CN117495114A - Power system risk prediction method and system based on big data analysis - Google Patents
Power system risk prediction method and system based on big data analysis Download PDFInfo
- Publication number
- CN117495114A CN117495114A CN202410005501.2A CN202410005501A CN117495114A CN 117495114 A CN117495114 A CN 117495114A CN 202410005501 A CN202410005501 A CN 202410005501A CN 117495114 A CN117495114 A CN 117495114A
- Authority
- CN
- China
- Prior art keywords
- state
- risk
- prediction
- nth
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000007704 transition Effects 0.000 claims abstract description 92
- 230000009466 transformation Effects 0.000 claims abstract description 49
- 238000010586 diagram Methods 0.000 claims abstract description 30
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000013507 mapping Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 101100134058 Caenorhabditis elegans nth-1 gene Proteins 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 5
- 238000013461 design Methods 0.000 description 20
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a power system risk prediction method and system based on big data analysis, which are used for constructing a comprehensive state transition model of at least one power unit in a power system by acquiring a historical data set and carrying out big data analysis on the historical data set; constructing a state transformation network diagram of each power unit by utilizing each state transformation model; acquiring current operation parameters of the power system, analyzing big data of the current operation parameters, and determining initial state probability sets corresponding to all power units; determining a combined risk prediction sequence of the power system according to each initial state probability set and each state transformation network diagram by using a preset tracking algorithm; and determining and outputting risk prompt information according to the combined risk prediction sequence. The technical problem of how to conduct efficient and accurate risk prediction on the power system is solved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a power system risk prediction method and system based on big data analysis.
Background
Along with the continuous development of science and technology and productivity, the requirements on stable and safe operation of electric power sources are continuously improved, namely the requirements on the risk resistance capability of an electric power system are continuously improved, and the risk can only be passively resisted by traditional personnel on duty, so that the risk resistance requirement cannot be met. Therefore, risk prediction, i.e., active risk prevention, on the power system has become a development trend of safe operation of the power system. And then, the high-efficiency and accurate risk prediction of the power system becomes a technical problem to be solved urgently.
Disclosure of Invention
The application provides a power system risk prediction method and system based on big data analysis, which are used for solving the technical problem of how to perform high-efficiency and accurate risk prediction on a power system.
In a first aspect, the present application provides a power system risk prediction method based on big data analysis, including:
acquiring a historical data set, performing big data analysis on the historical data set, and constructing a comprehensive state transition model of at least one power unit in the power system, wherein the comprehensive state transition model is used for representing the probability of internal state transition of each power unit caused by internal factors and/or external factors of the system;
constructing a state transformation network diagram corresponding to a plurality of prediction periods of each power unit by utilizing each state transformation model;
acquiring current operation parameters of the power system, performing big data analysis on the current operation parameters, and determining initial state probability sets corresponding to all power units, wherein each initial state probability set comprises a plurality of initial state probabilities, and each initial state probability corresponds to one internal operation state;
determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm;
And determining and outputting risk prompt information according to the combined risk prediction sequence.
In one possible design, the determining, by using a preset tracking algorithm, a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transition network diagram includes:
determining a state transition path of each power unit in a plurality of prediction periods according to each initial state probability set and each corresponding state transition network diagram by using a preset tracking algorithm;
determining a unit risk sequence of each power unit in a plurality of prediction periods according to each internal operation state in each state transformation path and a risk value corresponding to the internal operation state;
and combining the risk sequences of the units into a combined risk prediction sequence according to a preset combination mode.
In one possible design, a historical data set is obtained, big data analysis is performed on the historical data set, and a comprehensive state transition model of at least one power unit in the power system is constructed, including:
obtaining a first historical data set and a second historical data set, the first historical data set comprising at least one internal operational data of the power system during one or more historical periods, the second historical data set comprising at least one external environmental data of the power system during one or more historical periods;
Performing big data analysis on the first historical data set and the second historical data set, and constructing one or more comprehensive state transition models corresponding to the power units;
the integrated state transition model includes: a state transition model for characterizing a first probability of a transition between the various internal operating states caused by the system internal factors, and a state mapping model for characterizing a second probability of an associated effect between each system external factor and at least one internal operating state.
In one possible design, using a preset tracking algorithm, determining a state transition path of each power unit in a plurality of prediction periods according to each initial state probability set and each corresponding state transition network diagram includes:
determining the 1 st state of a state transformation path corresponding to each power unit and the 1 st state judgment value corresponding to the 1 st state according to an initial state probability set corresponding to each power unit through a state prediction rule, wherein the states in the state transformation path correspond to the prediction periods one by one;
according to the state prediction rules, according to each state conversion model, each state mapping model, the n-1 state in each state conversion path and the corresponding n-1 state judgment value, calculating the n state in each state conversion path and the corresponding n state judgment value until n reaches a preset maximum value, wherein n is greater than or equal to 2.
In one possible design, determining, according to a state prediction rule, a 1 st state of a state transition path corresponding to each power unit and a 1 st state determination value corresponding to the 1 st state according to an initial state probability set corresponding to each power unit includes:
the maximum value in each initial state probability set is used as a 1 st state judgment value, and the state corresponding to the maximum value is used as a 1 st state.
In one possible design, calculating, by a state prediction rule, an nth state and a corresponding nth state determination value in each state transition path according to each state transition model, each state mapping model, the nth-1 state and a corresponding nth-1 state determination value in each state transition path includes:
according to the first probability matrix in each state transition model, the second probability matrix in each state mapping model and each n-1 th state, calculating one or more candidate state judgment values corresponding to each candidate state in each n-th candidate state set, wherein each n-th candidate state set corresponds to the n-th state in each state transition path:
wherein,representing candidate state determination values, A being a first probability matrix corresponding to an nth prediction period, Is any element in A, +.>For the n-1 th state, +.>For any one candidate state, M is the total number of all candidate states of each power unit in the nth prediction period, B is a second probability matrix, +.>Is any element in B, N is the total number of the external environment states, and +.>The external environment state corresponding to the nth prediction period;
according to the n-1 state judgment value corresponding to each state transformation path and each candidate state judgment value, determining the n-1 state judgment value corresponding to each state transformation path through a state prediction rule;
and taking the candidate state corresponding to the nth state judgment value as the nth state.
In one possible design, determining, by a state prediction rule, an nth state determination value corresponding to each state transition path according to the nth-1 state determination value corresponding to each state transition path and each candidate state determination value, includes:
calculating a first product of each n-1 state judgment value and the first weight value;
calculating a second product of each candidate state judgment value corresponding to each nth state and each second weight value, wherein the second weight values correspond to the candidate state judgment values one by one;
And taking the maximum value of the sum of the first product and at least one second product as an nth state judgment value.
In one possible design, determining a cell risk sequence for each power cell over a plurality of prediction periods based on respective internal operating states in each state transition path and risk values corresponding to the internal operating states includes:
judging whether each internal operation state in each state transformation path belongs to a normally-operable class or not;
if yes, setting a risk value corresponding to the internal running state as a first risk value;
otherwise, setting a risk value corresponding to the internal running state as a second risk value;
and arranging the risk values into a unit risk sequence according to the sequence of the prediction period.
In one possible design, combining the unit risk sequences into a combined risk prediction sequence according to a preset combination manner includes:
judging whether the last-last risk value in each unit risk sequence is a first risk value or not, wherein the first risk value corresponds to the internal running state of the normally working class;
if not, the unit risk sequence is taken as a subsequence of the combined risk prediction sequence.
In a second aspect, the present application provides a power system risk prediction system based on big data analysis, comprising:
The acquisition module is used for acquiring the historical data set;
the big data analysis module is used for carrying out big data analysis on the historical data set, constructing a comprehensive state transition model of at least one power unit in the power system, and the comprehensive state transition model is used for representing the probability of internal state transition of each power unit caused by internal factors and/or external factors of the system;
the risk prediction module is used for constructing a state transformation network diagram corresponding to a plurality of prediction periods of each power unit by utilizing each state transformation model;
the acquisition module is also used for acquiring the current operation parameters of the power system;
the big data analysis module is further used for carrying out big data analysis on the current operation parameters, determining initial state probability sets corresponding to the power units, wherein the initial state probability sets comprise a plurality of initial state probabilities, and each initial state probability corresponds to one internal operation state;
the risk prediction module is further used for:
determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm; and determining and outputting risk prompt information according to the combined risk prediction sequence.
In a third aspect, the present application provides an electronic device, comprising: a processor, a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes the computer-executable instructions stored in the memory to implement any one of the possible big data analysis based power system risk prediction methods provided in the first aspect.
In a fourth aspect, the present application provides a storage medium having stored therein computer-executable instructions which, when executed by a processor, are configured to implement any one of the possible big data analysis based power system risk prediction methods provided in the first aspect.
In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements any one of the possible big data analysis based power system risk prediction methods provided in the first aspect.
The application provides a power system risk prediction method and system based on big data analysis, which are characterized in that a historical data set is obtained, big data analysis is carried out on the historical data set, a comprehensive state transition model of at least one power unit in a power system is constructed, and the comprehensive state transition model is used for representing the probability of internal state transition of each power unit caused by internal factors and/or external factors of the system; constructing a state transformation network diagram corresponding to a plurality of prediction periods of each power unit by utilizing each state transformation model; acquiring current operation parameters of the power system, performing big data analysis on the current operation parameters, and determining initial state probability sets corresponding to all power units, wherein each initial state probability set comprises a plurality of initial state probabilities, and each initial state probability corresponds to one internal operation state; determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm; and determining and outputting risk prompt information according to the combined risk prediction sequence. The technical problem of how to conduct efficient and accurate risk prediction on the power system is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic flow chart of a power system risk prediction method based on big data analysis according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a possible implementation of step S104 provided in the embodiment of the present application;
fig. 3 is a schematic structural diagram of a power system risk prediction system based on big data analysis according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, including but not limited to combinations of embodiments, which can be made by one of ordinary skill in the art without inventive faculty, are intended to be within the scope of the present application, based on the embodiments herein.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims of this application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be capable of operation in sequences other than those illustrated or described herein, for example. Furthermore, 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 apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The traditional on duty or passive risk prevention of personnel can not meet the requirement of the current power system on the risk resistance, so that the risk prediction technology becomes an important core technology for the risk prevention of the power system. In recent years, the rise of big data analysis technology injects new vitality into risk prediction, and the application builds a power system risk prediction method by virtue of big data analysis, and can predict the internal running state of the power system through the prediction result of the external observable state of the external environment where the power system is located. The method and the system realize the prediction of the internal running state of the implicit power system through explicit data, achieve the efficient and accurate prediction of the risk of the power system, timely perform risk prevention, improve the stable running capacity of the system, and provide stable guarantee for the power supply of production and life.
Fig. 1 is a flow chart of a power system risk prediction method based on big data analysis according to an embodiment of the present application. As shown in fig. 1, the specific steps of the method include:
s101, acquiring a historical data set, analyzing big data of the historical data set, and constructing a comprehensive state transition model of at least one electric power unit in the electric power system.
In this step, the integrated state transition model is used to characterize the probability of internal state transitions of each power cell caused by internal and/or external factors of the system.
Specifically, acquiring a historical dataset includes:
a first historical data set and a second historical data set are acquired.
The first set of historical data includes at least one internal operating data of the power system over one or more historical periods of time, and the second set of historical data includes at least one external environmental data of the power system over one or more historical periods of time.
Performing big data analysis on the historical data set, and constructing a comprehensive state transition model of at least one power unit in the power system, wherein the method comprises the following steps:
and carrying out big data analysis on the first historical data set and the second historical data set, and constructing one or more comprehensive state transition models corresponding to the power units.
The integrated state transition model includes: a state transition model for characterizing a first probability of a transition between the various internal operating states caused by the system internal factors, and a state mapping model for characterizing a second probability of an associated effect between each system external factor and at least one internal operating state.
For example, during a certain period of time, the internal operating states that one of the power units in the power system can possess include: s is S 1 、S 2 And S is 3 Suppose S 1 Representing a completely normal state, S 2 Representing partial failure but not affecting normal operation, S 3 Representing the completion ofAnd (3) a total failure state. Then over time and maintenance actions by the service personnel, the power units may switch between these three states, and the state transition model is used to characterize the probability of such internal operating states switching, i.e. the state transition model may comprise a 33, thereby characterizing the probability relationship of the inter-switching between the internal operating states.
It should be noted that the internal switching is not considered to be influenced by external factors of the system, for example, the state of the external environment may also influence the internal operation state of the system. Thus, the present application introduces a state mapping model to represent the probability that a power unit is in some internal operating state under the influence of different system external factors.
For example, assume that the system external cause includes 4 external environmental states: e (E) 1 、E 2 、E 3 And E is 4 The external environmental state may be determined by one or more environmental parameters such as temperature, humidity, wind, weather, etc. Thus, the state mapping model may include a second probability matrix for representing each external state E i Under different internal operating states S j Is a probability of (2). For example, the second probability matrix is 34, each row representing the probability that the same internal operating state corresponds to a different external environmental state.
It should be noted that, the external factor, such as the external environment state, may be predicted by the data of the external mechanism, for example, the weather bureau may issue weather data in the future week, and the weather data may be used to learn the external environment state of the environment in which the power system is located in the future week, so that the internal operation state of one or more power units of the power system may be predicted.
The detailed prediction steps are described in the subsequent steps of this embodiment, and are not described herein.
S102, constructing a state transformation network diagram corresponding to a plurality of prediction periods for each power unit by utilizing each state transformation model.
In this step, the plurality of prediction periods may be continuous time periods or may be partially continuous, i.e., the time in which at least two of the prediction periods are discontinuous. Alternatively, the time periods corresponding to different prediction periods may be the same or different.
It is worth noting that the internal operating conditions that can be reached may be different for different power units in the power system during different prediction periods. For example, in the ith prediction period, power unit j may only be in S 1 And S is 2 Two internal operating states, while power unit j+1 may be in S 1 、S 2 And S is 3 Three internal operating states, while in the (i+1) th prediction period, power unit j may be in S 1 、S 2 And S is 3 Three internal operating states.
It should be further noted that, according to the time periods of different prediction periods, the possible internal operation state of each power unit in the prediction period is obtained through big data analysis. And then adding the state transition probability in the state transition model corresponding to each power unit, so as to obtain all possible state transition network diagrams of each power unit in a plurality of prediction periods.
S103, acquiring current operation parameters of the power system, analyzing big data of the current operation parameters, and determining initial state probability sets corresponding to all the power units.
In this step, the initial state probabilities are used to characterize the probability that the power system is in any one of the internal operating states at the current time, i.e. the initial state probability set includes a plurality of initial state probabilities, each of which corresponds to one of the internal operating states.
The initial state probabilities in the initial probability set are state transition probabilities of switching the internal operation states when the current time goes to the next time. And may also be considered as the probability of each internal operating state being entered upon a power system start-up or restart.
It is noted that if the probability that the power unit or the power system maintains the state unchanged at two consecutive moments is also included in the state transition probabilities, i.e. the state transition probabilities may characterize the probability of transitioning from state a to state B, or the probability of maintaining the state a unchanged.
S104, determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm.
In this step, the combined risk prediction sequence includes: a plurality of combined risk values corresponding to respective prediction periods. The preset tracking algorithm comprises the following steps of; optimal path algorithms, ant colony algorithms, neural network algorithms, and the like.
In this example, one possible implementation of this step is specifically described by fig. 2.
Fig. 2 is a schematic flow chart of a possible implementation of step S104 provided in the embodiment of the present application. As shown in fig. 2, in this step, the specific implementation manner includes:
S1041, determining a state transformation path of each power unit in a plurality of prediction periods according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm.
In this embodiment, this step may be performed multiple times, resulting in state transition paths of the power units under different conditions. Such as a maximum probability path, a minimum probability path, a composite probability path, etc. So as to cover all kinds of risk possibilities comprehensively and accurately.
In one possible design, this step may also be implemented according to the following loop procedure:
s1041-1, determining the 1 st state of the state transformation path corresponding to each power unit and the 1 st state judgment value corresponding to the 1 st state according to the initial state probability set corresponding to each power unit through a state prediction rule.
In this step, the states in the state transition path correspond one-to-one to the prediction periods. In one possible design, the maximum value, the minimum value, the median value, and the like in each initial state probability set may be taken as the 1 st state determination value, and the state corresponding to the 1 st state determination value may be taken as the 1 st state.
It should be noted that, when the maximum value is taken, the maximum possible path, that is, the most likely state transformation path of the power unit, can be predicted later; when the minimum value is taken, the risk with small probability can be tested, and when the median value is taken, the comprehensive risk can be predicted. In practical applications, one skilled in the art may choose at least one to predict, without limitation to a specific number of applications.
S1041-2, calculating an nth state and a corresponding nth state judgment value in each state conversion path according to each state conversion model, each state mapping model, the nth-1 state in each state conversion path and the corresponding nth-1 state judgment value through a state prediction rule until n reaches a preset maximum value.
This step is a cyclic step, n being greater than or equal to 2.
Specifically, first, according to a first probability matrix in each state transition model, a second probability matrix in each state mapping model, and each n-1 th state, one or more candidate state determination values corresponding to each candidate state in each n-th candidate state set are calculated, and each n-th candidate state set corresponds to an n-th state in each state transition path, as shown in formula (1):
（1）
wherein,representing candidate state determination values, A being a first probability matrix corresponding to an nth prediction period,is any element in A, +.>For the n-1 th state, +.>For any one candidate state, M is the total number of all candidate states of each power unit in the nth prediction period, B is a second probability matrix, +.>Is any element in B, N is the total number of the external environment states, and +. >And the external environment state corresponding to the nth prediction period. />Representing candidate state determination values.
Then, according to the n-1 state judgment value corresponding to each state transition path and each candidate state judgment value, the n-1 state judgment value corresponding to each state transition path is determined through a state prediction rule. And taking the candidate state corresponding to the nth state judgment value as the nth state.
In one possible design, this specifically includes:
calculating a first product of each n-1 state judgment value and the first weight value;
calculating a second product of each candidate state judgment value corresponding to each nth state and each second weight value, wherein the second weight values correspond to the candidate state judgment values one by one;
and taking the maximum value of the sum of the first product and at least one second product as an nth state judgment value.
After the above steps are finished, n is added with 1, and the above steps are repeatedly executed until n reaches a preset maximum value. The first weight value may be preset by a worker.
S1042, determining a unit risk sequence of each power unit in a plurality of prediction periods according to each internal operation state in each state conversion path and a risk value corresponding to the internal operation state.
In this step, first, it is judged whether or not each internal operation state in each state transition path belongs to a normally operable class;
if yes, setting a risk value corresponding to the internal running state as a first risk value;
otherwise, setting a risk value corresponding to the internal running state as a second risk value;
then, the individual risk values are arranged in the order of the prediction period into a unit risk sequence.
S1043, combining the unit risk sequences into a combined risk prediction sequence according to a preset combination mode.
In this step, the combined risk prediction sequence includes: a plurality of combined risk values corresponding to the predicted time period.
In one possible design, the method specifically includes:
judging whether the last-last risk value in each unit risk sequence is a first risk value or not, wherein the first risk value corresponds to the internal running state of the normally working class;
if not, the unit risk sequence is taken as a subsequence of the combined risk prediction sequence, i.e. the combined risk prediction sequence is composed of a plurality of subsequences.
It should be noted that, in this embodiment, the second last internal operation state is selected and may be classified as an internal operation state capable of being normally operated, because effective support of the power unit on the operation of the whole system in the prediction period corresponding to the multiple prediction periods is required to be considered, only if the power unit can still normally operate in the second last prediction period, the selection of the prediction period can be proved to be reasonable, otherwise, the power unit will have a larger deviation from the actual situation of reality when in the inoperable state for a long time.
S105, determining and outputting risk prompt information according to the combined risk prediction sequence.
In this step, each sub-sequence in the combined risk prediction sequence represents the probability of risk occurrence of each power unit in each prediction period, so that corresponding personnel can be arranged in advance to perform early residence, or corresponding maintenance plans can be prepared in advance.
The embodiment provides a power system risk prediction method based on big data analysis, which comprises the steps of obtaining a historical data set, carrying out big data analysis on the historical data set, and constructing a comprehensive state transition model of at least one power unit in a power system, wherein the comprehensive state transition model is used for representing the probability of internal state transition of each power unit caused by internal factors and/or external factors of the system; constructing a state transformation network diagram corresponding to a plurality of prediction periods of each power unit by utilizing each state transformation model; acquiring current operation parameters of the power system, performing big data analysis on the current operation parameters, and determining initial state probability sets corresponding to all power units, wherein each initial state probability set comprises a plurality of initial state probabilities, and each initial state probability corresponds to one internal operation state; determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm; and determining and outputting risk prompt information according to the combined risk prediction sequence. The technical problem of how to conduct efficient and accurate risk prediction on the power system is solved.
Fig. 3 is a schematic structural diagram of a power system risk prediction system based on big data analysis according to an embodiment of the present application. The risk prediction system 300 may be implemented in software, hardware, or a combination of both.
As shown in fig. 3, the risk prediction system 300 includes:
an acquisition module 301, configured to acquire a historical dataset;
the big data analysis module 302 is configured to perform big data analysis on the historical data set, and construct a comprehensive state transition model of at least one power unit in the power system, where the comprehensive state transition model is used to characterize a probability of internal state transition of each power unit caused by an internal factor and/or an external factor of the system;
a risk prediction module 303, configured to construct a state transformation network map corresponding to a plurality of prediction periods for each power unit using each state transformation model;
an obtaining module 301, configured to obtain a current operation parameter of the power system;
the big data analysis module is further used for carrying out big data analysis on the current operation parameters, determining initial state probability sets corresponding to the power units, wherein the initial state probability sets comprise a plurality of initial state probabilities, and each initial state probability corresponds to one internal operation state;
The risk prediction module 303 is further configured to:
determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm; and determining and outputting risk prompt information according to the combined risk prediction sequence.
In one possible design, risk prediction module 303 is further configured to:
determining a state transition path of each power unit in a plurality of prediction periods according to each initial state probability set and each corresponding state transition network diagram by using a preset tracking algorithm;
determining a unit risk sequence of each power unit in a plurality of prediction periods according to each internal operation state in each state transformation path and a risk value corresponding to the internal operation state;
and combining the risk sequences of the units into a combined risk prediction sequence according to a preset combination mode.
In one possible design, the obtaining module 301 is further configured to obtain a first historical data set and a second historical data set, where the first historical data set includes at least one internal operation data of the power system in one or more historical periods, and the second historical data set includes at least one external environmental data of the power system in one or more historical periods;
The big data analysis module 302 is further configured to perform big data analysis on the first historical data set and the second historical data set, and construct a comprehensive state transition model corresponding to one or more power units;
the integrated state transition model includes: a state transition model for characterizing a first probability of a transition between the various internal operating states caused by the system internal factors, and a state mapping model for characterizing a second probability of an associated effect between each system external factor and at least one internal operating state.
In one possible design, risk prediction module 303 is further configured to:
determining the 1 st state of a state transformation path corresponding to each power unit and the 1 st state judgment value corresponding to the 1 st state according to an initial state probability set corresponding to each power unit through a state prediction rule, wherein the states in the state transformation path correspond to the prediction periods one by one;
according to the state prediction rules, according to each state conversion model, each state mapping model, the n-1 state in each state conversion path and the corresponding n-1 state judgment value, calculating the n state in each state conversion path and the corresponding n state judgment value until n reaches a preset maximum value, wherein n is greater than or equal to 2.
In one possible design, risk prediction module 303 is further configured to:
the maximum value in each initial state probability set is used as a 1 st state judgment value, and the state corresponding to the maximum value is used as a 1 st state.
In one possible design, risk prediction module 303 is further configured to:
according to the first probability matrix in each state transition model, the second probability matrix in each state mapping model and each n-1 th state, calculating one or more candidate state judgment values corresponding to each candidate state in each n-th candidate state set, wherein each n-th candidate state set corresponds to the n-th state in each state transition path:
wherein,represents candidate state determination value, A is the firstA first probability matrix corresponding to n prediction periods,is any element in A, +.>For the n-1 th state, +.>For any one candidate state, M is the total number of all candidate states of each power unit in the nth prediction period, B is a second probability matrix, +.>Is any element in B, N is the total number of the external environment states, and +.>The external environment state corresponding to the nth prediction period;
according to the n-1 state judgment value corresponding to each state transformation path and each candidate state judgment value, determining the n-1 state judgment value corresponding to each state transformation path through a state prediction rule;
And taking the candidate state corresponding to the nth state judgment value as the nth state.
In one possible design, risk prediction module 303 is further configured to:
calculating a first product of each n-1 state judgment value and the first weight value;
calculating a second product of each candidate state judgment value corresponding to each nth state and each second weight value, wherein the second weight values correspond to the candidate state judgment values one by one;
and taking the maximum value of the sum of the first product and at least one second product as an nth state judgment value.
In one possible design, risk prediction module 303 is further configured to:
judging whether each internal operation state in each state transformation path belongs to a normally-operable class or not;
if yes, setting a risk value corresponding to the internal running state as a first risk value;
otherwise, setting a risk value corresponding to the internal running state as a second risk value;
and arranging the risk values into a unit risk sequence according to the sequence of the prediction period.
In one possible design, risk prediction module 303 is further configured to:
judging whether the last-last risk value in each unit risk sequence is a first risk value or not, wherein the first risk value corresponds to the internal running state of the normally working class;
If not, the unit risk sequence is taken as a subsequence of the combined risk prediction sequence.
It should be noted that, the system provided in the embodiment shown in fig. 3 may perform the method provided in any of the above method embodiments, and the specific implementation principles, technical features, explanation of terms, and technical effects are similar, and are not repeated herein.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 4, the electronic device 400 may include: at least one processor 401 and a memory 402. Fig. 4 shows an apparatus for example a processor.
A memory 402 for storing a program. In particular, the program may include program code including computer-operating instructions.
Memory 402 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 401 is configured to execute computer-executable instructions stored in the memory 402 to implement the methods described in the above method embodiments.
The processor 401 may be a central processing unit (central processing unit, abbreviated as CPU), or an application specific integrated circuit (application specific integrated circuit, abbreviated as ASIC), or one or more integrated circuits configured to implement embodiments of the present application.
Alternatively, the memory 402 may be separate or integrated with the processor 401. When the memory 402 is a device independent from the processor 401, the electronic apparatus 400 may further include:
a bus 403 for connecting the processor 401 and the memory 402. The bus may be an industry standard architecture (industry standard architecture, abbreviated ISA) bus, an external device interconnect (peripheral component, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. Buses may be divided into address buses, data buses, control buses, etc., but do not represent only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 402 and the processor 401 are integrated on a chip, the memory 402 and the processor 401 may complete communication through an internal interface.
Embodiments of the present application also provide a computer-readable storage medium, which may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, and specifically, the computer readable storage medium stores program instructions for the methods in the above method embodiments.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the method of the above-described method embodiments.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. The power system risk prediction method based on big data analysis is characterized by comprising the following steps of:
acquiring a historical data set, performing big data analysis on the historical data set, and constructing a comprehensive state transition model of at least one power unit in the power system, wherein the comprehensive state transition model is used for representing the probability of internal state transition of each power unit caused by internal factors and/or external factors of the system;
constructing a state transformation network diagram corresponding to a plurality of prediction periods of each power unit by utilizing each state transformation model;
acquiring current operation parameters of the power system, performing big data analysis on the current operation parameters, and determining initial state probability sets corresponding to the power units, wherein each initial state probability set comprises a plurality of initial state probabilities, and each initial state probability corresponds to an internal operation state;
determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm;
and determining and outputting risk prompt information according to the combined risk prediction sequence.
2. The method for predicting risk of a power system based on big data analysis according to claim 1, wherein the determining, by using a preset trace-finding algorithm, a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transition network diagram includes:
determining a state transition path of each power unit in a plurality of prediction periods according to each initial state probability set and each corresponding state transition network diagram by using the preset tracking algorithm;
determining a unit risk sequence of each power unit in a plurality of prediction periods according to each internal operation state in each state transformation path and a risk value corresponding to the internal operation state;
and combining the unit risk sequences into the combined risk prediction sequence according to a preset combination mode.
3. The method for predicting risk of a power system based on big data analysis according to claim 2, wherein the steps of obtaining a historical data set, analyzing the historical data set, and constructing a comprehensive state transition model of at least one power unit in the power system include:
Obtaining a first historical data set comprising at least one internal operational data of a power system over one or more historical periods and a second historical data set comprising at least one external environmental data of the power system over the one or more historical periods;
performing big data analysis on the first historical data set and the second historical data set, and constructing one or more comprehensive state transition models corresponding to the power units;
the comprehensive state transition model includes: a state transition model for characterizing a first probability of a transition between each of said internal operating states caused by a factor within the system, and a state mapping model for characterizing a second probability of an associated effect between each of the system external factors and at least one of said internal operating states.
4. A method for predicting risk of a power system based on big data analysis according to claim 3, wherein said determining, by using a preset trace-finding algorithm, a state transition path of each power unit in a plurality of prediction periods according to each initial state probability set and each corresponding state transition network diagram comprises:
Determining a 1 st state of the state transformation path corresponding to each power unit and a 1 st state judgment value corresponding to the 1 st state according to the initial state probability set corresponding to each power unit through a state prediction rule, wherein the states in the state transformation path correspond to the prediction periods one by one;
and calculating the nth state and the corresponding nth state judgment value in each state transformation path according to each state transformation model, each state mapping model, the nth-1 state in each state transformation path and the corresponding nth-1 state judgment value through the state prediction rule until n reaches a preset maximum value, wherein n is greater than or equal to 2.
5. The method according to claim 4, wherein the determining, by a state prediction rule, a 1 st state of the state transition path corresponding to each power unit and a 1 st state determination value corresponding to the 1 st state according to the initial state probability set corresponding to each power unit, comprises:
and taking the maximum value in each initial state probability set as the 1 st state judgment value, and taking the state corresponding to the maximum value as the 1 st state.
6. The method according to claim 4, wherein calculating, by the state prediction rule, the nth state and the corresponding nth state determination value in each of the state transition paths according to each of the state transition models, each of the state mapping models, the nth-1 state in each of the state transition paths, and the corresponding nth-1 state determination value, comprises:
calculating one or more candidate state decision values corresponding to each candidate state in each nth candidate state set according to the first probability matrix in each state transition model, the second probability matrix in each state mapping model and each n-1 th state, wherein each nth candidate state set corresponds to the nth state in each state transition path:
；
wherein,representing the candidate state judgment value, wherein A is the first probability matrix corresponding to the nth prediction period,/and B is the first probability matrix corresponding to the nth prediction period>Is any element in A, +.>For the n-1 th state, < > and>for any one candidate state, M is the total number of all candidate states of each power unit in the nth prediction period, B is the second probability matrix, and +. >In BN is the total number of external environmental states, +.>The external environment state corresponding to the nth prediction period is obtained;
determining the nth state judgment value corresponding to each state conversion path according to the nth-1 state judgment value corresponding to each state conversion path and each candidate state judgment value through the state prediction rule;
and taking the candidate state corresponding to the nth state judgment value as the nth state.
7. The method according to claim 6, wherein determining the nth state determination value corresponding to each state transition path according to the nth-1 state determination value corresponding to each state transition path and each candidate state determination value according to the state prediction rule, comprises:
calculating a first product of each n-1 state judgment value and a first weight value;
calculating a second product of each candidate state judgment value corresponding to each nth state and each second weight value, wherein the second weight values are in one-to-one correspondence with the candidate state judgment values;
And taking the maximum value of the sum of the first product and at least one second product as the nth state judgment value.
8. The method for predicting risk of a power system based on big data analysis according to claim 2, wherein determining a unit risk sequence of each power unit in a plurality of prediction periods according to the respective internal operation states in each state transition path and the risk values corresponding to the internal operation states comprises:
judging whether each internal operation state in each state transition path belongs to a normally-operable class or not;
if yes, setting the risk value corresponding to the internal running state as a first risk value;
otherwise, setting the risk value corresponding to the internal running state as a second risk value;
and arranging the risk values into the unit risk sequence according to the order of the prediction period.
9. The method for predicting risk of a power system based on big data analysis according to claim 2, wherein the combining each of the unit risk sequences into the combined risk prediction sequence according to a preset combination manner includes:
Judging whether the last second risk value in each unit risk sequence is a first risk value or not, wherein the first risk value corresponds to the internal operation state of a normally-workable class;
if not, the unit risk sequence is used as a subsequence of the combined risk prediction sequence.
10. A power system risk prediction system based on big data analysis, comprising:
the acquisition module is used for acquiring the historical data set;
the big data analysis module is used for carrying out big data analysis on the historical data set and constructing a comprehensive state transition model of at least one power unit in the power system, wherein the comprehensive state transition model is used for representing the probability of internal state transition of each power unit caused by internal factors and/or external factors of the system;
the risk prediction module is used for constructing a state transformation network diagram corresponding to a plurality of prediction periods of each power unit by utilizing each state transformation model;
the acquisition module is also used for acquiring the current operation parameters of the power system;
the big data analysis module is further used for carrying out big data analysis on the current operation parameters, and determining initial state probability sets corresponding to the power units, wherein the initial state probability sets comprise a plurality of initial state probabilities, and each initial state probability corresponds to one internal operation state;
The risk prediction module is further configured to:
determining a combined risk prediction sequence of the power system according to each initial state probability set and each corresponding state transformation network diagram by using a preset tracking algorithm; and determining and outputting risk prompt information according to the combined risk prediction sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410005501.2A CN117495114B (en) | 2024-01-03 | 2024-01-03 | Power system risk prediction method and system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410005501.2A CN117495114B (en) | 2024-01-03 | 2024-01-03 | Power system risk prediction method and system based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117495114A true CN117495114A (en) | 2024-02-02 |
| CN117495114B CN117495114B (en) | 2024-03-22 |
Family
ID=89671254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410005501.2A Active CN117495114B (en) | 2024-01-03 | 2024-01-03 | Power system risk prediction method and system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117495114B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358415A (en) * | 2021-12-31 | 2022-04-15 | 国网上海市电力公司 | Typhoon season overhead line trip prediction method based on interactive hidden Markov model |
| US20230052730A1 (en) * | 2017-09-04 | 2023-02-16 | Southeast University | Method for predicting operation state of power distribution network with distributed generations based on scene analysis |
| CN115730749A (en) * | 2023-01-05 | 2023-03-03 | 佰聆数据股份有限公司 | Electric power dispatching risk early warning method and device based on fused electric power data |
| CN116777202A (en) * | 2023-05-18 | 2023-09-19 | 国网冀北电力有限公司张家口供电公司 | Power distribution network line risk assessment method, device, equipment and readable storage medium |
-
2024
- 2024-01-03 CN CN202410005501.2A patent/CN117495114B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230052730A1 (en) * | 2017-09-04 | 2023-02-16 | Southeast University | Method for predicting operation state of power distribution network with distributed generations based on scene analysis |
| CN114358415A (en) * | 2021-12-31 | 2022-04-15 | 国网上海市电力公司 | Typhoon season overhead line trip prediction method based on interactive hidden Markov model |
| CN115730749A (en) * | 2023-01-05 | 2023-03-03 | 佰聆数据股份有限公司 | Electric power dispatching risk early warning method and device based on fused electric power data |
| CN116777202A (en) * | 2023-05-18 | 2023-09-19 | 国网冀北电力有限公司张家口供电公司 | Power distribution network line risk assessment method, device, equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 智鹏飞 等: "综合电力推进系统风险预测评估方法", 哈尔滨工程大学学报, vol. 40, no. 5, 5 May 2019 (2019-05-05), pages 1 - 6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117495114B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112131673B (en) | Engine surge fault prediction system and method based on fusion neural network model | |
| CN109324291B (en) | Prediction method for predicting service life of proton exchange membrane fuel cell | |
| Jain et al. | Optimal replacement policy for a repairable system with multiple vacations and imperfect fault coverage | |
| CN112308126A (en) | Fault recognition model training method, fault recognition device and electronic equipment | |
| CN113343581B (en) | Transformer fault diagnosis method based on graph Markov neural network | |
| CN112102011A (en) | User grade prediction method, device, terminal and medium based on artificial intelligence | |
| CN116794510A (en) | Fault prediction method, device, computer equipment and storage medium | |
| CN116599050A (en) | Photovoltaic prediction method and related device based on self-attention mechanism | |
| CN116663746A (en) | Power load prediction method and device, computer equipment and storage medium | |
| CN117493066B (en) | Fault prediction method, device, equipment and medium of server | |
| CN117495114B (en) | Power system risk prediction method and system based on big data analysis | |
| CN112232985B (en) | Power distribution and utilization data monitoring method and device for ubiquitous power Internet of things | |
| US20100076917A1 (en) | System and method for predicting rare events | |
| CN108805323B (en) | Data prediction method and device | |
| CN115185804A (en) | Server performance prediction method, system, terminal and storage medium | |
| Tong et al. | A prediction model for complex equipment remaining useful life using gated recurrent unit complex networks | |
| CN111354449B (en) | Long-term care strategy distribution method, device, computer equipment and storage medium | |
| Wang et al. | HARRD: Real-time software rejuvenation decision based on hierarchical analysis under weibull distribution | |
| CN111368412B (en) | Simulation model construction method and device for nursing demand prediction | |
| CN112512072B (en) | VoLTE network fault prediction method and equipment | |
| CN117649118A (en) | Method, system, equipment and medium for evaluating power supply reliability of wind power grid-connected system | |
| CN117010563A (en) | New energy output rolling prediction method, system, computer equipment and medium | |
| CN118153737A (en) | Method and device for predicting line loss of power distribution network | |
| CN115392509A (en) | Power supply and transformation equipment maintenance method, system and equipment based on parallel learning | |
| CN116646923A (en) | Method, device, terminal and storage medium for predicting medium and long term power load |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |