CN114781915A - Method, device and system for acquiring energy consumption characteristics and edge proxy equipment - Google Patents
Method, device and system for acquiring energy consumption characteristics and edge proxy equipment Download PDFInfo
- Publication number
- CN114781915A CN114781915A CN202210513422.3A CN202210513422A CN114781915A CN 114781915 A CN114781915 A CN 114781915A CN 202210513422 A CN202210513422 A CN 202210513422A CN 114781915 A CN114781915 A CN 114781915A
- Authority
- CN
- China
- Prior art keywords
- data
- energy consumption
- power
- fuzzy
- control process
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
Abstract
The application discloses a method, a device and a system for acquiring energy consumption characteristics and edge proxy equipment, wherein the method comprises the following steps: acquiring energy consumption data of industrial production equipment in energy consumption monitoring equipment and power data of new energy power generation equipment in an inverter; monitoring and controlling the state information of the inverter, and acquiring control process data; and decomposing the energy consumption data and the power data into information particle sequences based on the control process data, sending the information particle sequences to a monitoring center, and predicting the energy consumption characteristics by the monitoring center according to the information particle sequences. The method solves the problems that due to the defects of analysis and evaluation means, the existing energy consumption analysis method based on artificial intelligence and the like can not guarantee to give a complete and real causal structure, and certain risks exist in application. The method improves the correlation between the analysis method and the operation rule of the actual equipment, meets the requirements of industrial control on high reliability and high stability, and further supports planning, construction, operation and maintenance of the low-carbon industrial park.
Description
Technical Field
The present application relates to the field of optimal configuration of an integrated energy system, and in particular, to a method, an apparatus, a system, and an edge proxy device for acquiring energy consumption characteristics.
Background
Industrial production is an important energy consuming entity. With the continuous improvement of science and technology and management level, distributed new energy sources such as photovoltaic power generation, wind power generation, tidal power generation and the like are built in an industrial park to realize reasonable utilization and optimized scheduling of the energy sources in the industrial production process, and the method is an inevitable requirement and an important way for reducing the energy consumption of the industrial park.
In general, the energy consumption of an industrial park is closely related to the production process and the distributed new energy power generation process. For example, under the influence of the production process flow and the operation state of industrial equipment, the energy consumption of an industrial park has the characteristic of high-frequency fluctuation; under the influence of production plan adjustment, the energy consumption of the industrial park shows periodic characteristics related to social factors; the distributed new energy power generation has the influence of intermittent characteristics, and the energy consumption of the industrial park has the periodic fluctuation characteristics. Therefore, obtaining effective energy consumption characteristics is very important for low-carbon operation of the industrial park, and supports planning, construction, operation and maintenance of the industrial park.
However, due to the lack of analysis and evaluation means, the existing energy consumption analysis method based on artificial intelligence and the like usually judges the energy consumption of the industrial park through a certain rule, cannot guarantee to give a complete and real causal structure, and the industrial control requires high reliability and high stability, so that the existing energy consumption analysis method has certain risks in application.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, a system, and an edge proxy device for obtaining energy consumption characteristics, so as to improve reliability and stability of industrial control.
According to a first aspect, an embodiment of the present invention provides a method for acquiring an energy consumption characteristic, where the method is applied to an edge proxy device, and the method includes:
acquiring energy consumption data of industrial production equipment in the energy consumption monitoring equipment;
acquiring power data of new energy power generation equipment in an inverter;
monitoring and controlling the state information of the inverter, and acquiring control process data;
and decomposing the energy consumption data and the power data into information particle sequences based on the control process data, and sending the information particle sequences to a monitoring center so that the monitoring center predicts energy consumption characteristics according to the information particle sequences.
With reference to the first aspect, in a first embodiment of the first aspect, the status information includes at least one of voltage, current, active power, and reactive power, and the controlling includes frequency modulation control and/or voltage regulation control;
the control process data includes a plurality of data samples, each of the data samples having a plurality of attribute values, the attribute values including at least one of a voltage, a current, an active power, a reactive power, a phase control signal, a frequency control signal, and a voltage control signal.
With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the decomposing the energy consumption data and the power data into a sequence of information particles based on the control process data includes:
performing fuzzy clustering processing on the control process data to generate a time window sequence of the control process data;
and decomposing the energy consumption data and the power data according to the time window sequence based on the time window sequence to obtain an information particle sequence of the energy consumption data and the power data.
With reference to the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the performing fuzzy clustering processing on the control process data to generate a time window sequence of the control process data includes:
dividing the control process data into a plurality of fuzzy prototype types, and constructing the fuzzy prototype types into fuzzy prototype matrixes;
obtaining the degree value of the data sample belonging to each fuzzy prototype so as to construct a fuzzy partition matrix;
solving the fuzzy partition matrix and the fuzzy prototype matrix, and acquiring a solving result;
and performing ascending arrangement on the solving results to obtain a time window series.
With reference to the third embodiment of the first aspect, in the fourth embodiment of the first aspect, the degree value is determined by the following formula:
wherein u isim∈[0,1]Uim denotes the degree value of the ith fuzzy class prototype to which the mth data sample belongs, i ∈ [1, c]C represents the number of the fuzzy prototypes, and M represents the number of data samples in the control process data;
constructing a fuzzy partition matrix by the following formula:
U＝[uim]∈Rc×M；
wherein, U represents a fuzzy partition matrix for storing a degree value corresponding to each data sample, and R represents that the result of the computation is in a matrix form.
With reference to the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the solving the fuzzy partition matrix and the fuzzy prototype matrix, and obtaining a solution result includes:
solving the fuzzy partition matrix and the fuzzy prototype matrix by the following formulas:
q represents an objective function, dm represents an mth data sample in the control process data, vi represents an ith fuzzy prototype, V represents the fuzzy prototype matrix, f represents a fuzzification factor, and f > 1.
With reference to any one of the second implementation manner to the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, the decomposing the energy consumption data and the power data according to the time window sequence based on the time window sequence to obtain an information particle sequence of the energy consumption data and the power data includes:
based on the time window sequence, dividing the energy consumption data and the power data into a plurality of energy consumption subsets and a plurality of power subsets, wherein the energy consumption subsets and the power subsets are in one-to-one correspondence based on the time window sequence;
and acquiring the maximum value and the minimum value of each energy consumption subset, acquiring the maximum value and the minimum value of each power subset, and taking the combination of the maximum value and the minimum value as the information grain characteristics of the corresponding energy consumption subset and the corresponding power subset, wherein the set of each information grain characteristic forms an information grain sequence.
According to a second aspect, an embodiment of the present invention provides an apparatus for obtaining energy consumption characteristics, where the apparatus includes:
the energy consumption data acquisition module is used for acquiring energy consumption data of industrial production equipment in the energy consumption monitoring equipment;
the power data acquisition module is used for acquiring power data of the new energy power generation equipment in the inverter;
the control process data acquisition module is used for monitoring and controlling the state information of the inverter and acquiring control process data;
and the energy consumption characteristic acquisition module is used for decomposing the energy consumption data and the power data into information particle sequences based on the control process data and sending the information particle sequences to a monitoring center so that the monitoring center can predict the energy consumption characteristics according to the information particle sequences.
According to a third aspect, an embodiment of the present invention provides an edge proxy device, which includes a processor and a memory for storing executable instructions of the processor;
wherein the executable instructions, when executed by the processor, implement the following functions:
acquiring energy consumption data of industrial production equipment in the energy consumption monitoring equipment;
acquiring power data of new energy power generation equipment in an inverter;
monitoring and controlling the state information of the inverter, and acquiring control process data;
and decomposing the energy consumption data and the power data into information particle sequences based on the control process data, and sending the information particle sequences to a monitoring center so that the monitoring center can predict energy consumption characteristics according to the information particle sequences.
According to a fourth aspect, an embodiment of the present invention provides an energy consumption feature obtaining system, including: the system comprises industrial production equipment, energy consumption monitoring equipment, new energy power generation equipment, a combiner box, an inverter, a transformer, a monitoring center and edge proxy equipment provided by the third aspect of the embodiment of the invention;
the edge agent equipment is connected with the energy consumption monitoring equipment through a wireless network, connected with the inverter through a Modbus communication protocol and connected with the monitoring center through an industrial switch.
The technical scheme provided by the application can comprise the following beneficial effects:
the embodiment of the application provides a method, a device and a system for acquiring energy consumption characteristics and edge proxy equipment, wherein the relevance between the energy consumption characteristics of an industrial park and a production process and the relevance between the energy consumption characteristics of the industrial park and a distributed new energy power generation process are considered by acquiring energy consumption data of industrial production equipment and power data of new energy power generation equipment; by acquiring control process data of the inverter, factors such as production processes, high-frequency fluctuation of energy consumption of industrial equipment, intermittent fluctuation of distributed energy generation and the like are considered; the energy consumption data and the power data are decomposed into information particle sequences, particle calculation is introduced, a complete and real causal structure is given, the correlation between an analysis method and the operation rule of actual equipment is improved, the influence of different periodic characteristics of energy production and consumption on the energy consumption characteristics is more accurately described, the high reliability and high stability required by industrial control are met, and the planning, construction, operation and maintenance of a low-carbon industrial park are further supported.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments are briefly described below, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a method for acquiring an energy consumption characteristic according to an embodiment of the present application.
Fig. 2 is a flowchart of a method for acquiring an energy consumption characteristic according to an embodiment of the present disclosure.
Fig. 3 is a block diagram of a structure of an apparatus for acquiring an energy consumption characteristic disclosed in an embodiment of the present application.
Fig. 4 is a schematic diagram of an edge proxy apparatus disclosed in an embodiment of the present application.
Fig. 5 is a schematic structural diagram of an energy consumption characteristic obtaining system disclosed in an embodiment of the present application.
Fig. 6 is a schematic diagram of a long-short term memory network according to an embodiment of the disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the method, the apparatus, the system and the edge proxy device for obtaining energy consumption characteristics provided in this specification relate to the technical field of optimal configuration of an integrated energy system, for example, the field of energy consumption analysis of an industrial park, and the like. In the examples described below, the energy consumption analysis field applied to the industrial park is described in detail as an example.
Due to the lack of analysis and evaluation means, the existing energy consumption analysis method based on artificial intelligence and the like usually judges the energy consumption of an industrial park through a certain rule, cannot guarantee that a complete and real causal structure is given, industrial control requires high reliability and high stability, and the existing energy consumption analysis method has certain risks in application.
Based on this, an embodiment of the present application provides a method for acquiring an energy consumption characteristic, which is applied to an edge proxy device, and as shown in fig. 1, the method includes:
and S101, acquiring energy consumption data of industrial production equipment in the energy consumption monitoring equipment.
Specifically, the edge proxy device may be a dedicated computer for performing data processing nearby. The energy consumption monitoring device monitors and acquires energy consumption data of the industrial production device, the energy consumption data edge proxy device acquires the energy consumption data from the energy consumption monitoring device, and the energy consumption data can be defined as a time sequence data set E:
E＝{e1,e2....en}；
as can be seen, the time-series data set E (i.e., energy consumption data) is composed of n time-series data E, where the time-series data refers to time-series data. The time-series data is a data series recorded in time series according to a uniform index. Each data in the same data column must be of the same caliber, requiring comparability. The time series data can be the number of epochs or the number of epochs. The purpose of time series analysis is to develop regularity by finding out the statistical properties of the time series within the sample.
And S102, acquiring power data of the new energy power generation equipment in the inverter.
Specifically, the new energy power generation equipment can be photovoltaic power generation equipment, wind power generation equipment, tidal power generation equipment and the like, in an actual application scene, the photovoltaic power generation equipment is very refined, reliable, stable, long in service life and simple and convenient to install and maintain, and can be used for any occasions needing a power supply and the like. The inverter acquires power data of the photovoltaic module (new energy power generation equipment), and the edge proxy equipment acquires the power data from the inverter, wherein the power data can be defined as a time sequence data set P:
P＝{p1,p2...pn}；
therefore, the time sequence data set P (namely the power data) is composed of n time sequence data P, and by acquiring the energy consumption data of the industrial production equipment and the power data of the new energy power generation equipment, the relevance between the energy consumption characteristics of the industrial park and the production process and the distributed new energy power generation process is considered.
And step S103, monitoring and controlling the state information of the inverter and acquiring control process data.
Specifically, the state information includes at least one of voltage, current, active power and reactive power, and the control includes frequency modulation control and/or voltage regulation control; the control process data includes a plurality of data samples, each data sample having a plurality of attribute values including at least one of a voltage, a current, an active power, a reactive power, a phase control signal, a frequency control signal, and a voltage control signal. The edge proxy equipment monitors and controls the state information of the inverter and acquires control process data. Wherein, the frequency modulation control is to control the frequency to be 50HZ alternating current, and the voltage regulation control is to control the voltage to be 10 kilovolt grade. The control process data may be defined as a data set D containing M data samples:
D＝{d1,d2...dM}；
wherein each data sample may comprise s attribute values due to different types of monitoring state quantities and control signals, and thus the target data sample D in the data set DmCan be expressed as:
dm＝{d1m,d2m...dsm}；
it should be noted that the target data sample dm may be any data sample in the data set D.
And step S104, decomposing the energy consumption data and the power data into information particle sequences based on the control process data, and sending the information particle sequences to a monitoring center so that the monitoring center can predict energy consumption characteristics according to the information particle sequences.
Specifically, the edge proxy device performs fuzzy clustering processing on the control process data, performs fuzzy C-means clustering on the data set D (control process data), namely, divides the data set D (control process data) into C fuzzy prototype models to construct a fuzzy prototype matrix, and obtains a degree value of each fuzzy prototype which the data sample belongs to through the following formula to construct a fuzzy partition matrix:
wherein u isim∈[0,1]，uimRepresenting the degree value of the ith fuzzy class prototype to which the mth data sample belongs, i ∈ [1, c ∈ [ ]]C represents the number of the fuzzy class prototypes, and M represents the number of data samples in the control process data.
It should be noted that the fuzzy class prototype matrix is used for storing each fuzzy class prototype, and is presented in the form of a matrix, which can be represented by the following formula:
V＝[v1,v2...vc]∈Rs×c；
wherein, V expresses the fuzzy prototype matrix for storing each fuzzy prototype, ViFuzzy class prototype representing ith, i ∈ [1, c)]R represents that the calculation result is in a matrix form, c represents the number of fuzzy prototype types, and s represents the number of attribute values contained in the data sample.
The fuzzy partition matrix is used for storing the corresponding degree value of each data sample, is presented in a matrix form, and can be represented by the following formula:
U＝[uim]∈Rc×M；
wherein, U represents a fuzzy partition matrix, and R represents that the calculation result is in a matrix form.
After the fuzzy prototype matrix and the fuzzy partition matrix are constructed, the edge proxy equipment solves the fuzzy partition matrix and the fuzzy prototype matrix through the following formulas, and obtains a solving result:
wherein Q represents an objective function, dmRepresents the m-th data sample, v, in the control process dataiRepresenting the fuzzy prototype of the ith, V representing the fuzzy prototype matrix, f representing the fuzzification factor, f>1。
After obtaining the solution result, the edge proxy device performs ascending arrangement on the solution result to obtain a time window series, and divides the energy consumption data and the power data into a plurality of energy consumption subsets and a plurality of power subsets which are in one-to-one correspondence based on the time window series, so that the number of the time windows in the time window series is the same as the number of the energy consumption subsets and the number of the power subsets, and the time windows are in one-to-one correspondence.
After the subsets are divided, the edge proxy device acquires the maximum value and the minimum value of each energy consumption subset and the maximum value and the minimum value of each power subset, the combination of the maximum value and the minimum value of the corresponding energy consumption subset and power subset is used as the information particle characteristics of the corresponding energy consumption subset and power subset, the set of each information particle characteristic forms an information particle sequence (namely, the time sequence data set E and the time sequence data set P are respectively divided into a plurality of energy consumption subsets Ex and power subsets Px, then the minimum value and the maximum value of each energy consumption subset Ex and power subset Px are used for describing the information particle characteristics, for example, ten time windows in the time window sequence, the edge proxy device divides the energy consumption data and the power data into ten energy consumption subsets and ten power subsets which are in one-to-one correspondence according to each time window, therefore, the first information particle characteristic is a set formed by the minimum value and the maximum value of the first energy consumption subset and the first power subset corresponding to the first time window, and so on, ten information particle characteristics are obtained, and these ten information particle characteristics form the final information particle sequence), and the target information particle characteristic can be represented by the following formula:
Ωx＝[min(Ex),min(Px),max(Ex),max(Px)]；
wherein omegaxRepresenting a target information particle characteristic, wherein the target information particle characteristic is any information particle characteristic in the information particle sequence.
And finally, after the edge proxy equipment obtains the information particle sequence, the information particle sequence is sent to a monitoring center, and the monitoring center predicts the energy consumption characteristics according to the information particle sequence.
It should be noted that the monitoring center may use the information particle sequence as an input of a Long Short-Term Memory network (LSTM) to predict the energy consumption characteristics. A Long Short-Term Memory network (LSTM) is a time-cycle neural network, and features in sequence input data are learned through a gating mechanism, wherein the features comprise a forgetting gate, an input gate, an output gate and a storage unit. Wherein the memory unit can memorize information at any time interval, and the three gates regulate the information flow entering the memory unit. Referring to the schematic diagram of the Long-Short Term Memory network provided in fig. 6, fig. 6 is a Long-Short Term Memory network (LSTM) model with two-step sequence input, which can be implemented by a tensrflow platform, wherein a gate control unit uses a sigmoid function, denoted by σ, and generates contents to be updated by candidates using a tanh function in an input gate. The method realizes the identification of the energy consumption characteristics based on the Long Short-Term Memory network (LSTM), and can more accurately describe the influence of different periodic rules of energy production and consumption on the energy consumption characteristics compared with an analysis method based on a single time dimension.
In summary, the embodiment of the present application provides an energy consumption characteristic obtaining method, which considers the relevance between the energy consumption characteristics of an industrial park and a production process and a distributed new energy power generation process by obtaining energy consumption data of industrial production equipment and power data of new energy power generation equipment; through the acquisition of control process data of the inverter, factors such as production procedures, high-frequency fluctuation of energy consumption of industrial equipment, intermittent fluctuation of distributed energy generation and the like are considered; the energy consumption data and the power data are decomposed into information particle sequences, particle calculation is introduced, a complete and real causal structure is given, the correlation between an analysis method and the operation rule of actual equipment is improved, the influence of different periodic characteristics of energy production and consumption on the energy consumption characteristics is more accurately described, the high reliability and high stability required by industrial control are met, and the planning, construction, operation and maintenance of a low-carbon industrial park are further supported.
Fig. 2 shows another flowchart of a method for obtaining an energy consumption characteristic according to an embodiment of the present application, where the method may include the following steps:
step S201, energy consumption data of industrial production equipment in the energy consumption monitoring equipment is obtained.
In one possible implementation, the edge proxy device may be a dedicated computer for performing data processing nearby. The energy consumption monitoring device monitors and acquires energy consumption data of the industrial production device, the energy consumption data edge proxy device acquires the energy consumption data from the energy consumption monitoring device, and the energy consumption data can be defined as a time sequence data set E:
E＝{e1,e2....en}；
as can be seen, the time-series data set E (i.e., energy consumption data) is composed of n time-series data E, where the time-series data refers to time-series data. The time-series data is a data sequence in which the same uniform index is recorded in time series. The data in the same data column must be of the same aperture, requiring comparability. The time series data can be the number of epochs or the number of epochs. The purpose of time series analysis is to develop regularity by finding out the statistical properties of the time series within the sample.
And S202, acquiring power data of the new energy power generation equipment in the inverter.
In practical application scenarios, the photovoltaic power generation equipment is extremely refined, reliable, stable, long in service life, simple and convenient to install and maintain, and can be used for any occasions needing power supplies, and the like. The inverter acquires power data of the photovoltaic module (new energy power generation equipment), and the edge proxy equipment acquires the power data from the inverter, wherein the power data can be defined as a time sequence data set P:
P＝{p1,p2...pn}；
therefore, the time sequence data set P (namely the power data) is composed of n time sequence data P, and by acquiring the energy consumption data of the industrial production equipment and the power data of the new energy power generation equipment, the relevance between the energy consumption characteristics of the industrial park and the production process and the relevance between the energy consumption characteristics of the industrial park and the distributed new energy power generation process are considered.
And step S203, monitoring and controlling the state information of the inverter and acquiring control process data.
In one possible implementation, the status information includes at least one of voltage, current, active power and reactive power, and the controlling includes frequency modulation control and/or voltage regulation control; the control process data includes a plurality of data samples, each having a plurality of attribute values including at least one of a voltage, a current, an active power, a reactive power, a phase control signal, a frequency control signal, and a voltage control signal. The edge proxy equipment monitors and controls the state information of the inverter and acquires control process data. The frequency modulation control is to control the frequency to be 50HZ alternating current, and the voltage regulation control is to control the voltage to be 10 kilovolt grade. The control process data may be defined as a data set D containing M data samples:
D＝{d1,d2...dM}；
since each data sample may include s attribute values due to the different types of the monitoring state quantity and the control signal, the target data sample dm in the data set D may be represented as:
dm＝{d1m,d2m...dsm}；
it should be noted that the target data sample dm may be any data sample in the data set D.
Step S204, carrying out fuzzy clustering processing on the control process data to generate a time window sequence of the control process data;
in a possible implementation manner, the control process data is divided into a plurality of fuzzy prototype models, and the plurality of fuzzy prototype models obtained through division are constructed into a fuzzy prototype matrix; acquiring degree values of the data samples belonging to the fuzzy prototype classes to construct a fuzzy partition matrix; solving the fuzzy partition matrix and the fuzzy prototype matrix, and obtaining a solving result; and (4) carrying out ascending arrangement on the solving results to obtain a time window series.
In another possible implementation, the degree value is determined by the following formula:
wherein u isim∈[0,1]，uimRepresenting the degree value of the ith fuzzy class prototype to which the mth data sample belongs, i belongs to [1, c ]]C represents theThe number of fuzzy class prototypes, M, represents the number of data samples in the control process data.
Constructing a fuzzy partition matrix by the following formula:
U＝[uim]∈Rc×M；
wherein, U represents a fuzzy partition matrix for storing a degree value corresponding to each data sample, and R represents that the calculation result is in a matrix form.
It should be noted that the fuzzy class prototype matrix is used for storing each fuzzy class prototype, and is presented in the form of a matrix, which can be represented by the following formula:
V＝[v1,v2...vc]∈Rs×c；
wherein, V expresses the fuzzy prototype matrix for storing each fuzzy prototype, ViFuzzy class prototype representing ith, i ∈ [1, c ]]R represents that the calculation result is in a matrix form, c represents the number of fuzzy prototype types, and s represents the number of attribute values contained in the data sample.
In another possible implementation, the fuzzy partition matrix and the fuzzy prototype matrix are solved by the following formulas:
wherein Q represents an objective function, dmRepresents the m-th data sample, v, in the control process dataiRepresenting the fuzzy prototype of the ith, V representing the fuzzy prototype matrix, f representing the fuzzification factor, f>1。
Step S205, decomposing the energy consumption data and the power data according to the time window sequence based on the time window sequence to obtain an information particle sequence of the energy consumption data and the power data.
In one possible implementation, the energy consumption data and the power data are divided into a plurality of energy consumption subsets and a plurality of power subsets based on the time window sequence, and the energy consumption subsets and the power subsets are in one-to-one correspondence based on the time window sequence. And acquiring the maximum value and the minimum value of each energy consumption subset, acquiring the maximum value and the minimum value of each power subset, and taking the combination of the maximum value and the minimum value as the information particle characteristics of the corresponding energy consumption subset and power subset, wherein the set of each information particle characteristic forms an information particle sequence. (that is, the time-series data set E and the time-series data set P are respectively divided into a plurality of energy consumption subsets Ex and power subsets Px, and then the minimum value and the maximum value of each energy consumption subset Ex and power subset Px are used to describe the information particle characteristics, for example, ten time windows in the time window sequence are used, then the edge proxy device divides the energy consumption data and the power data into ten energy consumption subsets corresponding to one another and ten power subsets according to each time window, so that the first information particle characteristic is a set formed by the respective minimum value and maximum value of the first energy consumption subset and the first power subset corresponding to the first time window, and so on, ten information particle characteristics are obtained, and these ten information particle characteristics form the final information particle sequence), and the target information particle characteristic can be represented by the following formula:
Ωx＝[min(Ex),min(Px),max(Ex),max(Px)]；
wherein omegaxRepresenting a target information particle characteristic, wherein the target information particle characteristic is any information particle characteristic in the information particle sequence.
And step S206, sending the information particle sequence to a monitoring center so that the monitoring center can predict the energy consumption characteristics according to the information particle sequence.
It should be noted that the monitoring center may use the information particle sequence as an input of a Long Short-Term Memory network (LSTM) to predict the energy consumption characteristics. Long Short-Term Memory networks (LSTM) are a time-cycled neural network that learns features in sequential input data through a gating mechanism, including forgetting gates, input gates, output gates, and storage cells. Wherein the memory unit can memorize information at any time interval, and the three gates regulate the information flow entering the memory unit. Referring to fig. 6, a schematic diagram of a Long-Short-Term Memory network is provided, and fig. 6 is a Long-Short-Term Memory network (LSTM) model with two-step sequence input, which can be implemented by a tensrflow platform, wherein a gate control unit uses a sigmoid function, denoted by σ, and generates contents to be updated in an input gate by using a tanh function. The method realizes the identification of the energy consumption characteristics based on the Long Short-Term Memory network (LSTM), and can more accurately describe the influence of different periodic rules of energy production and consumption on the energy consumption characteristics compared with an analysis method based on a single time dimension.
In summary, the embodiment of the present application provides an energy consumption characteristic obtaining method, which considers the relevance between the energy consumption characteristics of an industrial park and a production process and a distributed new energy power generation process by obtaining energy consumption data of industrial production equipment and power data of new energy power generation equipment; by acquiring control process data of the inverter, factors such as production processes, high-frequency fluctuation of energy consumption of industrial equipment, intermittent fluctuation of distributed energy generation and the like are considered; the energy consumption data and the power data are decomposed into information particle sequences, particle calculation is introduced, a complete and real causal structure is given, the correlation between an analysis method and the operation rule of actual equipment is improved, the influence of different periodic characteristics of energy production and consumption on the energy consumption characteristics is more accurately described, the high reliability and high stability required by industrial control are met, and the planning, construction, operation and maintenance of a low-carbon industrial park are further supported.
An embodiment of the present application provides an apparatus for obtaining an energy consumption characteristic, as shown in fig. 3, including:
the energy consumption data acquisition module 101 is configured to acquire energy consumption data of industrial production equipment in the energy consumption monitoring equipment.
And the power data acquisition module 102 is configured to acquire power data of the new energy power generation device in the inverter.
And a control process data acquisition module 103, configured to monitor and control the state information of the inverter, and acquire control process data.
It should be noted that the status information includes at least one of voltage, current, active power and reactive power, and the control includes frequency modulation control and/or voltage regulation control; the control process data includes a plurality of data samples, each of the data samples having a plurality of attribute values including at least one of a voltage, a current, an active power, a reactive power, a phase control signal, a frequency control signal, and a voltage control signal.
The energy consumption characteristic obtaining module 104 is configured to decompose the energy consumption data and the power data into an information particle sequence based on the control process data, and send the information particle sequence to a monitoring center, so that the monitoring center predicts an energy consumption characteristic according to the information particle sequence.
The energy consumption characteristic obtaining module 104 includes:
and the time window sequence acquisition submodule is used for carrying out fuzzy clustering processing on the control process data so as to generate a time window sequence of the control process data.
And the information particle sequence acquisition submodule is used for decomposing the energy consumption data and the power data according to the time window sequence based on the time window sequence so as to obtain the information particle sequence of the energy consumption data and the power data.
The time window sequence acquisition submodule includes:
and the fuzzy prototype matrix construction unit is used for dividing the control process data into a plurality of fuzzy prototypes and constructing the fuzzy prototype matrices by the plurality of fuzzy prototypes obtained by division.
And the fuzzy partition matrix construction unit is used for acquiring the degree value of the data sample attached to each fuzzy prototype so as to construct a fuzzy partition matrix.
And the solving result obtaining unit is used for solving the fuzzy partition matrix and the fuzzy prototype matrix and obtaining a solving result.
And the time window series acquisition unit is used for carrying out ascending arrangement on the solving results to acquire the time window series.
The fuzzy partition matrix construction unit comprises:
a first calculating subunit for determining the degree value by the following formula:
wherein u isim∈[0,1]，uimRepresenting the degree value of the ith fuzzy class prototype to which the mth data sample belongs, i ∈ [1, c ∈ [ ]]C represents the number of fuzzy prototype and M represents the number of data samples in the control process data.
A second calculating subunit, configured to construct a fuzzy partition matrix by the following formula:
U＝[uim]∈Rc×M；
wherein, U represents a fuzzy partition matrix for storing a degree value corresponding to each data sample, and R represents that the calculation result is in a matrix form.
The solution result obtaining unit includes:
the third calculation subunit is used for solving the fuzzy partition matrix and the fuzzy prototype matrix through the following formulas:
wherein Q represents an objective function, dmRepresents the m-th data sample, v, in the control process dataiRepresenting the fuzzy prototype of the ith, V representing the fuzzy prototype matrix, f representing the fuzzification factor, f>1。
The information particle sequence acquisition submodule comprises:
and the subset dividing unit is used for dividing the energy consumption data and the power data into a plurality of energy consumption subsets and a plurality of power subsets respectively based on the time window sequence, and the energy consumption subsets and the power subsets are in one-to-one correspondence based on the time window sequence.
And the information particle sequence acquisition unit is used for acquiring the maximum value and the minimum value of each energy consumption subset, acquiring the maximum value and the minimum value of each power subset, and taking the combination of the maximum value and the minimum value as the information particle characteristics of the corresponding energy consumption subset and the corresponding power subset, wherein the set of each information particle characteristic forms an information particle sequence.
To sum up, the embodiment of the present application provides an apparatus for acquiring energy consumption characteristics, which acquires energy consumption data of industrial production equipment and power data of new energy power generation equipment, and considers the relevance between the energy consumption characteristics of an industrial park and a production process and a distributed new energy power generation process; through the acquisition of control process data of the inverter, factors such as production procedures, high-frequency fluctuation of energy consumption of industrial equipment, intermittent fluctuation of distributed energy generation and the like are considered; the energy consumption data and the power data are decomposed into information particle sequences, particle calculation is introduced, a complete and real causal structure is given, the correlation between an analysis method and the operation rule of actual equipment is improved, the influence of different periodic characteristics of energy production and consumption on the energy consumption characteristics is more accurately described, the high reliability and high stability required by industrial control are met, and the planning, construction, operation and maintenance of a low-carbon industrial park are further supported.
An embodiment of the present application provides an edge proxy device, as shown in fig. 4, which includes a processor and a memory for storing executable instructions of the processor.
Wherein the executable instructions, when executed by the processor, implement the following functions:
and acquiring energy consumption data of industrial production equipment in the energy consumption monitoring equipment.
And acquiring power data of the new energy power generation equipment in the inverter.
And monitoring and controlling the state information of the inverter, and acquiring control process data.
And decomposing the energy consumption data and the power data into information particle sequences based on the control process data, and sending the information particle sequences to a monitoring center so that the monitoring center predicts energy consumption characteristics according to the information particle sequences.
It should be noted that the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement a vehicle control method according to an embodiment of the present application.
The processor may be a Central Processing Unit (CPU). The Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the methods of the embodiments of the present application. The processor executes various functional applications and data processing of the processor by executing non-transitory software programs, instructions and modules stored in the memory, that is, the method in the above method embodiment is realized.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
An embodiment of the present application provides an energy consumption characteristic obtaining system, as shown in fig. 5, including: industrial production equipment, energy consumption monitoring facilities, new forms of energy power generation equipment, collection flow box, dc-to-ac converter, transformer, surveillance center and the marginal agency equipment that this application embodiment provided.
The edge agent equipment is connected with the energy consumption monitoring equipment through a wireless network, connected with the inverter through a Modbus communication protocol and connected with the monitoring center through an industrial switch.
In an actual application scene, because the photovoltaic power generation equipment is extremely refined, reliable, stable, long in service life and simple and convenient to install and maintain, the photovoltaic power generation equipment can be used for any occasions needing a power supply and the like, and the new energy power generation equipment in an industrial park generally adopts a photovoltaic module to obtain light energy and convert the light energy into electric energy. The electric energy obtained by a plurality of photovoltaic modules is converged by a converging box and then is converted into alternating current and direct current in an inverter, the converted alternating current is converted into alternating voltage and alternating current through a transformer to provide electric energy for industrial production equipment of an industrial park, in addition, the transformer is also connected with a power grid, when the solar energy is insufficient, the electric energy is obtained through the power grid to supply power for the industrial production equipment of the industrial park, energy consumption monitoring equipment monitors and obtains the energy consumption data of the industrial production equipment, edge proxy equipment obtains the energy consumption data of the industrial production equipment in the energy consumption monitoring equipment and the power data output by the photovoltaic modules in the inverter, meanwhile, the edge proxy equipment monitors and controls the state information of the inverter and obtains control process data, and the energy consumption data and the power data are decomposed into information particle sequences based on the control process data, and sending the information particle sequence to a monitoring center, and predicting the energy consumption characteristics by the monitoring center according to the information particle sequence.
The embodiment of the present application also provides a computer-readable storage medium, where at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the method for obtaining an energy consumption feature according to the embodiment of the present application, and is used to store at least one computer program, and the at least one computer program is loaded and executed by a processor to implement all or part of the steps in the above method. For example, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
The present application has been described in detail with reference to particular embodiments and illustrative examples, but the description is not intended to be construed as limiting the application. Those skilled in the art will appreciate that various equivalent substitutions, modifications or improvements may be made to the embodiments and implementations thereof without departing from the spirit and scope of the present application, and are within the scope of the present application.
Claims (10)
1. The method for acquiring the energy consumption characteristics is applied to edge proxy equipment, and comprises the following steps:
acquiring energy consumption data of industrial production equipment in energy consumption monitoring equipment;
acquiring power data of new energy power generation equipment in an inverter;
monitoring and controlling the state information of the inverter and acquiring control process data;
and decomposing the energy consumption data and the power data into information particle sequences based on the control process data, and sending the information particle sequences to a monitoring center so that the monitoring center can predict energy consumption characteristics according to the information particle sequences.
2. The method of claim 1, wherein the status information comprises at least one of voltage, current, active power, and reactive power, and wherein the controlling comprises frequency modulation control and/or voltage regulation control;
the control process data includes a plurality of data samples, each of the data samples having a plurality of attribute values including at least one of a voltage, a current, an active power, a reactive power, a phase control signal, a frequency control signal, and a voltage control signal.
3. The method of claim 2, wherein the decomposing the energy consumption data and the power data into a sequence of information particles based on the control process data comprises:
performing fuzzy clustering processing on the control process data to generate a time window sequence of the control process data;
and decomposing the energy consumption data and the power data according to the time window sequence based on the time window sequence to obtain an information particle sequence of the energy consumption data and the power data.
4. The method of claim 3, wherein the fuzzy clustering of the control process data to generate the sequence of time windows of the control process data comprises:
dividing the control process data into a plurality of fuzzy prototype types, and constructing the fuzzy prototype types into fuzzy prototype matrixes;
obtaining the degree value of the data sample attached to each fuzzy prototype to construct a fuzzy partition matrix;
solving the fuzzy partition matrix and the fuzzy prototype matrix, and obtaining a solving result;
and performing ascending arrangement on the solving results to obtain a time window series.
5. The method of claim 4, wherein the degree value is determined by the formula:
wherein u isim∈[0,1]，uimRepresenting the degree value of the ith fuzzy class prototype to which the mth data sample belongs, i ∈ [1, c ∈ [ ]]C represents the number of the fuzzy prototypes, and M represents the number of data samples in the control process data;
constructing a fuzzy partition matrix by the following formula:
U＝[uim]∈Rc×M；
and U represents a fuzzy partition matrix and is used for storing the corresponding degree value of each data sample, and R represents that the calculation result is in a matrix form.
6. The method according to claim 5, wherein solving the fuzzy partition matrix and the fuzzy prototype matrix and obtaining a solution result comprises:
solving the fuzzy partition matrix and the fuzzy prototype matrix by the following formulas:
q represents an objective function, dm represents an mth data sample in the control process data, vi represents an ith fuzzy type prototype, V represents the fuzzy type prototype matrix, f represents a fuzzification factor, and f > 1.
7. The method according to any one of claims 3 to 6, wherein the decomposing the energy consumption data and the power data according to the time window sequence based on the time window sequence to obtain the information particle sequence of the energy consumption data and the power data comprises:
based on the time window sequence, dividing the energy consumption data and the power data into a plurality of energy consumption subsets and a plurality of power subsets, wherein the energy consumption subsets and the power subsets are in one-to-one correspondence based on the time window sequence;
and acquiring the maximum value and the minimum value of each energy consumption subset, acquiring the maximum value and the minimum value of each power subset, and taking the combination of the maximum value and the minimum value as the information particle characteristics of the corresponding energy consumption subset and the corresponding power subset, wherein the set of the information particle characteristics forms an information particle sequence.
8. An apparatus for obtaining a characteristic of energy consumption, the apparatus comprising:
the energy consumption data acquisition module is used for acquiring energy consumption data of industrial production equipment in the energy consumption monitoring equipment;
the power data acquisition module is used for acquiring power data of new energy power generation equipment in the inverter;
the control process data acquisition module is used for monitoring and controlling the state information of the inverter and acquiring control process data;
and the energy consumption characteristic acquisition module is used for decomposing the energy consumption data and the power data into information particle sequences based on the control process data and sending the information particle sequences to a monitoring center so that the monitoring center can predict the energy consumption characteristics according to the information particle sequences.
9. An edge proxy device comprising a processor and a memory for storing executable instructions for the processor;
wherein the executable instructions, when executed by the processor, implement the following functions:
acquiring energy consumption data of industrial production equipment in the energy consumption monitoring equipment;
acquiring power data of new energy power generation equipment in an inverter;
monitoring and controlling the state information of the inverter and acquiring control process data;
and decomposing the energy consumption data and the power data into information particle sequences based on the control process data, and sending the information particle sequences to a monitoring center so that the monitoring center predicts energy consumption characteristics according to the information particle sequences.
10. An energy consumption characteristic acquisition system, comprising: industrial production equipment, energy consumption monitoring equipment, new energy generation equipment, combiner boxes, inverters, transformers, monitoring centers and edge proxy equipment according to claim 9;
the edge agent equipment is connected with the energy consumption monitoring equipment through a wireless network, the inverter is connected with the inverter through a Modbus communication protocol, and the monitoring center is connected with the inverter through an industrial switch.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210513422.3A CN114781915A (en) | 2022-05-11 | 2022-05-11 | Method, device and system for acquiring energy consumption characteristics and edge proxy equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210513422.3A CN114781915A (en) | 2022-05-11 | 2022-05-11 | Method, device and system for acquiring energy consumption characteristics and edge proxy equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114781915A true CN114781915A (en) | 2022-07-22 |
Family
ID=82436473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210513422.3A Pending CN114781915A (en) | 2022-05-11 | 2022-05-11 | Method, device and system for acquiring energy consumption characteristics and edge proxy equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114781915A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115933503A (en) * | 2023-03-10 | 2023-04-07 | 山东盛日电力集团有限公司 | Intelligent adjustment control method and system for power generation equipment |
-
2022
- 2022-05-11 CN CN202210513422.3A patent/CN114781915A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115933503A (en) * | 2023-03-10 | 2023-04-07 | 山东盛日电力集团有限公司 | Intelligent adjustment control method and system for power generation equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ghaderi et al. | Deep forecast: Deep learning-based spatio-temporal forecasting | |
| Malbasa et al. | Voltage stability prediction using active machine learning | |
| Chen et al. | Intelligent traffic adaptive resource allocation for edge computing-based 5G networks | |
| Alavi et al. | Forecast-based consensus control for DC microgrids using distributed long short-term memory deep learning models | |
| CN110738344B (en) | Distributed reactive power optimization method and device for load prediction of power system | |
| CN116245033B (en) | Artificial intelligent driven power system analysis method and intelligent software platform | |
| Dou et al. | Hybrid model for renewable energy and loads prediction based on data mining and variational mode decomposition | |
| CN107204615B (en) | Method and system for realizing power prediction | |
| Chakraborty et al. | Virtual battery parameter identification using transfer learning based stacked autoencoder | |
| Mahmoud et al. | Advanced method for short‐term wind power prediction with multiple observation points using extreme learning machines | |
| WO2020228568A1 (en) | Method for training power generation amount prediction model of photovoltaic power station, power generation amount prediction method and device of photovoltaic power station, training system, prediction system and storage medium | |
| CN114781915A (en) | Method, device and system for acquiring energy consumption characteristics and edge proxy equipment | |
| Montero-Sousa et al. | Hydrogen consumption prediction of a fuel cell based system with a hybrid intelligent approach | |
| Renold et al. | Comprehensive Review of Machine Learning, Deep Learning, and Digital Twin Data-Driven Approaches in Battery Health Prediction of Electric Vehicles | |
| CN112330044A (en) | Support vector regression model based on iterative aggregation grid search algorithm | |
| Naoui et al. | Integrating iot devices and deep learning for renewable energy in big data system | |
| Sudha et al. | GA-ANN hybrid approach for load forecasting | |
| CN116307111A (en) | Reactive load prediction method based on K-means clustering and random forest algorithm | |
| CN115907000A (en) | Small sample learning method for optimal power flow prediction of power system | |
| Duan et al. | A non-convex dispatch problem with generator constraints using neural network and particle swarm optimization | |
| Zjavka | Wind speed and global radiation forecasting based on differential, deep and stochastic machine learning of patterns in 2-level historical meteo-quantity sets | |
| Li et al. | Multi-objective bi-directional V2G behavior optimization and strategy deployment | |
| D’Amore et al. | Integrating model predictive control and deep learning for the management of an EV charging station | |
| Soham et al. | Application of LoRa Network for Data Transmission in Intelligent Smart Grid Systems | |
| Arora et al. | Shallow neural networks to deep neural networks for probabilistic wind 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 |