CN116307215A - Load prediction method, device, equipment and storage medium of power system - Google Patents
Load prediction method, device, equipment and storage medium of power system Download PDFInfo
- Publication number
- CN116307215A CN116307215A CN202310299162.9A CN202310299162A CN116307215A CN 116307215 A CN116307215 A CN 116307215A CN 202310299162 A CN202310299162 A CN 202310299162A CN 116307215 A CN116307215 A CN 116307215A
- Authority
- CN
- China
- Prior art keywords
- prediction
- data
- historical
- index
- load
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 238000003062 neural network model Methods 0.000 claims abstract description 61
- 230000008859 change Effects 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 48
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 230000005611 electricity Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004519 manufacturing process Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 12
- 239000004973 liquid crystal related substance Substances 0.000 claims description 5
- 230000007774 longterm Effects 0.000 abstract description 9
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 210000001520 comb Anatomy 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- XOFYZVNMUHMLCC-ZPOLXVRWSA-N prednisone Chemical compound O=C1C=C[C@]2(C)[C@H]3C(=O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 XOFYZVNMUHMLCC-ZPOLXVRWSA-N 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The embodiment of the invention discloses a load prediction method, a load prediction device, load prediction equipment and a load prediction storage medium of a power system. The method comprises the following steps: determining each influence index influencing the load change of the power system, and acquiring historical index data corresponding to each influence index in a historical time period; if the historical time period meets the preset time condition, network prediction data corresponding to the historical index data are predicted based on the historical index data and the prediction neural network model, a target curve is fitted based on the historical index data and the network prediction data, and load prediction is performed on the current power system to be predicted based on a function model of the target curve. The technical scheme of the embodiment of the invention solves the problems that the existing prediction model cannot accurately predict long-term load and the training difficulty of the prediction model is high, and improves the generation efficiency of the load prediction model and the accuracy of the load prediction model.
Description
Technical Field
The present invention relates to the field of power load prediction technologies, and in particular, to a load prediction method, apparatus, device, and storage medium for a power system.
Background
The power load prediction is one of important works of the power sector, and is mainly classified into short-term load prediction and medium-term (more than 5 years) load prediction according to the prediction period. Compared with short-term load prediction, the medium-term load prediction is subject to a plurality of uncertain factors, so that the prediction difficulty is increased. And the medium-long term load prediction is an important basis for carrying out power planning, production, operation and other works. Therefore, accurate load prediction is beneficial to improving the safety and stability of power grid operation, effectively reducing the power generation cost, guaranteeing the power consumption requirement and enhancing the power supply reliability, thereby improving the economic benefit and the social benefit of the power system.
The medium-and long-term power load has close relation with various related factors such as industrial production value, agricultural production value, GDP, environment, population, average consumption level of people, industrial structure, local policy and the like, and if the factors are used as network inputs, the network structure is complex, the training time is long, and the prediction accuracy is not necessarily high. The load prediction generally adopts a neural network prediction method, but the neural network has a plurality of defects, mainly including complex structure, slow training, relatively poor processing of emergency, and random network weight determination, so that the relationship between input and output after each training is unstable, and the prediction results are different. The current prediction methods are many, but in the aspect of predicting the long-term load in the power system, the change rule of the historical load cannot be fully excavated, and the development trend of the future load cannot be accurately judged, so that the problem of low prediction precision exists.
Disclosure of Invention
The invention provides a load prediction method, device, equipment and storage medium for a power system, which are used for accurately predicting long-term load of the power system and improving the generation efficiency of a prediction model.
According to an aspect of the present invention, there is provided a load prediction method of an electric power system, including:
determining each influence index influencing the load change of the power system, and acquiring historical index data corresponding to each influence index in a historical time period;
if the historical time period meets a preset time condition, predicting network prediction data corresponding to the historical index data based on the historical index data and the prediction neural network model, wherein the load prediction neural network model is obtained by training an initial neural network model based on the historical index data and historical load data when the power system runs with the historical index data;
fitting a target curve based on the historical index data and the network prediction data, and carrying out load prediction on the current power system to be predicted based on a function model of the target curve.
According to another aspect of the present invention, there is provided a load prediction apparatus of an electric power system, including:
The historical index data acquisition module is used for determining each influence index influencing the load change of the power system and acquiring historical index data corresponding to each influence index in a historical time period;
the network prediction data determining module is used for predicting network prediction data corresponding to the historical index data based on the historical index data and the prediction neural network model if the historical time period meets a preset time condition, wherein the load prediction neural network model is obtained by training an initial neural network model based on the historical index data and the historical load data when the power system runs with the historical index data;
and the power system load prediction module is used for fitting a target curve based on the historical index data and the network prediction data and carrying out load prediction on the current power system to be predicted based on a function model of the target curve.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the load prediction method of the power system according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute a load prediction method of an electric power system according to any one of the embodiments of the present invention.
According to the technical scheme, through determining each influence index influencing the load change of the power system, historical index data corresponding to each influence index in a historical time period are obtained; if the historical time period meets the preset time condition, network prediction data corresponding to the historical index data are predicted based on the historical index data and the prediction neural network model, a target curve is fitted based on the historical index data and the network prediction data, and load prediction is performed on the current power system to be predicted based on a function model of the target curve. The technical scheme of the embodiment of the invention solves the problems that the existing prediction model cannot accurately predict long-term load and the training difficulty of the prediction model is high, and improves the generation efficiency of the load prediction model and the accuracy of the load prediction model.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a load prediction method of an electric power system according to an embodiment of the present invention;
fig. 2 is a flowchart of a load prediction method of a power system according to a second embodiment of the present invention;
fig. 3 is a flowchart of a load prediction method of an electric power system according to a third embodiment of the present invention;
FIG. 4 is a knowledge graph of the mid-to-long term power load prediction impact provided by the third embodiment of the invention;
FIG. 5 is a schematic diagram of two S-shaped curve increases provided in accordance with a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of a load prediction device of an electric power system according to a fourth embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise 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.
Example 1
Fig. 1 is a flowchart of a load prediction method of an electric power system according to an embodiment of the present invention, where the method may be performed by a load prediction device of an electric power system, the load prediction device of the electric power system may be implemented in hardware and/or software, and the load prediction device of the electric power system may be configured in a computer device. As shown in fig. 1, the method includes:
S110, determining each influence index influencing the load change of the power system, and acquiring historical index data corresponding to each influence index in a historical time period.
The impact index is understood to be some factor affecting the load change in the power system, for example, the impact index is the number of users, and if the number of users using electricity is changed, the load of the corresponding power system is changed. The historical time period may be some time period in the past, such as the past five years, or three years; the history index data refers to specific data corresponding to the influence index, for example, the influence index is the number of users, and the corresponding history index data is a specific value of the number of users in the history period.
Specifically, each influence index affecting the load change of the power system is determined, and it is understood that, as time changes, data corresponding to each influence index may also change, and data corresponding to each influence index may be recorded as historical index data in a historical time period.
In an embodiment of the present invention, the determining each impact indicator that affects the load change of the power system includes: acquiring each index to be used associated with the load change of the power system in a network database, taking each index to be used as a first entity, and taking load prediction as a second entity; determining an association relationship between the first entity and the second entity, and constructing a target knowledge graph based on the first entity, the second entity and the association relationship; and searching a first entity with the association degree with the second entity larger than a preset association degree threshold value from the target knowledge graph, taking the first entity as a target first entity, and determining an index to be used corresponding to the target first entity as the influence index.
The target knowledge graph refers to an established knowledge graph, and the knowledge graph has corresponding entities and association relations; the preset association degree threshold value refers to a preset threshold value, and is used for judging the association degree.
Specifically, the information related to the power load change can be retrieved from a network or a network database with complicated information by using methods such as crawler technology, machine learning and the like, extracted from different data structures and types of data, and further analyzed and processed to be used as an index to be used; that is, these indicators to be used are associated with power load changes. Further, each index to be used is used as a first entity, load prediction is used as a second entity, the association relation between each first entity and the second entity is analyzed in a plurality of association analysis modes, and a target knowledge graph is built based on the association relation and the first entity and the second entity. On the basis, when the influence index needs to be determined, the degree of association with each first entity and each second entity can be directly searched from the target knowledge graph, and whether the degree of association reaches a preset threshold value or not is judged; the indexes to be used corresponding to the first entity reaching the preset association degree threshold are used as the influence indexes influencing the power load change, so that a plurality of indexes with the largest association with the power load change can be determined from the indexes to be used as the influence indexes, and further, the load prediction is performed through the data corresponding to the influence indexes, and the operation complexity can be reduced.
In order to simplify the network structure and improve the prediction accuracy, firstly, all factors which possibly influence the load prediction accuracy are found, and then, main influence factors are found out from the plurality of influence factors, so that the accuracy of a load prediction result is improved.
On the basis of the above scheme, the acquiring the historical index data corresponding to each influence index in the historical time period and the historical load data when the power system runs with the historical index data include: if the influence index is a production total value index or a user quantity index, determining production total value data corresponding to the production total value index or the user quantity corresponding to the user quantity index as the history index data; if the influence index is an industrial structure index, acquiring industrial electricity data, commercial electricity data and resident electricity data of the power system, and determining historical index data based on the industrial electricity data, commercial electricity data and resident electricity data;
wherein the impact index comprises at least one of a total production value index, a user quantity index and an industrial structure index.
Specifically, if the impact index is a production total value index or a user number index, such an index belongs to an index that can be quantified, and therefore, data corresponding to the index may be directly used as history index data, that is, production total value data corresponding to the production total value index or the user number corresponding to the user number index is to be used as history index data.
If the impact index is an industrial structure index and belongs to an index which cannot be quantized, the impact index can be quantized in a corresponding quantization mode, and a specific quantization mode can be that a result value is calculated according to industrial point data, commercial structure electricity data and resident electricity data through a preset calculation formula and is used as historical index data.
And S120, if the historical time period meets a preset time condition, predicting network prediction data corresponding to the historical index data based on the historical index data and the prediction neural network model.
The load prediction neural network model is obtained by training an initial neural network model based on the historical index data and the historical load data when the power system runs with the historical index data.
Specifically, if the obtained historical index data satisfies the preset time condition, for example, the historical time period corresponding to the historical index data is 5 years, that is, the historical index data of the past 5 years is obtained, it is considered that the preset time period is satisfied. Further, the historical index data is predicted through a prediction neural network for carrying out load prediction, and corresponding network prediction data is obtained.
The prediction neural network is trained by an initial neural network model, and historical load data corresponding to the historical index data, namely, the corresponding historical load data when the power system runs with the historical index data, is obtained. Training the initial neural network model based on the historical index data and the historical load data to obtain a predicted neural network model.
On the basis of the technical scheme, the load prediction neural network model is trained by the following modes: training the initial neural network model by taking the historical index data and the historical load data as training samples, and determining an error function corresponding to the initial neural network model; determining a weight value to be adjusted and a threshold value to be adjusted of each neuron in the initial neural network based on the partial derivative of the error function, and correcting the weight and the threshold value of each neuron based on the weight to be adjusted and the threshold value to be adjusted; and if the prediction error of the corrected initial neural network model is smaller than the error threshold value, determining the corrected initial neural network model as the prediction neural network model.
Specifically, when the initial neural network model is trained, the historical index data and the historical coincidence data can be used as training samples, the initial neural network model is trained, and a corresponding error function is calculated. Further, adjusting the weight and the threshold value of each neuron along the negative direction of the partial derivative of the error function by a gradient descent method; and continuing to predict through the corrected initial neural network model, and taking the corrected initial neural network model as a predicted neural network model if the obtained prediction error is smaller than a threshold value.
In this example, if the time of the historical index data meets a preset time condition, predicting network prediction data corresponding to the historical index data based on the historical index data and the prediction neural network model includes: and taking the historical index data as an input value, inputting the input value into the prediction neural network model, and determining an output value of the prediction neural network model as network prediction data corresponding to the historical index data.
The network prediction data is equivalent to load data predicted by the prediction neural network model based on the historical index data.
Specifically, the historical index data is used as an input value and is input into a prediction neural network model, and an output value of the prediction neural network model is determined as network prediction data corresponding to the historical index data.
And S130, fitting a target curve based on the historical index data and the network prediction data, and carrying out load prediction on the current power system to be predicted based on a function model of the target curve.
Specifically, a curve can be obtained by fitting based on historical index data and network prediction data, and correction and the like are performed on the curve, so as to calculate a corresponding function model, and load prediction is performed on the current power system to be predicted through the function model, for example, the historical index data of the current power system to be predicted is obtained, and the data is substituted into a value function model, so that a corresponding load prediction value can be obtained. Because the prediction comparison of the neural network fluctuates every time, no expectation exists for the predicted trend, and the uncertainty is solved by fitting after the neural network prediction, so that the accuracy of the obtained function model on the load prediction is higher.
On the basis of the above, the fitting of the target curve based on the historical index data and the network prediction data, and the load prediction of the current power system to be predicted based on the function model of the target curve, includes: fitting the historical index data and the prediction data based on a preset function to obtain a load prediction function; and carrying out load prediction on the current power system to be predicted based on the load prediction function so as to obtain a load value of the power system to be predicted.
Wherein the preset function includes, but is not limited to, an S-shaped curve.
Specifically, fitting historical index data and prediction data based on a preset function to obtain a load prediction function; and carrying out load prediction on the current power system to be predicted based on the load prediction function so as to obtain a load value of the power system to be predicted.
According to the technical scheme, through determining each influence index influencing the load change of the power system, historical index data corresponding to each influence index in a historical time period are obtained; if the historical time period meets the preset time condition, network prediction data corresponding to the historical index data are predicted based on the historical index data and the prediction neural network model, a target curve is fitted based on the historical index data and the network prediction data, and load prediction is performed on the current power system to be predicted based on a function model of the target curve. The technical scheme of the embodiment of the invention solves the problems that the existing prediction model cannot accurately predict long-term load and the training difficulty of the prediction model is high, and improves the generation efficiency of the load prediction model and the accuracy of the load prediction model.
Example two
Fig. 2 is a flowchart of a load prediction method of a power system according to a second embodiment of the present invention, where the case where the historical time period does not satisfy the preset time condition is described in detail on the basis of the foregoing embodiment. As shown in fig. 2, the method includes:
s210, determining each influence index influencing the load change of the power system, and acquiring historical index data corresponding to each influence index in a historical time period;
and S220, if the historical time period does not meet the preset time condition, fitting a load prediction curve based on the historical index data and the historical load data.
It will be appreciated that if the historical time period does not meet the preset time condition, it is indicated that the historical index data may be data within the last 3 years, in which case the amount of data is less and insufficient to train the neural network model, so that the load prediction curve may be fitted directly from the historical index data and the historical compliance data. For example, an S-shaped curve is fitted.
And S230, carrying out load prediction on the current power system to be predicted based on a function model corresponding to the load prediction curve.
Specifically, the historical index data of the current power system to be predicted is substituted into the function model, so that the load information of the power system to be predicted can be obtained.
According to the technical scheme, each influence index influencing the load change of the power system is determined, and history index data corresponding to each influence index in a history time period is obtained; and if the historical time period does not meet the preset time condition, fitting a load prediction curve based on the historical index data and the historical load data. And carrying out load prediction on the current power system to be predicted based on the function model corresponding to the load prediction curve. When the historical time period is shorter, prediction cannot be performed through the neural network, a curve can be fitted directly through the embodiment, load is predicted through a function model of the curve, and the accuracy of load prediction is improved.
Example III
Fig. 3 is a flowchart of a load prediction method of an electric power system according to a third embodiment of the present invention, where the present embodiment is a preferred embodiment of the foregoing embodiments, and a specific implementation manner of the present embodiment may be referred to a technical solution of the present embodiment. Wherein, the technical terms identical to or corresponding to the above embodiments are not repeated herein.
The embodiment of the invention provides a load prediction method of a power system. The method comprises five parts of contents, wherein a first part finds and quantifies key factors influencing load prediction through a knowledge graph, a second part predicts the load for a long time by using a BP neural network, a third part fits a prediction result of the BP neural network by using an S-shaped curve to obtain a load prediction model, a fourth part predicts the load by using only the S-shaped curve (without the BP neural network) to obtain the load prediction model, and a fifth part combs a joint solving flow chart. As shown in fig. 3. The following describes five parts of the content, respectively.
1. The first part finds and quantifies key factors affecting load prediction through a knowledge graph.
(1) Acquiring factors related to load prediction
Knowledge is required to be obtained by constructing a knowledge graph, information related to medium-and long-term power load change is extracted from a network (internet, a knowledge network, a foreign language website) with complicated information by using methods such as crawlers, machine learning and the like, and then the information is ordered according to rules for further analysis and utilization.
(2) Drawing a knowledge graph
The knowledge graph is a semantic net built by using the concepts of the graph and the network, wherein the edges represent the relationship between the graph and the network, and the nodes point to the entity. Based on the information extracted from the step (1), based on intelligent inquiry, a knowledge graph affecting the medium-and-long-term power load prediction can be obtained by taking the power load prediction influence factor as a key word, as shown in fig. 4.
(3) Quantifying factors affecting medium-to-long term power load prediction
The patent determines three factors that affect medium-to-long term power load prediction, including GDP, population count, and industry architecture. Wherein GDP and population number can be directly input as prediction data without change, but industrial structure cannot be directly input, and conversion is required by using mathematical formula, such as formula (1)
Wherein w is 1 Representing industrial electricity, w 2 Represents commercial power consumption, w 3 Representing the electricity consumption of the residents.
2. The second part uses BP neural network to predict load for a long time
(1) Initializing. Including thresholds for connection weights of the network, given all historical load data, historical demographic data, GDP, industry agencies. The number of input, output and hidden layer neurons are determined.
(2) Solving for neuron weights and thresholds
Let the input of the ith node be x i It is added to obtain I i The output O is obtained by limiting the output to a certain range through f i ：
Where wij represents the connection weight between nodes i, j, and θi represents the threshold of neuron i.
The output of each of them is again the input to the next layer, iterating through the already designed network until the final output. O is added with k And desired output T k Performing mean square error calculation, wherein a mean square error value E is an important reference index in the neural network training process;
if E is made as small as possible, the weight and threshold of the neuron should be adjusted, and the neural network adjusts the weight and threshold of each neuron along the negative direction of the partial derivative of the error function by a gradient descent method, and the neural network is corrected according to the following formula:
Repeating the steps (4) to (6) until delta E (t) = [ E (t+1) -E (t) ]isless than or equal to s.
And carrying out medium-and-long-term power load prediction based on the prediction model to obtain a power load prediction result.
3. The third part fits the prediction result of BP neural network by using S-shaped curve
The S-shaped curve is fitted by two functions, namely a Logistic curve and a Gompertz curve, and the formulas of the two are shown as formulas (7) and (8). The growth situation of the two curves is approximately the same as that of fig. 5, but the growth of each stage of the Logistic curve is relatively uniform, the increment of the initial development stage of the Gompertz curve is smaller, the increment of the saturation stage is larger, and a curve with a relatively close situation growth is selected for adjustment when the data are fitted.
And after the prediction result of the BP neural network is obtained, correcting or fitting the prediction result by adopting an S-shaped curve. The fitting data is that the values of a, b and c in the formulas (7) and (8) are adjusted to lead the fitting result to reach the result of the formula (9)
4. The fourth part is to predict the load by using S-shaped curve only
The method is the same as in the third section except that the historical data used is different. And all results in the third part are predicted results of the BP neural network in the second part, and the third part directly uses historical data to fit an S-shaped curve to obtain predicted results.
5. Fifth part carding the combination solving flow chart
According to the method, firstly, the factors influencing the medium-long term load prediction are determined and quantified through the knowledge graph of the first part. And judging whether the collected historical data quantity meets n (n=5) years (the data quantity is too small and cannot be predicted by adopting a neural network method), if n is smaller than 5, directly fitting by using an S-shaped curve of a fourth part, and if n is larger than or equal to 5, firstly predicting by adopting a BP neural network and then fitting by using the S-shaped curve.
According to the technical scheme, through determining each influence index influencing the load change of the power system, historical index data corresponding to each influence index in a historical time period are obtained; if the historical time period meets the preset time condition, network prediction data corresponding to the historical index data are predicted based on the historical index data and the prediction neural network model, a target curve is fitted based on the historical index data and the network prediction data, and load prediction is performed on the current power system to be predicted based on a function model of the target curve. The technical scheme of the embodiment of the invention solves the problems that the existing prediction model cannot accurately predict long-term load and the training difficulty of the prediction model is high, and improves the generation efficiency of the load prediction model and the accuracy of the load prediction model.
The embodiment of the invention firstly utilizes the knowledge graph to determine the factors influencing the power load prediction, and selects the key factors influencing the load prediction from the factors. Secondly, in order to overcome the defect of BP neural network method prediction, the patent provides a load prediction method based on BP neural network and S-shaped curve fitting. Finally, the method forms a completion flow, realizes accurate prediction of the medium-long term load in the region, and can provide guidance for operation and planning of the power distribution network.
Example IV
Fig. 6 is a schematic structural diagram of a load prediction device of a power system according to a fourth embodiment of the present invention. As shown in fig. 6, the apparatus includes:
a historical index data obtaining module 410, configured to determine each impact index affecting the load change of the power system, and obtain historical index data corresponding to each impact index in a historical time period;
the network prediction data determining module 420 is configured to predict, based on the historical index data and the prediction neural network model, network prediction data corresponding to the historical index data if the historical time period meets a preset time condition, where the load prediction neural network model is obtained by training an initial neural network model based on the historical index data and historical load data when the power system runs with the historical index data;
The power system load prediction module 430 is configured to fit a target curve based on the historical index data and the network prediction data, and perform load prediction on a current power system to be predicted based on a function model of the target curve.
According to the technical scheme, through determining each influence index influencing the load change of the power system, historical index data corresponding to each influence index in a historical time period are obtained; if the historical time period meets the preset time condition, network prediction data corresponding to the historical index data are predicted based on the historical index data and the prediction neural network model, a target curve is fitted based on the historical index data and the network prediction data, and load prediction is performed on the current power system to be predicted based on a function model of the target curve. The technical scheme of the embodiment of the invention solves the problems that the existing prediction model cannot accurately predict long-term load and the training difficulty of the prediction model is high, and improves the generation efficiency of the load prediction model and the accuracy of the load prediction model.
Optionally, the historical index data obtaining module 410 includes:
the entity determining module is used for acquiring each index to be used, which is associated with the load change of the power system, in the network database, taking each index to be used as a first entity, and taking load prediction as a second entity;
The target atlas establishing module is used for determining the association relation between the first entity and the second entity and establishing a target knowledge atlas based on the first entity, the second entity and the association relation;
the influence index determining module is used for searching a first entity, the association degree of which is greater than a preset association degree threshold value, from the target knowledge graph as a target first entity, and determining an index to be used corresponding to the target first entity as the influence index.
Optionally, the historical index data obtaining module 410 includes:
the first determining module is used for determining the production total value data corresponding to the production total value index or the user quantity corresponding to the user quantity index as the historical index data if the influence index is the production total value index or the user quantity index;
the second determining module is used for acquiring industrial electricity data, commercial electricity data and resident electricity data of the electric power system if the influence index is an industrial structure index, and determining historical index data based on the industrial electricity data, the commercial electricity data and the resident electricity data;
Wherein the impact index comprises at least one of a total production value index, a user quantity index and an industrial structure index.
Optionally, the load prediction device of the power system further includes a curve load prediction module, specifically configured to:
if the historical time period does not meet the preset time condition, fitting a load prediction curve based on the historical index data and the historical load data;
and carrying out load prediction on the current power system to be predicted based on the function model corresponding to the load prediction curve.
Optionally, the load predicting neural network model is trained by:
training the initial neural network model by taking the historical index data and the historical load data as training samples, and determining an error function corresponding to the initial neural network model;
determining a weight value to be adjusted and a threshold value to be adjusted of each neuron in the initial neural network based on the partial derivative of the error function, and correcting the weight and the threshold value of each neuron based on the weight to be adjusted and the threshold value to be adjusted;
and if the prediction error of the corrected initial neural network model is smaller than the error threshold value, determining the corrected initial neural network model as the prediction neural network model.
Optionally, the network prediction data determination module 420 includes:
and the prediction module is used for taking the historical index data as an input value, inputting the input value into the prediction neural network model, and determining the output value of the prediction neural network model as network prediction data corresponding to the historical index data.
Optionally, the power system load prediction module 430 is specifically configured to:
fitting the historical index data and the prediction data based on a preset function to obtain a load prediction function, wherein the preset function comprises but is not limited to an S-shaped curve;
and carrying out load prediction on the current power system to be predicted based on the load prediction function so as to obtain a load value of the power system to be predicted.
The load prediction device of the power system provided by the embodiment of the invention can execute the load prediction method of the power system provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example five
Fig. 7 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 7, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a load prediction method of the power system.
In some embodiments, the load prediction method of the power system may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the load prediction method of the power system described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the load prediction method of the power system by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A load prediction method of an electric power system, comprising:
determining each influence index influencing the load change of the power system, and acquiring historical index data corresponding to each influence index in a historical time period;
if the historical time period meets a preset time condition, predicting network prediction data corresponding to the historical index data based on the historical index data and the prediction neural network model, wherein the load prediction neural network model is obtained by training an initial neural network model based on the historical index data and historical load data when the power system runs with the historical index data;
Fitting a target curve based on the historical index data and the network prediction data, and carrying out load prediction on the current power system to be predicted based on a function model of the target curve.
2. The method of claim 1, wherein determining each impact indicator that affects a power system load change comprises:
acquiring each index to be used associated with the load change of the power system in a network database, taking each index to be used as a first entity, and taking load prediction as a second entity;
determining an association relationship between the first entity and the second entity, and constructing a target knowledge graph based on the first entity, the second entity and the association relationship;
and searching a first entity, the association degree of which with the second entity is greater than a preset association degree threshold value, from the target knowledge graph as a target first entity, and determining an index to be used corresponding to the target first entity as the influence index.
3. The method according to claim 1, wherein the acquiring the history index data corresponding to each of the influence indexes in the history period and the history load data when the power system operates with the history index data includes:
If the influence index is a production total value index or a user quantity index, determining production total value data corresponding to the production total value index or the user quantity corresponding to the user quantity index as the history index data;
if the influence index is an industrial structure index, acquiring industrial electricity data, commercial electricity data and resident electricity data of the power system, and determining historical index data based on the industrial electricity data, commercial electricity data and resident electricity data;
wherein the impact index comprises at least one of a total production value index, a user quantity index and an industrial structure index.
4. The method as recited in claim 1, further comprising:
if the historical time period does not meet the preset time condition, fitting a load prediction curve based on the historical index data and the historical load data;
and carrying out load prediction on the current power system to be predicted based on the function model corresponding to the load prediction curve.
5. The method of claim 1, wherein the load predictive neural network model is trained by:
training the initial neural network model by taking the historical index data and the historical load data as training samples, and determining an error function corresponding to the initial neural network model;
Determining a weight value to be adjusted and a threshold value to be adjusted of each neuron in the initial neural network based on the partial derivative of the error function, and correcting the weight and the threshold value of each neuron based on the weight to be adjusted and the threshold value to be adjusted;
and if the prediction error of the corrected initial neural network model is smaller than the error threshold value, determining the corrected initial neural network model as the prediction neural network model.
6. The method according to claim 1, wherein predicting network prediction data corresponding to the historical index data based on the historical index data and the prediction neural network model if the time of the historical index data satisfies a preset time condition comprises:
and taking the historical index data as an input value, inputting the input value into the prediction neural network model, and determining an output value of the prediction neural network model as network prediction data corresponding to the historical index data.
7. The method of claim 1, wherein the fitting a target curve based on the historical index data and the network prediction data and performing load prediction on a current power system to be predicted based on a functional model of the target curve comprises:
Fitting the historical index data and the prediction data based on a preset function to obtain a load prediction function, wherein the preset function comprises but is not limited to an S-shaped curve;
and carrying out load prediction on the current power system to be predicted based on the load prediction function so as to obtain a load value of the power system to be predicted.
8. A load prediction device for an electric power system, comprising:
the historical index data acquisition module is used for determining each influence index influencing the load change of the power system and acquiring historical index data corresponding to each influence index in a historical time period;
the network prediction data determining module is used for predicting network prediction data corresponding to the historical index data based on the historical index data and the prediction neural network model if the historical time period meets a preset time condition, wherein the load prediction neural network model is obtained by training an initial neural network model based on the historical index data and the historical load data when the power system runs with the historical index data;
and the power system load prediction module is used for fitting a target curve based on the historical index data and the network prediction data and carrying out load prediction on the current power system to be predicted based on a function model of the target curve.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the load prediction method of the power system of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the load prediction method of the power system of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310299162.9A CN116307215A (en) | 2023-03-24 | 2023-03-24 | Load prediction method, device, equipment and storage medium of power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310299162.9A CN116307215A (en) | 2023-03-24 | 2023-03-24 | Load prediction method, device, equipment and storage medium of power system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116307215A true CN116307215A (en) | 2023-06-23 |
Family
ID=86799443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310299162.9A Pending CN116307215A (en) | 2023-03-24 | 2023-03-24 | Load prediction method, device, equipment and storage medium of power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307215A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116817415A (en) * | 2023-08-28 | 2023-09-29 | 国网浙江省电力有限公司宁波供电公司 | Air conditioner load management and adjustment method, computing equipment and storage medium |
| CN117216469A (en) * | 2023-09-03 | 2023-12-12 | 国网江苏省电力有限公司信息通信分公司 | Big data processing method and system for real-time monitoring and prediction of power system |
| CN117455269A (en) * | 2023-12-21 | 2024-01-26 | 国网天津市电力公司城南供电分公司 | Snowflake type power distribution network power supply safety prediction method, device, equipment and storage medium |
-
2023
- 2023-03-24 CN CN202310299162.9A patent/CN116307215A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116817415A (en) * | 2023-08-28 | 2023-09-29 | 国网浙江省电力有限公司宁波供电公司 | Air conditioner load management and adjustment method, computing equipment and storage medium |
| CN116817415B (en) * | 2023-08-28 | 2024-01-12 | 国网浙江省电力有限公司宁波供电公司 | Air conditioner load management and adjustment method, computing equipment and storage medium |
| CN117216469A (en) * | 2023-09-03 | 2023-12-12 | 国网江苏省电力有限公司信息通信分公司 | Big data processing method and system for real-time monitoring and prediction of power system |
| CN117216469B (en) * | 2023-09-03 | 2024-03-15 | 国网江苏省电力有限公司信息通信分公司 | Big data processing method and system for real-time monitoring and prediction of power system |
| CN117455269A (en) * | 2023-12-21 | 2024-01-26 | 国网天津市电力公司城南供电分公司 | Snowflake type power distribution network power supply safety prediction method, device, equipment and storage medium |
| CN117455269B (en) * | 2023-12-21 | 2024-04-16 | 国网天津市电力公司城南供电分公司 | Snowflake type power distribution network power supply safety prediction method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN117332898A (en) | New energy small time scale power time sequence rolling prediction method based on machine learning | |
| CN117332896A (en) | New energy small time scale power prediction method and system for multilayer integrated learning | |
| CN113112311B (en) | Method for training causal inference model and information prompting method and device | |
| CN116125279A (en) | Method, device, equipment and storage medium for determining battery health state | |
| CN112667394B (en) | Computer resource utilization rate optimization method | |
| CN114943384A (en) | Transformer substation load prediction method, device, equipment and storage medium | |
| CN113435653B (en) | Method and system for predicting saturated power consumption based on logistic model | |
| CN116933896B (en) | Super-parameter determination and semantic conversion method, device, equipment and medium | |
| CN115497633B (en) | Data processing method, device, equipment and storage medium | |
| CN117934137A (en) | Bad asset recovery prediction method, device and equipment based on model fusion | |
| US20230106295A1 (en) | System and method for deriving a performance metric of an artificial intelligence (ai) model | |
| CN116307159A (en) | Load prediction method and device, electronic equipment and storage medium | |
| CN116011570A (en) | XAI model consistency training method, device, equipment and storage medium | |
| CN114612784A (en) | Target detection network training method, device, equipment and storage medium | |
| CN116703109A (en) | Method, device, equipment and storage medium for selecting power distribution network project | |
| CN115983486A (en) | Wind power output prediction method and device, electronic equipment and storage medium | |
| CN116186536A (en) | Risk prediction method, risk prediction device, electronic equipment and storage medium | |
| CN114626636A (en) | Power grid load prediction method and device, modeling method, computer equipment and medium | |
| CN117556935A (en) | Time sequence prediction method, device, equipment and readable storage medium | |
| CN117634437A (en) | Method and device for describing current running state of equipment and electronic equipment | |
| CN117592510A (en) | Load prediction method and system based on safety constraint | |
| CN117455067A (en) | Electric quantity consumption prediction method and device, electronic equipment and storage medium | |
| CN116361460A (en) | Data integration method and device, storage medium, electronic equipment and product | |
| CN117907872A (en) | Battery life prediction method and device, electronic 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 |