CN108428021A - Micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN - Google Patents
Micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN Download PDFInfo
- Publication number
- CN108428021A CN108428021A CN201810487990.4A CN201810487990A CN108428021A CN 108428021 A CN108428021 A CN 108428021A CN 201810487990 A CN201810487990 A CN 201810487990A CN 108428021 A CN108428021 A CN 108428021A
- Authority
- CN
- China
- Prior art keywords
- layer
- node
- hidden layer
- micro
- hsa
- 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.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 210000002569 neuron Anatomy 0.000 claims abstract description 23
- 230000000306 recurrent effect Effects 0.000 claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 28
- 230000009466 transformation Effects 0.000 claims description 4
- 230000006386 memory function Effects 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims 1
- 230000001537 neural effect Effects 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 2
- 238000004088 simulation Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 238000000034 method Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 101100121112 Oryza sativa subsp. indica 20ox2 gene Proteins 0.000 description 1
- 101100121113 Oryza sativa subsp. japonica GA20OX2 gene Proteins 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- 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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of micro-capacitance sensor Short-term Load Forecasting Models based on HSA RRNN, the model is made of ridge ripple recurrent neural networks prediction model, including input layer, hidden layer, associated layers and output layer, each neuron node is connected with node layer one-to-one correspondence is associated in hidden layer, and is associated with the weights between node layer and hidden layer node and can carry out dynamic regulation；And the parameter in ridge ripple recurrent neural networks prediction model is optimized using improved harmony chess game optimization algorithm, have many advantages, such as fast convergence rate, there is stronger optimizing ability, there is preferable generalization and convergence.Pass through predictive simulation to practical micro-grid load and test, it was demonstrated that the prediction model proposed can effectively improve precision of prediction.
Description
Technical field
The present invention relates to a kind of micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN.
Background technology
Smart city is that application is expanded and integrated to the depth of information technology, is the important set of global strategy new industry development
At part, advanced technical conditions provide platform for the development of micro-capacitance sensor group, while the development of micro-capacitance sensor group will be to wisdom
City provides strong energy support.Smart city micro-capacitance sensor group " source-net-lotus-storage " cooperates with Optimum Scheduling Technology research to have
Important practical significance.Micro-grid load prediction is the base that micro-capacitance sensor group " source-net-lotus-storage " cooperates with Optimum Scheduling Technology research
Plinth, accurate micro-grid load prediction will provide necessary foundation for collaboration Optimized Operation.Micro-capacitance sensor is by micro- source, load, energy storage
Compositions, the height of precision of prediction such as device and power electronics control protection equipment directly influence safety and the economy of system
Property.
Ridge ripple neural network (ridegelet neural network, RNN) is the vision skin by simulating human brain
Layer and generate, hidden layer neuron can receive the data information on specific direction, and by analyzing processing, keep network defeated
Go out expected data.Compared with other traditional neural network models, RNN models are using ridge ripple function as network model hidden layer
The excitation function of middle neuron, more set direction, it includes more dimension informations that can make network, to handle well
More high-dimensional data information approaches relatively good effect to non-linear high-dimension function.
1998, ridge ripple function was suggested in the doctoral thesis of Candes for the first time, and definition can be specifically described as：Assuming that
Smooth function ψ：RdFourier transformation corresponding to → RMeet following admissible condition：
ψ is referred to as admissible function, wherein ω is independent variable, and d is space dimensionality.Then meet the admissible function ψ institutes of above-mentioned condition
The ridge function ψ γ of generation are known as ridge ripple function, and expression formula is：
γ is parameter space in formula (2), i.e.,：
γ=(a, u, b)；a,b∈R；A ＞ 0；u∈Sd-1 (9)
Wherein, the scaling vector of ridge ripple function is indicated by a, and the direction vector of ridge ripple function is indicated by u, the position of ridge ripple function
It sets vector and indicates that Sd-1 is expressed as d-1 dimension spaces by b, and | | u | |=1.
RNN is named according to the excitation function of its neuron, i.e., using ridge ripple function as network model hidden layer god
Excitation function through member, structure is close with traditional feed-forward type neural network, all by three layers of input layer, hidden layer and output layer
Structure composition.
Parameter in existing above-mentioned ridge ripple neural network prediction model needs preferred, the selections of these parameters has no any
Theoretical foundation, and the selection of these parameters is very big for estimated performance influence, it is a kind of with height present invention aims at providing
The micro-grid load prediction model of precision of prediction.
Invention content
In order to solve the above technical problems, the present invention provides a kind of micro-capacitance sensor short-term load forecasting mould based on HSA-RRNN
Type can meet the purpose that actual scheduling prediction requires to reach raising precision of prediction.
In order to achieve the above objectives, technical scheme is as follows：
A kind of micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN, the model is by ridge ripple recurrent neural networks prediction
Model is constituted, and ridge ripple recurrent neural network is that associated layers are added on the basis of above-mentioned RNN prediction models, is made every in hidden layer
One neuron node can all be connected with node layer one-to-one correspondence is associated with, and be associated between node layer and hidden layer node
Weights can carry out dynamic regulation；And using improved harmony chess game optimization algorithm (HSA) to ridge ripple recurrent neural networks prediction
Parameter in model optimizes, and optimization formula is：
In formula, PAR is disturbance probability, and BW is disturbance bandwidth, and n is current iteration number, and N is maximum iteration, r ∈
(0,1), Z are arbitrary number.
In said program, its mathematic(al) representation of the ridge ripple recurrent neural networks prediction model is as follows：
In formula, xi(i=1,2 ..., m) indicates the input of network；Indicate the internal state of hidden layer neuron node h,
It inputs the output state for deriving from input layer and being associated with node layer；Indicate the output state of neuron node h in hidden layer；Indicate the output valve of prototype network；Indicate the internal state of associated layers interior joint c；Indicate that associated layers interior joint c's is defeated
It does well；Admissible function is used by ridge ripple function：
Wherein, z is expressed as the independent variable of admissible function.
In said program, the association node layer can be by the current output state of corresponding hidden layer neuron node
It stores, and each hidden layer neuron is passed in subsequent time, belong to the feedback of status inside model, using repeatedly
Iteration updates, so as to form dynamic memory function specific to recursiveness neural network.
In said program, the input vector of the ridge ripple recurrent neural networks prediction model is [x1, x2..., xm], total m
Dimension, it is the associated characteristic element that is captured out from load sequence, meteorologic factor and day type information chronologically sequence
The vector formed.
In said program, hidden layer neuron node is p in the ridge ripple recurrent neural networks prediction model, and every
One node all obtains input quantity from input layer and associated layers, and passes through ridge ripple function ψγCarry out nonlinear transformation, output
Value passes to output layer and associated layers again；Wherein, associated layers interstitial content is identical as the neuron node number in hidden layer.
In said program, the output layer number of nodes is 1, in ridge ripple recurrent neural networks prediction model structure,
w1o... ..., whoThe adjustable weights connected between hidden layer and output layer, wc1... ..., wchBetween hidden layer and associated layers
The adjustable weights of connection.
Through the above technical solutions, the micro-capacitance sensor Short-term Load Forecasting Model provided by the invention based on HSA-RRNN is by ridge
Wave recurrent neural network is constituted, and is optimized to parameter using improved harmony chess game optimization algorithm, has fast convergence rate, tool
There is stronger optimizing ability, there is preferable generalization and convergence.It is imitative by the prediction to practical micro-grid load
True and test, it was demonstrated that the prediction model proposed can effectively improve precision of prediction.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described.
Fig. 1 is the ridge ripple recurrent neural networks prediction model structure schematic diagram disclosed in the embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes.
The present invention provides a kind of micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN, specific embodiment are as follows：
Ridge ripple recurrent neural networks prediction model as shown in Figure 1, association node layer can be by corresponding hidden layer god
Current output state through first node stores, and passes to each hidden layer neuron in subsequent time, belongs to inside model
Feedback of status, using repeatedly iteration update, so as to form dynamic memory function specific to recursiveness neural network.
The input vector of ridge ripple recurrent neural networks prediction model is [x1, x2..., xm], total m dimensions, it is from load sequence
The associated characteristic element captured out in row, meteorologic factor and day type information the vector that chronologically sequence is formed.
Hidden layer neuron node is p in ridge ripple recurrent neural networks prediction model, and each node is from defeated
Enter and obtain input quantity in layer and associated layers, and passes through ridge ripple function ψγNonlinear transformation is carried out, output valve passes to output again
Layer and associated layers；Wherein, associated layers interstitial content is identical as the neuron node number in hidden layer.
Output layer number of nodes is 1, in ridge ripple recurrent neural networks prediction model structure, w1o... ..., whoIt is hidden
Containing the adjustable weights connected between layer and output layer, wc1... ..., wchThe adjustable weights connected between hidden layer and associated layers.
Its mathematic(al) representation of ridge ripple recurrent neural networks prediction model is as follows：
In formula, xi(i=1,2 ..., m) indicates the input of network；Indicate the internal state of hidden layer neuron node h,
It inputs the output state for deriving from input layer and being associated with node layer；Indicate the output state of neuron node h in hidden layer；Indicate the output valve of prototype network；Indicate the internal state of associated layers interior joint c；Indicate that associated layers interior joint c's is defeated
It does well；Admissible function is used by ridge ripple function：
Wherein, z is expressed as the independent variable of admissible function.
HSA is a kind of new heuristic full search algorithm, and HSA simulates band makes its performance by adjusting musical instrument repeatedly
Go out the process of most U.S. harmony, each musical instrument is analogous to each solution variable of optimization problem, and the harmony played out is analogous to optimization problem
Object function.Algorithm firstly generates the harmony data base (harmony memory, HM) comprising M solution vector and each variable
Then feasible zone retains probability P 1 in HM to each variable random search new explanation, with probability 1-P1 in feasible zone with harmony library
It finds new explanation and local dip is carried out to it with probability P 2 to the new explanation from HM, finally compare new explanation and the worst solution in HM,
If being better than worst solution, replace, iterative cycles are until meeting maximum iteration.It is calculated compared to the tradition such as population and heredity
Method, HSA is versatile, fast convergence rate, has stronger optimizing ability.
The generation of new explanation and be a most key step to the disturbance of new explanation in HSA, the present invention is also in this step
Relevant parameter is improved.Basic HSA is disturbed to new explanation with fixation probability PAR, and disturbance bandwidth is fixed value BW, is disturbed
Dynamic formula is xnewI=xi-BW+2BW*rand, this fixed perturbation scheme of parameter cannot preferably embody HSA global searches
With the ability of local search, therefore, the present invention in such a way that a kind of disturbance probability and bandwidth adaptively reduce with iterations,
Specifically formula is：
In formula, n is current iteration number, and N is maximum iteration, and r ∈ (0,1), Z are arbitrary number.
After improvement, the PAR and BW of HSA is larger in algorithm value early period, to increase the exploration range of algorithm, obtains stronger
Ability of searching optimum, with the increase of iterations, PAR and BW are gradually reduced, and algorithm is made finely to be explored near optimal value, with
Obtain stronger local search ability.
For verification this patent propose the micro-capacitance sensor Short-term Load Forecasting Model (model I) based on HSA-RRNN it is effective
Property, using BP-NN prediction models (model II), routine RNN prediction models (model III) respectively to 24 point load micro-capacitance sensor one day
It is predicted, the prediction application condition of three kinds of models is as shown in table 1.
The prediction application condition of 1 three kinds of prediction models of table
As it can be seen from table 1 using traditional BP-NN prediction models, mean absolute error 9.22% is maximum to miss relatively
Difference is 19.71%.Using conventional RNN prediction models, mean absolute error reduces 2.27% than traditional BP-NN prediction models,
Maximum relative error reduces 3.51%.Use the micro-capacitance sensor short-term load forecasting mould based on HSA-RRNN of this patent proposition
Type, mean absolute error reduce 4.13% than traditional BP-NN prediction models, and maximum relative error reduces 6.55%.It is each
Optimal in model, it is pre- that this shows that the micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN proposed can effectively improve
Precision is surveyed, actual scheduling prediction can be met and required.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (6)
1. the micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN, which is characterized in that the model is by ridge ripple recurrent neural net
Network prediction model is constituted, including input layer, hidden layer, associated layers and output layer, in hidden layer each neuron node with
It is associated with node layer one-to-one correspondence to be connected, and be associated with the weights between node layer and hidden layer node to carry out dynamic regulation；
And the parameter in ridge ripple recurrent neural networks prediction model is optimized using improved harmony chess game optimization algorithm, optimization is public
Formula is：
In formula, PAR is disturbance probability, and BW is disturbance bandwidth, and n is current iteration number, and N is maximum iteration, r ∈ (0,1),
Z is arbitrary number.
2. the micro-capacitance sensor Short-term Load Forecasting Model according to claim 1 based on HSA-RRNN, which is characterized in that described
Its mathematic(al) representation of ridge ripple recurrent neural networks prediction model is as follows：
In formula, xi(i=1,2 ..., m) indicates the input of network；Indicate the internal state of hidden layer neuron node h, it is defeated
Enter the output state for deriving from input layer and being associated with node layer；Indicate the output state of neuron node h in hidden layer；Table
The output valve of representation model network；Indicate the internal state of associated layers interior joint c；Indicate the output shape of associated layers interior joint c
State；Admissible function is used by ridge ripple function：
Wherein, z is expressed as the independent variable of admissible function.
3. the micro-capacitance sensor Short-term Load Forecasting Model according to claim 2 based on HSA-RRNN, which is characterized in that described
Association node layer can store the current output state of corresponding hidden layer neuron node, and be passed in subsequent time
Each hidden layer neuron is passed, the feedback of status inside model is belonged to, is updated using iteration repeatedly, so as to form recurrence
Dynamic memory function specific to nerve network.
4. the micro-capacitance sensor Short-term Load Forecasting Model according to claim 2 based on HSA-RRNN, which is characterized in that described
The input vector of ridge ripple recurrent neural networks prediction model is [x1, x2..., xm], total m dimension, it be from load sequence, it is meteorological because
The associated characteristic element captured out in element and day type information the vector that chronologically sequence is formed.
5. the micro-capacitance sensor Short-term Load Forecasting Model according to claim 2 based on HSA-RRNN, which is characterized in that described
Hidden layer neuron node is p in ridge ripple recurrent neural networks prediction model, and each node is from input layer and pass
Input quantity is obtained in connection layer, and passes through ridge ripple function ψγNonlinear transformation is carried out, output valve passes to output layer and association again
Layer；Wherein, associated layers interstitial content is identical as the neuron node number in hidden layer.
6. the micro-capacitance sensor Short-term Load Forecasting Model according to claim 2 based on HSA-RRNN, which is characterized in that described
Output layer number of nodes is 1, in ridge ripple recurrent neural networks prediction model structure, w1o... ..., whoFor hidden layer and defeated
Go out the adjustable weights connected between layer, wc1... ..., wchThe adjustable weights connected between hidden layer and associated layers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810487990.4A CN108428021B (en) | 2018-05-21 | 2018-05-21 | Micro-grid short-term load prediction model based on HSA-RRNN |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810487990.4A CN108428021B (en) | 2018-05-21 | 2018-05-21 | Micro-grid short-term load prediction model based on HSA-RRNN |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108428021A true CN108428021A (en) | 2018-08-21 |
| CN108428021B CN108428021B (en) | 2021-10-12 |
Family
ID=63163550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810487990.4A Active CN108428021B (en) | 2018-05-21 | 2018-05-21 | Micro-grid short-term load prediction model based on HSA-RRNN |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108428021B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348631A (en) * | 2019-07-09 | 2019-10-18 | 武汉四创自动控制技术有限责任公司 | A kind of regionality Methods of electric load forecasting and system |
| WO2022077587A1 (en) * | 2020-10-14 | 2022-04-21 | 深圳大学 | Data prediction method and apparatus, and terminal device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521671A (en) * | 2011-11-29 | 2012-06-27 | 华北电力大学 | Ultrashort-term wind power prediction method |
| CN104700116A (en) * | 2015-03-13 | 2015-06-10 | 西安电子科技大学 | Polarized SAR (synthetic aperture radar) image object classifying method based on multi-quantum ridgelet representation |
| CN105069468A (en) * | 2015-07-28 | 2015-11-18 | 西安电子科技大学 | Hyper-spectral image classification method based on ridgelet and depth convolution network |
| CN106529570A (en) * | 2016-10-14 | 2017-03-22 | 西安电子科技大学 | Image classification method based on deep ridgelet neural network |
-
2018
- 2018-05-21 CN CN201810487990.4A patent/CN108428021B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521671A (en) * | 2011-11-29 | 2012-06-27 | 华北电力大学 | Ultrashort-term wind power prediction method |
| CN104700116A (en) * | 2015-03-13 | 2015-06-10 | 西安电子科技大学 | Polarized SAR (synthetic aperture radar) image object classifying method based on multi-quantum ridgelet representation |
| CN105069468A (en) * | 2015-07-28 | 2015-11-18 | 西安电子科技大学 | Hyper-spectral image classification method based on ridgelet and depth convolution network |
| CN106529570A (en) * | 2016-10-14 | 2017-03-22 | 西安电子科技大学 | Image classification method based on deep ridgelet neural network |
Non-Patent Citations (4)
| Title |
|---|
| HUA等: "A new wind power prediction method based on ridgelet transforms, hybrid feature selection and closed-loop forecasting", 《ADVANCED ENGINEERING INFORMATICS》 * |
| NIMA等: "Short-term wind power forecasting using ridgelet neural network", 《ELECTRIC POWER SYSTEMS RESEARCH》 * |
| 张宜阳等: "基于分段分层相似日搜索和自适应脊波神经网络的风电功率多步预测", 《电网与清洁能源》 * |
| 茆美琴等: "基于脊波神经网络的短期风电功率预测", 《电力***自动化》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348631A (en) * | 2019-07-09 | 2019-10-18 | 武汉四创自动控制技术有限责任公司 | A kind of regionality Methods of electric load forecasting and system |
| WO2022077587A1 (en) * | 2020-10-14 | 2022-04-21 | 深圳大学 | Data prediction method and apparatus, and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108428021B (en) | 2021-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | A multi-agent deep reinforcement learning method for cooperative load frequency control of a multi-area power system | |
| Sözen et al. | Prediction of net energy consumption based on economic indicators (GNP and GDP) in Turkey | |
| CN107622329A (en) | The Methods of electric load forecasting of Memory Neural Networks in short-term is grown based on Multiple Time Scales | |
| Levent et al. | Energy management for microgrids: a reinforcement learning approach | |
| Yi et al. | An improved two-stage deep reinforcement learning approach for regulation service disaggregation in a virtual power plant | |
| CN110414719A (en) | A kind of vehicle flowrate prediction technique based on Multi-variable Grey Model time series | |
| CN108876001A (en) | A kind of Short-Term Load Forecasting Method based on twin support vector machines | |
| CN108647824A (en) | A kind of electricity price ultra-short term prediction method | |
| CN109886452A (en) | A kind of ultrashort-term wind power probability forecasting method and system based on experience dynamic modeling | |
| CN112884236B (en) | Short-term load prediction method and system based on VDM decomposition and LSTM improvement | |
| CN110222908A (en) | A kind of short-term electricity demand forecasting method based on data-driven | |
| Li et al. | A hybrid deep interval prediction model for wind speed forecasting | |
| CN109214546A (en) | A kind of Power Short-Term Load Forecasting method based on improved HS-NARX neural network | |
| CN110233484A (en) | Consider the multi-objective reactive optimization configuration method of compensation benefit | |
| CN108428021A (en) | Micro-capacitance sensor Short-term Load Forecasting Model based on HSA-RRNN | |
| Wu et al. | An ensemble neural network based on variational mode decomposition and an improved sparrow search algorithm for wind and solar power forecasting | |
| CN115470987A (en) | Short-term photovoltaic power generation prediction method based on improved long-term and short-term memory neural network | |
| CN115149544A (en) | Soft Actor-critical algorithm-based power distribution network continuous reactive voltage optimization method | |
| Huang et al. | Adaptive static equivalences for active distribution networks with massive renewable energy integration: a distributed deep reinforcement learning approach | |
| Karthik et al. | OELF: short term load forecasting for an optimal electrical load forecasting using hybrid whale optimization based convolutional neural network | |
| Kaplan et al. | Simplified model and genetic algorithm based simulated annealing approach for excitation current estimation of synchronous motor | |
| Cao et al. | Short-term load forecasting based on variational modal decomposition and optimization model | |
| Zhang et al. | Two-stage short-term wind speed prediction based on LSTM-LSSVM-CFA | |
| CN114662798B (en) | Scheduling method and device based on power grid economic operation domain and electronic equipment | |
| Ahmad et al. | A New approach for solving economic load dispatch problem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |