CN111931994A - Short-term load and photovoltaic power prediction method, system, equipment and medium thereof - Google Patents
Short-term load and photovoltaic power prediction method, system, equipment and medium thereof Download PDFInfo
- Publication number
- CN111931994A CN111931994A CN202010696519.3A CN202010696519A CN111931994A CN 111931994 A CN111931994 A CN 111931994A CN 202010696519 A CN202010696519 A CN 202010696519A CN 111931994 A CN111931994 A CN 111931994A
- Authority
- CN
- China
- Prior art keywords
- information
- photovoltaic power
- short
- network
- power prediction
- 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
- 230000015654 memory Effects 0.000 claims abstract description 80
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000012417 linear regression Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006403 short-term memory Effects 0.000 claims description 2
- 238000013136 deep learning model Methods 0.000 abstract description 2
- 210000004027 cell Anatomy 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 7
- 210000002569 neuron Anatomy 0.000 description 6
- 230000004913 activation Effects 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012706 support-vector machine 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a short-term load and photovoltaic power prediction method, a system, equipment and a medium thereof, wherein the method comprises the following steps: acquiring historical load information and historical photovoltaic power information; predicting historical load information and historical photovoltaic power information by using a pre-trained deep confidence network to obtain a first short-term load and photovoltaic power prediction result; moreover, historical load information and historical photovoltaic power information are predicted by using a long and short memory network trained in advance to obtain a second short-term load and photovoltaic power prediction result; and performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result. The system, apparatus, medium includes a carrier for performing the method. The method can realize the prediction of short-term load and photovoltaic power based on the dynamic combination deep learning model so as to improve the prediction precision.
Description
Technical Field
The invention relates to the technical field of short-term load and photovoltaic power prediction, in particular to a short-term load and photovoltaic power prediction method, a system, equipment and a medium thereof.
Background
The short-term load prediction is mainly used for forecasting the power load of several minutes, hours or weeks in the future, is used for scheduling and arranging a start-stop plan, has important significance for optimal combination, economic scheduling, optimal power flow and the like of a unit, and is also a foundation for ensuring effective operation of a power market. The generalized short-term load prediction relates to the prediction of power load and the prediction of photovoltaic and other power generation output, and the conventional short-term load and photovoltaic prediction model mainly comprises a time sequence model, a machine learning model such as a neural network or a support vector machine and the like.
The current short-term load and photovoltaic power prediction has the following problems:
on one hand, a shallow learning method is adopted, the learning capability of a shallow learning algorithm is limited, the deep level feature training process cannot be effectively utilized, and the prediction precision can easily reach the bottleneck. On the other hand, the existing model is usually predicted by adopting an algorithm, the robustness of a single algorithm is low, and if the single algorithm falls into a local minimum value in the training process, the corresponding prediction performance of the model is poor.
Disclosure of Invention
The invention aims to provide a short-term load and photovoltaic power prediction method and a system, computer equipment and a computer readable storage medium thereof, which can realize the prediction of the short-term load and the photovoltaic power based on a dynamic combination deep learning model so as to improve the prediction precision.
To achieve the above object, according to a first aspect, the present invention provides a short-term load and photovoltaic power prediction method, including:
acquiring historical load information and historical photovoltaic power information;
predicting the historical load information and the historical photovoltaic power information by using a pre-trained deep confidence network to obtain a first short-term load and photovoltaic power prediction result; predicting the historical load information and the historical photovoltaic power information by using a pre-trained long and short memory network to obtain a second short-term load and photovoltaic power prediction result;
and performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result.
Preferably, the deep confidence network obtains the optimal network parameters of the deep confidence network by calculating the maximum log-likelihood function in the pre-training process.
Preferably, the long and short memory networks obtain the optimal network parameters of the long and short memory networks through a self-adaptive time estimation method in the pre-training process.
Preferably, the long and short memory network includes a network input unit, an input gate, a forgetting gate, an output gate and a network output unit, the network input unit is configured to receive network input information at a current time, the network input information at the current time includes the historical load information and the historical photovoltaic power information, the input gate is configured to obtain network input and output information at the current time, previous memory state information and previous time network output information, the forgetting gate is configured to determine information to be deleted from the previous memory state information, the output gate is configured to calculate output gate information according to the network input and output information, the previous memory state information and the previous time network output information, and the network output unit is configured to calculate an initial photovoltaic power prediction result according to the output gate information and the state information at the current time; and the state information of the current moment is obtained by calculation according to the network input and output information of the current moment, the last memory state information, the network output information of the last moment and the information to be deleted.
According to a second aspect, the present invention provides a short-term load and photovoltaic power prediction system, comprising:
the information acquisition unit is used for acquiring historical load information and historical photovoltaic power information;
the deep confidence network prediction unit is used for predicting the historical load information and the historical photovoltaic power information by using a pre-trained deep confidence network to obtain a first short-term load and photovoltaic power prediction result;
the long and short memory network prediction unit is used for predicting the historical load information and the historical photovoltaic power information by utilizing a long and short memory network trained in advance to obtain a second short-term load and photovoltaic power prediction result; and
and the linear regression processing unit is used for performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result.
Preferably, the deep confidence network obtains the optimal network parameters of the deep confidence network by calculating the maximum log-likelihood function in the pre-training process.
Preferably, the long and short memory networks obtain the optimal network parameters of the long and short memory networks through a self-adaptive time estimation method in the pre-training process.
Preferably, the long and short memory network includes a network input unit, an input gate, a forgetting gate, an output gate and a network output unit, the network input unit is configured to receive network input information at a current time, the network input information at the current time includes the historical load information and the historical photovoltaic power information, the input gate is configured to obtain network input and output information at the current time, previous memory state information and previous time network output information, the forgetting gate is configured to determine information to be deleted from the previous memory state information, the output gate is configured to calculate output gate information according to the network input and output information, the previous memory state information and the previous time network output information, and the network output unit is configured to calculate an initial photovoltaic power prediction result according to the output gate information and the state information at the current time; and the state information of the current moment is obtained by calculation according to the network input and output information of the current moment, the last memory state information, the network output information of the last moment and the information to be deleted.
According to a third aspect, the invention proposes a computer device comprising: the short term load and photovoltaic power prediction system of the second aspect; or a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the short term load and photovoltaic power prediction method according to the first aspect.
According to a fourth aspect, the invention proposes a computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the short term load and photovoltaic power prediction method according to the first aspect.
The embodiment of the invention provides a short-term load and photovoltaic power prediction method and a system, computer equipment and a computer readable storage medium thereof, wherein a pre-trained deep confidence network is used for processing historical load information to output a short-term load prediction result, a pre-trained long and short memory network is used for processing historical photovoltaic power information to output a photovoltaic power prediction result, and finally a linear model is used for carrying out regression processing on the short-term load prediction result and the photovoltaic power prediction result to realize the dynamic combination of the load prediction result and the photovoltaic power prediction result and then output, so that the output precision is improved, the problem of low robustness of a single algorithm is avoided, the learning capability is strong, and the precision of the short-term load prediction and the photovoltaic power prediction can be effectively improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating a short-term load and photovoltaic power prediction method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a deep belief network structure according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a long/short memory network structure according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of training of the deep belief network and the long-short memory network in an embodiment of the present invention.
FIG. 5 is a diagram illustrating the results of a prediction based on a week of real load data according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating the result of a prediction based on another week of real load data according to an embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating the result of prediction based on the actual photovoltaic data of a day according to an embodiment of the present invention;
FIG. 8 is a graph illustrating the results of a prediction based on another one-day real photovoltaic data according to an embodiment of the present invention;
fig. 9 is a block diagram of a short term load and photovoltaic power prediction system according to another embodiment of the present invention.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, well known means have not been described in detail so as not to obscure the present invention.
Referring to fig. 1, an embodiment of the invention provides a method for predicting short-term load and photovoltaic power, including the following steps:
step S1, acquiring historical load information and historical photovoltaic power information;
specifically, the historical load information and the historical photovoltaic power information are preferably historical information of the last week, and the photovoltaic power information refers to photovoltaic power generation power of the power system. Preferably, the historical load information and the historical photovoltaic power information respectively include load and corresponding weather information, photovoltaic power and corresponding weather information.
Step S2, predicting the historical load information and the historical photovoltaic power information by using a pre-trained deep confidence network to obtain a first short-term load and photovoltaic power prediction result; predicting the historical load information and the historical photovoltaic power information by using a pre-trained long and short memory network to obtain a second short-term load and photovoltaic power prediction result;
and step S3, performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result.
Specifically, in step S3, the prediction results of the deep belief network and the long and short memory networks are dynamically combined to be the final prediction result, so that the calculation results of the two networks can make up for the deficiencies of each other, and the prediction effect is improved.
In a specific embodiment, the deep confidence network obtains the optimal network parameters of the deep confidence network by calculating a maximum log-likelihood function in a pre-training process.
In particular, the optimal parameters of the model, v, are found by calculating a maximum log-likelihood function(t)For the known t-th input sample, i.e.:
the training process of the deep confidence network is as follows:
the deep confidence network describes the whole system state in the form of an energy function, viRepresents the state of the ith visible neuron, hjRepresenting the state of the jth hidden neuron. The overall structure of the deep confidence network is shown in fig. 2, the energy function of the deep confidence network is E (v, h), and the joint probability distribution is P (v, h);
wherein, aiAnd bjIndicating the bias information for the ith visual cell and the jth implicit cell, respectively, wijRepresenting weight information between the ith visible neuron and the jth hidden neuron, nv、nhRepresenting the number of visible and hidden neurons, and Z is a uniform partition variable.
In a specific embodiment, the long and short memory networks obtain the optimal network parameters of the long and short memory networks through a self-adaptive time estimation method in the pre-training process.
Specifically, aiming at the optimization of the prediction model parameters of the long-term and short-term memory network, an Adaptive moment estimation (ADAM) method is adopted, and the ADAM can design a customized Adaptive learning rate according to different parameter states, so that the ADAM algorithm is suitable for the problems of instability or gradient sparse gradient. And updating parameters of the long and short memory networks by adopting ADAM (adaptive dynamic analysis of dynamic analysis) so as to improve the capability of the model for mining the change trend of load and photovoltaic power output.
The long and short memory network comprises a network input unit, an input gate, a forgetting gate, an output gate and a network output unit, wherein the network input unit is used for receiving network input information at the current moment, the network input information at the current moment comprises historical load information and historical photovoltaic power information, the input gate is used for acquiring network input and output information at the current moment, previous memory state information and previous time network output information, the forgetting gate is used for determining information to be deleted from the previous memory state information, the output gate is used for calculating to obtain output gate information according to the network input and output information, the previous memory state information and the previous time network output information, and the network output unit is used for calculating an initial photovoltaic power prediction result according to the output gate information and the state information at the current moment; and the state information of the current moment is obtained by calculation according to the network input and output information of the current moment, the last memory state information, the network output information of the last moment and the information to be deleted.
The training process of the long and short memory networks is as follows:
given an input X ═ X1,x2,…xTThe output of the long-short term memory network is Y ═ Y1,y2,…yTEvery moment memory cell receives current input x through each gatetFrom the last hidden state output ht-1And internal cell state ct-1The calculation process of the long and short memory networks is as follows:
forget door ftDetermining which information will be transferred from memory cell state Ct-1And the activation state of the forgetting gate is determined by an activation function sigma (·):
ft＝σ(Wfxxt+Wfhht-1+WfcCt-1+bf)
output f of the above formulatIs corresponding to the last cell state Ct-1A value between 0 and 1. When C is presentt-1Taking 0 means that the last state is completely forgotten, and taking 1 means that the last state is completely maintained.
Secondly, the long and short memory networks use the input gate itTo decide that a new cell state C is to be storedtNew information of (2), calculation processThe following were used:
it＝σ(Wixxt+Wihht-1+WicCt-1+bi)
Ut＝g(Wcxxt+Wchht-1+bc)
in the formula of UtTo add to a new cell state CtA candidate value of (a); g (-) is the activation function.
Old memory cell state Ct-1Updated to a new state CtThe procedure of (2) is as follows:
Ct＝Ct-1ft+Utit
in the formula Ct-1ftThe effect is to determine how much information is to be transferred from Ct-1Forgetting to turn on, UtitDetermining how much information to add to the new cell state Ct。
Finally using the output gate otCalculate htAnd ytThe process of (2) is as follows:
ot＝σ(Woxxt+Wohht-1+WocCt-1+bo)
in the formula, an activation function sigma is a sigmoid function;
and g is the tanh function; wix,Wfx,Wox,WcxRepresenting input information xtThe weight matrix of (2); wih,Wfh,Woh,WchRepresenting the output signal htThe weight matrix of (2); wic,Wfc,WocRepresents the output vector ctA diagonal matrix of sum-gate functions; bi,bf,bo,bcIndicating the corresponding offset for each gate.
The deep confidence network and the long and short memory network training principle in the method of the embodiment can be seen in fig. 4.
An example is provided below to illustrate the method of this embodiment.
The load actual data of a certain area is selected as a case, two application scenes are selected, and the access capacity of the distributed photovoltaic in each scene reaches a higher proportion. And the first scene is a photovoltaic power prediction scene, the photovoltaic installed capacity is 400kW under the scene, and the prediction target is the photovoltaic output condition of the next hour. And a second scene is a load forecasting scene, which is the electricity utilization condition of the load of residents, and the forecasting target is the load of the next hour.
In each scenario, the error indicators used include the mean relative error MAPE, the root mean square error RMSE, as shown in the following equation:
where n is the number of samples of the data set, aiAnd biAnd respectively determining the real value and the predicted value of each prediction task at the moment i.
Based on the training schematic diagram shown in fig. 4, first, the short-term load, the weather data, and the holiday data are divided into a training set and a test set, and the photovoltaic data and the weather data are divided into the training set and the test set. Then, training the deep confidence network and the long-short term memory network, wherein the hidden layer of the long-short term memory network is set to be 2 layers, the number of neurons is set to be 20, the number of variables is 1020, and the training time duration is total to be 61 s. Finally, the prediction results in the first layer are dynamically combined using a linear regression method. Fig. 5 to 6 are schematic diagrams of short-term load prediction results predicted by the method according to the present embodiment based on two weeks of real load data, and fig. 7 to 8 are schematic diagrams of photovoltaic power prediction results predicted by the method according to two days of real photovoltaic data. Referring to fig. 5-8, the method of the present embodiment can accurately predict the short-term load and the photovoltaic power.
And comparing the prediction result with the prediction results of a deep confidence network, a random forest and a time sequence algorithm. The prediction accuracy results are shown in table 1 below.
Table 1 load prediction and photovoltaic prediction error evaluation considering a plurality of models
The results in table 1 show that the short-term load prediction and photovoltaic prediction performed by the method of the present embodiment are superior to the other three methods.
Referring to fig. 9, another embodiment of the present invention further provides a short-term load and photovoltaic power prediction system, including:
the information acquisition unit 1 is used for acquiring historical load information and historical photovoltaic power information;
the deep confidence network prediction unit 2 is used for predicting the historical load information and the historical photovoltaic power information by using a pre-trained deep confidence network to obtain a first short-term load and photovoltaic power prediction result;
the long and short memory network prediction unit 3 is used for predicting the historical load information and the historical photovoltaic power information by using a long and short memory network trained in advance to obtain a second short-term load and photovoltaic power prediction result; and
and the linear regression processing unit 4 is used for performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result.
In a specific embodiment, the deep confidence network obtains the optimal network parameters of the deep confidence network by calculating a maximum log-likelihood function in a pre-training process.
In a specific embodiment, the long and short memory networks obtain the optimal network parameters of the long and short memory networks through a self-adaptive time estimation method in the pre-training process.
In one embodiment, the long and short memory network includes a network input unit, an input gate, a forgetting gate, an output gate and a network output unit, the network input unit is used for receiving network input information at the current moment, the network input information at the current moment comprises the historical load information and the historical photovoltaic power information, the input gate is used for acquiring the network input and output information at the current moment, the last memory state information and the last time network output information, the forgetting gate is used for determining information to be deleted from the last memory state information, the output gate is used for calculating to obtain output gate information according to the network input and output information, the last memory state information and the last time network output information, the network output unit is used for calculating an initial photovoltaic power prediction result according to the output gate information and the state information at the current moment; and the state information of the current moment is obtained by calculation according to the network input and output information of the current moment, the last memory state information, the network output information of the last moment and the information to be deleted.
It should be noted that the system described in the foregoing embodiment corresponds to the method described in the foregoing embodiment, and therefore, portions of the system described in the foregoing embodiment that are not described in detail can be obtained by referring to the content of the method described in the foregoing embodiment, and details are not described here.
Another embodiment of the present invention further provides a computer device, including: the short-term load and photovoltaic power prediction system according to the above embodiment; or a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the short term load and photovoltaic power prediction method according to the above embodiments.
Of course, the computer device may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the computer device may also include other components for implementing the functions of the device, which are not described herein again.
Illustratively, the computer program may be divided into one or more units, which are stored in the memory and executed by the processor to accomplish the present invention. The one or more units may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the computer device.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center for the computer device and connects the various parts of the overall computer device using various interfaces and lines.
The memory may be used for storing the computer program and/or unit, and the processor may implement various functions of the computer device by executing or executing the computer program and/or unit stored in the memory and calling data stored in the memory. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Another embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the short-term load and photovoltaic power prediction method according to the above-mentioned embodiments.
Specifically, the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A short-term load and photovoltaic power prediction method is characterized by comprising the following steps:
acquiring historical load information and historical photovoltaic power information;
predicting the historical load information and the historical photovoltaic power information by using a pre-trained deep confidence network to obtain a first short-term load and photovoltaic power prediction result; predicting the historical load information and the historical photovoltaic power information by using a pre-trained long and short memory network to obtain a second short-term load and photovoltaic power prediction result;
and performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result.
2. The method of claim 1, wherein the deep belief network is trained in advance to obtain optimal network parameters for the deep belief network by computing a maximum log-likelihood function.
3. The method of claim 1, wherein the long-short term load and photovoltaic power prediction method is characterized in that the optimal network parameters of the long-short term memory network and the short-term memory network are obtained through a self-adaptive time estimation method in a pre-training process.
4. The short term load and photovoltaic power prediction method of claim 3, the long and short memory network comprises a network input unit, an input gate, a forgetting gate, an output gate and a network output unit, the network input unit is used for receiving network input information at the current moment, the network input information at the current moment comprises the historical load information and the historical photovoltaic power information, the input gate is used for acquiring the network input and output information at the current moment, the last memory state information and the last time network output information, the forgetting gate is used for determining information to be deleted from the last memory state information, the output gate is used for calculating to obtain output gate information according to the network input and output information, the last memory state information and the last time network output information, the network output unit is used for calculating an initial photovoltaic power prediction result according to the output gate information and the state information at the current moment; and the state information of the current moment is obtained by calculation according to the network input and output information of the current moment, the last memory state information, the network output information of the last moment and the information to be deleted.
5. A short-term load and photovoltaic power prediction system, comprising:
the information acquisition unit is used for acquiring historical load information and historical photovoltaic power information;
the deep confidence network prediction unit is used for predicting the historical load information and the historical photovoltaic power information by using a pre-trained deep confidence network to obtain a first short-term load and photovoltaic power prediction result;
the long and short memory network prediction unit is used for predicting the historical load information and the historical photovoltaic power information by utilizing a long and short memory network trained in advance to obtain a second short-term load and photovoltaic power prediction result; and
and the linear regression processing unit is used for performing linear regression processing on the first short-term load and photovoltaic power prediction result and the second short-term load and photovoltaic power prediction result by using a pre-trained linear model to obtain a short-term load and photovoltaic power prediction result.
6. The short term load and photovoltaic power prediction system of claim 1, wherein the deep confidence network is trained in advance to obtain optimal network parameters for the deep confidence network by computing a maximum log-likelihood function.
7. The short-term load and photovoltaic power prediction system as claimed in claim 1, wherein the long and short memory networks find optimal network parameters of the long and short memory networks through a self-adaptive time estimation method in a pre-training process.
8. The short term load and photovoltaic power prediction system of claim 7, the long and short memory network comprises a network input unit, an input gate, a forgetting gate, an output gate and a network output unit, the network input unit is used for receiving network input information at the current moment, the network input information at the current moment comprises the historical load information and the historical photovoltaic power information, the input gate is used for acquiring the network input and output information at the current moment, the last memory state information and the last time network output information, the forgetting gate is used for determining information to be deleted from the last memory state information, the output gate is used for calculating to obtain output gate information according to the network input and output information, the last memory state information and the last time network output information, the network output unit is used for calculating an initial photovoltaic power prediction result according to the output gate information and the state information at the current moment; and the state information of the current moment is obtained by calculation according to the network input and output information of the current moment, the last memory state information, the network output information of the last moment and the information to be deleted.
9. A computer device, comprising: the short term load and photovoltaic power prediction system of claims 5-8; or a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the short term load and photovoltaic power prediction method according to any one of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the short term load and photovoltaic power prediction method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010696519.3A CN111931994A (en) | 2020-07-20 | 2020-07-20 | Short-term load and photovoltaic power prediction method, system, equipment and medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010696519.3A CN111931994A (en) | 2020-07-20 | 2020-07-20 | Short-term load and photovoltaic power prediction method, system, equipment and medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111931994A true CN111931994A (en) | 2020-11-13 |
Family
ID=73313693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010696519.3A Pending CN111931994A (en) | 2020-07-20 | 2020-07-20 | Short-term load and photovoltaic power prediction method, system, equipment and medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931994A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115907136A (en) * | 2022-11-16 | 2023-04-04 | 北京国电通网络技术有限公司 | Electric vehicle scheduling method, device, equipment and computer readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012244897A (en) * | 2011-05-13 | 2012-12-10 | Fujitsu Ltd | Apparatus and method for predicting short-term power load |
| CN110119826A (en) * | 2018-02-06 | 2019-08-13 | 天津职业技术师范大学 | A kind of power-system short-term load forecasting method based on deep learning |
| CN110909958A (en) * | 2019-12-05 | 2020-03-24 | 国网江苏省电力有限公司南通供电分公司 | Short-term load prediction method considering photovoltaic grid-connected power |
-
2020
- 2020-07-20 CN CN202010696519.3A patent/CN111931994A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012244897A (en) * | 2011-05-13 | 2012-12-10 | Fujitsu Ltd | Apparatus and method for predicting short-term power load |
| CN110119826A (en) * | 2018-02-06 | 2019-08-13 | 天津职业技术师范大学 | A kind of power-system short-term load forecasting method based on deep learning |
| CN110909958A (en) * | 2019-12-05 | 2020-03-24 | 国网江苏省电力有限公司南通供电分公司 | Short-term load prediction method considering photovoltaic grid-connected power |
Non-Patent Citations (1)
| Title |
|---|
| 熊图等: "动态组合深度学习模型在短期负荷及光伏功率预测中的应用", 《可再生能源》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115907136A (en) * | 2022-11-16 | 2023-04-04 | 北京国电通网络技术有限公司 | Electric vehicle scheduling method, device, equipment and computer readable medium |
| CN115907136B (en) * | 2022-11-16 | 2023-10-20 | 北京国电通网络技术有限公司 | Electric automobile dispatching method, device, equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210133536A1 (en) | Load prediction method and apparatus based on neural network | |
| CN107506868B (en) | Method and device for predicting short-time power load | |
| Li et al. | An integrated missing-data tolerant model for probabilistic PV power generation forecasting | |
| CN111027772A (en) | Multi-factor short-term load prediction method based on PCA-DBILSTM | |
| CN112884236B (en) | Short-term load prediction method and system based on VDM decomposition and LSTM improvement | |
| CN113240155A (en) | Method and device for predicting carbon emission and terminal | |
| CN113887801A (en) | Building cold load prediction method, system, equipment and readable storage medium | |
| CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
| Liao et al. | Short-term load forecasting with dense average network | |
| CN115907131B (en) | Method and system for constructing electric heating load prediction model in northern area | |
| CN117543544A (en) | Load prediction method, device, equipment and storage medium | |
| CN111461445A (en) | Short-term wind speed prediction method and device, computer equipment and storage medium | |
| CN116757378A (en) | Demand response evaluation model training method, application evaluation method and related equipment | |
| CN116799796A (en) | Photovoltaic power generation power prediction method, device, equipment and medium | |
| CN116542701A (en) | Carbon price prediction method and system based on CNN-LSTM combination model | |
| Wu et al. | Automatic fuzzy model identification for short-term load forecast | |
| Nawar et al. | Transfer learning in deep learning models for building load forecasting: Case of limited data | |
| CN117454668A (en) | Method, device, equipment and medium for predicting failure probability of parts | |
| CN111931994A (en) | Short-term load and photovoltaic power prediction method, system, equipment and medium thereof | |
| CN117335389A (en) | Power load prediction method, system, equipment and medium based on multitask learning | |
| CN117350336A (en) | Charging load prediction and model training method, device, equipment and storage medium | |
| CN117217591A (en) | Method and system for predicting photovoltaic power generation power | |
| CN114239945B (en) | Short-term power load prediction method, device, equipment and storage medium | |
| Ogawa et al. | PV output forecasting by deep Boltzmann machines with SS‐PPBSO | |
| Inteha et al. | An Artificial Intelligence Based Day Lag Technique for Day Ahead Short Term Load Forecasting |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201113 |
|
| RJ01 | Rejection of invention patent application after publication |