CN118199059B

CN118199059B - Intelligent power scheduling method and system for dynamic guarantee

Info

Publication number: CN118199059B
Application number: CN202410607743.9A
Authority: CN
Inventors: 孟威; 梁鹏; 范宏亮; 方春雷; 张瑜; 林茂; 刘碧琦; 赵龙; 谷博; 潘子毅; 夏雨
Original assignee: Information and Telecommunication Branch of State Grid Liaoning Electric Power Co Ltd
Current assignee: Information and Telecommunication Branch of State Grid Liaoning Electric Power Co Ltd
Priority date: 2024-05-16
Filing date: 2024-05-16
Publication date: 2024-09-13
Anticipated expiration: 2044-05-16
Also published as: CN118199059A

Abstract

The invention discloses an intelligent power dispatching method and system for dynamic guarantee, which relate to the related field of intelligent power grids, wherein the method comprises the following steps: obtaining a power topology data set, and performing standardized processing to obtain a standard power topology data set; constructing a power dispatching topology network; performing real-time monitoring to obtain a power monitoring topology network; activating a power failure feature prediction channel, performing abnormality positioning, and determining an abnormal power topology network; collecting load equipment information to obtain abnormal topological load distribution; activating a standby power supply module, collecting information of each standby power supply unit, and determining a standby power supply data set; and carrying out power dispatching optimization, determining a standby power supply dispatching scheme, and carrying out guaranteed power dispatching. The technical problems that the existing power dispatching lacks flexibility and dynamic adaptability and is difficult to meet real-time dispatching requirements are solved, and the technical effects of improving the flexibility and dynamic adaptability of power dispatching and improving the reliability and stability of power supply are achieved.

Description

Intelligent power scheduling method and system for dynamic guarantee

Technical Field

The application relates to the field of intelligent power grid, in particular to an intelligent power dispatching method and system for dynamic security.

Background

The power dispatching is a vital management means in the power system, and is characterized in that the safety and economic running state of the power grid is judged by collecting data fed back by various information acquisition devices or combining actual running parameters (such as voltage, current, frequency, load and the like) of the power grid according to information provided by monitoring personnel, comprehensively considering the development condition of various production works, issuing an operation instruction according to the safety and economic running state, and commanding on-site operators or an automatic control system to adjust. In the existing power dispatching method, when the power faults are handled, a fixed standby power supply scheme is generally adopted, and the scheme lacks flexibility and dynamic adaptability, so that the real-time dispatching requirement of a power system after the faults occur is difficult to meet.

In the related technology of the present stage, the power dispatching has the technical problems of lack of flexibility and dynamic adaptability, and difficulty in meeting the real-time dispatching requirement.

Disclosure of Invention

The application provides the intelligent power dispatching method and system for dynamic guarantee, which adopts the technical means of obtaining a standard power topology data set, constructing a power dispatching topology network, carrying out real-time monitoring, carrying out abnormal positioning, carrying out power dispatching optimization and the like, realizes the dynamic adjustment of a standby power supply scheme according to the real-time running state and the fault type of a power system, reduces the influence of faults on the power system, and achieves the technical effects of improving the flexibility and dynamic adaptability of power dispatching and the reliability and stability of power supply.

The application provides an intelligent power dispatching method for dynamic security, which comprises the following steps:

Collecting topology information of a power system, obtaining a power topology data set, and carrying out standardized processing on the power topology data set to obtain a standard power topology data set;

Constructing a power dispatching topological network according to the standard power topological data set;

the power system is monitored in real time according to the power dispatching topology network, and a power monitoring topology network is obtained;

Activating a power failure feature prediction channel, combining the power monitoring topology network to perform abnormal positioning on the power dispatching topology network, and determining an abnormal power topology network;

collecting load equipment information of the abnormal power topology network to obtain abnormal topology load distribution;

Activating a standby power supply module of the power system, collecting information of each standby power supply unit in the standby power supply module, and determining a standby power supply data set;

And carrying out power dispatching optimization according to the standby power supply data set and the abnormal topological load distribution, determining a standby power supply dispatching scheme meeting dispatching optimization composite constraint, and carrying out guarantee power dispatching according to the standby power supply dispatching scheme.

In a possible implementation manner, the activating a power failure feature prediction channel performs abnormality positioning on the power scheduling topology network in combination with the power monitoring topology network, determines an abnormal power topology network, and performs the following processing:

extracting a plurality of power line monitoring data sets according to the power monitoring topology network;

Inputting the plurality of power line monitoring data sets into the power failure feature prediction channel to obtain a plurality of line failure prediction feature indexes;

Judging whether the line fault prediction characteristic indexes are smaller than a preset fault prediction characteristic index or not, and obtaining abnormal fault prediction characteristic distribution which is not smaller than the preset fault prediction characteristic index;

and positioning the power monitoring topology network according to the abnormal fault prediction characteristic distribution to obtain an abnormal power topology network.

In a possible implementation manner, the inputting the plurality of power line monitoring data sets into the power failure feature prediction channel obtains a plurality of line failure prediction feature indexes, and performs the following processing:

The power failure feature prediction channel comprises a bilateral power failure prediction branch and a failure feature calculation branch;

Inputting the plurality of power line monitoring data sets into the bilateral power failure prediction branch to obtain a plurality of line failure prediction results, wherein each line failure prediction result comprises a predicted line failure probability and a predicted line failure risk coefficient;

And inputting the plurality of line fault prediction results into the fault feature calculation branch to generate the plurality of line fault prediction feature indexes.

In a possible implementation manner, the fault feature calculation branch includes a fault feature calculation function, where the fault feature calculation function is:

The CFP characterizes a line fault prediction characteristic index, the CFA characterizes a predicted line fault probability, the FAO characterizes a line fault probability threshold, the CFB characterizes a predicted line fault risk coefficient and the FBO characterizes a line fault risk threshold.

In a possible implementation manner, the construction step of the bilateral power failure prediction branch performs the following processing:

Connecting the power system, and loading a power line monitoring record set, a line fault probability record set and a line fault risk coefficient record set;

activating a fault learning channel, wherein the fault learning channel comprises a plurality of fault learners;

extracting a first random fault learner and a second random fault learner according to the fault learning channel;

Taking the power line monitoring record set as input information, taking the line fault probability record set as output information, performing supervised learning on the first random fault learner, and generating a power fault probability predictor meeting fault probability learning accuracy;

Taking the power line monitoring record set as input data, taking the line fault risk coefficient record set as output data, performing supervised learning on the second random fault learner, and generating a power fault risk predictor meeting fault risk learning accuracy;

and merging the power failure probability predictor and the power failure risk predictor as parallel nodes to generate the bilateral power failure prediction branch.

In a possible implementation manner, the power scheduling optimizing is performed according to the standby power supply data set and the abnormal topological load distribution, a standby power supply scheduling scheme meeting the scheduling optimizing composite constraint is determined, and the following processing is performed:

carrying out load equipment criticality identification according to the abnormal topological load distribution, and constructing abnormal topological key load distribution meeting the key constraint of the load equipment;

taking the standby power supply data set as a standby power dispatching constraint, and taking the abnormal topological key load distribution as a standby power dispatching target;

Carrying out random power dispatching according to the standby power dispatching constraint and the standby power dispatching target, and constructing a standby power dispatching solution domain meeting a first dispatching solution capacity constraint;

the scheduling optimizing composite constraint comprises a scheduling optimizing evaluation constraint and a scheduling optimizing iteration constraint;

Activating a scheduling evaluation prediction channel, and carrying out initial optimization on the standby power supply scheduling solution domain by combining the scheduling optimization evaluation constraint to construct an optimized standby power supply scheduling solution domain meeting a second scheduling solution capacity constraint;

performing mutation according to the optimizing standby power supply scheduling solution domain, and constructing a mutated standby power supply scheduling solution domain meeting the capacity constraint of a third scheduling solution;

And carrying out deep optimization on the optimizing standby power supply dispatching solution domain and the variant standby power supply dispatching solution domain according to the dispatching evaluation prediction channel, the dispatching optimizing evaluation constraint and the dispatching optimizing iteration constraint to generate the standby power supply dispatching scheme.

In a possible implementation manner, the active schedule evaluation prediction channel performs initial optimization on the standby power supply schedule solution domain in combination with the schedule optimization evaluation constraint, constructs an optimized standby power supply schedule solution domain meeting a second schedule solution capacity constraint, and performs the following processing:

Extracting a first standby power supply scheduling solution according to the standby power supply scheduling solution domain;

Performing predictive evaluation on the first standby power supply scheduling solution based on the scheduling evaluation prediction channel to obtain first scheduling prediction evaluation feature data, wherein the scheduling evaluation prediction channel comprises a multi-dimensional scheduling evaluation prediction index, and the multi-dimensional scheduling evaluation prediction index comprises power supply scheduling loss, power supply scheduling efficiency and scheduling load balance;

Judging whether the first scheduling prediction evaluation characteristic data meets the scheduling optimizing evaluation constraint;

If the first scheduling prediction evaluation characteristic data meets the scheduling optimizing evaluation constraint, adding the first standby power supply scheduling solution to the optimizing standby power supply scheduling solution domain;

And continuing optimizing the standby power supply scheduling solution domain according to the scheduling evaluation prediction channel and the scheduling optimizing evaluation constraint until the optimizing standby power supply scheduling solution domain meeting the second scheduling solution capacity constraint is generated.

In a possible implementation manner, the performing deep optimization on the optimized standby power supply scheduling solution domain and the variant standby power supply scheduling solution domain according to the scheduling evaluation prediction channel, the scheduling optimizing evaluation constraint and the scheduling optimizing iteration constraint to generate the standby power supply scheduling scheme, and executing the following processing:

Performing power supply scheduling loss minimization optimizing according to the optimizing standby power supply scheduling solution domain, and determining an initial standby power supply scheduling scheme;

carrying out optimizing analysis on the variable standby power supply dispatching solution domain according to the dispatching evaluation prediction channel to generate an optimizing variable standby power supply dispatching solution domain meeting the dispatching optimizing evaluation constraint;

extracting a first optimizing variation standby power supply scheduling solution according to the optimizing variation standby power supply scheduling solution domain;

performing power supply scheduling loss minimization optimization according to the initial standby power supply scheduling scheme and the first optimizing variation standby power supply scheduling solution, and generating a current standby power supply scheduling scheme;

And continuing to perform power supply scheduling loss minimization iterative optimization on the current standby power supply scheduling scheme and the optimizing variation standby power supply scheduling solution domain until the standby power supply scheduling scheme meeting the scheduling optimizing iteration constraint is obtained.

The application also provides an intelligent power dispatching system for dynamic guarantee, which comprises the following steps:

the standard power topology data set acquisition module is used for acquiring topology information of the power system, obtaining a power topology data set, and carrying out standardization processing on the power topology data set to obtain a standard power topology data set;

The power dispatching topological network construction module is used for constructing a power dispatching topological network according to the standard power topological data set;

the real-time monitoring module is used for monitoring the power system in real time according to the power dispatching topology network to obtain a power monitoring topology network;

the abnormal positioning module is used for activating a power failure feature prediction channel, combining the power monitoring topology network to perform abnormal positioning on the power dispatching topology network and determining an abnormal power topology network;

The load equipment information acquisition module is used for acquiring load equipment information of the abnormal power topology network and obtaining abnormal topology load distribution;

The standby power supply data set determining module is used for activating a standby power supply module of the power system, collecting information of each standby power supply unit in the standby power supply module and determining a standby power supply data set;

And the guarantee power dispatching module is used for carrying out power dispatching optimization according to the standby power supply data set and the abnormal topological load distribution, determining a standby power supply dispatching scheme meeting dispatching optimization composite constraint and carrying out guarantee power dispatching according to the standby power supply dispatching scheme. The power intelligent scheduling method and the system for dynamic guarantee are proposed, firstly, the topology information of a power system is acquired, a power topology data set is obtained, the power topology data set is subjected to standardized processing, a standard power topology data set is obtained, then, a power scheduling topology network is built according to the standard power topology data set, further, the power system is monitored in real time according to the power scheduling topology network, a power monitoring topology network is obtained, then, a power failure characteristic prediction channel is activated, the power scheduling topology network is subjected to abnormal positioning by combining the power monitoring topology network, an abnormal power topology network is determined, load equipment information of the abnormal power topology network is acquired, abnormal topology load distribution is obtained, then, a standby power supply module of the power system is activated, information of each standby power supply unit in the standby power supply module is acquired, a standby power supply data set is determined, finally, power scheduling optimizing is carried out according to the standby power supply data set and the abnormal topology load distribution, a standby power supply scheduling scheme meeting scheduling optimizing composite constraint is determined, and power scheduling is guaranteed according to the standby power scheduling scheme, and the technical effects of improving flexibility and dynamic adaptability of power scheduling are achieved, and reliability and stability of power supply are improved.

Drawings

In order to more clearly illustrate the technical solution of the embodiments of the present application, the following description will briefly refer to the accompanying drawings of the embodiments of the present application, in which flowcharts are used to illustrate operations performed by systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic flow chart of an intelligent power dispatching method for dynamic security according to an embodiment of the present application;

Fig. 2 is a schematic structural diagram of an intelligent power dispatching system for dynamic security according to an embodiment of the present application. Reference numerals illustrate: the system comprises a standard power topology data set acquisition module 10, a power dispatching topology network construction module 20, a real-time monitoring module 30, an abnormality locating module 40, a load equipment information acquisition module 50, a standby power supply data set determination module 60 and a power dispatching module 70.

Detailed Description

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.

The embodiment of the application provides an intelligent power scheduling method for dynamic security, as shown in fig. 1, the method comprises the following steps:

Step S100, collecting topology information of a power system, obtaining a power topology data set, and carrying out standardization processing on the power topology data set to obtain a standard power topology data set. Specifically, the topology information such as device connection information, device type, capacity and the like of the power system is collected by using sensors, remote monitoring devices (such as RTUs, remote terminal units), SCADA (supervisory control and data acquisition) systems and other automation tools, and the topology information includes connection relations, parameters and states of substations, lines, transformers, generators, loads and the like. And (3) sorting the collected topology information into structural data to construct a power topology data set, wherein the power topology data set is a structural data set containing information such as equipment connection relation, equipment attributes and the like of a power system, and comprises information such as nodes (such as equipment) and edges (such as connection relation) and related attributes (such as voltage level, equipment capacity and the like). And (3) carrying out standardized processing on the power topology data set, removing repeated data, error data or invalid data, enabling the format, unit and coding mode of the data to be consistent, converting the data as required, such as converting voltage from kilovolts to volts or converting equipment capacity from megawatts to kilowatts and the like, converting the data into a standard format, such as XML, JSON or relational database format, and obtaining a clean, unified and standardized power topology data set after the standardized processing of the steps.

And step 200, building a power dispatching topological network according to the standard power topological data set. Specifically, information of nodes (e.g., substations, generators, loads, etc.) and edges (e.g., transmission lines, cables, etc.) in the standard power topology dataset is analyzed, and attributes of the nodes and edges, such as voltage class, capacity, impedance, etc., are determined. According to the requirements of power dispatching and the used technical stack, a network modeling tool is determined, wherein the network modeling tool comprises graph theory software, a network simulation tool or custom programming and the like. In the network modeling tool, nodes and edges are added into a network according to information of a standard power topology data set, attributes of the nodes and the edges are set, a power dispatching topology network is built, namely the power dispatching topology network is based on a topology structure and operation characteristics of a power system, a network model for power dispatching built by the network modeling tool is used, the network model can reflect actual operation conditions of the power system, and various power dispatching algorithms and application of analysis methods are supported.

And step S300, monitoring the power system in real time according to the power dispatching topology network to obtain a power monitoring topology network. In particular, monitoring points are set on key nodes and edges of the power dispatching topology network, and the monitoring points can be sensors, measuring devices or other data acquisition devices. Real-time data of the power system, including parameters such as voltage, current, power, temperature and the like, are continuously collected through monitoring points, and are transmitted to a data processing center through a network. The data processing center integrates and processes the received real-time monitoring data, including data cleaning, format conversion, time synchronization and other operations, so that the data can keep accuracy and consistency. According to the real-time monitoring data, the power monitoring topology network is constructed by combining the structure and the attribute of the power dispatching topology network, and the power monitoring topology network is the real-time mapping of the power dispatching topology network and reflects the real-time running state of the power system.

And step S400, activating a power failure feature prediction channel, combining the power monitoring topology network to perform abnormal positioning on the power dispatching topology network, and determining an abnormal power topology network. Specifically, a pre-configured power failure feature prediction channel is initiated, which is an algorithm or model for predicting power system failure features that identifies potential failure modes or features based on real-time monitoring data and other relevant information. The method comprises the steps of processing and analyzing data in a power monitoring topological network by using a power fault feature prediction channel, identifying potential fault features or modes, comparing and analyzing the predicted fault features with a power dispatching topological network, and determining the specific position or area where the abnormality occurs by using methods such as graph theory, network analysis and the like. And determining a power topology network part containing abnormal nodes or edges, namely an abnormal power topology network, according to the abnormal positioning result, wherein the abnormal power topology network is a set of one or more interconnected nodes and edges, and the abnormal power topology network constitutes a potential fault area in the power system.

In one possible implementation, step S400 further includes step S410 of extracting a plurality of power line monitoring data sets according to the power monitoring topology network. Specifically, the power monitoring topology network includes a plurality of power lines, and for each power line, real-time monitoring data of the power lines including parameters such as voltage, current, power factor, temperature and the like are collected, and these data are organized into structured power line monitoring data sets, where each power line monitoring data set represents a real-time state of one power line. Step S420, inputting the plurality of power line monitoring data sets into the power failure feature prediction channel to obtain a plurality of line failure prediction feature indexes. Specifically, the plurality of power line monitoring data sets acquired in step S410 are input into a pre-trained power failure feature prediction channel, and the power failure feature prediction channel calculates a line failure prediction feature index of each power line according to the input power line monitoring data sets, where the line failure prediction feature index represents a possibility or a risk degree of failure of the power line. Step S430, judging whether the line fault prediction characteristic indexes are smaller than a preset fault prediction characteristic index, and obtaining abnormal fault prediction characteristic distribution which is not smaller than the preset fault prediction characteristic index. Specifically, a predetermined failure prediction feature index threshold is set based on historical data and experience, the line failure prediction feature index of each power line calculated in step S420 is compared with the threshold, power lines with the line failure prediction feature index greater than or equal to the threshold are found out, the power lines are considered to have higher failure risks, and the failure prediction feature index distribution of the power lines with higher failure risks is sorted and analyzed to obtain abnormal failure prediction feature distribution. And step S440, positioning the power monitoring topological network according to the abnormal fault prediction characteristic distribution to obtain an abnormal power topological network. Specifically, according to the abnormal fault prediction feature distribution obtained in step S430, corresponding power lines are located in the power monitoring topology network, and the network part formed by the power lines with higher fault risk and the relevant nodes and edges thereof is used as the abnormal power topology network. According to the implementation mode, the power failure characteristic prediction is carried out by extracting the plurality of power line monitoring data sets, so that the abnormal region in the power system is accurately and efficiently positioned, and the technical effects of improving the accuracy and efficiency of abnormality positioning are achieved.

In one possible implementation, step S420 further includes step S421, where the power failure feature prediction channel includes a bilateral power failure prediction branch and a failure feature calculation branch. Specifically, the bilateral power failure prediction branch is used for receiving a power line monitoring data set and predicting the failure probability and the failure risk coefficient of the power line based on the power line monitoring data set, namely, simultaneously analyzing the possibility of failure occurrence and the potential influence (namely, risk) of the failure occurrence; the fault signature computation branch is to receive the prediction results from the bilateral power fault prediction branch and to generate a line fault prediction signature using a particular fault signature computation function. Step S422, inputting the plurality of power line monitoring data sets into the bilateral power failure prediction branch to obtain a plurality of line failure prediction results, where each line failure prediction result includes a predicted line failure probability and a predicted line failure risk coefficient. Specifically, a plurality of power line monitoring data sets are respectively input into a bilateral power failure prediction branch, the bilateral power failure prediction branch performs failure prediction calculation according to the input power line monitoring data sets, and for each power line, two prediction results are output: predicting line fault probability (likelihood of a line failing within a certain time period in the future) and predicting line fault risk factor (potential loss or impact of a fault for assessing the severity of the fault). Step S423, inputting the plurality of line fault prediction results into the fault feature calculation branch, and generating the plurality of line fault prediction feature indexes. Specifically, the line fault prediction feature index is an index that combines the fault probability and the fault risk coefficient, and is used to quantify the fault risk level of the power line. According to the implementation mode, the fault probability and the fault risk coefficient are predicted simultaneously through the bilateral power fault prediction branches, the fault risk of the power line is comprehensively estimated, and the technical effects of improving the accuracy and the reliability of the acquisition of the line fault prediction characteristic index are achieved.

In one possible implementation, step S421 further includes step S4211 of connecting the power system, loading a power line monitoring record set, a line fault probability record set, and a line fault risk factor record set. Specifically, a connection is established with the power system, and power line monitoring data is accessed and acquired. Loading a historical power line monitoring record set which contains state data of the power line at different time points; and loading a line fault probability record set and a line fault risk coefficient record set simultaneously, wherein the two record sets comprise historical data of probability and risk coefficients related to line faults. Step S4212, activating a fault learning channel, wherein the fault learning channel comprises a plurality of fault learners. Specifically, a fault learning channel composed of a plurality of fault learners for learning and predicting the probability of failure and risk coefficient of the power line from the history data is started. Step S4213, extracting a first random fault learner and a second random fault learner according to the fault learning channel. Specifically, two failure learners are randomly selected from the failure learning channel as a first random failure learner and a second random failure learner, respectively. Step S4214, using the power line monitoring record set as input information, using the line fault probability record set as output information, performing supervised learning on the first random fault learner, and generating a power fault probability predictor meeting the fault probability learning accuracy. Specifically, the power line monitoring record set is used as input data, the line fault probability record set is used as target output data, the first random fault learner is trained by using a supervised learning algorithm until the predicted fault probability reaches the preset fault probability learning precision, and the first random fault learner becomes the power fault probability predictor after training is completed. Step S4215, using the power line monitoring record set as input data, using the line risk coefficient record set as output data, performing supervised learning on the second random fault learner, and generating a power fault risk predictor meeting the fault risk learning accuracy. Specifically, similar to step S4214, this time, using the power line monitoring record set as input, the line fault risk factor record set as target output, training the second random fault learner until the predicted fault risk factor reaches the predetermined fault risk learning accuracy, and after training, obtaining the power fault risk predictor by the second random fault learner. Step S4216, merging the power failure probability predictor and the power failure risk predictor as parallel nodes, and generating the bilateral power failure prediction branch. Specifically, the power failure probability predictor and the power failure risk predictor are combined together as two parallel nodes, and the two nodes are respectively responsible for predicting the failure probability and the failure risk coefficient of the power line to form a bilateral power failure prediction branch. According to the implementation mode, the fault probability and the fault risk coefficient are learned from the historical data through supervised learning, so that an accurate power fault probability predictor and an accurate power fault risk predictor are trained, and the technical effect of improving the power fault prediction accuracy is achieved.

In one possible implementation manner, step S423 further includes step S4231, where the fault feature calculation branch includes a fault feature calculation function, where the fault feature calculation function is:

the CFP characterizes a line fault prediction characteristic index, the CFA characterizes a predicted line fault probability, the FAO characterizes a line fault probability threshold, the CFB characterizes a predicted line fault risk coefficient and the FBO characterizes a line fault risk threshold. By providing the fault characteristic calculation function, the implementation method achieves the technical effect of ensuring the accuracy and objectivity of line fault prediction characteristic index calculation.

And S500, collecting load equipment information of the abnormal power topology network to obtain abnormal topology load distribution. Specifically, a specific network range in which load equipment information needs to be collected is determined according to an abnormal power topology network, and all load equipment, namely equipment or a system consuming electric energy, including a transformer, a motor, a lighting system and the like, are identified in the abnormal power topology network range. The load equipment information comprises equipment type, position, capacity, current load value and the like, and real-time information of the load equipment is acquired by using a sensor, an intelligent ammeter, a remote monitoring system and other tools, wherein the real-time information comprises parameters such as the current load value, the load change rate and the like of the equipment. And (3) sorting the collected load equipment information, processing and analyzing the load data by using a data analysis tool or algorithm, and identifying the equipment with abnormal load or overload load. And generating abnormal topological load distribution according to the analysis result of the load data, wherein the abnormal topological load distribution is a description or report of the load value and the distribution condition of the load equipment in an abnormal power topological network, and the position and the load value of the abnormal load equipment and the association relation of the abnormal load equipment and other equipment are displayed.

And S600, activating a standby power supply module of the power system, collecting information of each standby power supply unit in the standby power supply module, and determining a standby power supply data set. Specifically, the standby power supply module is activated by steps of sending a starting instruction, initializing, self-checking and the like, and is a standby power supply or energy storage equipment in the power system and is used for providing power support when the main power supply fails. The standby power supply module comprises a plurality of standby power supply units, such as a standby generator, a storage battery pack and the like, and key information of the standby power supply units, such as voltage, current, power, temperature, humidity, running state, running time and the like, is acquired in real time by using tools such as a sensor, monitoring equipment and the like according to basic information of the type, capacity, state and the like of each standby power supply unit. And sorting the acquired standby power supply unit information, including unit numbers, types, capacities, real-time data, states and the like, to form a standby power supply data set.

And step S700, carrying out power dispatching optimization according to the standby power supply data set and the abnormal topological load distribution, determining a standby power supply dispatching scheme meeting dispatching optimization composite constraint, and carrying out guarantee power dispatching according to the standby power supply dispatching scheme. Specifically, according to the standby power supply data set and the abnormal topological load distribution, a power dispatching target is determined, such as minimizing load loss, maximizing power supply reliability, optimizing energy utilization efficiency and the like, and corresponding evaluation indexes or constraint conditions are set according to the power dispatching target. Based on the network structure, equipment characteristics and real-time running state of the power system, a mathematical model of power dispatching optimization is constructed, a standby power supply data set and abnormal topological load distribution are used as the input of the model, and meanwhile, according to the running constraint and the dispatching strategy of the power system, an optimization algorithm such as a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm and the like is used for solving the power dispatching optimization model. According to the iterative and searching processes of the algorithm, a standby power supply scheduling scheme meeting the scheduling optimizing composite constraint (a group of constraint conditions which need to be met in the power scheduling optimizing process) is gradually found, a plurality of standby power supply scheduling schemes obtained through solving are evaluated and compared, the aspects including cost, benefit, feasibility and the like of the scheme are included, and the optimal standby power supply scheduling scheme is selected according to the evaluation result. And (3) making a power dispatching plan according to an optimal standby power supply dispatching scheme, wherein the power dispatching plan comprises the input sequence, time, capacity and the like of a standby power supply unit, ensuring power dispatching according to the dispatching plan, ensuring the stable operation and power supply reliability of a power system, and monitoring the operation state of the power system and the working condition of the standby power supply unit in real time in the dispatching process, and timely adjusting and optimizing. The embodiment of the application adopts the technical means of obtaining a standard power topology data set, constructing a power dispatching topology network, carrying out real-time monitoring, carrying out abnormal positioning, carrying out power dispatching optimization and the like, realizes the dynamic adjustment of a standby power supply scheme according to the real-time running state and the fault type of a power system, reduces the influence of faults on the power system, and achieves the technical effects of improving the flexibility and dynamic adaptability of power dispatching and improving the reliability and stability of power supply.

In one possible implementation manner, power scheduling optimizing is performed according to the standby power supply data set and the abnormal topological load distribution, a standby power supply scheduling scheme meeting scheduling optimizing composite constraint is determined, step S700 further includes step S710, load equipment criticality identification is performed according to the abnormal topological load distribution, and an abnormal topological key load distribution meeting load equipment critical constraint is constructed. Specifically, the abnormal topology load distribution data is analyzed to identify critical ones of the load devices (e.g., critical production lines, hospital emergency rooms, etc.). And constructing abnormal topological key load distribution meeting key constraints of the load equipment according to the load characteristics and the importance of the key equipment. And step S720, taking the standby power supply data set as a standby power dispatching constraint, and taking the abnormal topological key load distribution as a standby power dispatching target. In particular, the backup power data set provides available backup power resources and constraints thereof (e.g., capacity, geographic location, etc.), and uses the abnormal topology critical load distribution as a backup power scheduling target for ensuring that the critical loads are also provided with a stable power supply in the event of an abnormality. And step S730, carrying out random power scheduling according to the standby power scheduling constraint and the standby power scheduling target, and constructing a standby power supply scheduling solution domain meeting the first scheduling solution capacity constraint. Specifically, on the premise of meeting the constraint of standby power scheduling, multiple groups of power scheduling schemes are randomly generated, and the power scheduling schemes which are randomly generated form an initial standby power scheduling solution domain. In order to ensure that the number of schemes in the solution domain is within a processable range, a first scheduling solution capacity constraint is set, wherein the first scheduling solution capacity constraint refers to the upper limit of the number of generated schemes when a power scheduling scheme is randomly generated, and the spare power supply scheduling solution domain is constructed through the first scheduling solution capacity constraint. Step S740, the scheduling optimization composite constraint comprises a scheduling optimization evaluation constraint and a scheduling optimization iteration constraint. Specifically, the scheduling optimizing evaluation constraint is an evaluation criterion for evaluating the merits of the power scheduling scheme, such as power supply reliability, economy, and the like; the scheduling optimizing iteration constraint is a condition which needs to be met in the iterative optimizing process, such as the maximum iteration times, the convergence condition and the like. And S750, activating a scheduling evaluation prediction channel, and carrying out initial optimization on the standby power supply scheduling solution domain by combining the scheduling optimization evaluation constraint to construct an optimized standby power supply scheduling solution domain meeting a second scheduling solution capacity constraint. Specifically, a scheduling evaluation prediction channel is activated, and the scheduling evaluation prediction channel is used for performing prediction evaluation on each scheme in the solution domain based on historical data and current state, so as to predict the effect of each scheme in practical application. And carrying out initial evaluation and optimization on the scheme in the standby power supply scheduling solution domain by combining the scheduling optimizing evaluation constraint, removing the scheme which does not meet the scheduling optimizing evaluation constraint, and forming the optimizing standby power supply scheduling solution domain which meets the second scheduling solution capacity constraint by the remaining schemes. The second scheduling solution capacity constraint refers to the upper limit of the number of schemes reserved after screening in the initial optimizing process, and is used for reducing the complexity of the problem while maintaining the diversity of the solution domain. Step 760, performing mutation according to the optimized standby power supply scheduling solution domain, and constructing a mutated standby power supply scheduling solution domain meeting the constraint of the third scheduling solution capacity. Specifically, a mutation operation, such as exchange, insertion, deletion, etc., is performed on a scheme in the optimizing standby power supply scheduling solution domain, fine adjustment is performed on certain parameters or structures in the scheme, a new power scheduling scheme is generated, the new scheme generated through the mutation operation forms a mutation standby power supply scheduling solution domain, and the scheme in the mutation standby power supply scheduling solution domain is similar to the scheme in the optimizing standby power supply scheduling solution domain in structure, but is different in certain parameters or details, so that the diversity of search space is increased. in order to ensure that the number of schemes in the variant standby power supply scheduling solution domain is within a processable range, a third scheduling solution capacity constraint is also set, and the third scheduling solution capacity constraint is used for limiting the number of schemes generated after the variant operation. And step S770, performing deep optimization on the optimized standby power supply scheduling solution domain and the variant standby power supply scheduling solution domain according to the scheduling evaluation prediction channel, the scheduling optimizing evaluation constraint and the scheduling optimizing iteration constraint, and generating the standby power supply scheduling scheme. Specifically, the scheduling evaluation prediction channel is utilized to evaluate the schemes in the optimizing standby power supply scheduling solution domain and the variant standby power supply scheduling solution domain, the scheduling optimizing evaluation constraint and the scheduling optimizing iteration constraint are combined, the iterative optimization algorithm (such as a genetic algorithm, a particle swarm algorithm and the like) is utilized to carry out deep optimization, and finally the standby power supply scheduling scheme which meets all constraint conditions and is optimal in evaluation is generated. by identifying the key load and constructing abnormal topological key load distribution, the realization method ensures that the key load can still obtain stable power supply when the topological structure of the power grid changes or the load is abnormal, and achieves the technical effect of ensuring stable power supply of the key load.

In a possible implementation manner, step S750 further includes step S751, extracting a first standby power supply scheduling solution according to the standby power supply scheduling solution domain. Specifically, one solution is selected as the first standby power supply scheduling solution from the constructed standby power supply scheduling solution domain randomly or according to a certain strategy (such as polling, priority, etc.). Step S752, performing predictive evaluation on the first standby power supply scheduling solution based on the scheduling evaluation prediction channel, to obtain first scheduling prediction evaluation feature data, where the scheduling evaluation prediction channel includes a multidimensional scheduling evaluation prediction index, and the multidimensional scheduling evaluation prediction index includes power supply scheduling loss, power supply scheduling efficiency and scheduling load balancing. Specifically, the scheduling evaluation prediction channel is a model or framework integrated with multiple evaluation indexes and is used for predicting the performance of the power scheduling scheme in actual operation, the first standby power supply scheduling solution is input into the scheduling evaluation prediction channel, the scheduling evaluation prediction channel evaluates the first standby power supply scheduling solution based on multidimensional scheduling evaluation prediction indexes (power supply scheduling loss, power supply scheduling efficiency and scheduling load balance) and outputs first scheduling prediction evaluation characteristic data, and the first scheduling prediction evaluation characteristic data reflects the performance of the first standby power supply scheduling solution under the multidimensional indexes. Wherein, the power supply scheduling loss represents energy loss in the power scheduling process; The power supply scheduling efficiency represents the overall efficiency of power scheduling; scheduling load balancing indicates whether the load of each node in the power grid is balanced. And step S753, judging whether the first scheduling prediction evaluation characteristic data meets the scheduling optimizing evaluation constraint. Specifically, the scheduling optimization evaluation constraint is a set of evaluation criteria for judging whether the power scheduling scheme satisfies a predetermined requirement. And comparing the first scheduling prediction evaluation characteristic data with the scheduling optimizing evaluation constraint, and if the first scheduling prediction evaluation characteristic data meets all constraint conditions, judging that the first standby power supply scheduling solution meets the requirement. Step S754, if the first scheduling prediction evaluation feature data meets the scheduling optimizing evaluation constraint, adding the first standby power supply scheduling solution to the optimizing standby power supply scheduling solution domain. Specifically, if the first scheduling prediction evaluation feature data meets the scheduling optimizing evaluation constraint, the first standby power supply scheduling solution is a better solution, and the first standby power supply scheduling solution is added into the optimizing standby power supply scheduling solution domain. And step S755, continuing optimizing the standby power supply scheduling solution domain according to the scheduling evaluation prediction channel and the scheduling optimizing evaluation constraint until the optimizing standby power supply scheduling solution domain meeting the second scheduling solution capacity constraint is generated. Specifically, steps S751 to S754 are repeated, each solution in the standby power supply scheduling solution domain is subjected to predictive evaluation and screening, solutions meeting the scheduling optimizing evaluation constraint are continuously added into the optimizing standby power supply scheduling solution domain, and when the number of solutions in the optimizing standby power supply scheduling solution domain reaches the second scheduling solution capacity constraint, the optimizing process is stopped. In the implementation mode, the scheduling optimizing evaluation constraint ensures the feasibility and the effectiveness of knowing in actual operation, avoids the resource waste or the operation risk caused by the fact that the solution does not meet the actual requirement, and achieves the technical effect of ensuring the feasibility and the quality of the solution in the optimizing standby power supply scheduling solution domain.

In a possible implementation manner, step S770 further includes step S771, performing power supply scheduling loss minimization optimization according to the optimized standby power supply scheduling solution domain, and determining an initial standby power supply scheduling scheme. Specifically, from the optimizing standby power supply scheduling solution domain, an optimizing algorithm (such as a genetic algorithm, a particle swarm optimizing algorithm and the like) is used for searching a solution with minimum power supply scheduling loss, the performance of each solution in terms of power supply scheduling loss is evaluated, and the solution with minimum power supply scheduling loss is selected as an initial standby power supply scheduling scheme. And step 772, carrying out optimizing analysis on the variable standby power supply dispatching solution domain according to the dispatching evaluation prediction channel to generate an optimizing variable standby power supply dispatching solution domain meeting the dispatching optimizing evaluation constraint. Specifically, for each solution in the variant backup power supply scheduling solution domain, performance evaluation is performed using a scheduling evaluation prediction channel. And screening out solutions meeting the requirements according to the scheduling optimizing evaluation constraint, and constructing an optimizing variation standby power supply scheduling solution domain meeting the constraint conditions. And step S773, extracting a first optimizing variation standby power supply scheduling solution according to the optimizing variation standby power supply scheduling solution domain. Specifically, from the optimizing variation standby power supply scheduling solution domain, one solution is randomly selected or selected according to a certain strategy to be used as the first optimizing variation standby power supply scheduling solution. And step S774, carrying out power supply scheduling loss minimization optimization according to the initial standby power supply scheduling scheme and the first optimizing variation standby power supply scheduling solution, and generating a current standby power supply scheduling scheme. Specifically, an optimization algorithm is used for hybrid optimization by combining an initial standby power supply scheduling scheme and a first optimizing variation standby power supply scheduling solution, and in the process, the main objective is to further reduce power supply scheduling loss, and the current standby power supply scheduling scheme is generated through iteration and optimization. And step S775, continuing to perform power supply scheduling loss minimization iterative optimization on the current standby power supply scheduling scheme and the optimizing variation standby power supply scheduling solution domain until the standby power supply scheduling scheme meeting the scheduling optimizing iteration constraint is obtained. Specifically, steps S773 to S774 are repeated, at this time, the current standby power supply scheduling scheme is used as a new starting point, and new solutions are continuously extracted from the optimizing variant standby power supply scheduling solution domain to perform hybrid optimization. In each iteration, a new current standby power supply scheduling scheme is generated, and the iteration process is continued until the scheduling optimizing iteration constraint is met (such as reaching a preset iteration number, power supply scheduling loss is smaller than a certain threshold value, etc.). Finally, a standby power supply scheduling scheme meeting the scheduling optimizing iteration constraint is obtained. The implementation mode aims at minimizing the power supply scheduling loss, and gradually approaches the optimal solution in an iterative optimization mode, so that the power supply scheduling loss of the finally obtained standby power supply scheduling scheme is minimized, and the technical effect of reducing energy waste is achieved.

Hereinabove, the power intelligent scheduling method for dynamic security according to the embodiment of the present invention is described in detail with reference to fig. 1. Next, an intelligent power dispatching system for dynamic security according to an embodiment of the present invention will be described with reference to fig. 2.

The intelligent power dispatching system for dynamic guarantee is used for solving the technical problems that the existing power dispatching lacks flexibility and dynamic adaptability and is difficult to meet real-time dispatching requirements, and achieves the technical effects of improving the flexibility and dynamic adaptability of power dispatching and improving the reliability and stability of power supply. The intelligent power dispatching system for dynamic security comprises: the system comprises a standard power topology data set acquisition module 10, a power dispatching topology network construction module 20, a real-time monitoring module 30, an abnormality positioning module 40, a load equipment information acquisition module 50, a standby power supply data set determination module 60 and a guarantee power dispatching module 70.

The standard power topology data set acquisition module 10 is used for acquiring topology information of a power system, obtaining a power topology data set, and carrying out standardization processing on the power topology data set to obtain a standard power topology data set;

The power dispatching topology network construction module 20 is used for constructing a power dispatching topology network according to the standard power topology data set;

the real-time monitoring module 30 is configured to monitor the power system in real time according to the power dispatching topology network, so as to obtain a power monitoring topology network;

The abnormality positioning module 40 is configured to activate a power failure feature prediction channel, perform abnormality positioning on the power scheduling topology network in combination with the power monitoring topology network, and determine an abnormal power topology network;

The load equipment information acquisition module 50 is used for acquiring load equipment information of the abnormal power topology network to obtain abnormal topology load distribution;

The standby power supply data set determining module 60 is configured to activate a standby power supply module of the power system, collect information of each standby power supply unit in the standby power supply module, and determine a standby power supply data set;

The guaranteed power scheduling module 70 is configured to perform power scheduling optimization according to the standby power supply data set and the abnormal topological load distribution, determine a standby power supply scheduling scheme that meets a scheduling optimization composite constraint, and perform guaranteed power scheduling according to the standby power supply scheduling scheme.

Next, the specific configuration of the abnormality locating module 40 will be described in detail. As described above, activating a power failure feature prediction channel, performing anomaly localization on the power scheduling topology network in conjunction with the power monitoring topology network, determining an anomaly power topology network, the anomaly localization module 40 may further include: the power line monitoring data set extraction unit is used for extracting a plurality of power line monitoring data sets according to the power monitoring topological network; the line fault prediction characteristic index acquisition unit is used for inputting the plurality of power line monitoring data sets into the power fault prediction channel to obtain a plurality of line fault prediction characteristic indexes; the abnormal fault prediction characteristic distribution acquisition unit is used for judging whether the line fault prediction characteristic indexes are smaller than a preset fault prediction characteristic index or not and acquiring abnormal fault prediction characteristic distribution which is not smaller than the preset fault prediction characteristic index; the abnormal power topology network acquisition unit is used for positioning the power monitoring topology network according to the abnormal fault prediction characteristic distribution to acquire an abnormal power topology network.

Wherein the plurality of power line monitoring data sets are input into the power failure feature prediction channel to obtain a plurality of line failure prediction feature indexes, and the line failure prediction feature index obtaining unit may further include: the power failure feature prediction channel construction subunit is used for the power failure feature prediction channel to comprise a bilateral power failure prediction branch and a failure feature calculation branch; the line fault prediction result obtaining subunit is used for inputting the plurality of power line monitoring data sets into the bilateral power fault prediction branch to obtain a plurality of line fault prediction results, wherein each line fault prediction result comprises a predicted line fault probability and a predicted line fault risk coefficient; the line fault prediction feature index generation subunit is configured to input the plurality of line fault prediction results into the fault feature calculation branch, and generate the plurality of line fault prediction feature indexes.

Wherein the line fault prediction characteristic index generation subunit may further include: the fault characteristic calculation function construction micro unit is used for the fault characteristic calculation branch to comprise a fault characteristic calculation function, wherein the fault characteristic calculation function is as follows: The CFP characterizes a line fault prediction characteristic index, the CFA characterizes a predicted line fault probability, the FAO characterizes a line fault probability threshold, the CFB characterizes a predicted line fault risk coefficient and the FBO characterizes a line fault risk threshold.

Wherein constructing the bilateral power failure prediction branch, the power failure feature prediction channel construction subunit may further include: the record set loading micro-unit is used for connecting the power system and loading a power line monitoring record set, a line fault probability record set and a line fault risk coefficient record set; the fault learning channel activation micro-unit is used for activating a fault learning channel, wherein the fault learning channel comprises a plurality of fault learners; the random fault learner extraction micro unit is used for extracting a first random fault learner and a second random fault learner according to the fault learning channel; the power failure probability predictor generating micro unit is used for taking the power line monitoring record set as input information, taking the line failure probability record set as output information, performing supervised learning on the first random failure learner, and generating a power failure probability predictor meeting failure probability learning accuracy; the power failure risk predictor generating micro-unit is used for taking the power line monitoring record set as input data, taking the line failure risk coefficient record set as output data, performing supervised learning on the second random failure learner, and generating a power failure risk predictor meeting failure risk learning accuracy; and the bilateral power failure prediction branch generation micro unit is used for combining the power failure probability predictor and the power failure risk predictor as parallel nodes to generate the bilateral power failure prediction branch.

Next, the specific configuration of the guaranteed power scheduling module 70 will be described in detail. As described above, performing power scheduling optimization according to the standby power supply data set and the abnormal topological load distribution, determining a standby power supply scheduling scheme that satisfies a scheduling optimization composite constraint, and ensuring that the power scheduling module 70 may further include: the abnormal topological key load distribution construction unit is used for carrying out load equipment key identification according to the abnormal topological load distribution and constructing abnormal topological key load distribution meeting the key constraint of the load equipment; the standby power dispatching setting unit is used for taking the standby power supply data set as a standby power dispatching constraint and taking the abnormal topological key load distribution as a standby power dispatching target; the random power scheduling unit is used for carrying out random power scheduling according to the standby power scheduling constraint and the standby power scheduling target, and constructing a standby power supply scheduling solution domain meeting a first scheduling solution capacity constraint; the scheduling optimizing composite constraint setting unit is used for the scheduling optimizing composite constraint comprising a scheduling optimizing evaluation constraint and a scheduling optimizing iteration constraint; the initial optimizing unit is used for activating a scheduling evaluation prediction channel, and combining the scheduling optimizing evaluation constraint to perform initial optimizing on the standby power supply scheduling solution domain to construct an optimizing standby power supply scheduling solution domain meeting a second scheduling solution capacity constraint; the mutation unit is used for carrying out mutation according to the optimizing standby power supply scheduling solution domain, and constructing a mutation standby power supply scheduling solution domain meeting the capacity constraint of the third scheduling solution; and the standby power supply scheduling scheme generating unit is used for carrying out deep optimization on the optimizing standby power supply scheduling solution domain and the variant standby power supply scheduling solution domain according to the scheduling evaluation prediction channel, the scheduling optimizing evaluation constraint and the scheduling optimizing iteration constraint to generate the standby power supply scheduling scheme.

The method comprises the steps of activating a scheduling evaluation prediction channel, carrying out initial optimization on the standby power supply scheduling solution domain by combining the scheduling optimization evaluation constraint, constructing an optimized standby power supply scheduling solution domain meeting a second scheduling solution capacity constraint, and the initial optimization unit can further comprise: the first standby power supply scheduling solution extraction subunit is used for extracting a first standby power supply scheduling solution according to the standby power supply scheduling solution domain; the prediction evaluation subunit is used for performing prediction evaluation on the first standby power supply scheduling solution based on the scheduling evaluation prediction channel to obtain first scheduling prediction evaluation characteristic data, wherein the scheduling evaluation prediction channel comprises a multi-dimensional scheduling evaluation prediction index, and the multi-dimensional scheduling evaluation prediction index comprises power supply scheduling loss, power supply scheduling efficiency and scheduling load balance; the judging subunit is used for judging whether the first scheduling prediction evaluation characteristic data meets the scheduling optimizing evaluation constraint; and the optimizing standby power supply dispatching solution domain generation subunit is used for adding the first standby power supply dispatching solution to the optimizing standby power supply dispatching solution domain if the first dispatching prediction evaluation characteristic data meets the dispatching optimizing evaluation constraint, and continuing optimizing the standby power supply dispatching solution domain according to the dispatching evaluation prediction channel and the dispatching optimizing evaluation constraint until the optimizing standby power supply dispatching solution domain meeting the second dispatching solution capacity constraint is generated.

The method may further include performing deep optimization on the optimized standby power supply scheduling solution domain and the variant standby power supply scheduling solution domain according to the scheduling evaluation prediction channel, the scheduling optimizing evaluation constraint and the scheduling optimizing iteration constraint, and generating the standby power supply scheduling scheme, where the standby power supply scheduling scheme generating unit may further include: the initial standby power supply scheduling scheme determining subunit is used for performing power supply scheduling loss minimization optimization according to the optimizing standby power supply scheduling solution domain, and determining an initial standby power supply scheduling scheme; the optimizing variant standby power supply scheduling solution domain generation subunit is used for carrying out optimizing analysis on the variant standby power supply scheduling solution domain according to the scheduling evaluation prediction channel to generate an optimizing variant standby power supply scheduling solution domain meeting the scheduling optimizing evaluation constraint; the first optimizing variation standby power supply scheduling solution extracting subunit is used for extracting a first optimizing variation standby power supply scheduling solution according to the optimizing variation standby power supply scheduling solution domain; the current standby power supply scheduling scheme generation subunit is used for carrying out power supply scheduling loss minimization optimization according to the initial standby power supply scheduling scheme and the first optimizing variation standby power supply scheduling solution to generate a current standby power supply scheduling scheme; and the power supply scheduling loss minimization iteration optimizing subunit is used for continuing to perform power supply scheduling loss minimization iteration optimizing on the current standby power supply scheduling scheme and the optimizing variation standby power supply scheduling solution domain until the standby power supply scheduling scheme meeting the scheduling optimizing iteration constraint is obtained.

The power intelligent scheduling system for dynamic security provided by the embodiment of the invention can execute the power intelligent scheduling method for dynamic security provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server, including units and modules that are merely partitioned by functional logic, but are not limited to the above-described partitioning, so long as the corresponding functionality is enabled; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present application.

The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application. In some cases, the acts or steps recited in the present application may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The intelligent power scheduling method for dynamic security is characterized by comprising the following steps:

Performing power dispatching optimization according to the standby power supply data set and the abnormal topological load distribution, determining a standby power supply dispatching scheme meeting dispatching optimization composite constraint, and guaranteeing power dispatching according to the standby power supply dispatching scheme;

the activating a power failure feature prediction channel, combining the power monitoring topology network to perform abnormal positioning on the power dispatching topology network, and determining an abnormal power topology network, includes:

positioning the power monitoring topology network according to the abnormal fault prediction characteristic distribution to obtain an abnormal power topology network;

Inputting the plurality of power line monitoring data sets into the power failure feature prediction channel to obtain a plurality of line failure prediction feature indexes, including:

2. The intelligent power dispatching method for dynamic assurance of claim 1, wherein the fault signature computation branch comprises a fault signature computation function, the fault signature computation function being:

3. The power intelligent scheduling method for dynamic security as claimed in claim 1, wherein the constructing step of the bilateral power failure prediction branch comprises:

4. The intelligent power scheduling method for dynamic security according to claim 1, wherein the performing power scheduling optimization according to the standby power supply data set and the abnormal topological load distribution, determining a standby power supply scheduling scheme satisfying a scheduling optimization composite constraint, comprises:

5. The intelligent power dispatching method for dynamic security according to claim 4, wherein the activating dispatching evaluation prediction channel, in combination with the dispatching optimizing evaluation constraint, performs initial optimizing on the standby power supply dispatching solution domain to construct an optimizing standby power supply dispatching solution domain meeting a second dispatching solution capacity constraint, comprises:

6. The intelligent power scheduling method for dynamic security according to claim 4, wherein the generating the backup power scheduling scheme by performing deep optimization on the optimized backup power scheduling solution domain and the variant backup power scheduling solution domain according to the scheduling evaluation prediction channel, the scheduling optimizing evaluation constraint and the scheduling optimizing iteration constraint comprises:

7. A power intelligent scheduling system for dynamic security, characterized in that the system is for implementing the power intelligent scheduling method for dynamic security according to any one of claims 1 to 6, the system comprising:

And the guarantee power dispatching module is used for carrying out power dispatching optimization according to the standby power supply data set and the abnormal topological load distribution, determining a standby power supply dispatching scheme meeting dispatching optimization composite constraint and carrying out guarantee power dispatching according to the standby power supply dispatching scheme.