CN116307060A - Power load prediction method, device, equipment and storage medium - Google Patents
Power load prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116307060A CN116307060A CN202211730273.2A CN202211730273A CN116307060A CN 116307060 A CN116307060 A CN 116307060A CN 202211730273 A CN202211730273 A CN 202211730273A CN 116307060 A CN116307060 A CN 116307060A
- Authority
- CN
- China
- Prior art keywords
- signal
- residual
- load prediction
- data
- component signal
- 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 52
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 35
- 238000012360 testing method Methods 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 238000002156 mixing Methods 0.000 claims description 29
- 230000004913 activation Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000306 recurrent effect Effects 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
- 238000012546 transfer 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power load prediction method, a device, equipment and a storage medium. The method comprises the following steps: acquiring historical load data of a target power line in a certain time period; decomposing the historical load data according to a set signal decomposition algorithm to obtain a group of component signals, and dividing the component signals into training component signals and test component signal data; and inputting the test component signals into a load prediction network model trained by the training component signals to obtain a load prediction result of the target power line. According to the technical scheme, historical load data of the power line are verified, the historical load data are decomposed by using a signal decomposition algorithm, a training component signal and a test component signal are obtained, the test component signal is predicted through a load prediction network model trained by the training component signal, and the power load prediction precision is improved.
Description
Technical Field
The present invention relates to the field of power grid security technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting an electric load.
Background
The accurate load prediction can economically and reasonably arrange the start and stop of the generator set in the power grid, maintain the safety and stability of the operation of the power grid, reasonably arrange the maintenance plan, ensure the normal production and life of society, effectively reduce the power generation cost, improve the economic benefit and the social benefit and make a contribution to environmental protection.
Disclosure of Invention
The invention provides a power load prediction method, a device, equipment and a storage medium, which are used for solving the problem of low power load prediction precision.
In a first aspect, an embodiment of the present invention provides a power load prediction method, including:
acquiring historical load data of a target power line in a certain time period;
decomposing the historical load data according to a set signal decomposition algorithm to obtain a group of component signals, and dividing the component signals into training component signals and test component signal data;
and inputting the test component signals into a load prediction network model trained by the training component signals to obtain a load prediction result of the target power line.
In a second aspect, an embodiment of the present invention provides an electrical load prediction apparatus, including:
the acquisition module is used for acquiring historical load data of the target power line in a certain period of time;
the signal decomposition module is used for decomposing the historical load data according to a set signal decomposition algorithm to obtain a group of component signals and dividing the component signals into training component signals and test component signal data;
and the load prediction module is used for inputting the test component signal into the load prediction network model trained by the training component signal to obtain a load prediction result of the target power line.
In a third aspect, an embodiment of the present invention provides an electronic device, 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 power load prediction method of any one of the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing computer instructions for causing a processor to execute the power load prediction method according to any one of the embodiments of the present invention.
The embodiment of the invention provides a power load prediction method, a device, equipment and a storage medium, which are used for acquiring historical load data of a target power line in a certain time period; decomposing the historical load data according to a set signal decomposition algorithm to obtain a group of component signals, and dividing the component signals into training component signals and test component signal data; and inputting the test component signals into a load prediction network model trained by the training component signals to obtain a load prediction result of the target power line. According to the technical scheme, historical load data of the power line are verified, the historical load data are decomposed by using a signal decomposition algorithm, a training component signal and a test component signal are obtained, the test component signal is predicted through a load prediction network model trained by the training component signal, and the power load prediction precision is improved.
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 flow chart of a method for predicting electrical loads according to a first embodiment of the invention;
FIG. 2 is a graph showing an example of measured load data collected by a power load prediction method according to a first embodiment of the present invention;
FIG. 3 is a diagram illustrating an exemplary residual network collected by a power load prediction method according to a first embodiment of the present invention;
FIG. 4 is a diagram illustrating an exemplary internal structure of a GRU collected by a power load prediction method according to a first embodiment of the present invention;
fig. 5 is a schematic structural diagram of a power load prediction device according to a second embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to a third 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 power load prediction method according to an embodiment of the present invention, where the method is applicable to a power load prediction situation, and the method may be performed by a power load prediction device, where the power load prediction device may be implemented in a form of hardware and/or software, and optionally, may be implemented by an electronic device as an execution terminal, where the electronic device may be a mobile terminal, a PC side, a server, or the like.
As shown in fig. 1, a power load prediction method provided by an embodiment of the present disclosure may specifically include the following steps:
s110, historical load data of the target power line in a certain period of time is obtained.
In this embodiment, the power line may refer to a line used to transfer electrical energy between a power plant, a substation, and a power consumer. The power line is an important component of the power supply system and is responsible for the task of delivering and distributing electrical energy. The electric load refers to the sum of electric power taken by electric equipment of electric energy users to an electric power system at a certain moment. There are many power lines in the power supply system, and each power line can predict the power load by adopting the method in the embodiment of the invention.
FIG. 2 is a graph showing an example of measured load data collected by a power load prediction method according to a first embodiment of the present invention; and acquiring a power line in a certain power grid as a target power line, and acquiring historical actual measurement load data of the power line in a certain time period. The obtained historical measured load data is shown in fig. 2.
S120, decomposing historical load data according to a set signal decomposition algorithm to obtain a group of component signals, and dividing the component signals into training component signals and test component signal data.
In this embodiment, the signal decomposition algorithm is set to be a fully adaptive noise set empirical mode decomposition algorithm (Complete EEMD with Adaptive Noise, CEEMDAN), also known as a fully set empirical mode decomposition algorithm. The components of the component signals (Intrinsic Mode Functions, IMF) represent frequency components in the original signal, respectively, and are arranged in order from high frequency to low frequency.
Specifically, an initial white noise signal and an original signal of history load data are acquired, wherein the standard deviation of the added white noise may be set to 0.2. The original signal is taken as the original residual component signal. And carrying out noise mixing and decomposition on the residual component signals based on the white noise signals to obtain current component signals of the original signals. The signal difference between the residual component signal and the current component signal is taken as a new residual component signal. And performing noise mixing and decomposition operation of the residual component signals in a circulating way until the residual component signals are non-decomposable signals, and summarizing each current component signal to form a group of component signals. The component signals are divided into training component signal data and test component signal data according to a set proportion.
On the basis of the optimization, the embodiment of the disclosure can decompose historical load data according to a set signal decomposition algorithm, and the method for obtaining a group of component signals is specifically optimized as follows:
a1 An initial white noise signal and an original signal of the history load data are acquired, and the original signal is taken as an initial residual component signal.
b1 Noise mixing and decomposing the residual component signal based on the white noise signal to obtain the current component signal of the original signal.
Specifically, an original white noise signal n (t) and an original signal x (t) of historical load data are obtained, the original signal is taken as an original residual component signal, the white noise n (t) is added to the original signal x (t), and the ith signal is
x i (t)＝x(t)+n i (t)
Where I is the number of white noise additions i=1, 2, …, I.
X decomposing the ith added white noise i (t) obtaining a current component signal,
c1 A signal difference between the residual component signal and the current component signal is taken as a new residual component signal.
d1 If the residual component signal is a resolvable signal, returning to re-perform the noise mixing and decomposing operations of the residual component signal; otherwise, the current component signals are summed to form a set of component signals.
Following the above description, the residual component obtained by subtracting the above-described current component signal from the original signal x (t)
r 1 (t)＝x(t)-IMF 1
If the residual component signal is a resolvable signal, a return is made to re-perform the noise mixing and decomposing operations of the residual component signal. Adding white noise n (t) to the residual component, and the residual component expression of the ith added white noise is
r i1 (t)＝r 1 (t)+n i (t)
Decompose r of ith added white noise i1 (t) obtaining IMF i1 Then
Obtaining new residual components
r 2 (t)＝r 1 (t)-IMF 2
And so on, repeatedly performing the above process until the residual component r n (t) failing to decompose. The signal x (t) is expressed as
Wherein the number of the IMFs obtained by decomposition is n.
In the technical scheme, the CEEMDAN method is used for reducing modal aliasing by adding white noise. Wherein, the surplus of CEEMDAN is not obtained according to independent decomposition after adding noise each time, but is obtained according to the surplus obtained by last decomposition, which reduces the reconstruction error after decomposition.
On the basis of the optimization, the embodiment of the disclosure can perform noise mixing and decomposition on the residual component signal based on the white noise signal, and the current component signal of the original signal is obtained by specifically optimizing the following steps:
b11 Initializing the white noise mix times.
b12 A white noise signal is mixed with the residual component signal to obtain a mixed component signal.
b13 The mixed component signal is decomposed to obtain a decomposed component signal, the white noise signal is updated, and the number of white noise mixing times is increased by 1.
b14 If the white noise mixing times are less than the set times, returning to re-execute the signal mixing operation; otherwise, summarizing the decomposed component signals to obtain the current component signal of the original signal.
Specifically, the set number of times is the set number of times that the stop condition is reached, wherein the stop condition is the number of times that the remaining component cannot be decomposed. Firstly, initializing white noise mixing times, mixing a white noise signal with a residual component signal, and obtaining a mixed component signal. The mixed component signal is decomposed to obtain a decomposed component signal, the white noise signal is updated, and the number of white noise mixing times is increased by 1. If the white noise mixing number is less than the set number, the signal mixing operation is returned to be re-performed. Otherwise, summarizing the decomposed component signals to obtain the current component signal of the original signal.
S130, inputting the test component signals into a load prediction network model trained by the training component signals, and obtaining a load prediction result of the target power line.
In this embodiment, the load prediction network model is trained using the training component signal, then the test component signal is input to the trained load prediction network model, feature extraction and association relation processing are performed, and the output load prediction data is used as the load prediction result of the target power line. The load prediction network model consists of a residual error module and a GRU module.
Wherein the load prediction network model comprises: a depth residual sub-network and a gate-controlled loop sub-network; the depth residual sub-network comprises a first residual module and a second residual module, a batch normalization layer and a RELU activation function layer are added in each residual module, and characteristic data output by the depth residual sub-network included in the load prediction network model is input into the gating circulation sub-network after flattening treatment.
Specifically, the load prediction network model comprises a depth residual sub-network and a gating circulation sub-network. The depth residual sub-network consists of two residual modules, namely a first residual module and a second residual module, and a batch normalization layer and a ReLU activation function layer are added on the basis of the traditional residual network. Fig. 3 is a diagram illustrating a residual network collected by a power load prediction method according to an embodiment of the present invention. As shown in fig. 3, x is the input of this layer residual block, also called F (x) is the residual, x is the input value, and F (x) is the output after the first layer is linearly changed and activated, which shows that in the residual network, F (x) is added to this layer input value x before activation after the second layer is linearly changed, and then the output after activation.
The first residual error module comprises a first residual error branch and a second residual error branch, and the first residual error branch is constructed with identity mapping so that the network structure of the first residual error module converges towards the direction of the identity mapping; the second residual branch is used for extracting the characteristics of the extracted output of the previous convolution layer included in the network model for the second time; and the two residual branches contained in the second residual module are used for carrying out feature refinement on the feature data output by the first residual module and outputting deep feature data with different scales.
Specifically, the first residual module is composed of two branches, namely a first residual branch and a second residual branch, and the first residual module constructs an identity mapping, so that the model structure converges towards the direction of the identity mapping. The second residual branch performs further feature extraction on the preliminary features mentioned by the previous convolution module. The second residual error module is also composed of two branches, features extracted by the first residual error module are further refined by the two branches, deep features of different scales are obtained, and feature complementation of different learning branches is achieved.
In the technical scheme, the residual error module is used for avoiding the increase of the prediction error along with the deepening of the network, and solving the problems of gradient explosion and gradient disappearance caused by the deepening of the network.
The gating circulation sub-network comprises a reset gate and an update gate, and is used for establishing an association relation between historical load data and load data in future set time; and the characteristic data input into the gating circulation sub-network are combined to establish an association relationship, load data prediction is carried out, and the output load data is used as load prediction data.
Specifically, the gating loop sub-network uses gating loop units (Gate Recurrent Unit, GRU). Fig. 4 is a diagram illustrating an example of an internal structure of a GRU collected by a power load prediction method according to an embodiment of the present invention. The reset gate and the update gate are included, r (t) and z (t) are respectively the reset gate and the update gate of the GRU in the figure, and the expressions are as follows:
r(t)＝σ(W r x(t)+U r h(t-1)+b r )
z(t)＝σ(W z x(t)+U z h(t-1)+b z )
in the formula, sigma represents a Sigmoid function, W r 、W z 、U r 、U z Weight matrix representing reset gate and update gate, b r 、b z Representing the offset vectors of the reset gate and the update gate. The value of the reset gate, after multiplication with the value of the hidden layer t-1, is activated by the activation function f together with the input x (t). Let the activated value be
The expression is as follows:
in which W is h 、U h Weight matrix representing current time, b h Representing the offset vector at the current time. The value of the update gate is divided into z (t) and 1-z (t) and then multiplied by h (t-1) and h (t-1), respectively
The final result is the output of the GRU, expressed as:
and establishing an association relation between the historical load and load data in a set time. The set time can be one day, namely, a relation between a historical load and a load from one day is established, so that load prediction of one day ahead is realized. And the characteristic data input into the gating circulation sub-network are combined to establish an association relationship, load data prediction is carried out, and the output load data is used as load prediction data.
On the basis of the optimization, the embodiment of the disclosure further comprises training the load prediction network model through the training component signals, wherein the load prediction network model comprises a target activation function and network optimization parameters after training; the test component signals are used as input data, the trained load prediction network model is subjected to feature extraction and association relation processing combined with construction, and the output load prediction data are used as load prediction results of the target power line.
Specifically, training the load prediction network model by the training component signal, wherein the prediction network model comprises a trained target activation function and network optimization parameters. And obtaining network model parameters after training. And then taking the test component signal as input data, performing feature extraction and association relation processing combined with the trained load prediction network model, and taking the output load prediction data as a load prediction result of the target power line.
According to the technical scheme, the network optimization parameters are obtained, so that the feature extraction of the load can be more accurate. The structural difference of the two residual modules and the branch difference of the same residual module can be utilized to realize feature complementation, and provide reference for capturing the time sequence features of the follow-up GRU network.
The embodiment of the disclosure provides a power load prediction method, which comprises the following steps: acquiring historical load data of a target power line in a certain time period; decomposing the historical load data according to a set signal decomposition algorithm to obtain a group of component signals, and dividing the component signals into training component signals and test component signal data; and inputting the test component signals into a load prediction network model trained by the training component signals to obtain a load prediction result of the target power line. According to the technical scheme, historical load data of the power line are verified, the historical load data are decomposed by using a signal decomposition algorithm, a training component signal and a test component signal are obtained, the test component signal is predicted through a load prediction network model trained by the training component signal, and the power load prediction precision is improved.
Example two
Fig. 5 is a schematic structural diagram of an enhanced power load prediction device according to a second embodiment of the present invention. As shown in fig. 5, the apparatus includes: the system comprises an acquisition module 210, a signal decomposition module 220 and a load prediction module 230.
An acquisition module 210, configured to acquire historical load data of a target power line in a certain period of time;
the signal decomposition module 220 is configured to decompose the historical load data according to a set signal decomposition algorithm to obtain a set of component signals, and divide the set of component signals into training component signals and test component signal data;
the load prediction module 230 is configured to input a test component signal to a load prediction network model trained by the training component signal, and obtain a load prediction result of the target power line.
According to the technical scheme provided by the embodiment of the disclosure, through verifying the historical load data of the power line, the historical load data is decomposed by using a signal decomposition algorithm to obtain the training component signal and the test component signal, the test component signal is predicted through the load prediction network model trained by the training component signal, and the power load prediction precision is improved.
Further, the power load prediction module 220 may include:
a signal acquisition unit for acquiring an initial white noise signal and an original signal of the history load data, and taking the original signal as an initial residual component signal;
a component signal decomposition unit, configured to perform noise mixing and decomposition on the remaining component signal based on the white noise signal, to obtain a current component signal of the original signal;
and the component signal calculation unit is used for taking the signal difference value between the residual component signal and the current component signal as a new residual component signal.
A component signal summarizing unit for returning to re-perform noise mixing and decomposition operations of the remaining component signals if the remaining component signals are decomposable signals; otherwise, the current component signals are summed to form a set of component signals.
Further, the component signal decomposition unit may specifically include:
initializing white noise mixing times;
mixing the white noise signal with the residual component signal to obtain a mixed component signal;
decomposing the mixed component signal to obtain a decomposed component signal, updating the white noise signal and adding 1 to the white noise mixing times;
returning to re-execute the signal mixing operation if the white noise mixing frequency is less than or equal to the set frequency; otherwise, summarizing the decomposed component signals to obtain the current component signal of the original signal.
Further, the load prediction module 230 may be specifically configured to:
the depth residual sub-network comprises a first residual module and a second residual module, wherein each residual module is added with a batch normalization layer and a RELU activation function layer,
and characteristic data output by the depth residual sub-network included in the load prediction network model is input into the gating circulation sub-network after flattening treatment.
Further, the load prediction module 230 may be specifically configured to:
the first residual error module comprises a first residual error branch and a second residual error branch, and the first residual error branch is constructed with an identity mapping so that the network structure of the first residual error module converges towards the direction of the identity mapping; the second residual branch is used for extracting the characteristics of the extracted output of the previous convolution layer included in the network model for the second time;
and the two residual branches contained in the second residual module are used for carrying out feature refinement on the feature data output by the first residual module and outputting deep feature data with different scales.
Further, the load prediction module 230 may be specifically configured to:
the gating circulation sub-network comprises a reset gate and an update gate, and is used for establishing an association relation between historical load data and load data in future set time;
and inputting the characteristic data of the gating circulation sub-network, establishing an association relation, predicting load data, and taking the output load data as load prediction data.
Further, the load prediction module 230 may be specifically configured to:
after the load prediction network model is trained through the training component signals, the load prediction network model comprises a trained target activation function and network optimization parameters;
the power load prediction device structure provided by the embodiment of the disclosure can execute the power load prediction method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
It should be noted that each unit and module included in the above apparatus are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for convenience of distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present disclosure.
Example III
Fig. 6 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the 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. 6, 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 the power load prediction method.
In some embodiments, the power load prediction method 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 RAM 13 and executed by processor 11, one or more steps of the power load prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the power load prediction method in any other suitable manner (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 method of predicting an electrical load, comprising:
acquiring historical load data of a target power line in a certain time period;
decomposing the historical load data according to a set signal decomposition algorithm to obtain a group of component signals, and dividing the component signals into training component signals and test component signal data;
and inputting the test component signals into a load prediction network model trained by the training component signals to obtain a load prediction result of the target power line.
2. The method of claim 1, wherein decomposing the historical load data according to a set signal decomposition algorithm to obtain a set of component signals comprises:
acquiring an initial white noise signal and an original signal of the historical load data, and taking the original signal as an initial residual component signal;
performing noise mixing and decomposition on the residual component signal based on the white noise signal to obtain a current component signal of the original signal;
taking the signal difference value of the residual component signal and the current component signal as a new residual component signal;
returning to re-perform noise mixing and decomposition operations of the residual component signal if the residual component signal is a decomposable signal; otherwise, the current component signals are summed to form a set of component signals.
3. The method according to claim 2, wherein said noise mixing and decomposing the residual component signal based on the white noise signal to obtain a current component signal of the original signal comprises:
initializing white noise mixing times;
mixing the white noise signal with the residual component signal to obtain a mixed component signal;
decomposing the mixed component signal to obtain a decomposed component signal, updating the white noise signal and adding 1 to the white noise mixing times;
if the white noise mixing times are smaller than the set times, returning to re-execute the signal mixing operation; otherwise, summarizing the decomposed component signals to obtain the current component signal of the original signal.
4. The method of claim 1, wherein the load prediction network model comprises: a depth residual sub-network and a gate-controlled loop sub-network;
the depth residual sub-network comprises a first residual module and a second residual module, wherein each residual module is added with a batch normalization layer and a RELU activation function layer,
and characteristic data output by the depth residual sub-network included in the load prediction network model is input into the gating circulation sub-network after flattening treatment.
5. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
the first residual error module comprises a first residual error branch and a second residual error branch, and the first residual error branch is constructed with an identity mapping so that the network structure of the first residual error module converges towards the direction of the identity mapping; the second residual branch is used for extracting the characteristics of the extracted output of the previous convolution layer included in the network model for the second time;
and the two residual branches contained in the second residual module are used for carrying out feature refinement on the feature data output by the first residual module and outputting deep feature data with different scales.
6. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
the gating circulation sub-network comprises a reset gate and an update gate, and is used for establishing an association relation between historical load data and load data in future set time;
and inputting the characteristic data of the gating circulation sub-network, establishing an association relation, predicting load data, and taking the output load data as load prediction data.
7. The method according to claim 1, wherein after the load prediction network model is trained by the training component signal, the load prediction network model includes a trained target activation function and network optimization parameters;
and taking the test component signal as input data, performing feature extraction and association relation processing combined and constructed by the trained load prediction network model, and taking the output load prediction data as a load prediction result of the target power line.
8. An electrical load prediction apparatus, comprising:
the acquisition module is used for acquiring historical load data of the target power line in a certain period of time;
the signal decomposition module is used for decomposing the historical load data according to a set signal decomposition algorithm to obtain a group of component signals and dividing the component signals into training component signals and test component signal data;
and the load prediction module is used for inputting the test component signal into the load prediction network model trained by the training component signal to obtain a load prediction result of the target power line.
9. An electronic device, the electronic device comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the power load prediction method of any of claims 1-7.
10. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the power load prediction method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211730273.2A CN116307060A (en) | 2022-12-30 | 2022-12-30 | Power load prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211730273.2A CN116307060A (en) | 2022-12-30 | 2022-12-30 | Power load prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116307060A true CN116307060A (en) | 2023-06-23 |
Family
ID=86789487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211730273.2A Pending CN116307060A (en) | 2022-12-30 | 2022-12-30 | Power load prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307060A (en) |
-
2022
- 2022-12-30 CN CN202211730273.2A patent/CN116307060A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113963110B (en) | Texture map generation method and device, electronic equipment and storage medium | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN115221795A (en) | Training method, prediction method, device, equipment and medium of capacity prediction model | |
| CN114943384A (en) | Transformer substation load prediction method, device, equipment and storage medium | |
| CN115271218A (en) | Carbon emission prediction method, device, equipment and medium based on electric carbon factor | |
| CN117786500A (en) | Method, device, equipment and storage medium for predicting earth surface subsidence in shield construction | |
| CN117332896A (en) | New energy small time scale power prediction method and system for multilayer integrated learning | |
| CN117332898A (en) | New energy small time scale power time sequence rolling prediction method based on machine learning | |
| CN116307060A (en) | Power load prediction method, device, equipment and storage medium | |
| CN116151446A (en) | Ultra-short-term wind power prediction method and device based on CEEMD and CNN-LSTM models | |
| CN114817985A (en) | Privacy protection method, device, equipment and storage medium for electricity consumption data | |
| CN116125279A (en) | Method, device, equipment and storage medium for determining battery health state | |
| CN117293923B (en) | Method, device, equipment and storage medium for generating day-ahead scheduling plan of power grid | |
| CN117878905A (en) | Power grid load prediction method, device, equipment and medium based on white noise signals | |
| CN117458500A (en) | Tidal current analysis method and device, electronic equipment and storage medium | |
| CN117293923A (en) | Method, device, equipment and storage medium for generating day-ahead scheduling plan of power grid | |
| CN117634437A (en) | Method and device for describing current running state of equipment and electronic equipment | |
| CN116911466A (en) | Method, device, equipment and medium for determining park construction degree | |
| CN117455067A (en) | Electric quantity consumption prediction method and device, electronic equipment and storage medium | |
| CN117967508A (en) | Wind generating set starting control method and training method of speed prediction model | |
| CN116166506A (en) | System operation data processing method, device, equipment and storage medium | |
| CN117833208A (en) | Power distribution network state deduction method and device, electronic equipment and storage medium | |
| CN117540628A (en) | Power system simulation method and device, electronic equipment and storage medium | |
| CN116523051A (en) | Model mixed-precision reasoning method, device, equipment and storage medium | |
| CN115329940A (en) | Recommendation method, device and equipment for convolution algorithm 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 |