CN114498634B - Electric automobile charging load prediction method based on ammeter data - Google Patents
Electric automobile charging load prediction method based on ammeter data Download PDFInfo
- Publication number
- CN114498634B CN114498634B CN202210144543.5A CN202210144543A CN114498634B CN 114498634 B CN114498634 B CN 114498634B CN 202210144543 A CN202210144543 A CN 202210144543A CN 114498634 B CN114498634 B CN 114498634B
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- charging load
- ammeter
- electric automobile
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000013598 vector Substances 0.000 claims abstract description 19
- 238000005096 rolling process Methods 0.000 claims abstract description 3
- 230000007246 mechanism Effects 0.000 claims description 17
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000007787 long-term memory Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 230000007774 longterm Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 230000005611 electricity Effects 0.000 claims 1
- 238000005065 mining Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/40—The network being an on-board power network, i.e. within a vehicle
- H02J2310/48—The network being an on-board power network, i.e. within a vehicle for electric vehicles [EV] or hybrid vehicles [HEV]
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses an electric vehicle charging load prediction method based on ammeter data, which mainly solves the problem that the existing prediction method needs a large amount of traffic flow, position and other information. The method comprises the following steps: (S1) acquiring charging load of a user electric automobile according to acquired resident user ammeter data; (S2) input feature selection: according to the identification result of the charging load of the electric automobile, combining the total power data of the intelligent ammeter to serve as input data of a prediction network to be constructed; (S3) constructing a prediction network: mining the incidence relation of input data by CNN-LSTM, obtaining important feature vectors, adding the feature vectors into a Dropout layer to prevent overfitting; (S4) outputting a charging load prediction result of the electric automobile and a total power prediction result of the intelligent ammeter; (S5) rolling the updated prediction network. The method can effectively improve the prediction precision, simultaneously predicts the required data type only of the household ammeter data, is easy to obtain, does not need to calculate the load density, the distribution and the like, and is simple and convenient to operate.
Description
Technical Field
The invention belongs to the technical field of electric vehicle charging, and particularly relates to an electric vehicle charging load prediction method based on ammeter data.
Background
Along with the development and planning requirements of the 'double-carbon' target and new energy automobile industry, the user side electric automobile shows a large-scale growth trend, and the disordered charging of the large-scale electric automobile can cause the problems of increased load peak demand, overload operation of primary equipment, unbalanced three-phase power and the like, so that the safe and stable operation of a power grid is seriously affected. The charging behavior of the home user has strong subjectivity, and the charging requirement of the home electric automobile user is difficult to determine. Therefore, it is necessary to explore a method for predicting the charging load of a home user to formulate a corresponding demand response strategy and guide the charging behavior thereof.
Aiming at the prediction of the charging load of the electric automobile, a great deal of research has been carried out at home and abroad, for example, according to the charging power of different charging behaviors of different types of electric automobiles, an electric automobile charging load calculation method for simulating and extracting the initial state of charge and the initial charging time by adopting Monte Carlo is provided, the subjectivity and regularity of the charging behaviors of the electric automobile are comprehensively simulated, and a foundation is provided for subsequent research. And then, the charging position, the charging time, the state of charge and the traffic and travel chains of the electric vehicle based on big data analysis provide feasibility for more accurate charge load space-time prediction. And for example, the origin-destination points of the private car and the taxi are respectively obtained through a travel chain theory and an OD matrix method, a travel path is planned, and then an electric car charging load prediction method considering multi-source information real-time interaction and user remorse psychology is provided based on real-time speed and consumption and the like. And for example, a data-driven electric vehicle quick charge load prediction method based on a behavior decision model is used for constructing a single electric vehicle model by considering the running and charging behavior characteristics of a user. And commonly introducing a traffic travel rule obtained by data mining and a charging strategy obtained by a regret theory decision model into a framework of the quick charging demand prediction method. The method is concentrated on the charge load prediction of the charging station, a large amount of traffic, charging facility position information and the like are needed, and the research of predicting the charge load of the resident user by directly utilizing the lumped intelligent ammeter data is less aiming at the household charging condition of the home user.
Disclosure of Invention
The invention aims to provide an electric vehicle charging load prediction method based on ammeter data, which mainly solves the problems that the existing prediction method needs a large amount of traffic flow, position and other information and needs to simulate the traveling and charging process of a user.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
an electric vehicle charging load prediction method based on ammeter data comprises the following steps:
(S1) acquiring charging load of a user electric automobile by adopting non-invasive load identification according to acquired resident user ammeter data;
(S2) input feature selection: according to the identification result of the charging load of the electric automobile, combining the total power data of the intelligent ammeter to serve as input data of a prediction network to be constructed;
(S3) constructing a prediction network: digging an input data association relation by using CNN-LSTM, introducing an attention mechanism to obtain important feature vectors, and adding the feature vectors into a Dropout layer to prevent overfitting;
s4, outputting a charging load prediction result of the electric vehicle and a total power prediction result of the intelligent ammeter through a prediction network;
and (S5) rolling and updating the prediction network according to the actual measurement condition of the total power of the intelligent ammeter, so as to reduce the deviation.
Further, in the present invention, in step (S3), the LSTM long-term memory model is used to capture long-term time-series dependency relationships between input data, so that the learning efficiency of the model can be ensured when a large number of training samples are input.
Further, in the present invention, in step (S3), a CNN convolutional neural network is introduced for sufficiently extracting features between data to form a feature vector X t (t＝1,2,…T)。
Further, in the present invention, in step (S3), the specific procedure of the attention mechanism is as follows:
feature vector X extracted by CNN convolutional neural network t (t=1, 2, … T) is input into the LSTM long-term memory model to obtain an output vector h t (t=1, 2, … T); thereby obtaining an unnormalized weight matrix:
e t ＝u s tanh(w s h t +b s )； (1)
wherein ,ws 、b s and us The attention mechanism weight matrix, the offset and the time sequence matrix are initialized randomly respectively;
the probability distribution of attention from the attention mechanism to the LSTM output is obtained by equation (1):
and then the feature vector output by the attention mechanism is obtained by the formulas (1) and (2):
further, in the present invention, in step (S5), the correction basis for updating the prediction network is the deviation between the actual measured total power of the smart meter and the total power prediction value.
Compared with the prior art, the invention has the following beneficial effects:
according to the charging load prediction method, charging load data of the electric vehicle of the charging station or the charging pile is not required to be obtained, charging behavior and charging process simulation are not required, the household charging load is obtained through an ammeter installed by a household user through any non-invasive identification method, meanwhile, the lumped power of the ammeter is combined to input into a prediction network, the association relation between the charging load and the lumped power is excavated, and network deviation is corrected through the lumped power measured value. The prediction accuracy can be effectively improved, and meanwhile, the data type required by prediction is only household ammeter data, so that the method is easy to obtain. When the charging load demand is in the prediction area, all household prediction results are only needed to be overlapped, the load density, the load distribution and the like are not needed to be obtained, and the operation is simple and convenient.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a schematic diagram of a frame structure of the method of the present invention.
Detailed Description
The invention will be further illustrated by the following description and examples, which include but are not limited to the following examples.
Examples
As shown in fig. 1 and 2, the electric vehicle charging load prediction method based on ammeter data disclosed by the invention,
firstly, power data in a period of time is obtained from an ammeter arranged at a user inlet, and by combining with charging characteristics of an electric vehicle provided by a present household load data platform or an electric vehicle data platform and the like, a non-invasive identification method which is proposed in the prior study is adopted to extract charging load of the electric vehicle from user total load information collected from monitoring equipment, wherein the charging load comprises charging start time, charging end time, stable charging power and the like, and the charging condition of the electric vehicle in a period of time of the user is obtained, which is generally referred to as a charging power time sequence.
Further consider the time sequence relativity of the charging load of the electric automobile, namely the time sequence of the charging load of the electric automobile not only has nonlinear characteristics, but also the current moment load condition is not only related to the current moment load condition, but also can be influenced by the previous moment charging load condition. And taking the identification result of the charging load as the input of a prediction network, excavating the relevance of the charging load on time sequence, and predicting the charging condition in a future period of time. However, at the same time, there is a certain error in the identification of the charging load of the electric vehicle, and the prediction using only the non-invasive identification result as input will further introduce the error caused by the identification into the prediction result. In order to avoid error diffusion, in consideration of the association relationship between the lumped power data of the intelligent electric meter and the charging load of the electric automobile, the self-correlation of the charging load and the cross-correlation between the lumped power data and the identification result are taken as input, so that the prediction precision is improved.
After the input data is determined, based on time sequence association characteristics of the charging load of the electric automobile, a Long-term Memory model (LSTM) is adopted to capture the Long-term time sequence dependency relationship between the data, and the learning efficiency of the model can be ensured when a large number of training samples are input. On the other hand, the electric vehicle charging load has strong randomness and uncertainty, and features related to the charging load need to be captured from long data samples, so that a convolutional neural network (Convolutional Neural Network, CNN) is introduced to fully extract features among data to form feature vectors, and the feature vectors are input into an LSTM. Meanwhile, the attention mechanism (Attention Mechanism) can screen information, concentrate on valuable data to perform association mining, and highlight some important characteristics of the valuable data.
The specific process of the attention mechanism is as follows:
feature vector X extracted by CNN convolutional neural network t (t=1, 2, … T) is input into the LSTM long-term memory model to obtain an output vector h t (t=1, 2, … T); thereby obtaining an unnormalized weight matrix:
e t ＝u s tanh(w s h t +b s )； (1)
wherein ,ws 、b s and us The attention mechanism weight matrix, the offset and the time sequence matrix are initialized randomly respectively;
the probability distribution of attention from the attention mechanism to the LSTM output is obtained by equation (1):
and then the feature vector output by the attention mechanism is obtained by the formulas (1) and (2):
introducing an attention mechanism behind the LSTM layer, inputting an LSTM layer output matrix, giving different weights to the hidden state of the LSTM layer through mapping weighting and learning parameter matrix, enabling the network to concentrate on the characteristic relation of the network and better modeling, and enabling the model function to be more approximate to the real situation; finally, adding a Dropout layer prevents overfitting, and prevents certain characteristics from being effective only under fixed combination by randomly extracting neurons with certain probability in a model, so that the network is intentionally allowed to learn some common commonalities instead of the characteristics of certain training samples, and the local optimization is prevented.
And (3) inputting an identification result of the charging load of the electric automobile and a lumped power sequence of the intelligent electric meter, adjusting network parameters such as an activation function, a loss function, an optimization function, the number of network layers, the number of neurons and the like, training and verifying a network, and outputting a predicted sequence of the charging load of the electric automobile and a predicted result of the lumped power of the intelligent electric meter through a constructed CNN-LSTM-Attention prediction network learning training. Because the charging load data of the electric automobile cannot be directly measured but is acquired through a non-invasive identification method, the charging load data has deviation from the actual charging condition; the lumped power of the intelligent electric meter can be updated at a certain sampling frequency, so that the deviation between the actual measured lumped power of the intelligent electric meter and the lumped power predicted value is considered as the basis for the correction of the prediction network, and the prediction error is reduced along with the updating of the lumped data of the intelligent electric meter. And predicting the charging load of the community electric automobile, and collecting the prediction results of each user.
The above embodiment is only one of the preferred embodiments of the present invention, and should not be used to limit the scope of the present invention, but all the insubstantial modifications or color changes made in the main design concept and spirit of the present invention are still consistent with the present invention, and all the technical problems to be solved are included in the scope of the present invention.
Claims (5)
1. The electric automobile charging load prediction method based on the ammeter data is characterized by comprising the following steps of:
(S1) acquiring charging load of a user electric automobile by adopting non-invasive load identification according to acquired resident user ammeter data;
(S2) input feature selection: according to the identification result of the charging load of the electric automobile, combining the total power data of the intelligent ammeter to serve as input data of a prediction network to be constructed;
(S3) constructing a prediction network: digging an input data association relation by using CNN-LSTM, introducing an attention mechanism to obtain important feature vectors, and adding the feature vectors into a Dropout layer to prevent overfitting;
s4, outputting a charging load prediction result of the electric vehicle and a total power prediction result of the intelligent ammeter through a prediction network;
and (S5) rolling and updating the prediction network according to the actual measurement condition of the total power of the intelligent ammeter, so as to reduce the deviation.
2. The electric vehicle charging load prediction method based on ammeter data according to claim 1, wherein in step (S3), an LSTM long-term memory model is used to capture long-term time sequence dependency relationships between input data, and learning efficiency of the model can be ensured when a large number of training samples are input.
3. The electric vehicle charging load prediction method based on ammeter data according to claim 2, wherein in step (S3), a CNN convolutional neural network is introduced for fully extracting feature formation feature vectors between dataX t (t=1,2,…T)。
4. The electric vehicle charging load prediction method based on electricity meter data according to claim 3, wherein in step (S3), the specific procedure of the attention mechanism is as follows:
feature vector extracted by CNN convolutional neural networkX t (t=1,2,…T) Inputting into LSTM long-term memory model to obtain output vectorh t (t=1,2,…T) The method comprises the steps of carrying out a first treatment on the surface of the Thereby obtaining an unnormalized weight matrix:
（1）；
wherein ,、/> and />The attention mechanism weight matrix, the offset and the time sequence matrix are initialized randomly respectively;
the probability distribution of attention from the attention mechanism to the LSTM output is obtained by equation (1):
（2）；
and then the feature vector output by the attention mechanism is obtained by the formulas (1) and (2):
（3）。
5. the method according to claim 4, wherein in step (S5), the correction basis for updating the prediction network is a deviation between the actual measured total power of the smart meter and the total power predicted value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210144543.5A CN114498634B (en) | 2022-02-17 | 2022-02-17 | Electric automobile charging load prediction method based on ammeter data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210144543.5A CN114498634B (en) | 2022-02-17 | 2022-02-17 | Electric automobile charging load prediction method based on ammeter data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114498634A CN114498634A (en) | 2022-05-13 |
| CN114498634B true CN114498634B (en) | 2023-08-29 |
Family
ID=81482763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210144543.5A Active CN114498634B (en) | 2022-02-17 | 2022-02-17 | Electric automobile charging load prediction method based on ammeter data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114498634B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115112989B (en) * | 2022-08-29 | 2022-11-22 | 四川大学 | Non-invasive load monitoring method based on low-frequency data |
| CN116108320B (en) * | 2023-04-13 | 2023-06-09 | 佳源科技股份有限公司 | Intelligent electric energy meter operation control method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570014A (en) * | 2019-08-07 | 2019-12-13 | 浙江大学 | Electric vehicle charging load prediction method based on Monte Carlo and deep learning |
| CN111476441A (en) * | 2020-05-29 | 2020-07-31 | 南方电网科学研究院有限责任公司 | Load prediction method for electric vehicle charging equipment and related device |
| CN112016734A (en) * | 2020-04-07 | 2020-12-01 | 沈阳工业大学 | Stack type self-coding multi-model load prediction method and system based on LSTM |
| CN112134300A (en) * | 2020-10-09 | 2020-12-25 | 国网江苏省电力有限公司无锡供电分公司 | Reservation-based rolling optimization operation method and system for electric vehicle light storage charging station |
| CN112200373A (en) * | 2020-10-15 | 2021-01-08 | 中国科学院深圳先进技术研究院 | Training method and training device for load prediction model, storage medium and equipment |
| CN112766078A (en) * | 2020-12-31 | 2021-05-07 | 辽宁工程技术大学 | Power load level prediction method of GRU-NN based on EMD-SVR-MLR and attention mechanism |
| CN113067355A (en) * | 2021-03-30 | 2021-07-02 | 四川大学 | Electric automobile flexibility mining and cooperative regulation and control method for improving reliability of power grid |
| CN113435663A (en) * | 2021-07-15 | 2021-09-24 | 国网冀北电力有限公司唐山供电公司 | CNN-LSTM combined load prediction method considering electric vehicle charging load influence |
| CN113627661A (en) * | 2021-08-02 | 2021-11-09 | 深圳供电局有限公司 | Method for predicting charging load of electric automobile |
-
2022
- 2022-02-17 CN CN202210144543.5A patent/CN114498634B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570014A (en) * | 2019-08-07 | 2019-12-13 | 浙江大学 | Electric vehicle charging load prediction method based on Monte Carlo and deep learning |
| CN112016734A (en) * | 2020-04-07 | 2020-12-01 | 沈阳工业大学 | Stack type self-coding multi-model load prediction method and system based on LSTM |
| CN111476441A (en) * | 2020-05-29 | 2020-07-31 | 南方电网科学研究院有限责任公司 | Load prediction method for electric vehicle charging equipment and related device |
| CN112134300A (en) * | 2020-10-09 | 2020-12-25 | 国网江苏省电力有限公司无锡供电分公司 | Reservation-based rolling optimization operation method and system for electric vehicle light storage charging station |
| CN112200373A (en) * | 2020-10-15 | 2021-01-08 | 中国科学院深圳先进技术研究院 | Training method and training device for load prediction model, storage medium and equipment |
| CN112766078A (en) * | 2020-12-31 | 2021-05-07 | 辽宁工程技术大学 | Power load level prediction method of GRU-NN based on EMD-SVR-MLR and attention mechanism |
| CN113067355A (en) * | 2021-03-30 | 2021-07-02 | 四川大学 | Electric automobile flexibility mining and cooperative regulation and control method for improving reliability of power grid |
| CN113435663A (en) * | 2021-07-15 | 2021-09-24 | 国网冀北电力有限公司唐山供电公司 | CNN-LSTM combined load prediction method considering electric vehicle charging load influence |
| CN113627661A (en) * | 2021-08-02 | 2021-11-09 | 深圳供电局有限公司 | Method for predicting charging load of electric automobile |
Non-Patent Citations (1)
| Title |
|---|
| 刘继春 ; 贾琢玉 ; 向月 ; 杨昕然 ; 刘俊勇 ; .泛在电力物联网下电动汽车充电服务费定价模型.工程科学与技术.2020,(04),27-35. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114498634A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114498634B (en) | Electric automobile charging load prediction method based on ammeter data | |
| Li et al. | Probabilistic charging power forecast of EVCS: Reinforcement learning assisted deep learning approach | |
| CN110070713A (en) | A kind of traffic flow forecasting method based on two-way nested-grid ocean LSTM neural network | |
| Panahi et al. | Forecasting plug-in electric vehicles load profile using artificial neural networks | |
| CN103605757B (en) | High-speed rail power quality data sorting method based on SVM (support vector machine) | |
| CN107991873A (en) | A kind of metro stray current leakage class Forecasting Methodology based on convolutional neural networks and BP neural network | |
| CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
| CN103136539A (en) | Grounding grid corrosion rate level prediction method | |
| CN103268519A (en) | Electric power system short-term load forecast method and device based on improved Lyapunov exponent | |
| Zhao et al. | Short term traffic flow prediction of expressway service area based on STL-OMS | |
| CN105911476A (en) | Battery energy storage system SOC predication method based on data mining | |
| CN105809349A (en) | Scheduling method considering incoming water correlation cascade hydropower stations | |
| CN111695666A (en) | Wind power ultra-short term conditional probability prediction method based on deep learning | |
| Li et al. | Forecast of renewable energy penetration potential in the goal of carbon peaking and carbon neutrality in China | |
| CN112632840A (en) | Power grid transient stability evaluation method based on adaptive differential evolution algorithm and ELM | |
| CN107203827A (en) | A kind of wind turbine forecasting wind speed optimization method based on multiscale analysis | |
| CN105303835B (en) | A kind of Forecasting Approach for Short-term of road traffic stream mode | |
| Gao et al. | Charging load forecasting of electric vehicle based on Monte Carlo and deep learning | |
| CN106570582A (en) | Method and system for building transmission line dancing tripping risk prediction network model | |
| Pan et al. | Development of an energy consumption prediction model for battery electric vehicles in real-world driving: a combined approach of short-trip segment division and deep learning | |
| Ding et al. | Optimal management of parking lots as a big data for electric vehicles using internet of things and Long–Short term Memory | |
| CN103020733A (en) | Method and system for predicting single flight noise of airport based on weight | |
| CN107480897A (en) | A kind of Ecological Project Construction performance evaluation method | |
| Miao et al. | A queue hybrid neural network with weather weighted factor for traffic flow prediction | |
| CN106529713A (en) | Grey GMDH network combination model-based wind speed prediction method and system |
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 |