CN116760115A - Space-time feature fusion power system unit combination optimization method and system thereof - Google Patents
Space-time feature fusion power system unit combination optimization method and system thereof Download PDFInfo
- Publication number
- CN116760115A CN116760115A CN202310633005.7A CN202310633005A CN116760115A CN 116760115 A CN116760115 A CN 116760115A CN 202310633005 A CN202310633005 A CN 202310633005A CN 116760115 A CN116760115 A CN 116760115A
- Authority
- CN
- China
- Prior art keywords
- time
- unit
- space
- power
- power system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000005457 optimization Methods 0.000 title claims abstract description 66
- 238000010586 diagram Methods 0.000 claims abstract description 101
- 238000012545 processing Methods 0.000 claims abstract description 61
- 238000000605 extraction Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000010248 power generation Methods 0.000 claims description 48
- 238000003384 imaging method Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000011284 combination treatment Methods 0.000 claims description 5
- 230000002123 temporal effect Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000005611 electricity Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 239000000446 fuel Substances 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Classifications
-
- 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
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power system unit combination optimization method and a system thereof with time-space feature fusion, which are applied to the technical field of power system unit combination, wherein the method comprises the following steps: acquiring power data and a power equipment space association diagram of a power system; training a preset space-time fusion model according to the electric power data, and obtaining a preset scheduling table for starting and stopping the unit through the electric power data and the trained space-time fusion model, wherein the preset scheduling table comprises unit numbers and unit starting and stopping time; and carrying out time similarity extraction processing on the electric power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram. The invention can solve the technical problem that the traditional unit combination does not consider complex space-time dependency relationship.
Description
Technical Field
The invention relates to the technical field of power system unit combination, in particular to a power system unit combination optimization method and system for space-time feature fusion.
Background
After the electric automobile and the distributed energy source are connected into the electric power system, in order to schedule the output condition and the switch state of each unit under the constraint conditions of system load demand, power generation limitation and the like, the targets of the unit pollution gas emission amount, the total power generation cost or the fuel cost and the like are optimized, the optimal unit combination is obtained, and a technician usually designs the unit start-stop combination based on a method capable of learning an adjacent matrix or based on a transducer model.
However, the learning adjacency matrix-based method lacks the capability of characterizing complex space-time dependency, while the transducer-based model is prone to overfitting, and the existing models are designed under the condition that the spatial correlation is unchanged, but in the practical condition, the spatial correlation is unchanged.
Disclosure of Invention
The invention provides a power system unit combination optimization method and a system thereof with time-space feature fusion, wherein the power system unit combination optimization method and the system thereof with time-space feature fusion comprise the following steps: a space-time feature fusion power system unit combination optimization method, a space-time feature fusion power system unit optimization system, unit optimization equipment and a storage medium are provided, and the technical problem that the complex space-time dependency relationship is not considered in the traditional unit combination is solved.
In order to solve the problems, the invention provides a power system unit combination optimization method, a system, unit optimization equipment and a storage medium for space-time feature fusion, wherein the power system unit combination optimization method comprises the following steps:
acquiring power data and a power equipment space association diagram of a power system;
training a preset space-time fusion model according to the electric power data, and obtaining a preset scheduling table for starting and stopping the unit through the electric power data and the trained space-time fusion model, wherein the preset scheduling table comprises unit numbers and unit starting and stopping time;
and carrying out time similarity extraction processing on the electric power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
Optionally, the power data includes: the step of obtaining a preset schedule of starting and stopping of the unit through the power data and the trained space-time fusion model comprises the following steps of:
performing power generation analysis on the power output data through the trained space-time fusion model to obtain a unit output capacity table, wherein the power generation analysis is to analyze the power generation capacity of the unit;
Performing device state analysis on the power device state data through the trained space-time fusion model to obtain a unit state table, wherein the device state analysis is to analyze the start-stop state of the unit;
and obtaining a preset scheduling table for starting and stopping the unit according to the unit output capacity table and the unit state table.
Optionally, the step of obtaining a preset schedule of start and stop of the unit according to the unit output capability table and the unit state table includes:
determining a plurality of generator sets in a set of a power system according to the set output capacity table and the set state table;
and carrying out characteristic combination treatment on a plurality of generator sets to obtain a preset scheduling table for start and stop of the generator sets.
Optionally, the temporal similarity extraction process includes: the step of obtaining a dynamic time chart by carrying out time similarity extraction processing on the electric power data through a dynamic time warping algorithm comprises the following steps of:
carrying out serialization extraction processing on the electric power data through a dynamic time warping algorithm to obtain historical time sequence similarity;
and carrying out imaging processing on the historical time sequence similarity to obtain a dynamic time chart.
Optionally, the step of determining an optimal unit combination in the pre-scheduling table according to the dynamic time chart and the power equipment space association chart includes:
performing time feature extraction processing on the dynamic time map to obtain the time feature of the power system;
performing feature summarization according to the time features of the power system and the space association diagram of the power equipment to obtain hidden space-time features of the power system;
and determining the optimal unit combination in the pre-scheduling table according to the hidden space-time characteristics.
Optionally, the step of summarizing the features according to the time features of the power system and the spatial association diagram of the power equipment to obtain the hidden space-time features of the power system includes:
carrying out space feature extraction processing on the power equipment space association graph to obtain power system space features;
and carrying out feature summarization processing according to the time features of the power system and the space features of the power system to obtain the hidden space-time features of the power system.
Optionally, before the step of training a preset space-time fusion model according to the power data, the method further includes:
performing feature extraction processing on the power data to obtain power feature data;
The step of training the preset space-time fusion model according to the electric power data comprises the following steps:
and training a preset space-time fusion model according to the electric power characteristic data.
In addition, in order to solve the above problems, the present invention further provides a power system unit optimization system for space-time feature fusion, where the power system unit optimization system for space-time feature fusion includes:
the first acquisition module is used for acquiring power data of the power system and a power equipment space association diagram;
the pre-scheduling table calculation module is used for training a preset space-time fusion model according to the electric power data, and obtaining a pre-scheduling table for starting and stopping a unit through the electric power data and the trained space-time fusion model, wherein the pre-scheduling table comprises a unit number and unit starting and stopping time;
and the optimal unit determining module is used for extracting and processing the time similarity of the power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
In addition, in order to solve the above problems, the present invention also proposes a unit optimizing apparatus including: the system comprises a memory, a processor and a power system unit combination optimization program which is stored in the memory and can run on the processor, wherein the power system unit combination optimization program realizes the steps of the power system unit combination optimization method when being executed by the processor.
In addition, in order to solve the above-mentioned problems, the present invention also proposes a storage medium having stored thereon an electric power system unit combination optimization program, which when executed by a processor, implements the steps of the electric power system unit combination optimization method as described above.
The invention provides a space-time feature fusion power system unit combination optimization method, a system, unit optimization equipment and a storage medium, wherein the power system unit combination optimization method comprises the following steps: acquiring power data and a power equipment space association diagram of a power system; training a preset space-time fusion model according to the electric power data, and obtaining a preset scheduling table for starting and stopping the unit through the electric power data and the trained space-time fusion model, wherein the preset scheduling table comprises unit numbers and unit starting and stopping time; and carrying out time similarity extraction processing on the electric power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
The invention provides a space-time feature fusion power system unit combination optimization method, a space-time feature fusion power system unit optimization system, unit optimization equipment and a storage medium, wherein the power system unit combination optimization method comprises the following steps: acquiring power data of a power system and a power equipment space association diagram of each power equipment in the power system, training a preset space-time fusion model according to the power data, obtaining a pre-scheduling table for controlling the starting and stopping of a generator set through the power data and the trained space-time fusion model, wherein the pre-scheduling table comprises a set number and set starting and stopping time, extracting the time similarity of the power data through a dynamic time warping algorithm to obtain a dynamic time diagram, and determining the optimal generator set combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
Compared with the traditional mode of optimizing the unit combination under the condition that the space correlation is not changed through a learnable adjacency matrix and a transducer model, the method and the device can realize the effect of obtaining the unit pre-scheduling table by utilizing the power data of the unit of the power system by establishing the space-time fusion model through the power data in the power system, training the space-time fusion model through the power data and obtaining the unit pre-scheduling table, extract the time characteristics of each unit in the power system through a dynamic time warping algorithm to obtain a dynamic time diagram, and determine the optimal combination of the unit in the pre-scheduling table according to the dynamic time diagram and the power equipment space correlation diagram of the power system, so that the effect of combining the time characteristics and the space characteristics of the power system can be realized, and the generation cost of the optimal unit combination can be reduced on the premise of not influencing the stability of the power system.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic diagram of a device architecture of a hardware operating environment of a unit optimization device according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a power system unit combination optimization method with time-space feature fusion according to the present invention;
FIG. 3 is a schematic diagram of a model structure of an embodiment of a power system unit combination optimization method with space-time feature fusion according to the present invention;
FIG. 4 is a schematic diagram of a neural network layer of a single space-time fusion graph of an embodiment of a power system unit combination optimization method of the space-time feature fusion of the present invention;
FIG. 5 is a functional block diagram of an embodiment of a power system unit combination optimization system with temporal and spatial feature fusion according to the present invention.
Reference numerals illustrate:
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that all directional indicators (such as up, down, left, right, front, and rear … …) in the embodiments of the present invention are merely used to explain the relative positional relationship, movement, etc. between the components in a particular posture (as shown in the drawings), and if the particular posture is changed, the directional indicator is changed accordingly.
In the present invention, unless specifically stated and limited otherwise, the terms "connected," "affixed," and the like are to be construed broadly, and for example, "affixed" may be a fixed connection, a removable connection, or an integral body; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
Furthermore, descriptions such as those referred to as "first," "second," and the like, are provided for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implying an order of magnitude of the indicated technical features in the present disclosure. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
Referring to fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment of a unit optimizing device according to an embodiment of the present invention.
As shown in fig. 1, in a hardware operating environment of a unit optimizing device, the device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the unit optimizing device configuration shown in fig. 1 does not constitute a limitation of the device and may include more or fewer components than shown, or may combine certain components, or may be arranged in a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a power system crew optimization program may be included in a memory 1005, which is a type of computer storage medium.
In the device shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server, and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call the power system crew optimization program stored in the memory 1005, and perform the following operations:
acquiring power data and a power equipment space association diagram of a power system;
training a preset space-time fusion model according to the electric power data, and obtaining a preset scheduling table for starting and stopping the unit through the electric power data and the trained space-time fusion model, wherein the preset scheduling table comprises unit numbers and unit starting and stopping time;
and carrying out time similarity extraction processing on the electric power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
Optionally, the power data includes: the power output data and power device state data, the processor 1001 may be configured to invoke the power system crew combination optimization program stored in the memory 1005, and perform the following operations:
performing power generation analysis on the power output data through the trained space-time fusion model to obtain a unit output capacity table, wherein the power generation analysis is to analyze the power generation capacity of the unit;
performing device state analysis on the power device state data through the trained space-time fusion model to obtain a unit state table, wherein the device state analysis is to analyze the start-stop state of the unit;
and obtaining a preset scheduling table for starting and stopping the unit according to the unit output capacity table and the unit state table.
Alternatively, the processor 1001 may be configured to call a power system crew combination optimization program stored in the memory 1005, and perform the following operations:
determining a plurality of generator sets in a set of a power system according to the set output capacity table and the set state table;
and carrying out characteristic combination treatment on a plurality of generator sets to obtain a preset scheduling table for start and stop of the generator sets.
Optionally, the temporal similarity extraction process includes: the serialization extraction process and the imaging process, the processor 1001 may be configured to call the power system crew optimization program stored in the memory 1005, and perform the following operations:
Carrying out serialization extraction processing on the electric power data through a dynamic time warping algorithm to obtain historical time sequence similarity;
and carrying out imaging processing on the historical time sequence similarity to obtain a dynamic time chart.
Alternatively, the processor 1001 may be configured to call a power system crew combination optimization program stored in the memory 1005, and perform the following operations:
performing time feature extraction processing on the dynamic time map to obtain the time feature of the power system;
performing feature summarization according to the time features of the power system and the space association diagram of the power equipment to obtain hidden space-time features of the power system;
and determining the optimal unit combination in the pre-scheduling table according to the hidden space-time characteristics.
Alternatively, the processor 1001 may be configured to call a power system crew combination optimization program stored in the memory 1005, and perform the following operations:
carrying out space feature extraction processing on the power equipment space association graph to obtain power system space features;
and carrying out feature summarization processing according to the time features of the power system and the space features of the power system to obtain the hidden space-time features of the power system.
Alternatively, the processor 1001 may be configured to call a power system crew combination optimization program stored in the memory 1005, and perform the following operations:
Performing feature extraction processing on the power data to obtain power feature data;
the step of training the preset space-time fusion model according to the electric power data comprises the following steps:
and training a preset space-time fusion model according to the electric power characteristic data.
Based on the hardware structure, the overall conception of each embodiment of the power system unit combination optimization method of the space-time feature fusion is provided.
In the embodiment of the invention, after an electric automobile and a distributed energy source are connected into a power system, in order to schedule the output condition and the switch state of each unit under the constraint conditions of system load demand, power generation limitation and the like, the targets of unit pollution gas emission, total power generation cost or fuel cost and the like are optimized, the optimal unit combination is obtained, and a technician usually designs the unit start-stop combination based on a method capable of learning an adjacent matrix or based on a converter model.
However, the learning adjacency matrix-based method lacks the capability of characterizing complex space-time dependency, while the transducer-based model is prone to overfitting, and the existing models are designed under the condition that the spatial correlation is unchanged, but in the practical condition, the spatial correlation is unchanged.
Aiming at the problems, the embodiment of the invention provides a power system unit combination optimization method, a system, unit optimization equipment and a storage medium for space-time feature fusion, wherein the power system unit combination optimization method comprises the following steps: acquiring power data and a power equipment space association diagram of a power system; training a preset space-time fusion model according to the electric power data, and obtaining a preset scheduling table for starting and stopping the unit through the electric power data and the trained space-time fusion model, wherein the preset scheduling table comprises unit numbers and unit starting and stopping time; and carrying out time similarity extraction processing on the electric power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
The invention provides a space-time feature fusion power system unit combination optimization method, a space-time feature fusion power system unit optimization system, unit optimization equipment and a storage medium, wherein the power system unit combination optimization method comprises the following steps: acquiring power data of a power system and a power equipment space association diagram of each power equipment in the power system, training a preset space-time fusion model according to the power data, obtaining a pre-scheduling table for controlling the starting and stopping of a generator set through the power data and the trained space-time fusion model, wherein the pre-scheduling table comprises a set number and set starting and stopping time, extracting the time similarity of the power data through a dynamic time warping algorithm to obtain a dynamic time diagram, and determining the optimal generator set combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
Compared with the traditional mode of optimizing the unit combination under the condition that the space correlation is not changed through a learnable adjacency matrix and a transducer model, the method and the device can realize the effect of obtaining the unit pre-scheduling table by utilizing the power data of the unit of the power system by establishing the space-time fusion model through the power data in the power system, training the space-time fusion model through the power data and obtaining the unit pre-scheduling table, extract the time characteristics of each unit in the power system through a dynamic time warping algorithm to obtain a dynamic time diagram, and determine the optimal combination of the unit in the pre-scheduling table according to the dynamic time diagram and the power equipment space correlation diagram of the power system, so that the effect of combining the time characteristics and the space characteristics of the power system can be realized, and the generation cost of the optimal unit combination can be reduced on the premise of not influencing the stability of the power system.
Based on the general conception of the power system unit combination optimization method of the space-time feature fusion, various embodiments of the power system unit combination optimization method of the space-time feature fusion are provided.
Fig. 2 is a schematic flow chart of a first embodiment of the power system unit combination optimization method based on space-time feature fusion. It should be noted that although a logic sequence is shown in the flowchart, in some cases, the individual steps of the power system crew optimization method of the present invention may of course be performed in a different order than that herein.
In this embodiment, the power system unit combination optimization method includes:
step S10: acquiring power data and a power equipment space association diagram of a power system;
the electric power system is connected with an electric automobile and distributed energy, terminals for uploading electric power data are arranged in the electric automobile and the distributed energy, and the electric power equipment space association diagram refers to an electric pole line distribution association diagram, an energy station and a power station position distribution diagram.
In this embodiment, the unit optimizing device obtains power data of the power system through terminals connected to the electric vehicle and the distributed energy, obtains a distribution association diagram of the electric pole line through distribution conditions of the electric pole and the line in the power system, and obtains an energy station position distribution diagram and a power station position distribution diagram through spatial positions of the energy station and the power station.
Step S20: training a preset space-time fusion model according to the electric power data, and obtaining a preset scheduling table for starting and stopping the unit through the electric power data and the trained space-time fusion model, wherein the preset scheduling table comprises unit numbers and unit starting and stopping time;
it should be noted that the preset space-time fusion model may be an input layer formed by one full-connection layer, a plurality of space-time fusion graph neural network layers (STFGN layers) are stacked, and an output layer formed by two full-connection layers. Each STFGN layer is composed of a plurality of parallel space-time fusion graph neural modules (STFGN modules) and a gating CNN module, which includes two parallel one-dimensional expansion convolution modules.
In this embodiment, fig. 3 is a schematic diagram of a model structure of an embodiment of a power system unit combination optimization method of the present invention, and fig. 4 is a schematic diagram of a single space-time fusion graph neural network layer of an embodiment of a power system unit combination optimization method of the present invention, after obtaining a spatial correlation graph of power data and power equipment, a unit optimization device trains a preset space-time fusion model according to a genetic algorithm and the power data, inputs the power data into an input layer in the space-time fusion model, controls the optimization degree of the space-time fusion model through the genetic algorithm, and obtains a pre-scheduling table for controlling the start and stop of a unit in the power system according to the power data and the trained space-time fusion model, where the pre-scheduling table includes the unit number in the power system and the time for the start and stop of the unit.
Step S30: and carrying out time similarity extraction processing on the electric power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
In this embodiment, after a unit start-stop pre-scheduling table of an electric power system is obtained by using a space-time fusion model, a unit optimizing device performs time similarity extraction processing on electric power data through a dynamic time warping algorithm to obtain a dynamic time diagram in the electric power system, and determines an optimal generator unit combination in the pre-scheduling table according to the obtained dynamic time diagram and an electric power device space correlation diagram.
The dynamic time warping algorithm dynamically constructs a time chart by performing time similarity extraction processing on the power data of each unit node in the power system, and the time chart is a dynamic time chart.
By way of example, it is assumed that 100 electric vehicles and 50 distributed energy power stations are connected in the electric power system, and that 100 terminal devices are connected to the 100 electric vehicles, and 50 terminal devices are connected to the distributed energy power stations. In addition, there are several electric poles and several transmission lines in the power system. The unit optimizing equipment obtains power data of a power system through 150 terminals, and obtains a pole line distribution association diagram, an energy station position distribution diagram and a power station position distribution diagram through space positions of each pole, each power transmission line, each energy station and each power station. And training a pre-designed space-time fusion model by the unit optimizing equipment according to the obtained electric power data and a genetic algorithm, obtaining a pre-scheduling table for controlling the start and stop of the units in the electric power system through the electric power data and the trained space-time fusion model, wherein the pre-scheduling table comprises the corresponding numbers of the units in the electric power system and the start and stop time of the units, extracting the time similarity of the electric power data by the unit combination optimizing algorithm through a dynamic time warping algorithm to obtain a dynamic time diagram of each unit in the electric power system, and determining the optimal generator unit combination in the pre-scheduling table according to the obtained dynamic time diagram, the electric pole line distribution association diagram, the energy station position distribution diagram and the power station position distribution diagram.
In the embodiment, the pre-scheduling table is obtained through the space-time fusion model, and the optimal unit combination mode is obtained through the pre-scheduling table and the time diagram obtained through the dynamic time warping algorithm, so that the time characteristics and the space characteristics in the power system are combined, and the power generation cost of the obtained unit combination can be reduced on the premise of not influencing the stability of the power system.
Further, based on the first embodiment of the power system unit combination optimization method of the space-time feature fusion, a second embodiment of the power system unit combination optimization method of the space-time feature fusion is provided.
In this embodiment, the power data includes: power output data and power device status data, step S20 described above: and obtaining a preset schedule of starting and stopping of the unit through the power data and the trained space-time fusion model, wherein the preset schedule comprises the following components:
step S201: performing power generation analysis on the power output data through the trained space-time fusion model to obtain a unit output capacity table, wherein the power generation analysis is to analyze the power generation capacity of the unit;
it should be noted that, the power generation analysis refers to a power quantity value that the unit can generate, and the power quantity value can be the power quantity generated by the unit stably, or can be the maximum power generation power quantity of the unit.
In this embodiment, the power data includes power output data and power device state data, and after obtaining the power output data and the power device state data, the unit optimizing device performs power generation analysis on the power output data through the trained space-time fusion model, so as to obtain stable power generation amount of the unit, and further determines a unit output capacity table according to the power generation amount of the unit in a stable state.
Step S202: performing device state analysis on the power device state data through the trained space-time fusion model to obtain a unit state table, wherein the device state analysis is to analyze the start-stop state of the unit;
it should be noted that, the device state analysis refers to obtaining a start time period of the unit according to the power device state data, where the power device state data includes a start-stop state of the unit.
In this embodiment, the unit optimizing apparatus further performs device state analysis on the power device state data through the trained space-time fusion model to obtain a starting time period of each unit in the power system, and gathers according to the starting time period of each unit to obtain a unit state table.
Step S203: and obtaining a preset scheduling table for starting and stopping the unit according to the unit output capacity table and the unit state table.
In this embodiment, after the unit optimizing device obtains the unit output capability table and the unit state table, the unit output capability table and the unit state table are summarized, so as to obtain a preset scheduling table for starting and stopping the unit.
By way of example, it is assumed that 100 energy power stations are provided in the power system, and that the operating times of the 100 energy power stations are not exactly the same. After the power output data and the power device state data of 100 energy power stations are obtained, the unit optimizing equipment performs power generation analysis on the power output data through the trained space-time fusion model, so that stable output electric quantity of the 100 energy power stations is determined, and a unit output capacity table is obtained according to the stable output electric quantity. For example, one of the energy power stations is wind power generation, the unit optimizing equipment performs power generation analysis processing on wind power generation power output data of the energy power station through a space-time fusion model to obtain stable output electric quantity which is 1500 ℃ per hour, and then the unit output capacity meter records 1500 ℃ per hour of the power station; the unit optimizing equipment further performs device state analysis on the power device state data through the space-time fusion model to obtain a unit starting time period, so that a unit state table is obtained according to the unit starting time period, for example, the unit optimizing equipment records that the working time period of the wind power station is 01:00-10:00 in the unit state table when the working time period of the wind power generator obtained through the power device state data of the wind power generator is 01:00-10:00, and then the unit optimizing equipment obtains a pre-scheduling table for scheduling the start and stop of the unit according to the unit output capacity table and the unit state table of each energy power station. The pre-scheduling table records the power generation capacity, the power generation time, the unit number and other data of each unit.
Optionally, in one possible embodiment, step S203 above: obtaining a preset scheduling table for starting and stopping the unit according to the unit output capacity table and the unit state table, wherein the preset scheduling table comprises the following components:
step S2031: determining a plurality of generator sets in a set of a power system according to the set output capacity table and the set state table;
the unit optimizing device needs to determine a plurality of generator sets according to the generating capacity and generating time of each unit and the total amount of power generation required by the power system.
In this embodiment, after obtaining the unit output capability table and the unit state table of each generator unit in the power system, the unit optimizing device determines a plurality of generator units in the power system according to the unit output capability table and the unit state table and the electric quantity required by the power system.
Step S2032: and carrying out characteristic combination treatment on a plurality of generator sets to obtain a preset scheduling table for start and stop of the generator sets.
In this embodiment, after obtaining a plurality of generator sets, the set optimizing apparatus performs feature combination processing on the plurality of generator sets to obtain a pre-scheduling table for controlling starting and stopping of the power system set.
The feature combination processing means: and sequencing the priority of the units according to the power generation capacity of each unit and the power generation time.
For example, assuming that the unit output capability table and the unit state table record information of all the generator units in the electric power system, and the required power generation amount of the electric power system is 5000 degrees of electricity, the unit optimizing device searches out the units meeting the total amount of power generation in the electric power system according to the stable power generation amount of each unit recorded in the unit output capability table and the power generation time period information of each unit in the unit state table, for example, the first unit combination is as follows: the A unit generates 2000 degrees electricity in 02:00-10:00, the B unit generates 2000 degrees electricity in 8:00-18:00, the C unit generates 1000 degrees electricity in 16:00-02:00, and the second unit is combined with the following components: and the W unit generates 3000 degrees in the operation time period, and the D unit generates 2000 degrees in the operation time period, so that the generator set determined by the unit optimizing equipment comprises the following components: and then, the unit optimizing equipment performs priority ranking treatment on the unit A, the unit B, the unit C, the unit W and the unit D, namely, sets the combination with low power generation cost as higher priority and sets the combination with high power generation cost as lower priority, and obtains a pre-scheduling table for ranking all the units according to the priority.
In the embodiment, the power output data is subjected to power generation analysis through the space-time fusion model to obtain the unit output capacity table, the power device state data is subjected to device state analysis to obtain the unit state table, and then the pre-scheduling table is determined according to the unit output capacity table, the unit state table and the power generation cost, so that the power generation suitability of each unit in the pre-scheduling table is improved.
Further, based on the first embodiment and the second embodiment of the power system unit combination optimization method of the space-time feature fusion, a third embodiment of the power system unit combination optimization method of the space-time feature fusion is provided.
In a possible embodiment, the temporal similarity extraction process includes: a sequential extraction process and an imaging process, wherein in the step S30: performing time similarity extraction processing on the electric power data through a dynamic time warping algorithm to obtain a dynamic time chart, wherein the method comprises the following steps of:
step S301: carrying out serialization extraction processing on the electric power data through a dynamic time warping algorithm to obtain historical time sequence similarity;
the serialization extraction process refers to converting a plurality of pieces of electric power data into a plurality of time series, and performing similarity calculation on the plurality of time series.
In this embodiment, the unit optimizing device further converts the electric power data into a plurality of time sequences through a time-warping algorithm, and performs similarity calculation on the plurality of time sequences to obtain a historical time sequence similarity.
Step S302: and carrying out imaging processing on the historical time sequence similarity to obtain a dynamic time chart.
In this embodiment, after obtaining the historical time series similarity, the unit optimizing device performs imaging processing on the historical time series similarity, and converts the sequence similarity information into a dynamic time chart.
The imaging processing refers to converting similarity information in the historical time similarity into a graph structure, and may be a directed graph or an undirected graph.
The unit optimizing device converts the plurality of electric power data into a plurality of time sequences through a dynamic time warping algorithm after the pre-scheduling table is obtained, and calculates similarity of the plurality of time sequences, so that historical time sequence similarity is obtained, wherein time similarity information of the generation of the organic unit is stored in the historical time sequence similarity, for example, the generation time similarity of the unit A and the generation time of the unit B is higher, then the unit optimizing device performs imaging processing on the historical time sequence similarity, and converts the historical time sequence similarity information into a dynamic time diagram, and nodes for identifying the unit A and nodes for identifying the unit B are connected in the dynamic time diagram to identify the similarity of the unit A and the unit B.
Optionally, in one possible embodiment, step S30 above: determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram, wherein the method comprises the following steps of:
Step S303: performing time feature extraction processing on the dynamic time map to obtain the time feature of the power system;
it should be noted that the time feature extraction process refers to searching out generator sets with similar node features in the power system recorded in the dynamic time chart.
In this embodiment, after obtaining the dynamic time chart, the unit optimizing device determines the generator units with similar node characteristics recorded in the dynamic time chart as the time characteristics of the power system.
Step S304: performing feature summarization according to the time features of the power system and the space association diagram of the power equipment to obtain hidden space-time features of the power system;
in this embodiment, the unit optimizing device further performs feature summarizing processing according to the time feature of the power system and the power equipment space association diagram in the power system, so as to obtain the hidden space-time feature of the power system.
Step S305: and determining the optimal unit combination in the pre-scheduling table according to the hidden space-time characteristics.
In this embodiment, after the unit optimizing device obtains the hidden space-time feature by combining the power system time feature of the power system and the feature of the power device space correlation diagram, the unit optimizing device determines the optimal unit combination in the pre-scheduling table according to the hidden space-time feature.
For example, assuming that the time alignment algorithm performs time feature extraction processing according to the power generation time to obtain that the a unit is similar to the B unit, and the time alignment algorithm performs time feature extraction according to the power generation capacity to obtain that the B unit is similar to the C unit, the power system time feature obtained by the unit optimizing device is "the power generation time similarity of the a unit is high to the B unit, the power generation capacity similarity of the B unit is high to the C unit", and then the unit optimizing device performs feature summarization on the power system time feature and the power equipment space association diagram to obtain a hidden space-time feature, for example, the hidden space-time feature is "B and C are both hydroelectric power plants, and the geographic positions of a and B are similar", and then an optimal unit combination is determined in a pre-scheduling table according to the hidden space-time feature, that is, whether the power generation unit can be replaced by other similar units is determined in the pre-scheduling table.
Optionally, in one possible embodiment, step S304 described above: performing feature summarization according to the time feature of the power system and the space association diagram of the power equipment to obtain hidden space-time features of the power system, wherein the method comprises the following steps:
step S3041: carrying out space feature extraction processing on the power equipment space association graph to obtain power system space features;
The spatial feature extraction processing refers to extracting a connection relationship between a node and an edge in the power equipment spatial association graph and a power loss relationship of power transmission between the node, and it should be understood that if the types of the power equipment spatial association graphs are different, the extracted spatial features of the power system are also different.
In this embodiment, the unit optimizing device further performs a spatial feature extraction process on the spatial correlation diagram of the power device, so as to obtain spatial features of the power system. The unit optimizing device judges the category of the power equipment space association diagram to obtain a node circuit diagram or a transformer model diagram, and then extracts the connection relation between the nodes and the edges of the power equipment space association diagram and extracts the relation between the nodes to obtain the space characteristics of the power system.
Step S3042: and carrying out feature summarization processing according to the time features of the power system and the space features of the power system to obtain the hidden space-time features of the power system.
In this embodiment, the unit optimizing device performs feature summarizing processing according to the time feature of the power system and the space feature of the power system, so as to obtain the hidden space-time feature in the power system.
The feature summarization process is to combine the time features of the power system and the space features of the power system to determine the hidden space-time features in the power system.
The space correlation diagram of the electric power equipment is a unit-electric pole-line distribution diagram of electric poles and lines in the electric power system, the unit optimizing equipment performs space feature extraction processing on the unit-electric pole-line distribution diagram to obtain an electric power loss relation between the electric poles and an electric power loss relation between electric power output by the unit and the electric poles, so that space features of the electric power system are obtained, and then the unit optimizing equipment is combined with a time similarity relation of each unit in the electric power system to obtain hidden space-time features of the electric power system. For example, the unit a generates electricity, the unit B and the unit a have high time similarity (similar power output capability and similar power generation time period), the power output by the unit a needs to be transmitted through 30 electric poles to enter the power transmission line, the power output by the unit B only needs to be transmitted through 20 electric poles to enter the same power transmission line, and then the hidden space-time characteristics in the power system are as follows: the A machine set and the B machine set can be replaced with each other.
In the embodiment, the dynamic time diagram is obtained by carrying out sequential extraction and imaging processing on the electric power data through the time warping algorithm, the spatial characteristics are obtained through the space correlation diagram of the electric power equipment in the electric power system, and the effect of reducing the generating cost of the unit by utilizing the spatial and temporal characteristics in the electric power system can be realized by determining the optimal unit combination by combining the temporal characteristics and the spatial characteristics of the unit in the electric power system.
Further, the first embodiment, the second embodiment and the third embodiment of the power system unit combination optimization method based on the space-time feature fusion of the present invention provide a fourth embodiment of the power system unit combination optimization method based on the space-time feature fusion of the present invention.
In one possible embodiment, in step S20 above: before training the preset space-time fusion model according to the electric power data, the method further comprises:
step S40: performing feature extraction processing on the power data to obtain power feature data;
in this embodiment, before training the time fusion model by using the power data, the unit optimizing device performs feature extraction processing on the power data to obtain power feature data.
In the power system, the power data includes information such as current, power generation time, unit conventional log information and the like, and the unit conventional log information is not used for unit combination optimization processing, so that the unit optimization device removes unnecessary power data through feature extraction processing, and power feature data for unit combination optimization is obtained.
Based on this, step S20 described above: training a preset space-time fusion model according to the electric power data, wherein the training comprises the following steps:
And training a preset space-time fusion model according to the electric power characteristic data.
In this embodiment, the unit optimizing device trains the space-time fusion model through the electric power characteristic data to improve the model training efficiency.
In the embodiment, the power data is subjected to characteristic processing before the space-time fusion model is trained, and the calculated amount in the unit combination optimization process is reduced in a mode of training the space-time fusion model by the power data subjected to the characteristic processing.
In addition, the embodiment of the invention also provides a power system unit combination optimization system for space-time feature fusion.
Referring to fig. 5, the power system unit combination optimization system with temporal and spatial feature fusion of the present invention includes:
a first obtaining module 10, configured to obtain power data and a power equipment space association diagram of a power system;
the pre-scheduling table calculation module 20 is configured to train a preset space-time fusion model according to the electric power data, and obtain a pre-scheduling table for starting and stopping the unit according to the electric power data and the trained space-time fusion model, where the pre-scheduling table includes a unit number and a unit starting and stopping time;
and the optimal unit determining module 30 is configured to perform a time similarity extraction process on the power data through a dynamic time warping algorithm to obtain a dynamic time chart, and determine an optimal unit combination in the pre-scheduling table according to the dynamic time chart and the power equipment space association chart.
Optionally, the power data includes: power output data and power device status data, a prescheduler calculation module 20, comprising:
the output capacity determining unit is used for carrying out power generation analysis on the power output data through the trained space-time fusion model to obtain a unit output capacity table;
the unit state determining unit is used for carrying out device state analysis on the power device state data through the trained space-time fusion model to obtain a unit state table;
and the pre-scheduling table generating unit is used for obtaining a pre-scheduling table for starting and stopping the unit according to the unit output capacity table and the unit state table.
Optionally, the prescheduling table generating unit further includes:
a unit determining subunit, configured to determine a plurality of generator sets in a unit of an electric power system according to the unit output capability table and the unit state table;
and the characteristic combination subunit is used for carrying out characteristic combination treatment on the plurality of generator sets to obtain a preset scheduling table for start and stop of the generator sets.
Optionally, the temporal similarity extraction process includes: the optimal set determination module 30 includes:
the serialization unit is used for carrying out serialization extraction processing on the electric power data through a dynamic time warping algorithm to obtain historical time sequence similarity;
And the time chart determining unit is used for carrying out imaging processing on the historical time sequence similarity to obtain a dynamic time chart.
Optionally, the optimal unit determining module 30 includes:
the time feature extraction unit is used for carrying out time feature extraction processing on the dynamic time diagram to obtain the time feature of the power system;
the hidden space-time feature determining unit is used for carrying out feature summarization according to the time feature of the power system and the space-time association diagram of the power equipment to obtain hidden space-time features of the power system;
and the unit determining unit is used for determining the optimal unit combination in the pre-scheduling table according to the hidden space-time characteristics.
Optionally, the hidden space-time feature determining unit comprises:
the spatial feature extraction subunit is used for carrying out spatial feature extraction processing on the power equipment spatial association graph to obtain the spatial features of the power system;
and the space-time feature utilization unit is used for carrying out feature summarization processing according to the time features of the power system and the space features of the power system to obtain the hidden space-time features of the power system.
Optionally, the power system unit combination optimization system with the space-time feature fusion further comprises:
the data feature extraction module is used for carrying out feature extraction processing on the power data to obtain power feature data;
Based on this, the above-mentioned prescheduler calculation module 20 is also configured to: and training a preset space-time fusion model according to the electric power characteristic data.
The function implementation of each module in the power system unit combination optimization system with the time-space feature fusion corresponds to each step in the power system unit combination optimization method embodiment with the time-space feature fusion, and the functions and implementation processes of the function implementation are not described in detail herein.
In addition, the invention also provides a storage medium, wherein the storage medium is stored with a power system unit combination optimizing program, and the power system unit combination optimizing program realizes the steps of the power system unit combination optimizing method for the time-space characteristic fusion.
The specific embodiment of the storage medium of the present invention is basically the same as each embodiment of the above-mentioned power system unit combination optimization method with temporal and spatial feature fusion, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a car-mounted computer, a smart phone, a computer, or a server, etc.) to perform the method according to the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The power system unit combination optimization method based on space-time feature fusion is characterized by comprising the following steps of:
acquiring power data and a power equipment space association diagram of a power system;
training a preset space-time fusion model according to the electric power data, and obtaining a preset scheduling table for starting and stopping the unit through the electric power data and the trained space-time fusion model, wherein the preset scheduling table comprises unit numbers and unit starting and stopping time;
and carrying out time similarity extraction processing on the electric power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining an optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
2. The power system crew combination optimization method of space-time feature fusion of claim 1, wherein the power data comprises: the step of obtaining a preset schedule of starting and stopping of the unit through the power data and the trained space-time fusion model comprises the following steps of:
performing power generation analysis on the power output data through the trained space-time fusion model to obtain a unit output capacity table, wherein the power generation analysis is to analyze the power generation capacity of the unit;
Performing device state analysis on the power device state data through the trained space-time fusion model to obtain a unit state table, wherein the device state analysis is to analyze the start-stop state of the unit;
and obtaining a preset scheduling table for starting and stopping the unit according to the unit output capacity table and the unit state table.
3. The method for optimizing the combination of power system units by fusion of space-time characteristics according to claim 2, wherein the step of obtaining a pre-scheduling table for start and stop of the units according to the unit output capacity table and the unit state table comprises the following steps:
determining a plurality of generator sets in a set of a power system according to the set output capacity table and the set state table;
and carrying out characteristic combination treatment on a plurality of generator sets to obtain a preset scheduling table for start and stop of the generator sets.
4. The power system unit combination optimization method of space-time feature fusion according to claim 1, wherein the time similarity extraction process comprises: the step of obtaining a dynamic time chart by carrying out time similarity extraction processing on the electric power data through a dynamic time warping algorithm comprises the following steps of:
Carrying out serialization extraction processing on the electric power data through a dynamic time warping algorithm to obtain historical time sequence similarity;
and carrying out imaging processing on the historical time sequence similarity to obtain a dynamic time chart.
5. The method for optimizing power system crew combinations for space-time feature fusion according to claim 1, wherein the step of determining the optimal crew combination in the pre-scheduling table according to the dynamic time map and the power equipment space correlation map comprises:
performing time feature extraction processing on the dynamic time map to obtain the time feature of the power system;
performing feature summarization according to the time features of the power system and the space association diagram of the power equipment to obtain hidden space-time features of the power system;
and determining the optimal unit combination in the pre-scheduling table according to the hidden space-time characteristics.
6. The method for optimizing power system unit combination by fusion of space-time features according to claim 5, wherein the step of summarizing features according to the power system time features and the power equipment space-related graph to obtain hidden space-time features of the power system comprises the following steps:
carrying out space feature extraction processing on the power equipment space association graph to obtain power system space features;
And carrying out feature summarization processing according to the time features of the power system and the space features of the power system to obtain the hidden space-time features of the power system.
7. The method for optimizing a power system crew combination for space-time feature fusion according to claim 1, wherein before the step of training a preset space-time fusion model according to the power data, the method further comprises:
performing feature extraction processing on the power data to obtain power feature data;
the step of training the preset space-time fusion model according to the electric power data comprises the following steps:
and training a preset space-time fusion model according to the electric power characteristic data.
8. The utility model provides a space-time feature fused power system unit optimizing system which characterized in that, space-time feature fused power system unit optimizing system includes:
the first acquisition module is used for acquiring power data of the power system and a power equipment space association diagram;
the pre-scheduling table calculation module is used for training a preset space-time fusion model according to the electric power data, and obtaining a pre-scheduling table for starting and stopping a unit through the electric power data and the trained space-time fusion model, wherein the pre-scheduling table comprises a unit number and unit starting and stopping time;
And the optimal unit determining module is used for extracting and processing the time similarity of the power data through a dynamic time sorting algorithm to obtain a dynamic time diagram, and determining optimal unit combination in the pre-scheduling table according to the dynamic time diagram and the power equipment space association diagram.
9. A unit optimizing apparatus, characterized in that the unit optimizing apparatus comprises: a memory, a processor and a power system crew optimization program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the power system crew optimization method according to any of claims 1 to 7.
10. A storage medium, wherein a power system crew optimization program is stored on the storage medium, which when executed by a processor, implements the steps of the power system crew optimization method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310633005.7A CN116760115B (en) | 2023-05-30 | 2023-05-30 | Space-time feature fusion power system unit combination optimization method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310633005.7A CN116760115B (en) | 2023-05-30 | 2023-05-30 | Space-time feature fusion power system unit combination optimization method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116760115A true CN116760115A (en) | 2023-09-15 |
| CN116760115B CN116760115B (en) | 2024-04-12 |
Family
ID=87958130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310633005.7A Active CN116760115B (en) | 2023-05-30 | 2023-05-30 | Space-time feature fusion power system unit combination optimization method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116760115B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832542A (en) * | 2017-11-22 | 2018-03-23 | 国网河南省电力公司电力科学研究院 | A kind of Unit Combination Optimization Scheduling based on spatial and temporal scales consumption scene |
| WO2018059096A1 (en) * | 2016-09-30 | 2018-04-05 | 国电南瑞科技股份有限公司 | Combined decision method for power generation plans of multiple power sources, and storage medium |
| CN108492047A (en) * | 2018-03-30 | 2018-09-04 | 南京上古网络科技有限公司 | The efficient distribution method of hydroelectric generating set load continued based on immediate status |
| CN110311376A (en) * | 2019-07-31 | 2019-10-08 | 三峡大学 | A kind of Electrical Power System Dynamic security evaluation collective model and space-time method for visualizing |
| CN113610277A (en) * | 2021-07-15 | 2021-11-05 | 中山大学 | Power load prediction method, device and medium based on space-time attention mechanism |
| CN114139781A (en) * | 2021-11-17 | 2022-03-04 | 国网湖北省电力有限公司经济技术研究院 | Method and system for predicting operation trend of power system |
| CN114358520A (en) * | 2021-12-15 | 2022-04-15 | 华南理工大学 | Method, system, device and medium for economic dispatching decision of power system |
| WO2022188379A1 (en) * | 2021-03-12 | 2022-09-15 | 国网智能科技股份有限公司 | Artificial intelligence system and method serving electric power robot |
| CN115169128A (en) * | 2022-07-15 | 2022-10-11 | 山东大学 | Comprehensive energy system unit combination method and system considering network dynamic characteristics |
| CN115204035A (en) * | 2022-06-16 | 2022-10-18 | 河海大学 | Generator set operation parameter prediction method and device based on multi-scale time sequence data fusion model and storage medium |
| CN115241885A (en) * | 2022-07-26 | 2022-10-25 | 中国电力科学研究院有限公司 | Power grid real-time scheduling optimization method and system, computer equipment and storage medium |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN115293415A (en) * | 2022-07-28 | 2022-11-04 | 三峡大学 | Multi-wind-farm short-term power prediction method considering time evolution and space correlation |
| US20230072708A1 (en) * | 2021-09-08 | 2023-03-09 | Central South University | Asymmetric Laplace-based wind power forecasting method and system |
-
2023
- 2023-05-30 CN CN202310633005.7A patent/CN116760115B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018059096A1 (en) * | 2016-09-30 | 2018-04-05 | 国电南瑞科技股份有限公司 | Combined decision method for power generation plans of multiple power sources, and storage medium |
| CN107832542A (en) * | 2017-11-22 | 2018-03-23 | 国网河南省电力公司电力科学研究院 | A kind of Unit Combination Optimization Scheduling based on spatial and temporal scales consumption scene |
| CN108492047A (en) * | 2018-03-30 | 2018-09-04 | 南京上古网络科技有限公司 | The efficient distribution method of hydroelectric generating set load continued based on immediate status |
| CN110311376A (en) * | 2019-07-31 | 2019-10-08 | 三峡大学 | A kind of Electrical Power System Dynamic security evaluation collective model and space-time method for visualizing |
| WO2022188379A1 (en) * | 2021-03-12 | 2022-09-15 | 国网智能科技股份有限公司 | Artificial intelligence system and method serving electric power robot |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN113610277A (en) * | 2021-07-15 | 2021-11-05 | 中山大学 | Power load prediction method, device and medium based on space-time attention mechanism |
| US20230072708A1 (en) * | 2021-09-08 | 2023-03-09 | Central South University | Asymmetric Laplace-based wind power forecasting method and system |
| CN114139781A (en) * | 2021-11-17 | 2022-03-04 | 国网湖北省电力有限公司经济技术研究院 | Method and system for predicting operation trend of power system |
| CN114358520A (en) * | 2021-12-15 | 2022-04-15 | 华南理工大学 | Method, system, device and medium for economic dispatching decision of power system |
| CN115204035A (en) * | 2022-06-16 | 2022-10-18 | 河海大学 | Generator set operation parameter prediction method and device based on multi-scale time sequence data fusion model and storage medium |
| CN115169128A (en) * | 2022-07-15 | 2022-10-11 | 山东大学 | Comprehensive energy system unit combination method and system considering network dynamic characteristics |
| CN115241885A (en) * | 2022-07-26 | 2022-10-25 | 中国电力科学研究院有限公司 | Power grid real-time scheduling optimization method and system, computer equipment and storage medium |
| CN115293415A (en) * | 2022-07-28 | 2022-11-04 | 三峡大学 | Multi-wind-farm short-term power prediction method considering time evolution and space correlation |
Non-Patent Citations (3)
| Title |
|---|
| TAE-YOUNG KIM等: "Optimal Dispatch and Unit Commitment Strategies for Multiple Diesel Generators in Shipboard Power System Using Dynamic Programming", 《2018 21ST INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS)》 * |
| 谢应昭;卢继平;: "含风储混合***的多目标机组组合优化模型及求解", 电力自动化设备, no. 03 * |
| 赵适宜;: "机组启停优化中遗传算法的应用研究", 中国电业(技术版), no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116760115B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107547633B (en) | User constant standing point processing method and device and storage medium | |
| CN101600151B (en) | Radio-wave propagation characteristic prediction assisting system and radio-wave propagation characteristic prediction assisting method | |
| CN109816111A (en) | Reading understands model training method and device | |
| CN115800553A (en) | HPLC-based platform area topology identification method and device, electronic equipment and storage medium | |
| CN105338186A (en) | Context awareness-based Android mobile terminal power management method | |
| CN116760115B (en) | Space-time feature fusion power system unit combination optimization method and system thereof | |
| CN110519408A (en) | A kind of IP attribution inquiry method, device, electronic equipment and storage medium | |
| CN112541841B (en) | Method, device and terminal equipment for simulating past future data | |
| CN112104326A (en) | Power monitoring method and device for photovoltaic power generation | |
| CN117668692A (en) | Intelligent electric energy monitoring method, device, equipment and medium based on fault detection | |
| CN110032586B (en) | Storage method, query method and acquisition and storage system for energy storage cell data | |
| CN113778681B (en) | Data processing method and device based on cloud computing and storage medium | |
| CN115224727A (en) | Method and device for testing stability of dynamic power angle of wind power | |
| CN111025068A (en) | Method and device for reading load curve data of electric meter and electronic equipment | |
| CN101155369A (en) | Power-saving system and method for mobile device | |
| CN115858672A (en) | Power terminal management method and device, electronic equipment and storage medium | |
| CN113922411A (en) | Method and device for determining distributed photovoltaic absorption capacity | |
| CN105205605B (en) | Interactive service system of city intelligent portal terminal and electric power marketing terminal | |
| CN112184481B (en) | Smart power grid arrearage processing method and device combining RPA and AI | |
| Yu et al. | Hierarchical game for electric vehicle public charging market | |
| CN109697219B (en) | Block chain-based electric power distributed system and block chain recording method thereof | |
| CN110222024A (en) | Power supply unit exchanges method and its sales end mobile device | |
| CN104936136A (en) | Data transfer method based on mobility summary | |
| CN112188388A (en) | Hybrid indoor positioning method based on machine learning | |
| CN110021177A (en) | Heuristic random searching traffic lights timing designing method, 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 |