CN113516295B - Space load prediction method and system for rapid power restoration after disaster - Google Patents
Space load prediction method and system for rapid power restoration after disaster Download PDFInfo
- Publication number
- CN113516295B CN113516295B CN202110574453.5A CN202110574453A CN113516295B CN 113516295 B CN113516295 B CN 113516295B CN 202110574453 A CN202110574453 A CN 202110574453A CN 113516295 B CN113516295 B CN 113516295B
- Authority
- CN
- China
- Prior art keywords
- load
- period
- prediction
- time
- historical
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000011159 matrix material Substances 0.000 claims abstract description 63
- 238000010276 construction Methods 0.000 claims abstract description 12
- 238000011084 recovery Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 9
- 238000009826 distribution Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008439 repair process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000005096 rolling process Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a space load prediction method and system for rapid power restoration after disaster, which are used for determining a period T before prediction according to typhoon disaster information 1 And load prediction target period T 2 (ii) a According to the pre-prediction period T 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 ) (ii) a Based on the period T before prediction 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering the result C according to the fuzzy mean h (T 1 ) And real-time load data X c (T 1 ) Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h (T 1 ) Degree of membership matrix U c (ii) a Based on membership degree matrix U h 、U c And historical load data X of the target prediction period h (T 2 ) Constructing a load X for a target time period c (T 2 ) The load of the target period is predicted.
Description
Technical Field
The invention belongs to the technical field of restoring force improvement of power systems, and particularly relates to a space load prediction method and system for rapid power restoration after disaster.
Background
With the continuous promotion of the terminal electrification process, the dependence degree of various key infrastructures for human society to live on electric energy is higher and higher, the electric energy becomes the most important energy form for normal operation of the human society, and the guarantee of safe, reliable and continuous supply of electric power is of great importance. However, with the change of global climate, typhoon disasters are frequent, which has resulted in many large-scale power failure accidents, thereby causing huge economic loss and political social impact. The power distribution network is located at the tail end of a power system and a user, safe and reliable operation of the power distribution network is directly related to safe and reliable power supply of the user, and the capability of rapidly recovering power supply after the power distribution network fails in typhoon disasters is very important. However, metering equipment of a power distribution system in a typhoon may have a fault, so that the observability of the system is reduced, and key load data for determining a fault first-aid repair sequence and formulating a recovery strategy cannot be obtained.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a space load prediction method and system for fast power restoration after a disaster, aiming at the defects in the prior art, so as to quickly predict the space load after a typhoon disaster, and solve the problem that a recovery strategy cannot be formulated due to the loss of key load data in the disaster.
A space load prediction method for rapid power restoration after disaster comprises the following steps:
s1, determining a period T before prediction according to typhoon disaster information 1 And load prediction target period T 2 ；
S2, determining the period T before prediction according to the step S1 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 )；
S3, predicting the period T before the prediction based on the step S2 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering the result C according to the fuzzy mean h (T 1 ) And real-time load data X of step S2 c (T 1 ) Constructing real-time load data X of period before prediction c (T 1 ) For historical typical load curveLine C h (T 1 ) Membership degree matrix U c ；
S4, constructing a membership matrix U based on the step S3 h 、U c And the historical load data X of the target prediction period in step S2 h (T 2 ) Constructing a load X for a target time period c (T 2 ) The load of the target period is predicted.
Specifically, in step S2, the pre-prediction real-time load data X c And historical daily load data X h With the same sampling frequency.
Specifically, step S3 specifically includes:
s301, the number of power supply grids is n, the number k of clustering centers is given, and an initial membership matrix U is obtained h (0) Weighting index m, iteration threshold epsilon, and iteration time t =0;
s302, calculating a clustering center C according to the membership matrix h (t+1) (T 1 )；
S303, updating the membership degree;
s304, if | | C hi (t+1) (T 1 )-C hi (t) (T 1 ) If | < epsilon, the convergence condition is satisfied, the iteration is stopped, and the clustering center C is output h (T 1 ) And membership matrix U h ；
S305, according to the real-time load data X c (T 1 ) And historical typical load curve C h (T 1 ) Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h Membership degree matrix U c 。
Further, in step S304, if the convergence condition is not satisfied, the iteration time t = t +1, and the process returns to step S302 to continue the iteration; if the convergence condition is satisfied, the process proceeds to step S305.
Further, in step S305, the membership matrix U c Comprises the following steps:
wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to k and mu cij Membership, X, of real-time load to jth historical typical load for ith power grid ci (T 1 ) For the ith power supply grid at T 1 Real-time load data of time slots, C hj (T 1 ) For the jth historical typical load, m is a weighted index in fuzzy mean clustering, m =2,n is the number of power grids, and k is the number of cluster centers.
Specifically, step S4 specifically includes:
s401, load X corresponding to target time interval in historical load data in step S2 h (T 2 ) And the membership matrix U in step S3 h Construction of T 2 Historical typical load curve C for a period of time h (T 2 )；
S402, based on T in step S401 2 Historical typical load curve C of time period h (T 2 ) And the membership matrix U in step S3 c Building the load X of the target period c (T 2 )。
Further, in step S401, T 2 Historical typical load curve C for a period of time h (T 2 )：
C h (T 2 )＝{C h1 (T 2 ),C h2 (T 2 )...,C hk (T 2 )}
Wherein, mu hij The membership degree of the ith power supply grid historical load to the jth historical typical load is obtained in step S3; x hi (T 2 ) For the ith power supply grid at T 2 Historical load of the time period; m is a weighted index in fuzzy mean clustering, and m =2; k is the number of cluster centers.
In a further aspect of the present invention,in step S402, a load X of a target time period is constructed c (T 2 )：
X c (T 2 )＝U c ·C h (T 2 )
Specifically, after step S4 is completed, the pre-prediction period T is re-determined 1 And load prediction target period T 2 And load prediction is carried out until the comprehensive power recovery is carried out.
Another technical solution of the present invention is a space load prediction system for rapid power restoration after a disaster, including:
a time module for determining a pre-prediction time period T according to the typhoon disaster information 1 And load prediction target period T 2 ；
A load module for predicting the time interval T according to the time determined by the time module 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 )；
Matrix module based on pre-prediction period T of load module 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering the result C according to the fuzzy mean h (T 1 ) And real-time load data X of load module c (T 1 ) Constructing real-time load data X of period before prediction c (T 1 ) For historical typical load curve C h (T 1 ) Membership degree matrix U c ；
Prediction module, membership degree matrix U constructed based on matrix module h 、U c And historical load data X of target prediction period in load module h (T 2 ) Constructing a load X for a target time period c (T 2 ) And predicting the load of the target time interval.
Compared with the prior art, the invention has at least the following beneficial effects:
the invention relates to a space load prediction method for rapid power restoration after disaster, which applies a membership matrix to space load prediction, facilitates subsequent power companies to specifically make a power distribution system emergency repair sequence and a recovery strategy after disaster, and realizes the purposes of rapid load by digging and driving new load prediction through historical data, wherein the data source is simple, the algorithm complexity is low, and the purpose of rapid load can be achieved; load prediction can be continuously carried out along with the advancement of emergency repair work through rolling prediction, and the requirement on load data when the power distribution system recovers power supply after typhoon disasters is met; missing data in the real-time load data are corrected through the prediction result, and the problem of data missing caused by metering equipment failure under typhoon disasters is solved.
Further, in step S2, the pre-prediction real-time load data X c And historical daily load data X h The advantage of having the same sampling frequency setting is that need not carry out data dimension regulation when carrying out fuzzy mean clustering, reduces the error that data loss brought.
Further, step S3 is to obtain a mapping relationship between the historical load and the real-time load by fuzzy mean clustering and using the membership degree to simply and effectively characterize the characteristics of the historical load and the real-time load.
Further, if the convergence condition is not satisfied, the iteration time t = t +1, and the step S302 is returned to continue the iteration to determine whether the fuzzy mean clustering is converged.
Further, a membership matrix U is set c The real-time load is characterized by the membership degree of the real-time load to the historical typical load.
Further, the load of the target time interval is predicted according to the mapping relation between the historical load and the real-time load obtained in the step S3.
Further, T in step S401 2 Historical typical load curve C of time period h (T 2 ) The purpose of the arrangement is to obtain T from S3 1 The relation between the historical load and the historical typical load of the time interval is constructed 2 The historical typical load of the period.
Further, the load X of the target period is constructed in step S402 c (T 2 ) Is through T 2 Obtaining the load X of the target time interval according to the historical typical load of the time interval and the relation between the trial load and the historical load c (T 2 ) I.e. the load that needs to be predicted.
Further, after step S4 is completed, the period T before prediction is determined again 1 And load prediction target period T 2 And load forecasting is carried out until comprehensive power recovery means that the load in the next time period is dynamically forecasted along with the development of time, data basis is provided for power recovery decisions after typhoon disasters, and the power supply of all power supply grids is recovered to be normal.
In conclusion, the method is based on fuzzy mean clustering, the fuzziness and the complexity of the load are fully considered, an accurate prediction result can be obtained, the time complexity is low, the calculation is simple and convenient, the program is clear, the requirement of quick power restoration after typhoon is met, and the load prediction result can be used for optimizing the element fault first-aid repair sequence and making a power supply recovery strategy.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a graph of load prediction results according to an embodiment of the present invention;
FIG. 3 is a graph of a load prediction result for a power grid;
fig. 4 is a graph of the rolling prediction results.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Various structural schematics according to the disclosed embodiments of the invention are shown in the drawings. The figures are not drawn to scale, wherein certain details are exaggerated and possibly omitted for clarity of presentation. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are merely exemplary, and deviations may occur in practice due to manufacturing tolerances or technical limitations, and a person skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions, according to actual needs.
The invention provides a space load prediction method for fast power restoration after disaster, which relates to historical data and real-time data of a power supply grid under a power distribution system, and comprises the steps of firstly obtaining power supply grid load data and a typhoon influence period, then establishing a mapping relation between a load and the historical load in a period before prediction through fuzzy mean clustering, obtaining a membership matrix of the historical data and the real-time data relative to typical power consumption behaviors through fuzzy mean clustering calculation, predicting the load in a target time period according to the membership matrix, and finally predicting the load in the target time period based on the historical load data; a spatial load distribution over a target time period is obtained.
Referring to fig. 1, the method for predicting space load for fast power restoration after disaster according to the present invention includes the following steps:
s1, determining a period T before prediction according to typhoon disaster information 1 And load prediction target period T 2 ；
For the first prediction, T in step S1 1 To predict the pre-period:
T 1 ＝{t 0 ,t 1 ,...,t a }
load prediction target period T 2 Satisfies the following conditions:
T 2 ＝{t a+1 ,t a+2 ,...,t a+b }
b＜a
wherein, is as follows.
S2, acquiring load data of the power supply grid in the disaster area, including real-time load data X before prediction c And historical daily load data X h ；
Pre-prediction real-time load data X c And historical daily load data X h The same sampling frequency, i.e. X c And X h Having the same dimension s.
S3, predicting the period T before prediction based on the historical load data in the step S1 1 Corresponding load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h (T 1 ) Membership degree matrix U c ；
S301, setting the number of power supply grids to be n, setting the number k of clustering centers, and setting an initial membership matrix U h (0) Weighting index m, iteration threshold epsilon, and iteration number t =0, wherein the membership matrix:
satisfies the following conditions:
if t =0, randomly selecting an initial membership matrix; the initial membership matrix satisfies the following conditions:
satisfies the following conditions:
s302, calculating a clustering center C according to the membership matrix h (t+1) (T 1 ) The calculation formula is as follows:
wherein the content of the first and second substances,
s303, updating the membership degree, wherein the calculation formula is as follows:
wherein the content of the first and second substances,
s304, if
If the convergence condition is met, stopping iteration, otherwise, the iteration time t = t +1, and returning to the step S302 to continue iteration;
s305, constructing real-time load data X of period before prediction c (T 1 ) For historical typical load curve C h Degree of membership matrix U c ：
Wherein, mu cij Membership, X, of real-time load to jth historical typical load for ith power grid ci (T 1 ) For the ith power supply grid at T 1 Real-time load data of time slots, C hj (T 1 ) For the jth historical typical load, m is a weighted index in fuzzy mean clustering, m =2,n is the number of power grids, and k is the number of cluster centers.
S4, constructing a membership matrix U based on the step S3 c And the load X corresponding to the target time interval in the historical daily load data h (T 2 ) Building the load X of the target period c (T 2 ) Predicting the load of the target time interval;
s401, based on membership matrix U h Load X corresponding to target time interval in historical daily load data h (T 2 ) Construction of T 2 Historical typical load curve C of time period h (T 2 )：
Wherein, mu hij The membership degree of the ith power supply grid historical load to the jth historical typical load is obtained in step S3; x hi (T 2 ) For the ith power supply grid at T 2 The historical load of the time period, m is the weighted index in the fuzzy mean clustering, and m =2,k is the number of clustering centers.
S402, based on T 2 Historical typical load curve C of time period h (T 2 ) And membership matrix U c Building the load X of the target period c (T 2 )：
X c (T 2 )＝U c ·C h (T 2 )
And S5, continuously recovering the load along with the advancement of the emergency repair work, re-determining the time period before prediction and the target time period, and predicting the load until the comprehensive power restoration.
With increasing time, T 1 And T 2 The dimension of (2) is unchanged, newly added time nodes are added, and initial time nodes are deleted:
T 1 '＝{t 1 ,t 2 ,...,t a+1 }
T 2 '＝{t a+2 ,t a+3 ,...,t a+b+1 }
adding new node data x if the real-time load of the period before prediction c (T 1 ',t a+1 ) The node data x in the last prediction result can be used when the node data x cannot be acquired due to the failure of the metering equipment c (T 2 ,t a+1 ) And (4) replacing.
In another embodiment of the present invention, a space load prediction system for fast power restoration after a disaster is provided, where the system can be used to implement the space load prediction method for fast power restoration after a disaster, and specifically, the space load prediction system for fast power restoration after a disaster includes a time module, a load module, a matrix module, and a prediction module.
Wherein, the time module determines the period T before prediction according to the typhoon disaster information 1 And load prediction target period T 2 ；
A load module for predicting the time period T according to the time module 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 )；
Matrix module based on pre-prediction period T of load module 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Of time-interval power gridsHistorical typical load curve C h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering the result C according to the fuzzy mean h (T 1 ) And real-time load data X of load module c (T 1 ) Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h (T 1 ) Degree of membership matrix U c ；
Prediction module, membership degree matrix U constructed based on matrix module h 、U c And historical load data X of target prediction period in load module h (T 2 ) Constructing a load X for a target time period c (T 2 ) The load of the target period is predicted.
In yet another embodiment of the present invention, a terminal device is provided that includes a processor and a memory for storing a computer program comprising program instructions, the processor being configured to execute the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., which is a computing core and a control core of the terminal, and is adapted to implement one or more instructions, and is specifically adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; the processor provided by the embodiment of the invention can be used for the operation of the space load prediction method for the post-disaster quick power restoration, and comprises the following steps:
determining a period T before prediction according to typhoon disaster information 1 And load prediction target period T 2 (ii) a According to the pre-prediction period T 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 ) (ii) a Based on the period T before prediction 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering the result C according to the fuzzy mean h (T 1 ) And real-time load data X c (T 1 ) Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h (T 1 ) Degree of membership matrix U c (ii) a Based on membership degree matrix U h 、U c And historical load data X of the target prediction period h (T 2 ) Constructing a load X for a target time period c (T 2 ) The load of the target period is predicted.
In still another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a Memory device in a terminal device and is used for storing programs and data. It is understood that the computer readable storage medium herein may include a built-in storage medium in the terminal device, and may also include an extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also, one or more instructions, which may be one or more computer programs (including program code), are stored in the memory space and are adapted to be loaded and executed by the processor. It should be noted that the computer-readable storage medium may be a high-speed RAM memory, or may be a non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor can load and execute one or more instructions stored in the computer-readable storage medium to realize the corresponding steps of the space load prediction method for the post-disaster quick power restoration in the embodiment; one or more instructions in the computer-readable storage medium are loaded by the processor and perform the steps of:
determining a period T before prediction according to typhoon disaster information 1 And load prediction target period T 2 (ii) a According to the pre-prediction period T 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of a period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 ) (ii) a Based on the period T before prediction 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering the result C according to the fuzzy mean h (T 1 ) And real-time load data X c (T 1 ) Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h (T 1 ) Degree of membership matrix U c (ii) a Based on membership degree matrix U h 、U c And historical load data X of the target prediction period h (T 2 ) Constructing a load X for a target time period c (T 2 ) The load of the target period is predicted.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
And load prediction is carried out on the power supply grid, and the load time sequence data of the power supply grid is 48-point daily load time sequence data obtained by sampling every half hour from the day 00 to the day 23. All power grids have historical load data for the current year of the typhoon. Selecting a pre-prediction time period T 1 00 to 00, target prediction period T 2 The method comprises the following steps of 05 h Real-time load data X before prediction c Wherein the historical data is 48-dimensional, and the real-time load data before prediction is the period T before prediction 1 Load data of when T 1 And 10 dimensions at 00.
X h ＝{x h1 ,x h2 ,...,x h48 }
X c ＝{x c1 ,x c2 ,...x cT1 }
Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h And corresponding membership degree matrix U h 。
Referring to FIG. 2, a typical load pattern based on historical data is shown, along with the degree of membership of the load curve to all load patterns on a given day.
Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h (T 1 ) Membership degree matrix U c Based on the membership matrix and the load X corresponding to the target time interval in the historical daily load data h (T 2 ) Building the load X of the target time interval c (T 2 )。
X c (T 2 )＝U c ·C h (T 2 )
Fig. 3 shows the load prediction results of the power grid.
The prediction time length is selected to be 4h, and rolling prediction can be carried out on the load all day. Fig. 4 shows the results of the rolling prediction.
In summary, the space load prediction method for rapid power restoration after disaster is based on fuzzy mean clustering, and fully considers the fuzziness and complexity of the load, so that an accurate prediction result can be obtained. Meanwhile, the time complexity of the method is low, and the method meets the load spatial distribution prediction requirement after typhoon. The load prediction result can be used for optimizing the post-disaster fault first-aid repair sequence and making a power supply recovery strategy.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (10)
1. A space load prediction method for rapid power restoration after disaster is characterized by comprising the following steps:
s1, determining a period T before prediction according to typhoon disaster information 1 And load prediction target period T 2 ；
S2, determining the period T before prediction according to the step S1 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 )；
S3, predicting the period T based on the step S2 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering according to fuzzy meansResults C h (T 1 ) And real-time load data X of step S2 c (T 1 ) Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h (T 1 ) Membership degree matrix U c ；
S4, constructing a membership matrix U based on the step S3 h 、U c And the historical load data X of the target prediction period in step S2 h (T 2 ) Constructing a load X for a target time period c (T 2 ) The load of the target period is predicted.
2. The method according to claim 1, wherein in step S2, the pre-prediction real-time load data X c And historical daily load data X h With the same sampling frequency.
3. The method according to claim 1, wherein step S3 is specifically:
s301, the number of power supply grids is n, the number k of clustering centers is given, and an initial membership matrix U is obtained h (0) Weighting index m, iteration threshold epsilon, and iteration time t =0;
s302, calculating a clustering center according to the membership matrix
S303, updating the membership degree;
s304, if
Satisfying the convergence condition, stopping iteration and outputting a clustering center C h (T 1 ) And membership matrix U h ；
S305, according to the real-time load data X c (T 1 ) And historical typical load curve C h (T 1 ) Construction of Pre-prediction time-Domain real-time load data X c (T 1 ) For historical typical load curve C h Membership degree matrix U c 。
4. The method according to claim 3, wherein in step S304, if the convergence condition is not satisfied, the iteration time t = t +1, and returning to step S302 to continue the iteration; if the convergence condition is satisfied, the process proceeds to step S305.
5. The method of claim 3, wherein in step S305, the membership matrix U c Comprises the following steps:
wherein i is more than or equal to 1 and less than or equal to n, j is more than or equal to 1 and less than or equal to k, mu cij Membership, X, of real-time load to jth historical typical load for ith power grid ci (T 1 ) For the ith power supply grid at T 1 Real-time load data of time slots, C hj (T 1 ) For the jth historical typical load, m is a weighted index in fuzzy mean clustering, m =2,n is the number of power grids, and k is the number of cluster centers.
6. The method according to claim 1, wherein step S4 is specifically:
s401, load X corresponding to target time interval in historical load data in step S2 h (T 2 ) And the membership matrix U in step S3 h Construction of T 2 Historical typical load curve C for a period of time h (T 2 )；
S402, based on T in step S401 2 Historical typical load curve C of time period h (T 2 ) And the membership matrix U in step S3 c Building the load X of the target period c (T 2 )。
7. The method of claim 6, wherein in step S401, T is 2 Historical typical load curve C of time period h (T 2 )：
C h (T 2 )＝{C h1 (T 2 ),C h2 (T 2 )...,C hk (T 2 )}
Wherein, mu hij The membership degree of the ith power supply grid historical load to the jth historical typical load is obtained in step S3; x hi (T 2 ) For the ith power supply grid at T 2 Historical load of the time period; m is a weighted index in the fuzzy mean clustering, m =2; k is the number of cluster centers.
8. The method of claim 6, wherein in step S402, the load X of the target time period is constructed c (T 2 )：
X c (T 2 )＝U c ·C h (T 2 )。
9. The method of claim 1, wherein step S4 is completed and the pre-prediction time period T is re-determined 1 And load prediction target period T 2 And load prediction is carried out until the comprehensive power recovery.
10. A space load prediction system for rapid post-disaster recovery is characterized by comprising:
a time module for determining a pre-prediction time period T according to the typhoon disaster information 1 And load prediction target period T 2 ；
A load module for predicting the time period T according to the time module 1 And predicting the target period T 2 Acquiring load data of a power supply grid in a disaster area, wherein the load data comprises a period T before prediction 1 Real-time load data X c (T 1 ) Historical load data X of period before prediction h (T 1 ) Historical load data X of target prediction period h (T 2 )；
Matrix module based on pre-prediction period T of load module 1 Corresponding historical load data X h (T 1 ) Obtaining T by fuzzy mean clustering 1 Historical typical load curve C of time interval power supply grid h (T 1 ) And corresponding membership degree matrix U h (ii) a Clustering the result C according to the fuzzy mean h (T 1 ) And real-time load data X of load module c (T 1 ) Constructing real-time load data X of period before prediction c (T 1 ) For historical typical load curve C h (T 1 ) Membership degree matrix U c ；
Prediction module, membership degree matrix U constructed based on matrix module h 、U c And historical load data X of target prediction period in load module h (T 2 ) Constructing a load X for a target time period c (T 2 ) The load of the target period is predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110574453.5A CN113516295B (en) | 2021-05-25 | 2021-05-25 | Space load prediction method and system for rapid power restoration after disaster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110574453.5A CN113516295B (en) | 2021-05-25 | 2021-05-25 | Space load prediction method and system for rapid power restoration after disaster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113516295A CN113516295A (en) | 2021-10-19 |
| CN113516295B true CN113516295B (en) | 2023-01-20 |
Family
ID=78064885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110574453.5A Active CN113516295B (en) | 2021-05-25 | 2021-05-25 | Space load prediction method and system for rapid power restoration after disaster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113516295B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738773A (en) * | 2020-07-01 | 2020-10-02 | 国网宁夏电力有限公司 | New energy and load-based net load peak-valley time interval dividing method and system |
| CN112734135A (en) * | 2021-01-26 | 2021-04-30 | 吉林大学 | Power load prediction method, intelligent terminal and computer readable storage medium |
-
2021
- 2021-05-25 CN CN202110574453.5A patent/CN113516295B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738773A (en) * | 2020-07-01 | 2020-10-02 | 国网宁夏电力有限公司 | New energy and load-based net load peak-valley time interval dividing method and system |
| CN112734135A (en) * | 2021-01-26 | 2021-04-30 | 吉林大学 | Power load prediction method, intelligent terminal and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于模糊聚类识别及统计相关的短期负荷预测;张艳杰等;《电网技术》;20021124(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113516295A (en) | 2021-10-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Platbrood et al. | A generic approach for solving nonlinear-discrete security-constrained optimal power flow problems in large-scale systems | |
| CN113312761B (en) | Method and system for improving toughness of power distribution network | |
| CN105373517A (en) | Spark-based distributed matrix inversion parallel operation method | |
| CN104063559A (en) | Layout legalization method and system for distributed computing of large-scale integrated circuit | |
| CN114021425B (en) | Power system operation data modeling and feature selection method and device, electronic equipment and storage medium | |
| Goulart et al. | Permutation-based optimization for the load restoration problem with improved time estimation of maneuvers | |
| CN103838649A (en) | Method for reducing calculation amount in binary coding storage system | |
| CN109586281B (en) | Power distribution network reliability assessment method, device and medium based on node optimization number | |
| CN113705896A (en) | Target equipment determination method and device and electronic equipment | |
| CN113516295B (en) | Space load prediction method and system for rapid power restoration after disaster | |
| Ramesh et al. | Spatio-Temporal Deep Learning-Assisted Reduced Security-Constrained Unit Commitment | |
| Han et al. | Learning-based topology optimization of power networks | |
| CN117458453A (en) | Method, system, equipment and storage medium for predicting transient stability of power system | |
| Ma et al. | A parallel heuristic reduction based approach for distribution network fault diagnosis | |
| Hussain et al. | A fast and scalable transmission switching algorithm for boosting resilience of electric grids impacted by extreme weather events | |
| Dong et al. | An unbiased bi-objective optimization model and algorithm for constrained optimization | |
| Sulaima et al. | A 16kV distribution network reconfiguration by using evolutionaring programming for loss minimizing | |
| CN112751334A (en) | Power grid online modeling method and system based on memory computing architecture | |
| Zhang et al. | Batch computing method for sensitivity analysis of large power grids based on GPU acceleration | |
| CN113569315B (en) | Bridge cluster dynamic evaluation method, device, equipment and readable storage medium | |
| CN118117754A (en) | Online intelligent electric energy recovery method and system based on electricity price mechanism | |
| CN108288121B (en) | Verification method and device for power grid area | |
| Peng et al. | A discrete PSO for partitioning in VLSI circuit | |
| CN116683431A (en) | Rapid power distribution system restoring force assessment index and assessment method and system | |
| Mudalige et al. | Predictive analysis and optimisation of pipelined wavefront computations |
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 |