CN112488418B - Full topology load prediction method and device and computer equipment - Google Patents
Full topology load prediction method and device and computer equipment Download PDFInfo
- Publication number
- CN112488418B CN112488418B CN202011472436.2A CN202011472436A CN112488418B CN 112488418 B CN112488418 B CN 112488418B CN 202011472436 A CN202011472436 A CN 202011472436A CN 112488418 B CN112488418 B CN 112488418B
- Authority
- CN
- China
- Prior art keywords
- load
- data
- analysis
- full topology
- 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 65
- 238000004458 analytical method Methods 0.000 claims abstract description 67
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 18
- 238000010219 correlation analysis Methods 0.000 claims description 12
- 238000010206 sensitivity analysis Methods 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 7
- 238000013211 curve analysis Methods 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 5
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004445 quantitative analysis Methods 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 230000004927 fusion Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 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
- G06Q10/04—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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical 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)
Abstract
The application discloses a full topology load prediction method, a full topology load prediction device and computer equipment, wherein the full topology load prediction method firstly queries and collects historical load data of full topology according to preset type query conditions, corrects the obtained historical load data, analyzes load changes based on the corrected historical load data of the full topology to obtain analysis results, then selects a load prediction algorithm to conduct first type load prediction or second type load prediction on current actual load data and the analysis results, and outputs predicted load data. The full topology comprises a system load, a bus load and an industry user load, the period of the first type of load prediction is 1 day, and the period range of the second type of load prediction comprises 1 hour to 8 hours. The application can realize the load prediction of all elements and all topologies and is beneficial to the stable operation of the power system.
Description
Technical Field
The present application relates to the field of data prediction, and in particular, to a full topology load prediction method, apparatus, and computer device.
Background
Load prediction is critical in power systems and has important impact on many departments. For example, the generation schedule before date is formulated based on a daily load curve of short-term and ultra-short-term load predictions. Load prediction involves various aspects of the power system, such as planning and design of the system, economic and safe operation of the system, power market trading, extreme weather, holidays, domestic economic development situations and the like, which have an increasing influence on load prediction, resulting in an increasing difficulty in load prediction.
The existing load prediction scheme has the technical problems that the existing load prediction scheme is difficult to cope with the current load structure of the power grid, the influence factors are numerous, the load prediction difficulty is high, and the like.
Disclosure of Invention
In order to solve the technical problems, the application provides a full topology load prediction method, a full topology load prediction device and computer equipment, and the specific scheme is as follows:
in a first aspect, an embodiment of the present disclosure provides a full topology load prediction analysis method, the method including:
inquiring and collecting historical load data of the full topology according to preset type inquiry conditions, and correcting the obtained historical load data, wherein the preset type inquiry conditions comprise user names and inquiry time;
analyzing the load change based on the corrected historical load data of the full topology to obtain an analysis result;
selecting a load prediction algorithm to predict the current actual load data and the analysis result in a first type or a second type, and outputting predicted load data;
the full topology comprises system load, bus load and industry user load, the period of the first type of load prediction is 1 day, the period range of the second type of load prediction comprises 1-8 hours, and the load prediction algorithm comprises any one of a innovation smoothing method, a load trend method and a least square method.
According to one embodiment of the present disclosure, the step of querying and collecting historical load data of a full topology according to a preset type of query condition and correcting the obtained historical load data includes:
filtering the collected historical load data of the full topology, and if bad data is found, sending out alarm information by the system and correcting the bad data, wherein the bad data comprises at least any one of null data points, zero data points, continuous constant values and abnormal step values.
According to one embodiment of the present disclosure, the full topology is system load and/or industry user load;
analyzing the load change based on the corrected full topology historical load data to obtain an analysis result, comprising:
outputting graph curves corresponding to different evaluation types according to the corrected historical load data of the system load and/or the industry load, wherein the evaluation types comprise any one of electric quantity comparison, load characteristics, continuous curves, typical curves, probability distribution and average electricity price;
the change in load is analyzed based on the graph curves of different evaluation types.
According to one embodiment of the present disclosure, the full topology is bus load;
analyzing the load change based on the corrected historical load data of the full topology to obtain an analysis result, and further comprising:
carrying out load characteristic analysis, load stability analysis, load correlation analysis and weather sensitivity analysis based on the corrected historical load data of the bus load to obtain an analysis result;
the load characteristic analysis refers to the statistical analysis of load characteristics of day, week, month, season and year, and comprises at least one of maximum load, minimum load, average load, load rate, peak-valley difference and peak Gu Chalv of different buses;
the load stability analysis refers to performing data decomposition and component analysis on historical load data of the bus load, and quantitatively evaluating the internal regularity and stability of the development of different bus loads in different time periods;
the load correlation analysis refers to calculating the correlation among loads of different buses, wherein the correlation analysis comprises a load synchronous rate, a maximum load correlation, an average load correlation, a minimum load correlation and per unit curve similarity;
the weather sensitivity analysis refers to management, tracking analysis, identification of dominant factors and factor quantitative analysis of factors affecting weather.
According to one embodiment of the present disclosure, the method further comprises:
according to the received target query conditions, acquiring the historical load data of the full topology and the predicted load data of the full topology corresponding to the target query conditions, and performing chart display on the historical load data of the full topology and the predicted load data of the full topology;
acquiring actual load data of a full topology and predicted load data of the full topology according to a preset type of query condition, and monitoring load operation conditions based on the actual load data of the full topology and the predicted load data of the full topology;
and managing the role information, the authority information and the system parameters of each user, wherein the management comprises at least one of adding, deleting, modifying and inquiring.
According to one embodiment of the present disclosure, the step of monitoring the load operation condition based on the actual load data and the predicted load data includes:
continuously displaying the actual load and the predicted load on the same day in a data chart form according to a preset time interval, wherein the value range of the preset time interval is 1 to 60 minutes;
load characteristic monitoring and curve monitoring are carried out on the system load and/or the bus load and/or the industry user load according to the actual load data and the predicted load data;
the load characteristic monitoring provides at least one of maximum load, minimum load, average load, load factor, peak-to-valley difference, peak Gu Chalv of the full topology;
the curve monitoring comprises monitoring at least one of a historical load curve, a predicted load curve and an actual load curve, displaying the comparison of the historical load curve and the predicted load curve, and calculating the deviation rate of the predicted load curve and the actual load curve.
According to one embodiment of the disclosure, after the steps of load characteristic monitoring and curve monitoring of the system load and/or bus load and/or industry user load according to the actual load data and the predicted load data, the method further comprises:
setting a deviation rate reference value;
and when the deviation rate is larger than the deviation rate reference value, performing predictive deviation early warning and load abrupt change early warning.
In a second aspect, embodiments of the present disclosure provide a full topology load prediction apparatus, the apparatus comprising:
the data correction module is used for inquiring and collecting historical load data of the full topology according to preset type inquiry conditions and correcting the obtained historical load data, wherein the preset type inquiry conditions comprise user names and inquiry time;
the prediction analysis module is used for analyzing the load change based on the corrected historical load data of the full topology so as to obtain an analysis result;
the load prediction module is used for selecting a load prediction algorithm to predict the current actual load data and the analysis result in a first type or a second type, and outputting predicted load data;
the full topology comprises system load, bus load and industry user load, the period of the first type of load prediction is 1 day, the period range of the second type of load prediction comprises 1-8 hours, and the load prediction algorithm comprises any one of a innovation smoothing method, a load trend method and a least square method.
In a third aspect, the disclosed embodiments provide a computer device comprising a processor and a memory storing a computer program executable by the processor, the processor executing the computer program to implement the method of any one of the embodiments of the first aspect.
In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium storing computer-executable instructions that, when invoked and executed by a processor, cause the processor to implement the method of any one of the embodiments of the first aspect.
Compared with the prior art, the application has the following beneficial effects:
according to the full topology load prediction method provided by the application, historical load data of full topology is queried and collected according to query conditions of a preset type, the obtained historical load data is corrected, load changes are analyzed based on the corrected historical load data of the full topology to obtain an analysis result, then a load prediction algorithm is selected to conduct first type load prediction or second type load prediction on current actual load data and the analysis result, and predicted load data is output. The full topology comprises a system load, a bus load and an industry user load, the period of the first type of load prediction is 1 day, and the period range of the second type of load prediction comprises 1 hour to 8 hours. The application can realize the load prediction of all elements and all topologies and is beneficial to the stable operation of the power system.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are required for the embodiments will be briefly described, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope of the present application. Like elements are numbered alike in the various figures.
FIG. 1 is a schematic flow chart of a full topology load prediction method according to an embodiment of the present application;
fig. 2 is a block diagram of a full topology load prediction apparatus according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments.
The components of the embodiments of the present application 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 application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
The terms "comprises," "comprising," "including," or any other variation thereof, are intended to cover a specific feature, number, step, operation, element, component, or combination of the foregoing, which may be used in various embodiments of the present application, and are not intended to first exclude the presence of or increase the likelihood of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing.
Furthermore, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the application belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having a meaning that is the same as the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein in connection with the various embodiments of the application.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The embodiments described below and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, a flow chart of a full topology load prediction method provided by an embodiment of the present application, as shown in fig. 1, is shown, where the method mainly includes:
step S101, inquiring and collecting historical load data of a full topology according to preset type inquiry conditions, and correcting the obtained historical load data, wherein the preset type inquiry conditions comprise user names and inquiry time, and the full topology comprises system load, bus load and industry user load.
According to one embodiment of the present disclosure, the historical load data and the load prediction data should be kept consistent in statistical caliber, and should be stored in a 96 point daily load format at least at one point every 15 minutes.
According to one specific embodiment of the disclosure, the collected historical load data of the full topology is filtered, if bad data is found, the system sends out alarm information and corrects the bad data, wherein the bad data comprises at least any one of empty data points, zero data points, continuous constant values and abnormal step values.
And filtering bad data, and identifying by adopting a similar daily curve comparison method. For a certain daily load curve with bad data, selecting a load curve with a date similar to the day and week type, the climate type and other related factors as a characteristic curve, comparing the load curve with the daily load curve, and identifying the bad data by using the similarity of the shapes of the load curves.
The processing of the bad data can be corrected by linear interpolation. If the bad data x i At load point x a And x b In this case, the following correction can be performed assuming that the load curve changes in the section as a linear relationship:
wherein x' i Load value after correction for bad data, n i As load point x i And load point x a The number of bad load points among the load points, n is the load point x a And x b The number of bad load points between the two.
The processing of bad data can also use exponential flatteningThe sliding method is used for correction. For the load sequence x 1 ，x 2 ，x i If x i+1 If the data is bad, the following correction can be performed: when the initial condition is S 0 ＝x 1 At the time, the smoothing equation x' i+1 ＝ax i +(1-α)S i-1 Wherein x' i+1 As bad data x i+1 And the modified load value, alpha is an exponential smoothing coefficient.
Step S102, analyzing the load change based on the corrected historical load data of the full topology to obtain an analysis result.
According to one specific embodiment of the disclosure, if the full topology is a system load and/or an industry user load, a graph curve corresponding to different evaluation types is output according to the corrected historical load data of the system load and/or the industry load, wherein the evaluation types comprise any one of electric quantity comparison, load characteristics, continuous curves, typical curves, probability distribution and average electricity price, and then the change of the load is analyzed based on the graph curves of the different evaluation types.
According to one specific embodiment of the disclosure, if the full topology is a bus load, load characteristic analysis, load stability analysis, load correlation analysis and weather sensitivity analysis are performed based on the corrected historical load data of the bus load, so as to obtain an analysis result.
The load characteristic analysis includes characteristic analysis of at least one of maximum load, minimum load, average load, load factor, peak-to-valley difference, and peak Gu Chalv of the different bus bars. The load characteristic analysis provides load curve analysis of different bus bars on different typical days, such as: working day, saturday, sunday, maximum load day, maximum power day, maximum peak valley difference day, etc. Meanwhile, the load characteristic analysis provides continuous load curve analysis of different buses, and the continuous load curve analysis comprises information such as continuous hour percentage, continuous hour number, percentage of maximum load, corresponding load and the like. In addition, the load characteristic analysis also provides analysis of load probability distribution of different buses, including information such as the number of occurrence moments, the number of occurrence days, specific distribution time, corresponding loads and the like in different load ranges.
The load stability analysis refers to data decomposition and component analysis of the historical bus load data, and the inherent regularity and stability of the load development of different buses in different time periods are quantitatively evaluated. The load stability analysis can quantitatively analyze the bus load curves at a plurality of continuous moments to form an upper limit and a lower limit of stability, and evaluate the predicted possible precision range. In addition, the load stability analysis can count and sort the stability conditions of all buses so as to conveniently position buses with poor stability and difficult prediction.
The load correlation analysis refers to calculating the correlation among loads of different buses, and the correlation analysis comprises a load synchronous rate, a maximum load correlation, an average load correlation, a minimum load correlation and per unit curve similarity. And secondly, the load correlation analysis can calculate the load correlation of the bus and the system, and the analysis indexes mainly comprise load proportion, load synchronous rate, maximum load correlation, average load correlation, minimum load correlation and per unit curve similarity. Moreover, the load correlation analysis can count and sort the distribution factors and correlations of the buses so as to analyze the influence of different buses on the system load.
The weather sensitivity analysis refers to management, tracking analysis, identification of dominant factors and factor quantitative analysis of factors affecting weather. According to the first aspect, the weather sensitivity analysis can be used for manually inputting or automatically accessing actual measurement and forecast weather data, manually correcting weather factors, and managing the corresponding relation between the bus and site weather information for multi-site weather information. In a second aspect, the weather sensitivity analysis may analyze trends of weather indicators and actual loads, providing comparative analysis of live data, forecast data and actual load power indicators of various weather indicators. In the third aspect, the weather sensitivity analysis can automatically calculate dominant weather factors affecting different types of load indexes of different buses in different time periods in the local area, and calculate the correlation degree of the different weather factors and the load indexes of the buses, and in the process, the accumulation effect and the superposition effect need to be fully considered. In the fourth aspect, the weather sensitivity analysis should automatically establish an optimal model between dominant weather factors and different bus load indexes, and show the quantitative relationship between weather and load in the form of tables, graphs and the like.
Step S103, selecting a load prediction algorithm to predict the first type of load or the second type of load according to the current actual load data and the analysis result, and outputting predicted load data.
The period of the first-type load prediction is 1 day, the period range of the second-type load prediction comprises 1-8 hours, and the load prediction algorithm comprises any one of an innovation smoothing method, a load trend method and a least square method.
Specifically, the innovation smoothing method is to construct a daily standard curve to be predicted by taking load curves of the near day and the same type, predict the load level by using an exponential smoothing method according to the load change trend of a plurality of recent time periods, and restore to obtain the load of the point to be predicted.
The load trend method is to calculate the variation difference of the load curve of several days in the near future to obtain the load curve of typical day and predict the load variation of future point according to the known load point of the day.
The least square method is to construct a load trend curve from a plurality of days of the same type. The expression of the prediction model set at n history periods is y t = ≡ (S, X, t) (1+.ltoreq.t+.ltoreq.n), a parameter vector S is found that minimizes the unbalanced component of the equation, and the model thus determined best approximates the historical data. Let the sum of squares of the residuals of the fit be:
the goal is to use the dwell point condition by minimizing the sum of squares M of the fit residuals for each history periodSolving the model parameter S, and predicting the load y at the next moment by using the model parameter S t+1 。
In specific implementation, for the various prediction algorithms, a model fusion algorithm can be adopted to improve the accuracy of the prediction result. In this embodiment, the model fusion adopts a majority voting principle, where the majority voting principle refers to taking the predicted results of multiple classifiers as the final predicted results. The majority voting principle is only used for the case of classification, but can be easily generalized to multiple classifications, i.e. the simple majority voting method, so that the most classification can be selected as the final classification. Table 1 illustrates the voting concept of the majority voting principle and the simple majority voting method when 10 different classifiers are fused, wherein each number represents a class respectively.
Table 1 majority voting principle and simple majority voting method
| 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | Results were consistent |
| 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 2 | Most mainly |
| 1 | 1 | 1 | 1 | 2 | 2 | 2 | 3 | 3 | 3 | The relative majority is mainly |
Based on the existing training set, n different single classifiers (C 1 ,C 2 ...C n ). Under the majority voting principle, different classification algorithms can be fused. Such as SVM algorithm, LR algorithm, xgboost, decision tree, random forest algorithm, etc., and may be integrated with the same algorithm to use different training models. To predict targets by simple majority voting principles, all individual classifiers C need to be aggregated j And selecting the category with the highest voting rate:
for example: in the classification, assuming class 1= -1, class 2= +1, the model fusion prediction result based on the majority voting principle is expressed as:
the following conditions were set: the n single classifiers in the two classification problems all have the same error rate epsilon, each single classifier is independent, and the models are independent and uncorrelated, so that the error probability after the single classifier fusion is expressed as a probability density function of binomial distribution:
wherein the method comprises the steps ofIs the binomial coefficient of the n-selected k combination and is also the probability of model prediction error.
In the present embodiment, 11 single classifiers (n=11) are used, and the error rate of each single classifier is 0.25 (ε=0.25), thenI.e. the error rate after fusion is 0.034, which is far smaller than the error rate of 0.25 of a single classifier.
In practice, the prediction process employs rolling prediction, i.e., rolling to calculate the load for the next prediction period. The manual prediction function is provided on the basis of the automatic prediction task, and the manual prediction at any time can be performed under the condition that the set automatic prediction time is not reached.
According to a specific embodiment of the disclosure, the historical load data of the full topology and the predicted load data of the full topology corresponding to the target query condition may be obtained according to the received target query condition, and the historical load data of the full topology and the predicted load data of the full topology may be graphically displayed.
In the implementation, the actual load data of the full topology and the predicted load data of the full topology can be obtained according to the preset type of query conditions, and the load operation condition is monitored based on the actual load data of the full topology and the predicted load data of the full topology. And continuously displaying the actual load and the predicted load on the same day in a data chart form according to a preset time interval, wherein the value range of the preset time interval is 1 to 60 minutes. And carrying out load characteristic monitoring and curve monitoring on the system load and/or the bus load and/or the industry user load according to the actual load data and the predicted load data. The load characteristic monitoring provides at least one of a full topology maximum load, minimum load, average load, load factor, peak-to-valley difference, peak Gu Chalv, the curve monitoring includes monitoring at least one of a historical load curve, a predicted load curve, and an actual load curve, and exhibiting a comparison of the historical load curve and the predicted load curve, calculating a deviation ratio of the predicted load curve and the actual load curve. After this step, a deviation rate reference value may be set, and when the deviation rate is greater than the deviation rate reference value, predictive deviation early warning and load abrupt change early warning are performed.
According to a specific embodiment of the present disclosure, the role information, the authority information and the system parameters of each user may also be managed, where the management includes at least one of adding, deleting, modifying and querying. Displaying the character information of each user in the form of an organization tree, realizing the functions of adding, deleting, modifying and inquiring the characters, wherein the character management is used for controlling the function authority, controlling and supporting the characters by the flow participants, selecting personnel and endowing the personnel with the characters; displaying the authority information of each user in the form of an organization tree, realizing the functions of authority addition, deletion, modification and inquiry, wherein the authority management is used for configuring the use of each function of the system, supporting the authority group, selecting personnel and distributing the authorities for the personnel; and carrying out parameter maintenance on the system universality function, such as a pull-down value list, a display mode of a statistical chart, a display dimension and the like.
According to the full topology load prediction method provided by the application, the history load data of the full topology is queried and collected according to the query condition of the preset type, the obtained history load data is corrected, the load change is analyzed based on the corrected history load data of the full topology to obtain an analysis result, then the load prediction algorithm is selected to conduct the first type load prediction or the second type load prediction on the current actual load data and the analysis result, the predicted load data is output, the load prediction of the full element and the full topology is realized, and the stable operation of the power system is facilitated.
In addition, as shown in fig. 2, the present application further provides a full topology load prediction apparatus, and the full topology load prediction apparatus 200 includes:
the data correction module 201 is configured to query and collect historical load data of a full topology according to a preset type of query condition, and correct the obtained historical load data, where the preset type of query condition includes a user name and a query time;
the prediction analysis module 202 is configured to analyze the load change based on the corrected historical load data of the full topology, so as to obtain an analysis result;
the load prediction module 203 is configured to select a load prediction algorithm to perform a first type load prediction or a second type load prediction on the current actual load data and the analysis result, and output predicted load data;
the full topology comprises system load, bus load and industry user load, the period of the first type of load prediction is 1 day, the period range of the second type of load prediction comprises 1-8 hours, and the load prediction algorithm comprises any one of a innovation smoothing method, a load trend method and a least square method.
Furthermore, a computer device is provided, comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor executing the computer program to implement the above-mentioned full topology load prediction method.
Further, a computer readable storage medium is provided, the computer readable storage medium storing computer executable instructions that, when invoked and executed by a processor, cause the processor to implement the full topology load prediction method described above.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flow diagrams and block diagrams in the figures, which illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules or units in various embodiments of the application may be integrated together to form a single part, or the modules may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a smart phone, a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (8)
1. A method for full topology load prediction, the method comprising:
inquiring and collecting historical load data of the full topology according to preset type inquiry conditions, and correcting the obtained historical load data, wherein the preset type inquiry conditions comprise user names and inquiry time;
analyzing the load change based on the corrected historical load data of the full topology to obtain an analysis result;
selecting a load prediction algorithm to predict the current actual load data and the analysis result in a first type or a second type, and outputting predicted load data;
the full topology comprises system load, bus load and industry user load, the period of the first type of load prediction is 1 day, the period range of the second type of load prediction comprises 1 to 8 hours, and the load prediction algorithm comprises any one of a load trend method and a least square method;
the analysis of the load change based on the corrected historical load data of the full topology to obtain an analysis result further comprises:
carrying out load characteristic analysis, load stability analysis, load correlation analysis and weather sensitivity analysis based on the corrected historical load data of the bus load to obtain an analysis result;
the load characteristic analysis refers to load characteristic statistical analysis on days, weeks, months, seasons and years, comprising maximum loads, minimum loads, average loads, load rates, peak-to-valley differences and peaks Gu Chalv of different buses, wherein the load characteristic analysis provides load curve analysis on different typical days of different buses, comprising working days, saturday, sunday, maximum load days, maximum electric quantity days and maximum peak-to-valley differences, and simultaneously, the load characteristic analysis provides continuous load curve analysis on different buses, comprising continuous hour percentages, continuous hour numbers, percentages accounting for the maximum loads and corresponding load information;
the load stability analysis refers to performing data decomposition and component analysis on historical load data of the bus load, quantitatively evaluating the internal regularity and stability of the development of different bus loads in different time periods, and performing quantitative analysis on a plurality of bus load curves at continuous moments by the load stability analysis to form an upper limit and a lower limit of stability, and evaluating the predicted possible precision range;
the load correlation analysis refers to calculating the correlation among different bus loads, wherein the correlation comprises a load synchronous rate, a maximum load correlation, an average load correlation, a minimum load correlation and a per unit curve similarity;
the meteorological sensitivity analysis is to manage, track and analyze factors affecting the weather, identify dominant factors and quantitatively analyze factors;
the step of inquiring and collecting the history load data of the full topology according to the preset type of inquiry conditions and correcting the obtained history load data comprises the following steps:
filtering the collected historical load data of the full topology, identifying bad data by adopting a similar daily curve comparison method, and if the bad data is found, sending out alarm information by a system and correcting the bad data by adopting a linear interpolation method or an exponential smoothing method, wherein the bad data comprises null data points, zero data points, continuous constant values and abnormal step values.
2. The method of claim 1, wherein the full topology is system load and/or industry user load;
analyzing the load change based on the corrected full topology historical load data to obtain an analysis result, comprising:
outputting graph curves corresponding to different evaluation types according to the corrected historical load data of the system load and/or the industry load, wherein the evaluation types comprise any one of electric quantity comparison, load characteristics, continuous curves, typical curves, probability distribution and average electricity price;
the change in load is analyzed based on the graph curves of different evaluation types.
3. The method according to claim 1, wherein the method further comprises:
according to the received target query conditions, acquiring the historical load data of the full topology and the predicted load data of the full topology corresponding to the target query conditions, and performing chart display on the historical load data of the full topology and the predicted load data of the full topology;
acquiring actual load data of a full topology and predicted load data of the full topology according to a preset type of query condition, and monitoring load operation conditions based on the actual load data of the full topology and the predicted load data of the full topology;
and managing the role information, the authority information and the system parameters of each user, wherein the management comprises at least one of adding, deleting, modifying and inquiring.
4. A method according to claim 3, wherein the step of monitoring load operation based on the actual load data and the predicted load data comprises:
continuously displaying actual load data and predicted load data of the same day in a data chart form according to a preset time interval, wherein the value range of the preset time interval is 1 to 60 minutes;
load characteristic monitoring and curve monitoring are carried out on the system load and/or the bus load and/or the industry user load according to the actual load data and the predicted load data;
the load characteristic monitoring provides full topology maximum load, minimum load, average load, load factor, peak-to-valley difference, peak Gu Chalv;
the curve monitoring comprises monitoring at least one of a historical load curve, a predicted load curve and an actual load curve, displaying the comparison of the historical load curve and the predicted load curve, and calculating the deviation rate of the predicted load curve and the actual load curve.
5. The method of claim 4, wherein after the steps of load characteristic monitoring and profile monitoring of the system load and/or bus load and/or industry user load based on the actual load data and predicted load data, the method further comprises:
setting a deviation rate reference value;
and when the deviation rate is larger than the deviation rate reference value, performing predictive deviation early warning and load abrupt change early warning.
6. A full topology load prediction apparatus, the apparatus comprising:
the data correction module is used for inquiring and collecting historical load data of the full topology according to preset type inquiry conditions and correcting the obtained historical load data, wherein the preset type inquiry conditions comprise user names and inquiry time; filtering the collected historical load data of the full topology, identifying bad data by adopting a similar daily curve comparison method, and if the bad data is found, sending out alarm information by a system and correcting the bad data by adopting a linear interpolation method or an exponential smoothing method, wherein the bad data comprises null data points, zero data points, continuous constant values and abnormal step values;
the prediction analysis module is used for analyzing the load change based on the corrected historical load data of the full topology so as to obtain an analysis result; carrying out load characteristic analysis, load stability analysis, load correlation analysis and weather sensitivity analysis based on the corrected historical load data of the bus load to obtain an analysis result; the load characteristic analysis refers to load characteristic statistical analysis on days, weeks, months, seasons and years, comprising maximum loads, minimum loads, average loads, load rates, peak-to-valley differences and peaks Gu Chalv of different buses, wherein the load characteristic analysis provides load curve analysis on different typical days of different buses, comprising working days, saturday, sunday, maximum load days, maximum electric quantity days and maximum peak-to-valley differences, and simultaneously, the load characteristic analysis provides continuous load curve analysis on different buses, comprising continuous hour percentages, continuous hour numbers, percentages accounting for the maximum loads and corresponding load information; the load stability analysis refers to performing data decomposition and component analysis on historical load data of the bus load, quantitatively evaluating the internal regularity and stability of the development of different bus loads in different time periods, and performing quantitative analysis on a plurality of bus load curves at continuous moments by the load stability analysis to form an upper limit and a lower limit of stability, and evaluating the predicted possible precision range; the load correlation analysis refers to calculating the correlation among different bus loads, wherein the correlation comprises a load synchronous rate, a maximum load correlation, an average load correlation, a minimum load correlation and a per unit curve similarity; the meteorological sensitivity analysis is to manage, track and analyze factors affecting the weather, identify dominant factors and quantitatively analyze factors;
the load prediction module is used for selecting a load prediction algorithm to predict the current actual load data and the analysis result in a first type or a second type, and outputting predicted load data;
the full topology comprises system load, bus load and industry user load, the period of the first type of load prediction is 1 day, the period range of the second type of load prediction comprises 1-8 hours, and the load prediction algorithm comprises any one of a load trend method and a least square method.
7. A computer device, characterized in that it comprises a processor and a memory, the memory storing a computer program executable by the processor, the processor executing the computer program to implement the method of any one of claims 1-5.
8. A computer readable storage medium storing computer executable instructions which, when invoked and executed by a processor, cause the processor to implement the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011472436.2A CN112488418B (en) | 2020-12-14 | 2020-12-14 | Full topology load prediction method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011472436.2A CN112488418B (en) | 2020-12-14 | 2020-12-14 | Full topology load prediction method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112488418A CN112488418A (en) | 2021-03-12 |
| CN112488418B true CN112488418B (en) | 2023-09-26 |
Family
ID=74917746
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011472436.2A Active CN112488418B (en) | 2020-12-14 | 2020-12-14 | Full topology load prediction method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488418B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114329861B (en) * | 2021-12-17 | 2024-03-22 | 重庆邮电大学 | Power distribution network static topology implementation method based on marginal electricity price |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205547A (en) * | 2015-08-25 | 2015-12-30 | 广西电网有限责任公司 | Bus load prediction algorithm based on similarity matching of multiple uncertain factors |
| CN105787606A (en) * | 2016-03-24 | 2016-07-20 | 国网辽宁省电力有限公司电力科学研究院 | Power dispatching online trend early warning system based on ultra short term load prediction |
| CN105930930A (en) * | 2016-04-21 | 2016-09-07 | 国家电网公司 | Load data calibration method based on load characteristic analysis and load prediction technology |
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
| CN108009938A (en) * | 2016-11-02 | 2018-05-08 | 中国电力科学研究院 | A kind of mode identification method of system loading cluster and load period based on shape |
| CN108229742A (en) * | 2018-01-04 | 2018-06-29 | 国网浙江省电力公司电力科学研究院 | A kind of load forecasting method based on meteorological data and data trend |
| CN108898246A (en) * | 2018-06-19 | 2018-11-27 | 深圳供电局有限公司 | A kind of load prediction management system based on electric system |
| KR102090586B1 (en) * | 2018-12-27 | 2020-03-18 | 한국전기안전공사 | Apparatus and method using the smart power panel based on the IoT for the fault condition estimation of the power line and load |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101012863B1 (en) * | 2008-09-25 | 2011-02-08 | 한국전력공사 | Load forecasting analysis system for generation of customer baseline load |
| US20200310479A1 (en) * | 2019-03-28 | 2020-10-01 | PowerSecure Inc. | Systems and methods for controlling an energy supply system |
-
2020
- 2020-12-14 CN CN202011472436.2A patent/CN112488418B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205547A (en) * | 2015-08-25 | 2015-12-30 | 广西电网有限责任公司 | Bus load prediction algorithm based on similarity matching of multiple uncertain factors |
| CN105787606A (en) * | 2016-03-24 | 2016-07-20 | 国网辽宁省电力有限公司电力科学研究院 | Power dispatching online trend early warning system based on ultra short term load prediction |
| CN105930930A (en) * | 2016-04-21 | 2016-09-07 | 国家电网公司 | Load data calibration method based on load characteristic analysis and load prediction technology |
| CN108009938A (en) * | 2016-11-02 | 2018-05-08 | 中国电力科学研究院 | A kind of mode identification method of system loading cluster and load period based on shape |
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
| CN108229742A (en) * | 2018-01-04 | 2018-06-29 | 国网浙江省电力公司电力科学研究院 | A kind of load forecasting method based on meteorological data and data trend |
| CN108898246A (en) * | 2018-06-19 | 2018-11-27 | 深圳供电局有限公司 | A kind of load prediction management system based on electric system |
| KR102090586B1 (en) * | 2018-12-27 | 2020-03-18 | 한국전기안전공사 | Apparatus and method using the smart power panel based on the IoT for the fault condition estimation of the power line and load |
Non-Patent Citations (2)
| Title |
|---|
| Research on Short-term Power Load Forecasting Method Based on Temperature Accumulation Effect Embedded in Time Series;Duan Jinchang 等;《2019 International Conference on Energy, Chemical and Materials Science (ECMS 2019)》;第1-6页 * |
| 基于ARMA和最小二乘法的电力***短期负荷预测;孟繁波 等;《2011年全国通信安全学术会议论文集》;第387-389页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112488418A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751371B (en) | Commodity inventory risk early warning method and system based on statistical four-bit distance and computer readable storage medium | |
| US10248528B2 (en) | System monitoring method and apparatus | |
| JP6895416B2 (en) | Energy demand forecasting system and energy demand forecasting method | |
| WO2019049546A1 (en) | Prediction system and method | |
| US20140058705A1 (en) | System and Method for Detecting Abnormal Occurrences | |
| JP2018092439A5 (en) | ||
| CN106600959B (en) | Traffic congestion index prediction method | |
| CN115358651A (en) | Method, system and computer readable storage medium for automatic replenishment of retail store | |
| CN109583729B (en) | Data processing method and device for platform online model | |
| CN115375205B (en) | Method, device and equipment for determining water user portrait | |
| CN112488418B (en) | Full topology load prediction method and device and computer equipment | |
| CN112860769A (en) | Energy planning data management system | |
| JP4296026B2 (en) | Product demand forecasting system, product sales volume adjustment system | |
| Hodge et al. | Examining information entropy approaches as wind power forecasting performance metrics | |
| CN114037138A (en) | Subway short-time arrival passenger flow prediction system based on double-layer decomposition and deep learning and implementation method | |
| US20210248481A1 (en) | Data Processing System and Data Processing Method | |
| CN113962504A (en) | Power distribution network planning scheme cost-benefit ratio calculation method | |
| CN109840536A (en) | A kind of power grid power supply reliability horizontal clustering method and system | |
| CN112465266A (en) | Bus load prediction accuracy analysis method and device and computer equipment | |
| CN116258280A (en) | Short-term load prediction method based on time sequence clustering | |
| JP2021128478A5 (en) | ||
| CN114841590A (en) | Supply chain exception handling method, device, equipment, storage medium and program product | |
| CN111199419B (en) | Stock abnormal transaction identification method and system | |
| CN114418450A (en) | Data processing method and device | |
| CN113743994A (en) | Provider's season-busy prediction method, system, equipment and storage medium |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Zhiyong Inventor after: Liang Zhencheng Inventor after: Zhou Xin Inventor after: Wang Ziqiang Inventor after: Wang Wei Inventor before: Li Zhiyong Inventor before: Liang Zhencheng Inventor before: Zhou Xin Inventor before: Wang Ziqiang Inventor before: Wang Wei |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |