure V, σ i is the standard deviation of the observed data, P(V) is the prior probability of the preventive measures, μ V is the prior mean of the precautionary measures, σ V is the a priori standard deviation of the precautionary measure and Z is the normalization constant.
[0057] S3: Perform closed-loop control on collected data, continuously monitor and dynamically manage risks.
[0058] Furthermore, closed-loop control of the collected data includes information entropy.
[0059] It should be noted that the closed-loop control model constructs a control quantity that reflects the dynamic changes of risks by performing a time-weighted integral on the intensity of preventive measures. It adjusts the control measures of the system in real time by combining historical data. It quantifies the degree of system uncertainty by calculating the probability distribution of events. The closed-loop control feedback combines the control quantity and information entropy for normalization, which can be expressed as:
[0060]
[0061] Among them, C t is the closed-loop control quantity, γ is the attenuation factor, H is the information entropy, p i is the probability of event i occurring, F c is the closed-loop control feedback value, H max is the maximum information entropy.
[0062] Going further, continuously monitoring and dynamically managing risks includes dynamic management.
[0063] It should be noted that by combining closed-loop control feedback and optimal control theory, the system management strategy is dynamically adjusted and optimized, and the optimal solution is found under the preset constraints through the Lagrangian optimization control method, which is expressed as:
[0064]
[0065] Among them, G d To dynamically manage model values, α t To dynamically manage weights, is the Lagrangian function, f(x) is the objective function, λ1 is the Lagrangian multiplier, g i (x) is the constraint condition, b i is the constraint value.
[0066] It should also be noted that the deviation between the dynamic management model value and the expected value is minimized, and the rate of change of the dynamic management value is smoothed. The objective function is expressed as:
[0067]
[0068] in, is the expected dynamic management value, β is the smoothing parameter, and the constraints are expressed as:
[0069]
[0070] g2(x)=t f -T r ≤0
[0071] g3(x)=P q -P t ≤0
[0072] Among them, g1(x), g2(x), and g3(x) are resource constraints, time constraints, and risk thresholds, respectively. j is the resource allocation, R a is the total resources, t f is the actual completion time, T r To specify the completion time, P t is the risk threshold.
[0073] Example 2
[0074] An embodiment of the present invention provides a panoramic transparency and risk closed-loop control method for a power grid production command center. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
[0075] The experiment selected the production data of a certain power company, including real-time power load data, equipment operation data and environmental monitoring data, for standardized processing, dynamic analysis and risk management. First, the experiment prepared hardware facilities including data acquisition equipment, data processing servers and risk warning systems, and installed necessary software tools and algorithm modules. Specific data included parameters such as power load (MW), equipment temperature (℃), equipment vibration (mm / s), ambient temperature (℃) and humidity (%).
[0076] Before the experiment, power grid production data within one month were collected. The data were recorded every hour and divided into two groups. One group was processed and analyzed by the existing technology, and the other group was processed and analyzed by the method of the present invention. The collected power grid production data were standardized and multi-scale analysis was performed by wavelet transform. The data processing process included processing the mean and standard deviation of various raw data to eliminate the dimension effect, and capturing the instantaneous changes and local features in the data by wavelet transform to generate a standardized data set. The standardized data were comprehensively processed by multidimensional data modeling technology to construct a multidimensional data model. Complex network theory analyzes the relationship between data and identifies potential patterns and structures in the data. This step uses Bayesian networks and Markov chain models to dynamically analyze data, and uses nonlinear dynamics methods and chaotic mapping predictions to dynamically analyze and predict risk events that may occur in the power grid production process. Through sensitivity factors and risk thresholds, potential risk events are monitored and identified in real time. Combined with Bayesian inference methods, risks are dynamically evaluated and prevented. Information entropy is used to evaluate the complexity and uncertainty of feedback data. The system is dynamically adjusted through a closed-loop control model to ensure stable operation of the system at different risk levels.
[0077] As shown in Table 1, the prior art has certain fluctuations in the data processing process, resulting in insufficient accuracy and stability of the data. The present invention uses multi-scale analysis and wavelet transform to perform fine standardization processing on the data, significantly reducing the fluctuation range of the data, making the power load data more stable and accurate. The data processing results of the present invention show lower temperature and vibration values, indicating that through complex network analysis and nonlinear dynamics methods, potential risk events can be identified and prevented more timely, effectively reducing the operating risks of equipment. The present invention can monitor and manage environmental parameters more accurately to ensure the safe and stable operation of the power grid production process. The ambient temperature and humidity processed by the prior art fluctuate greatly, while the data processed by the present invention is more stable, indicating that the effectiveness of information entropy and closed-loop control methods in risk management has been fully verified.
[0078] Table 1 Experimental data table
[0079] Prior art 1 Prior Art 2 The present invention 1 The present invention 2 Power load 450MW 460MW 455MW 458MW Equipment temperature 85℃ 88℃ 83℃ 84℃ Equipment vibration 4.2mm / s 4.5mm / s 3.8mm / s 4mm / s Ambient temperature 30℃ 32℃ 29℃ 30℃ humidity 60% 65% 58% 62%
[0080] Example 3
[0081] Reference Figure 2 , which is an embodiment of the present invention, provides a panoramic transparency and risk closed-loop control system for a power grid production command center, including: a standardized modeling module, an analysis and prevention module, and a closed-loop control module.
[0082] The standardized modeling module is used to collect data and perform standardized processing and transparent management of real-time data in the power grid production process; the analysis and prevention module is used to dynamically analyze risk events in the production process, identify and prevent false acceptance and fictitious items; and the closed-loop control module is used to perform closed-loop control of the collected data, continuously monitor and dynamically manage risks.
[0083] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0084] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0085] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.
[0086] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.
[0087] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A panoramic transparency and risk closed-loop control method for a power grid production command center, characterized in that: include: Collect data and perform standardized processing and transparent management of real-time data in the power grid production process; Dynamically analyze risk events in the production process to identify and prevent false acceptance and fictitious items; Conduct closed-loop control of collected data to continuously monitor and dynamically manage risks.
2. The method for panoramic transparency and risk closed-loop control of a power grid production command center according to claim 1, characterized in that: The data collection and standardized processing and transparent management of real-time data in the power grid production process include multi-scale analysis, obtaining real-time power load data, equipment operation status data, and environmental monitoring data from various sensors and monitoring equipment, collecting power load, equipment temperature, equipment vibration, ambient temperature and humidity, processing the mean and standard deviation of various types of original data, and introducing time frequency factors and historical data weights to eliminate the dimensional influence of the data so that data of different scales can be compared on the same basis, performing multi-scale analysis on standardized data through wavelet transform, adjusting scale parameters and translation parameters, analyzing data at different time scales, and revealing structures and patterns at different time resolutions. The multi-scale analysis is expressed as: Among them, S i is the standardized data, D i are various raw data, μ D is the data mean, σ D is the data standard deviation, t is the time variable, ω is the time frequency factor, h is the historical data factor, α is the historical data weight, W(t, a) is the data after wavelet transformation, ψ is the mother wavelet function, a is the scale parameter, and b is the translation parameter.
3. The method for panoramic transparency and risk closed-loop control of a power grid production command center according to claim 2, characterized in that: The data collection and standardized processing and transparent management of real-time data in the power grid production process also include multi-dimensional data modeling, which integrates data sources and uses different weights to weight data, builds a multi-dimensional data model, and builds and analyzes the relationship network between data, calculates the degree distribution of nodes in the network, and adjusts the node relationship through periodic weights and sensitivity factors to reflect abnormal conditions and trends in the data in real time, which is expressed as: Among them, M k is a multidimensional data model, w i is the data weight, λ i is the decay factor, T is the time interval, P(k) is the node degree distribution, k i is the degree of the i-th node, A i is the abnormality measure of the i-th node, is the average degree of all nodes in the network, max(M k ) is the maximum value in the multidimensional data model result. If the abnormality measure A of the node i A value higher than all nodes indicates that the node's degree deviates from the average level and there are high outliers in the multidimensional data model, indicating unusual activities or problems.
4. The method for panoramic transparency and risk closed-loop control of a power grid production command center according to claim 3, characterized in that: The dynamic analysis of risk events in the production process includes dynamic analysis of risk events. The current high-risk nodes and potential risk events are identified through a dynamic scoring method, and the information is converted into a quantitative risk score. The current risk score reflects the abnormal situation of each node in the system at the current moment. Combined with the current risk score, historical risk score and the rate of change of the risk score, a prediction model is constructed. Through the time series prediction model, the risk score is further analyzed and predicted to determine the future risk trend, which is expressed as: Among them, R j Score the j-th risk event, β j is the attenuation factor of the risk event, θ j is the time offset of the risk event, P q is the qth risk prediction value, α1 is the current risk score coefficient, γ1 is the historical risk score coefficient, δ1 is the time derivative coefficient, and Δt is the time interval.
5. The method for panoramic transparency and risk closed-loop control of a power grid production command center according to claim 4, characterized in that: The identification and prevention of false acceptance and false listing of items includes risk prevention, which selects risk prevention measures based on the weighted sum of multiple risk prediction values, combines the observed data probability under different preventive measures and the prior probability of the preventive measures, and selects the optimal preventive measures in the Bayesian optimization model by maximizing the product of the observed data probability and the prior probability, which is expressed as: Among them, V s is the intensity of preventive measures, ω q is the weight of the precautionary measures, is the optimal preventive measure intensity, P(D|V) is the probability of observation data under the condition of preventive measure V, D i is the observed data, μV, i is the mean of the observed data under the preventive measure V, σ i is the standard deviation of the observed data, P(V) is the prior probability of the preventive measures, μ V is the prior mean of the precautionary measures, σ V is the a priori standard deviation of the precautionary measure and Z is the normalization constant.
6. The method for panoramic transparency and risk closed-loop control of a power grid production command center according to claim 5, characterized in that: The closed-loop control of the collected data includes information entropy. The closed-loop control model constructs a control quantity that reflects the dynamic changes of risks by performing time-weighted integration on the intensity of the preventive measures. Combined with historical data, the control measures of the system are adjusted in real time. The probability distribution of the event is calculated to quantify the degree of uncertainty of the system. The closed-loop control feedback combines the control quantity and information entropy for normalization, which is expressed as: Among them, C t is the closed-loop control quantity, γ is the attenuation factor, H is the information entropy, p i is the probability of event i occurring, F c is the closed-loop control feedback value, H max is the maximum information entropy.
7. The method for panoramic transparency and risk closed-loop control of a power grid production command center according to claim 6, characterized in that: The continuous monitoring and dynamic management of risks includes dynamic management, which dynamically adjusts and optimizes the system management strategy by combining closed-loop control feedback and optimal control theory, and finds the optimal solution under preset constraints through the Lagrangian optimization control method, which is expressed as: Among them, G d To dynamically manage model values, α t To dynamically manage weights, is the Lagrangian function, f(x) is the objective function, λ1 is the Lagrangian multiplier, g i (x) is the constraint condition, b i is the constraint value.
8. A system using the panoramic transparency and risk closed-loop control method of a power grid production command center as claimed in any one of claims 1 to 7, characterized in that: Includes standardized modeling module, analysis and prevention module, and closed-loop control module; The standardized modeling module is used to collect data and perform standardized processing and transparent management of real-time data in the power grid production process; The analysis and prevention module is used to dynamically analyze risk events in the production process, identify and prevent false acceptance and fictitious items; The closed-loop control module is used to perform closed-loop control on the collected data, continuously monitor and dynamically manage risks.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the panoramic transparency and risk closed-loop control method of the power grid production command center described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the panoramic transparency and risk closed-loop control method of a power grid production command center described in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Safety and energy efficiency monitoring system for station power utilization system based on multi-source information fusion
CN119716362A
Electrical equipment and control system thereof
CN119828476A
Safety protection method and system of intelligent electric energy meter
CN120512312A
A safety protection method and system for smart electric energy meter
CN120512312B
Online energy monitoring system and method
CN120832625A
