CN108335014B - Load analysis method, device, storage medium and processor - Google Patents
Load analysis method, device, storage medium and processor Download PDFInfo
- Publication number
- CN108335014B CN108335014B CN201711484711.0A CN201711484711A CN108335014B CN 108335014 B CN108335014 B CN 108335014B CN 201711484711 A CN201711484711 A CN 201711484711A CN 108335014 B CN108335014 B CN 108335014B
- Authority
- CN
- China
- Prior art keywords
- load
- target object
- predetermined
- information
- data
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 127
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000010801 machine learning Methods 0.000 claims abstract description 48
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 22
- 230000005611 electricity Effects 0.000 description 8
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process 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
- G06Q10/06—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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a load analysis method, a load analysis device, a storage medium and a processor. Wherein, the method comprises the following steps: acquiring load information of a target object; acquiring associated information corresponding to the load information, wherein the associated information is information capable of influencing the load; the method comprises the following steps of training a plurality of groups of data to be analyzed through machine learning to obtain a predetermined analysis model, wherein the predetermined analysis model is a model which is trained through machine learning to obtain a plurality of groups of data to be analyzed and is used for representing the corresponding relation between load information and associated information, and each group of data in the plurality of groups of data to be analyzed comprises: the load information of the target object and the associated information corresponding to the load information. The invention solves the technical problem that the prior art can not accurately analyze the line according to the factors influencing the line load.
Description
Technical Field
The invention relates to the field of electric power, in particular to a load analysis method, a load analysis device, a storage medium and a processor.
Background
The line load management of a 10kV cable (hereinafter referred to as a cable) is an important work for the distribution network management of a power supply company. The determination of rated current of a cable line (hereinafter referred to as a line) and the prediction of line load cannot be effectively solved by using a traditional calculation analysis method.
To improve the reliability of the power supply, the power company requires the line to operate at rated current, and for a two-way power supply line, the line is required to satisfy N-1(N for 1, power is supplied from multiple power sources, and one backup power source is prepared). This requires the operating unit to keep track of the line load. Since the load is a variable, the operating unit generally selects the annual maximum load of the line for analysis. The maximum load is generally not a continuous load state of a line and often only occurs for a short time, so that the cable load rate cannot be accurately described by comparing the short-time peak load of the cable with the rated current.
The line load prediction work is mainly carried out in a manual mode, the information amount which can be processed in the manual mode is extremely limited, and the data analysis capability is low. The line load is dynamic information, the size of the dynamic information depends on the actual electricity consumption condition of users carried by the line, and the electricity consumption condition is related to a plurality of factors including regional weather conditions, economic development conditions, industry development conditions, resident living standard conditions and the like. And the factors have no simple corresponding relation, thereby bringing practical difficulty to the prediction work.
Aiming at the problem that the prior art can not accurately analyze the line according to the factors influencing the line load, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a load analysis method, a load analysis device, a storage medium and a processor, which at least solve the technical problem that the prior art cannot accurately analyze a line according to factors influencing the load of the line.
According to an aspect of an embodiment of the present invention, there is provided a load analysis method including: acquiring load information of a target object; acquiring associated information corresponding to the load information, wherein the associated information is information capable of influencing the load; a predetermined analysis model trained through machine learning by using a plurality of sets of data to be analyzed, wherein the predetermined analysis model is a model trained through machine learning by using the plurality of sets of data to be analyzed and used for representing the corresponding relationship between the load information and the associated information, and each set of data in the plurality of sets of data to be analyzed includes: load information of a target object and associated information corresponding to the load information; analyzing the target object according to the predetermined analysis model.
Further, the acquiring of the load information of the target object includes: acquiring load data of the target object in a preset time period; and determining the load rate of the target object according to the load data, wherein the load rate is the ratio of the maximum load of the target object within a preset time period and with the duration higher than a preset time threshold to the power utilization capacity of the target object.
Further, the obtaining of the load information of the target object includes at least one of: acquiring the average load of the target object in a preset time period; acquiring the maximum load of the target object in a preset time period; acquiring the number of times that the load of the target object exceeds a preset threshold value in a preset time period, wherein the preset threshold value is determined according to the maximum load; acquiring the duration of the load of the target object exceeding the preset threshold value and the duration of the maximum load within a preset time range; acquiring the generation time when the load of the target object exceeds a preset threshold value in a preset time range and the generation time of the maximum load; the average load within a predetermined time range before the load to the target object exceeds a predetermined threshold and a predetermined time before the maximum load is generated is obtained.
Further, the predetermined analysis model trained through machine learning using the plurality of sets of data to be analyzed includes at least one of: a predetermined region analysis model trained by machine learning using a plurality of sets of data to be analyzed, wherein the predetermined region analysis model is a model representing a correspondence between the load information and a regional economic indicator, and the association information includes: the regional economic indicators; a predetermined industry analysis model trained by machine learning using a plurality of sets of data to be analyzed, wherein the predetermined industry analysis model is a model representing a correspondence between the load information and an industry economic indicator, and the association information includes: the industry economic indicator; a predetermined capacity analysis model trained through machine learning by using a plurality of sets of data to be analyzed, wherein the predetermined capacity analysis model is a model representing a correspondence between the load information and power connection capacity, and the association information includes: the power connection capacity; a predetermined weather analysis model trained through machine learning by using a plurality of sets of data to be analyzed, wherein the predetermined weather analysis model is a model representing a correspondence between the load information and weather indicators, and the association information includes: the weather indicator.
According to another aspect of the present invention, an embodiment of the present invention further provides a storage medium, where the storage medium includes a stored program, and when the program runs, the apparatus on which the storage medium is located is controlled to execute the load analysis method described above.
According to another aspect of the present invention, an embodiment of the present invention further provides a processor, where the processor is configured to execute a program, where the program executes the load analysis method described above.
According to another aspect of the embodiments of the present invention, there is also provided a load analysis apparatus including: a first acquisition unit configured to acquire load information of a target object; a second obtaining unit, configured to obtain associated information corresponding to the load information, where the associated information is information that can affect the load; a training unit, configured to use a plurality of sets of data to be analyzed to obtain a predetermined analysis model through machine learning, where the predetermined analysis model is a model that is obtained through machine learning and is used to represent a correspondence between the load information and the associated information, and each set of data in the plurality of sets of data to be analyzed includes: load information of a target object and associated information corresponding to the load information; an analyzing unit for analyzing the target object according to the predetermined analysis model.
Further, the first acquisition unit includes: the first acquisition module is used for acquiring load data of the target object within a preset time period; the determining unit is used for determining the load rate of the target object according to the load data, wherein the load rate is the ratio of the maximum load of the target object within a preset time period and with the duration higher than a preset time threshold value to the power utilization capacity of the target object.
Further, the first obtaining unit includes at least one of: the first acquisition module is used for acquiring the average load of the target object in a preset time period; the second acquisition module is used for acquiring the maximum load of the target object within a preset time period; a third obtaining module, configured to obtain the number of times that a load of the target object exceeds a predetermined threshold in a predetermined time period, where the predetermined threshold is determined according to the maximum load; a fourth obtaining module, configured to obtain a duration that a load of the target object exceeds the predetermined threshold within a predetermined time range, and a duration of the maximum load; a fifth obtaining module, configured to obtain a generation time when a load of the target object exceeds a predetermined threshold within a predetermined time range, and a generation time of a maximum load; and the sixth acquisition module is used for acquiring the average load of the target object within a preset time range before the load exceeds a preset threshold and before the maximum load is generated at a preset moment.
Further, the training unit comprises at least one of: a first training module, configured to use multiple sets of data to be analyzed to train a predetermined regional analysis model through machine learning, where the predetermined regional analysis model is a model representing a correspondence between the load information and a regional economic indicator, and the association information includes: the regional economic indicators; a second training module, configured to use a plurality of sets of data to be analyzed to obtain a predetermined industry analysis model through machine learning, where the predetermined industry analysis model is a model representing a correspondence between the load information and an industry economic indicator, and the association information includes: the industry economic indicator; a third training module, configured to use a predetermined capacity analysis model trained through machine learning by using multiple sets of data to be analyzed, where the predetermined capacity analysis model is a model representing a correspondence between the load information and power connection capacity, and the association information includes: the power connection capacity; a fourth training module, configured to use multiple sets of data to be analyzed to train a predetermined weather analysis model through machine learning, where the predetermined weather analysis model is a model representing a correspondence between the load information and a weather indicator, and the association information includes: the weather indicator.
In the embodiment of the invention, the load information of a plurality of target objects and the associated information which is corresponding to each target object and can affect the load of the target object are obtained, then the plurality of load information and the associated information corresponding to each load information are trained in a machine learning mode to obtain the predetermined analysis model which can represent the association relation between the load information and the associated information, and then the analysis is carried out according to the predetermined analysis model, so that the load information of the target object can be accurately determined according to the associated information of the target object, and the technical problem that the line cannot be accurately analyzed according to the line load factor which is affected in the prior art is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a method of load analysis according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data source according to an embodiment of the invention;
fig. 3 is a schematic diagram of a load analysis apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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 only a part of the embodiments of the present invention, and not all of the embodiments. 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 should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In accordance with an embodiment of the present invention, there is provided an embodiment of a load analysis method, it should be noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flow chart of a load analysis method according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S102, acquiring load information of a target object;
step S104, acquiring associated information corresponding to the load information, wherein the associated information is information capable of influencing the load;
step S106, using a plurality of groups of data to be analyzed to obtain a predetermined analysis model through machine learning, wherein the predetermined analysis model is a model which is obtained through machine learning and is used for representing the corresponding relation between the load information and the associated information, and each group of data in the plurality of groups of data to be analyzed comprises: load information of the target object and associated information corresponding to the load information;
step S108, analyzing the target object according to a predetermined analysis model.
Through the steps, the load information of a plurality of target objects and the associated information which is corresponding to each target object and can affect the load of the target object are obtained, then the plurality of load information and the associated information which is corresponding to each load information are trained in a machine learning mode to obtain a preset analysis model which can represent the association relation between the load information and the associated information, and then analysis is carried out according to the preset analysis model, so that the load information of the target object can be accurately determined according to the associated information of the target object, and the technical problem that the line cannot be accurately analyzed according to the line load factor which is affected in the prior art is solved.
Optionally, the multiple sets of data to be analyzed for performing machine learning may be multiple pieces of historical data of the target object, for example, multiple pieces of load information of the target object in different time periods, and associated information corresponding to each piece of load information; the data may also be real-time data of a plurality of target objects, for example, current load information of the plurality of target objects, and associated information corresponding to each target object.
In the step S108, analyzing the target object according to a predetermined analysis model may include: and predicting the association information of the target object, and then predicting the load information of the target object through a predetermined analysis model according to the predicted association information.
As an alternative embodiment, the obtaining the load information of the target object includes: acquiring load data of a target object in a preset time period; and determining the load rate of the target object according to the load data, wherein the load rate is the ratio of the maximum load of the target object within a preset time period and with the duration higher than a preset time threshold value to the electricity utilization capacity of the target object.
By adopting the embodiment of the invention, the load data of the target object in the preset time period is collected, and the load rate of the target object is determined according to the load data, so that the load condition of the target object can be visually determined according to the load rate.
Optionally, the acquiring the load data of the target object in the predetermined time period includes acquiring a maximum load of the target object, where the load of the target object is higher than a predetermined time threshold, and an electricity capacity of the target object, and then determining a load rate of the target object according to the acquired load data.
Optionally, a load rate model trained through machine learning using multiple sets of data, wherein the load rate model is trained through machine learning using multiple sets of data, and each set of data in the multiple sets of data includes: the load rate of the target object and the associated information corresponding to the target object.
As an alternative embodiment, the obtaining of the load information of the target object includes at least one of: acquiring the average load of a target object in a preset time period; acquiring the maximum load of a target object in a preset time period; acquiring the times that the load of a target object exceeds a preset threshold value in a preset time period, wherein the preset threshold value is determined according to the maximum load; acquiring the duration that the load of a target object exceeds a preset threshold value in a preset time range and the duration of the maximum load; acquiring the generation time when the load of the target object exceeds a preset threshold value within a preset time range and the generation time of the maximum load; an average load at a predetermined time before a load to the target object exceeds a predetermined threshold and before a maximum load is generated within a predetermined time is acquired.
By adopting the embodiment of the invention, the average load, the maximum load and the times that the load of the target object exceeds the preset threshold value in the preset time period are obtained; a duration of time that the load of the target object exceeds a predetermined threshold, and a duration of time of maximum load; a generation time when the load of the target object exceeds a predetermined threshold value, and a generation time of a maximum load; the load information of the target object is the average load of the target object before the load exceeds a preset threshold value and the average load at a preset time before the maximum load is generated, and the load information of various types is determined according to the load information of various types, so that the predetermined analysis model can support the load information of various types, and the load information meeting the requirements of users can be accurately obtained according to the related information.
As an alternative embodiment, the predetermined analysis model trained by machine learning using a plurality of sets of data to be analyzed includes at least one of: the method comprises the following steps of training a preset region analysis model by using a plurality of groups of data to be analyzed through machine learning, wherein the preset region analysis model is a model for expressing the corresponding relation between load information and regional economic indexes, and associated information comprises the following steps: regional economic indicators; the method comprises the following steps of training a preset industry analysis model by using a plurality of groups of data to be analyzed through machine learning, wherein the preset industry analysis model is a model representing the corresponding relation between load information and industry economic indicators, and associated information comprises the following steps: industrial economic indicators; the method comprises the following steps of training a preset capacity analysis model by using a plurality of groups of data to be analyzed through machine learning, wherein the preset capacity analysis model is a model representing the corresponding relation between load information and power connection capacity, and association information comprises the following steps: connecting the power capacity; the method comprises the following steps of training a preset weather analysis model by using a plurality of groups of data to be analyzed through machine learning, wherein the preset weather analysis model is a model representing the corresponding relation between load information and weather indexes, and association information comprises the following steps: a weather indicator.
With the above embodiment of the present invention, the associated information includes: regional economic indicator, trade economic indicator, connect electric capacity, weather index, the predetermined analysis model who trains out through the mode of machine learning includes: the system comprises a predetermined area analysis model, a predetermined industry analysis model, a predetermined capacity analysis model and a predetermined weather analysis model, so that the predetermined analysis model can establish the corresponding relation between the load information and the associated information of various types, the predetermined analysis model can support the associated information of various types, the application range of the predetermined analysis model is strengthened, and the predetermined analysis model can determine the corresponding load information according to the associated information of various types.
The invention also provides a preferred embodiment which provides a method for accurately carrying out the load analysis of the cable line and improving the economic operation level of the line.
According to the technical scheme provided by the invention, the idea and the method of big data are adopted to analyze all load data of the cable line, the actual load condition capable of reflecting the operation condition of the cable is obtained, the load is more accurately predicted on the basis of comprehensively considering the influence of various factors on the load, and finally the advanced load management of the cable line is realized.
According to yet another embodiment of the present invention, there is also provided a storage medium including a stored program, wherein the program performs any one of the methods described above when executed.
According to yet another embodiment of the present invention, there is also provided a processor for executing a program, wherein the program executes to perform any one of the methods described above.
Fig. 2 is a schematic diagram of a data source according to an embodiment of the present invention, as shown in fig. 2, load real-time data may be obtained from the main network automation system and the distribution automation system, and power grid related information, weather information, and economic information may be obtained from the marketing system and the PMS system, where the related information includes the power grid related information and other related information.
The technical scheme provided by the invention can be used for preprocessing according to the real-time load data, and the specific scheme is as follows:
optionally, with the 10kV feeder of the substation as a unit, the load (load real-time data) of one year is analyzed, and the following information is calculated: average load of line, maximum load of line, number of times line exceeds maximum load by 95%, 90% and 80% throughout the year, duration of each time, time of occurrence of each time, average load of first half hour of each time.
Optionally, the associated 10kV feeder lines may be subjected to combination calculation, and the summation calculation is performed on the dual-radio network and the single-ring network, so as to calculate the load condition of N-1(N is supplied for 1, a plurality of power supplies are used for supplying power, and a standby power supply is prepared); and summing the double-ring network, calculating the load condition of N-2(N is used for 1 standby, a plurality of power supplies are used for supplying power, and 2 standby power supplies are prepared), and calculating the load condition of N-1(N is used for 1 standby, a plurality of power supplies are used for supplying power, and one standby power supply is prepared) by combining the load condition of each section and considering the power supply mode of the ring network.
Optionally, the ring network switch (including the feeder switch of the switching station) is used as a unit, the load of the ring network switch in one year is analyzed, and the following information is calculated: average load of the segmented lines, maximum load duration of the segmented lines exceeding 20 minutes, and maximum load duration of 10kV users (including public distribution transformers, the same below) exceeding 20 minutes.
Optionally, the 10kV high-voltage user is taken as a unit, the historical load condition of the user is analyzed, and a corresponding relation between time and load rate is obtained from the initial production stage to the normal operation time, load rate change and the like.
According to the technical scheme provided by the invention, after the pretreatment of the real-time load data is finished, the relevant information data of the power grid can be processed, and the specific scheme is as follows:
alternatively, on a commercial-through basis, a typical load rate (ratio of maximum load to customer capacity in a year, with a maximum load duration exceeding 20 minutes) is calculated for each 10kV customer of the line.
Alternatively, by taking a line as a unit, the access capacity situation of a business expansion project (business expansion project) and a technical improvement project (technical improvement project) plan can be taken as a condition, and the typical load rate analyzed by big data is combined to deduce the situation that the load of the line is influenced by the project and the time change situation.
Alternatively, the load rate conditions of different areas under different power utilization categories, industry categories, different development stages and different time dimensions can be calculated.
The technical scheme provided by the invention can process other related data after finishing the preprocessing of the real-time load data, and the specific scheme is as follows:
optionally, the related information of the regional weather can be analyzed, and the corresponding relation between the regional weather and the load of each point and the load of each type can be analyzed.
Optionally, the regional economic information may be analyzed to correspond to the load of each point and various load conditions.
Optionally, each point load is used for performing predictive analysis on the existing power grid load, and each type of load is used for guiding a newly-accessed load to perform predictive analysis.
Optionally, since the load is a variable quantity, the idea of big data full sampling needs to be adopted to perform full sampling on each load point, and the real load condition of the line can be obtained by performing data processing and analysis on all samples.
Optionally, since the load is affected by various factors, the idea of large data diversity needs to be adopted to associate the relevant information, including regional economic indicators, industrial economic indicators, power connection capacity, weather indicators, and the like, with the load to obtain the correlations between the load and the relevant information, and the load prediction analysis is performed according to the correlations. Load prediction for new access (handover) needs to be performed based on big data analysis of existing loads.
According to the embodiment of the invention, by carrying out big data analysis on the load, two changes of load analysis can be realized, namely, the change of taking the maximum load as a reference and taking the comprehensive load as a reference; and secondly, the artificial experience type load prediction is changed into comprehensive prediction based on big data. The two changes realize objective judgment and accurate prediction of the whole load condition of the line.
According to the embodiment of the invention, on the basis of realizing objective judgment on the load, the improvement can be brought from the following three aspects: firstly, the power grid transformation management level is improved. Because the comprehensive load of the line replaces the maximum load, under the condition that the operation of the line is not influenced, the number of heavily overloaded lines is reduced to some extent, and the lines can not be subjected to branch-down path transformation, so that the investment of cable engineering brought about by the method is greatly reduced, for example, the Fanzhuang company can reduce the investment by 1000 ten thousand every year, and the reduced investment of the Beijing company can be more considerable. And secondly, the business expansion level is improved.
Due to the fact that the current load condition and the load prediction are accurate, business expansion scheme compilation personnel can accurately formulate a business expansion installation scheme, the problems that near electricity and far electricity supply or overload electricity connection of a user are caused due to error control of the load are avoided, and the later-stage line operation is guaranteed. And thirdly, improving the planning level. The planning personnel can further analyze the regional main distribution network on the basis of mastering accurate power grid load and load prediction, and compile a more effective planning development scheme, so that power grid construction can more accurately meet power grid development, and efficient utilization of funds is realized.
According to an embodiment of the present invention, there is also provided an embodiment of a load analysis apparatus, where the load analysis apparatus may be used to execute a load analysis method in the embodiment of the present invention, and the load analysis method in the embodiment of the present invention may be executed in the load analysis apparatus.
Fig. 3 is a schematic diagram of a load analysis apparatus according to an embodiment of the present invention, as shown in fig. 3, the apparatus may include: a first acquisition unit 30 for acquiring load information of a target object; a second obtaining unit 32, configured to obtain associated information corresponding to the load information, where the associated information is information that can affect the load; a training unit 34, configured to use a plurality of sets of data to be analyzed to obtain a predetermined analysis model through machine learning, where the predetermined analysis model is a model that is obtained through machine learning and is used to represent a corresponding relationship between load information and associated information, and each set of data in the plurality of sets of data to be analyzed includes: load information of the target object and associated information corresponding to the load information; an analyzing unit 36 for analyzing the target object according to a predetermined analysis model.
It should be noted that the first obtaining unit 30 in this embodiment may be configured to execute step S102 in this embodiment, the second obtaining unit 32 in this embodiment may be configured to execute step S104 in this embodiment, the training unit 34 in this embodiment may be configured to execute step S106 in this embodiment, and the analyzing unit 36 in this embodiment may be configured to execute step S108 in this embodiment. The modules are the same as the corresponding steps in the realized examples and application scenarios, but are not limited to the disclosure of the above embodiments.
According to the embodiment of the invention, the load information of a plurality of target objects and the associated information which is corresponding to each target object and can affect the load of the target object are obtained, then the plurality of load information and the associated information corresponding to each load information are trained in a machine learning mode to obtain the predetermined analysis model which can represent the association relation between the load information and the associated information, and then the analysis is carried out according to the predetermined analysis model, so that the load information of the target object can be accurately determined according to the associated information of the target object, and the technical problem that the line cannot be accurately analyzed according to the line load factor which is affected in the prior art is solved.
As an alternative embodiment, the first obtaining unit includes: the first acquisition module is used for acquiring load data of a target object in a preset time period; the determining unit is used for determining the load rate of the target object according to the load data, wherein the load rate is the ratio of the maximum load of the target object within a preset time period and with the duration higher than a preset time threshold to the electricity utilization capacity of the target object.
As an alternative embodiment, the first obtaining unit includes at least one of: the first acquisition module is used for acquiring the average load of the target object in a preset time period; the second acquisition module is used for acquiring the maximum load of the target object within a preset time period; a third obtaining module, configured to obtain the number of times that a load of the target object exceeds a predetermined threshold in a predetermined time period, where the predetermined threshold is determined according to the maximum load; a fourth obtaining module, configured to obtain a duration that a load of the target object exceeds the predetermined threshold within a predetermined time range, and a duration of the maximum load; a fifth obtaining module, configured to obtain a generation time when a load of the target object exceeds a predetermined threshold within a predetermined time range, and a generation time of a maximum load; and the sixth acquisition module is used for acquiring the average load of the target object within a preset time range before the load exceeds a preset threshold and before the maximum load is generated at a preset moment.
As an alternative embodiment, the training unit comprises at least one of: the system comprises a first training module, a second training module and a third training module, wherein the first training module is used for using a plurality of groups of data to be analyzed to train a predetermined region analysis model through machine learning, the predetermined region analysis model is a model representing the corresponding relation between load information and regional economic indexes, and the associated information comprises: regional economic indicators; the second training module is used for using a plurality of groups of data to be analyzed to train a predetermined industry analysis model through machine learning, wherein the predetermined industry analysis model is a model representing the corresponding relation between the load information and the industry economic indicators, and the associated information comprises: industrial economic indicators; the third training module is used for using a plurality of groups of data to be analyzed to train a predetermined capacity analysis model through machine learning, wherein the predetermined capacity analysis model is a model representing the corresponding relation between the load information and the power connection capacity, and the association information comprises: connecting the power capacity; the fourth training module is used for using a plurality of groups of data to be analyzed to train a preset weather analysis model through machine learning, wherein the preset weather analysis model is a model representing the corresponding relation between the load information and the weather indexes, and the association information comprises: a weather indicator.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit 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 invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (8)
1. A method of load analysis, comprising:
acquiring load information of a target object;
acquiring associated information corresponding to the load information, wherein the associated information is information capable of influencing the load;
a predetermined analysis model trained through machine learning by using a plurality of sets of data to be analyzed, wherein the predetermined analysis model is a model trained through machine learning by using the plurality of sets of data to be analyzed and used for representing the corresponding relationship between the load information and the associated information, and each set of data in the plurality of sets of data to be analyzed includes: load information of a target object and associated information corresponding to the load information;
analyzing the target object according to the predetermined analysis model;
wherein the plurality of sets of data to be analyzed includes: real-time data of a plurality of target objects;
wherein, acquiring the load information of the target object comprises:
acquiring load data of the target object in a preset time period;
and determining the load rate of the target object according to the load data, wherein the load rate is the ratio of the maximum load of the target object within a preset time period and with the duration higher than a preset time threshold to the power utilization capacity of the target object.
2. The method of claim 1, wherein obtaining load information of the target object comprises at least one of:
acquiring the average load of the target object in a preset time period;
acquiring the maximum load of the target object in a preset time period;
acquiring the number of times that the load of the target object exceeds a preset threshold value in a preset time period, wherein the preset threshold value is determined according to the maximum load;
acquiring the duration of the load of the target object exceeding the preset threshold value and the duration of the maximum load within a preset time range;
acquiring the generation time when the load of the target object exceeds a preset threshold value in a preset time range and the generation time of the maximum load;
the average load within a predetermined time range before the load to the target object exceeds a predetermined threshold and a predetermined time before the maximum load is generated is obtained.
3. The method of claim 1, wherein the predetermined analysis model trained by machine learning using the plurality of sets of data to be analyzed comprises at least one of:
a predetermined region analysis model trained by machine learning using a plurality of sets of data to be analyzed, wherein the predetermined region analysis model is a model representing a correspondence between the load information and a regional economic indicator, and the association information includes: the regional economic indicators;
a predetermined industry analysis model trained by machine learning using a plurality of sets of data to be analyzed, wherein the predetermined industry analysis model is a model representing a correspondence between the load information and an industry economic indicator, and the association information includes: the industry economic indicator;
a predetermined capacity analysis model trained through machine learning by using a plurality of sets of data to be analyzed, wherein the predetermined capacity analysis model is a model representing a correspondence between the load information and power connection capacity, and the association information includes: the power connection capacity;
a predetermined weather analysis model trained through machine learning by using a plurality of sets of data to be analyzed, wherein the predetermined weather analysis model is a model representing a correspondence between the load information and weather indicators, and the association information includes: the weather indicator.
4. A load analysis device, comprising:
a first acquisition unit configured to acquire load information of a target object;
a second obtaining unit, configured to obtain associated information corresponding to the load information, where the associated information is information that can affect the load;
a training unit, configured to use a plurality of sets of data to be analyzed to obtain a predetermined analysis model through machine learning, where the predetermined analysis model is a model that is obtained through machine learning and is used to represent a correspondence between the load information and the associated information, and each set of data in the plurality of sets of data to be analyzed includes: load information of a target object and associated information corresponding to the load information;
an analysis unit for analyzing the target object according to the predetermined analysis model;
wherein the plurality of sets of data to be analyzed includes: real-time data of a plurality of target objects;
wherein the first acquisition unit includes:
the first acquisition module is used for acquiring load data of the target object within a preset time period;
the determining unit is used for determining the load rate of the target object according to the load data, wherein the load rate is the ratio of the maximum load of the target object within a preset time period and with the duration higher than a preset time threshold value to the power utilization capacity of the target object.
5. The apparatus of claim 4, wherein the first obtaining unit comprises at least one of:
the first acquisition module is used for acquiring the average load of the target object in a preset time period;
the second acquisition module is used for acquiring the maximum load of the target object within a preset time period;
a third obtaining module, configured to obtain the number of times that a load of the target object exceeds a predetermined threshold in a predetermined time period, where the predetermined threshold is determined according to the maximum load;
a fourth obtaining module, configured to obtain a duration that a load of the target object exceeds the predetermined threshold within a predetermined time range, and a duration of the maximum load;
a fifth obtaining module, configured to obtain a generation time when a load of the target object exceeds a predetermined threshold within a predetermined time range, and a generation time of a maximum load;
and the sixth acquisition module is used for acquiring the average load of the target object within a preset time range before the load exceeds a preset threshold and before the maximum load is generated at a preset moment.
6. The apparatus of claim 4, wherein the training unit comprises at least one of:
a first training module, configured to use multiple sets of data to be analyzed to train a predetermined regional analysis model through machine learning, where the predetermined regional analysis model is a model representing a correspondence between the load information and a regional economic indicator, and the association information includes: the regional economic indicators;
a second training module, configured to use a plurality of sets of data to be analyzed to obtain a predetermined industry analysis model through machine learning, where the predetermined industry analysis model is a model representing a correspondence between the load information and an industry economic indicator, and the association information includes: the industry economic indicator;
a third training module, configured to use a predetermined capacity analysis model trained through machine learning by using multiple sets of data to be analyzed, where the predetermined capacity analysis model is a model representing a correspondence between the load information and power connection capacity, and the association information includes: the power connection capacity;
a fourth training module, configured to use multiple sets of data to be analyzed to train a predetermined weather analysis model through machine learning, where the predetermined weather analysis model is a model representing a correspondence between the load information and a weather indicator, and the association information includes: the weather indicator.
7. A storage medium comprising a stored program, wherein the program executes the load analysis method according to any one of claims 1 to 3.
8. A processor configured to run a program, wherein the program is configured to perform the load analysis method according to any one of claims 1 to 3 when the program is run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711484711.0A CN108335014B (en) | 2017-12-29 | 2017-12-29 | Load analysis method, device, storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711484711.0A CN108335014B (en) | 2017-12-29 | 2017-12-29 | Load analysis method, device, storage medium and processor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108335014A CN108335014A (en) | 2018-07-27 |
| CN108335014B true CN108335014B (en) | 2022-02-08 |
Family
ID=62924186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711484711.0A Active CN108335014B (en) | 2017-12-29 | 2017-12-29 | Load analysis method, device, storage medium and processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108335014B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112614006A (en) * | 2020-11-30 | 2021-04-06 | 国网北京市电力公司 | Load prediction method, device, computer readable storage medium and processor |
| CN115134767B (en) * | 2021-03-11 | 2024-02-09 | 上海大唐移动通信设备有限公司 | Method, device and storage medium for improving performance of signaling soft acquisition equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
| CN106529747A (en) * | 2017-01-04 | 2017-03-22 | 成都四方伟业软件股份有限公司 | Power load predicting method and system based on large data |
| CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学（保定） | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
| CN106846165A (en) * | 2016-12-02 | 2017-06-13 | 云南电网有限责任公司玉溪供电局 | Big industrial customer Methods of electric load forecasting under power market transaction environment |
| CN106997495A (en) * | 2017-04-13 | 2017-08-01 | 云南电网有限责任公司电力科学研究院 | A kind of Methods of electric load forecasting |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016069330A1 (en) * | 2014-10-26 | 2016-05-06 | Pavlovski Alexandre | Forecasting net load in a distributed utility grid |
-
2017
- 2017-12-29 CN CN201711484711.0A patent/CN108335014B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学（保定） | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
| CN106846165A (en) * | 2016-12-02 | 2017-06-13 | 云南电网有限责任公司玉溪供电局 | Big industrial customer Methods of electric load forecasting under power market transaction environment |
| CN106529747A (en) * | 2017-01-04 | 2017-03-22 | 成都四方伟业软件股份有限公司 | Power load predicting method and system based on large data |
| CN106997495A (en) * | 2017-04-13 | 2017-08-01 | 云南电网有限责任公司电力科学研究院 | A kind of Methods of electric load forecasting |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108335014A (en) | 2018-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105894172B (en) | Combined power failure research and judgment method based on marketing and distribution fusion | |
| CN108665186B (en) | Distribution transformer overload power failure monitoring method and device based on metering automation system | |
| CN106451761B (en) | Large-area power failure automatic monitoring and analyzing system based on dynamic data driving | |
| CN108335014B (en) | Load analysis method, device, storage medium and processor | |
| CN106327081B (en) | Distribution network project reliability benefit evaluation method based on life cycle | |
| CN108830406A (en) | A kind of main distribution based on data mining has a power failure configuration method in advance | |
| CN108898239A (en) | A kind of site selection method for distribution transformer based on data analysis | |
| CN114336690B (en) | Intelligent terminal-based three-phase imbalance management method, system and storage medium for transformer area | |
| CN108596450B (en) | Power grid risk early warning method and system | |
| Sun et al. | Relationship between the economic cost and the reliability of the electric power supply system in city: A case in Shanghai of China | |
| CN113112136A (en) | Comprehensive evaluation method and system for reliability of power distribution network | |
| CN110310048B (en) | Distribution network planning overall process evaluation method and device | |
| CN106651113A (en) | Dispatcher operation risk evaluation method based on advanced N-1 analysis | |
| CN116455078A (en) | Intelligent operation and maintenance management and control platform for power distribution network | |
| Luo et al. | Research on transmission and transformation engineering cost system based on BIM 3D modelling technology | |
| CN116128279A (en) | Method for modifying weak link of power grid | |
| CN111339664B (en) | Layer-by-layer load modeling method and system based on edge calculation | |
| CN114168662A (en) | Power distribution network problem combing and analyzing method and system based on multiple data sources | |
| CN110991825A (en) | Line loss judgment method based on big data | |
| CN113947251A (en) | Method, device, equipment and medium for predicting daily maximum load rate of transformer | |
| KR102096468B1 (en) | Active load management method | |
| CN112926777A (en) | Day-ahead load prediction method and system considering commercial building energy consumption behaviors | |
| CN111610371A (en) | Real-time calculation method for distribution room impedance | |
| Tanskanen et al. | Cost and benefit analysis for a distribution management system in electricity distribution networks | |
| CN104361422A (en) | Power consumer power quality data collection method based on economic evaluation |
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 |