CN115310698A - Energy consumption prediction system, method, device, equipment and medium - Google Patents
Energy consumption prediction system, method, device, equipment and medium Download PDFInfo
- Publication number
- CN115310698A CN115310698A CN202210945157.6A CN202210945157A CN115310698A CN 115310698 A CN115310698 A CN 115310698A CN 202210945157 A CN202210945157 A CN 202210945157A CN 115310698 A CN115310698 A CN 115310698A
- Authority
- CN
- China
- Prior art keywords
- real
- energy consumption
- learning model
- time
- joint learning
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an energy consumption prediction system, method, device, equipment and medium, the system includes: and sending the actual motion parameters to the real-time control system through the first type non-real-time system so that the real-time control system drives the motor to operate according to the actual motion parameters, acquiring the actual energy consumption value of the corresponding motor through the real-time control system, and feeding the actual energy consumption value as original training data back to the second type non-real-time system and the corresponding first type non-real-time system so as to create and obtain a corresponding non-joint learning model and a corresponding joint learning model. According to the embodiment of the invention, the operation environments of the joint learning model and the non-joint learning model are built at the same time through one set of hardware equipment, so that the energy consumption prediction conditions of the joint learning model and the non-joint learning model are conveniently analyzed and checked, and the working efficiency is improved; and moreover, the energy consumption of the motor can be predicted more accurately by adopting the combined learning model.
Description
Technical Field
The present invention relates to the field of machine learning technologies, and in particular, to an energy consumption prediction system, method, apparatus, device, and medium.
Background
Human devices have gone through a long period of conventional data processing, and many data with the same or similar data cannot be collected and analyzed, so that data islands are formed. With the development of internet technology, big data and artificial intelligence technology, technical support is provided for data sharing in the energy field. In some scenarios, the servers used for data training do not allow data to be collected, such as practical engineering limitations, network connections are expensive, slow or unreliable, or the amount of data is too large.
It can be seen that the data islanding problem affects the effect of machine learning, and the amount of data owned by each set of control system is not very large and has high similarity, for example, most tasks adopt the same control strategy. Due to the limitation of data, the motor energy consumption under other control strategies cannot be accurately predicted.
Disclosure of Invention
The invention provides an energy consumption prediction system, method, device, equipment and medium, which realize that the running environment of a joint learning model and a non-joint learning model is built simultaneously through a set of hardware equipment, are convenient for analyzing and checking the energy consumption prediction conditions of the joint learning model and the non-joint learning model, and improve the working efficiency; and moreover, the energy consumption of the motor can be predicted more accurately by adopting the joint learning model.
According to an aspect of the present invention, there is provided an energy consumption prediction system including: at least two non-real time systems and at least two real time control systems; wherein the non-real time system comprises: a first type of non-real time system and a second type of non-real time system;
each first type non-real-time system is accessed to the second type non-real-time system in a remote desktop control mode; the first type non-real-time system is connected with the real-time control system in a one-to-one correspondence manner; the second type non-real-time system is connected with each real-time control system;
sending actual motion parameters to a corresponding real-time control system through the first type non-real-time system so that the real-time control system drives a motor to operate according to the actual motion parameters, and acquiring actual energy consumption values of the corresponding motor through the real-time control system to serve as original training data to be fed back to the second type non-real-time system and the corresponding first type non-real-time system;
and the first type non-real-time system creates a corresponding non-joint learning model according to the original training data, and the second type non-real-time system creates a corresponding joint learning model according to the original training data of each real-time control system.
According to another aspect of the present invention, there is provided an energy consumption prediction method, including:
acquiring actual motion parameters of at least two motors;
inputting the actual motion parameters into a pre-established joint learning model and a corresponding non-joint learning model to obtain a corresponding energy consumption predicted value; the motor corresponds to the non-joint learning model one by one;
and determining the energy consumption prediction capability of the joint learning model and each non-joint learning model according to the energy consumption prediction value and the pre-acquired energy consumption actual value.
According to another aspect of the present invention, there is provided an energy consumption prediction apparatus including:
the acquisition module is used for acquiring actual motion parameters of at least two motors;
the input module is used for inputting the actual motion parameters into a pre-established joint learning model and a corresponding non-joint learning model so as to obtain a corresponding energy consumption predicted value; the motor corresponds to the non-joint learning model one by one;
and the determining module is used for determining the energy consumption prediction capability of the joint learning model and each non-joint learning model according to the energy consumption prediction value and the pre-acquired energy consumption actual value.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the energy consumption prediction method according to any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the method for energy consumption prediction according to any one of the embodiments of the present invention when the computer instructions are executed.
According to the technical scheme, the real-time control system sends the actual motion parameters to the corresponding real-time control system through the first type non-real-time system, so that the real-time control system drives the motor to operate according to the actual motion parameters, the real-time control system collects the energy consumption actual values of the corresponding motor to serve as original training data to be fed back to the second type non-real-time system and the corresponding first type non-real-time system, the first type non-real-time system creates the corresponding non-joint learning model according to the original training data, the second type non-real-time system creates the corresponding joint learning model according to the original training data of each real-time control system, the running environments of the joint learning model and the non-joint learning model are built through one set of hardware equipment at the same time, the energy consumption prediction conditions of the joint learning model and the non-joint learning model are analyzed and checked conveniently, and the working efficiency is improved; and moreover, the energy consumption of the motor can be predicted more accurately by adopting the joint learning model.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of an energy consumption prediction system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a connection among a USB peripheral device, a non-real-time system and a real-time control system according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of another energy consumption prediction system according to an embodiment of the present invention;
fig. 4 is a view of a control system scenario of an elevator according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating a method for energy consumption prediction according to an embodiment of the present invention;
FIG. 6 is a flow chart of another energy consumption prediction method according to an embodiment of the present invention;
fig. 7 is a block diagram illustrating an energy consumption prediction apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In an embodiment, fig. 1 is a schematic structural diagram of an energy consumption prediction system according to an embodiment of the present invention. In the embodiment, the structure of the energy consumption prediction system is described by taking the example that the energy consumption prediction system comprises N non-real-time systems (wherein, a second type non-real-time system and N-1 first type non-real-time systems), N-1 real-time control systems and N-1 motors. Wherein N is a positive integer greater than or equal to 2. As shown in fig. 1, the system includes:
at least two non-real time systems and at least two real time control systems; wherein, non-real-time system includes: a first type of non-real time system 120 and a second type of non-real time system 110;
wherein each first-type non-real-time system 120 is accessed to the second-type non-real-time system 110 in a remote desktop control manner; the first type non-real-time system 120 is connected with the real-time control system 130 in a one-to-one correspondence manner; the second type non-real time system 110 is connected with each real time control system 130;
the actual motion parameters are sent to the corresponding real-time control system 110 through the first-type non-real-time system 120, so that the real-time control system 130 drives the motor 140 to operate according to the actual motion parameters, and the real-time control system 130 acquires the actual energy consumption values of the corresponding motor 140 to serve as original training data to be fed back to the second-type non-real-time system 110 and the corresponding first-type non-real-time system 120;
the first type of non-real time system 120 creates a corresponding non-joint learning model from the original training data and the second type of non-real time system 110 creates a corresponding joint learning model from the original training data for each real time control system.
In this embodiment, the non-real-time system may also be referred to as a desktop system, for example, the non-real-time system may include, but is not limited to, a windows system, an apple system, or a Linux system, etc. In the energy consumption prediction system, the number of the non-real-time systems is at least two, and may include two types, one is the first type of non-real-time system 120, and one is the second type of non-real-time system 110. Illustratively, the first type of non-real time system 120 may be a Fedora system. The second type of non-real time system 110 may be a win10 system based on x86, x64, ARM architecture PC and tablet. In the embodiment, each first-type non-real-time system 120 is connected to the second-type non-real-time system 110 in a remote desktop control manner, the first-type non-real-time systems 120 are connected to the real-time control systems 130 in a one-to-one correspondence manner, and the second-type non-real-time systems 110 are connected to each real-time control system 130.
In this embodiment, the number of the first type non-real-time systems 120 is at least 1, and each first non-real-time control system 120 corresponds to one real-time control system 130 and one motor 140, so as to acquire relevant parameters, such as weight, acceleration, constant speed, length, and the like of the weight, corresponding to the motor 140 during actual operation through the real-time control system 130. It should be noted that the first-type non-real-time system 120 includes a human-machine interaction interface, and the setting of the relevant parameters of the motor 140, the display of data, and the storage of data may be performed in the human-machine interaction interface of the first-type non-real-time system 120 according to the actual motor motion parameters sent by the real-time controllable system through the human-machine interaction interface. Illustratively, the total time of operation of the motor, the weight, and the motion pattern are set accordingly in the first type of non-real time system 120.
In this embodiment, the actual motion parameter refers to an actual motion parameter of the motor operation. The actual motion parameters may include total running time, length, weight, and running mode, where the motion mode may include acceleration, uniform deceleration, and uniform speed.
In this embodiment, the real-time control system 130 refers to a system capable of performing a real-time reaction through a Controller, and for example, the real-time control system 130 may be a Programmable Logic Controller (PLC), a Controller, or the like, and of course, the real-time control system 130 is generally a system with relatively high efficiency and capable of performing a real-time reaction. In this embodiment, the actual control system 130 may collect relevant parameters of the motor 140 in actual operation, such as weight, acceleration, motion pattern, and the like, through the electricity meter.
In this embodiment, the original training data may be understood as the actual energy consumption value of the corresponding motor 140 obtained by the electricity meter, which may include the total running time, the length of each segment, the weight of the weight, and the running mode (related data such as acceleration, uniform deceleration, and uniform speed, etc. the actual energy consumption value may be understood as the actual energy consumption value of the motor 140 obtained by the electricity meter, and the electric energy of the motor output by the motor controller may be directly measured by the electricity meter to reflect the energy consumption corresponding to the motor 140.
In this embodiment, the real-time control system 130 sends the actual motion parameters of the corresponding motor 140 to the corresponding real-time control system 130 through the first-type non-real-time system 120, so that the real-time control system 130 can drive the corresponding motor 140 to operate according to the actual motion parameters of the motor 140, and meanwhile, in the operation process of the motor 140, the real-time control system 130 can collect an actual energy consumption value generated in the operation of the corresponding motor 140, and feed back the actual energy consumption value as original training data to the second-type non-real-time system 110 and the first-type non-real-time systems 120 corresponding to the motors 140, the first-type non-real-time systems 120 create non-joint learning models corresponding to the first-type non-real-time systems 120 according to the fed-back original training data, and the second-type non-real-time systems 110 create corresponding joint learning models according to the original training data of each real-time control system 130.
Illustratively, the real-time control system 1 acquires an energy consumption actual value of the motor 1, the real-time control system 2 acquires an energy consumption actual value of the motor 2, the real-time control system 3 acquires an energy consumption actual value of the motor 3, the energy consumption actual value of the motor 1 is used as original training data to be fed back to a first type non-real-time system corresponding to the motor 1, and a corresponding non-joint learning model is created; the actual value of the energy consumption of the motor 2 is used as original training data to be fed back to a first type non-real-time system corresponding to the motor 2, and a corresponding non-joint learning model is created; the actual value of the energy consumption of the motor 3 is used as original training data to be fed back to a first type non-real-time system corresponding to the motor 3, and a corresponding non-joint learning model is created; meanwhile, the actual energy consumption values corresponding to the motor 1, the motor 2 and the motor 3 are simultaneously used as original training data to be fed back to the second type non-real-time system, and corresponding joint learning models are created according to the original training data corresponding to the motor 1, the motor 2 and the motor 3.
In an embodiment, the non-real-time system is connected to the at least two USB controllers in a PCIE card manner, and the non-real-time system and the USB controllers correspond to each other one to one.
In this embodiment, the non-real-time system may be connected to at least two USB controllers in a PCIE card manner, and pass through the USB controllers, so that all the USB device non-real-time systems plugged in the USB controllers can be verified. Here, transparent transmission is understood as transparent transmission, which means that the content of transmission is only transmitted from a source address to a destination address without any change to the content of service data, regardless of the content of the transmitted service in communication.
It should be noted that the PCIE display card supports access of multiple displays, that is, multiple displays may be connected, one of the multiple displays may be used as a main display of the non-real-time system of the display card transparent transmission, and then the other displays are used as an extended desktop. In the non-real-time system of PCIE video card transparent transmission, other non-real-time systems may be opened by using a corresponding software tool through a Virtual Network Console (VCN), and the other non-real-time systems are placed in the extension desktop of each non-real-time system respectively. As each non-real-time system corresponds to the USB controller one by one, and the corresponding non-real-time system can be operated by inserting a keyboard mouse into each USB controller.
In one embodiment, all non-real-time systems are connected with a USB controller, and each non-real-time system is allocated with a set of USB external equipment.
The USB external device can be a keyboard and a mouse device connected with the system.
In this embodiment, all the non-real-time systems are connected to one USB controller, and each non-real-time system is allocated with one set of USB external device. In this embodiment, a plurality of sets of USB external devices are included, and are transparently transmitted to the USB external device, but are not transparently transmitted to the USB controller connected to the non-real-time system, and it can be understood that the non-real-time system may not verify the USB controller, but may verify the USB external device, and if the USB device is replaced, the non-real-time system may not verify the USB external device.
In this embodiment, the PCIE display card supports access to multiple displays, and is connected to multiple displays, where one display is used as a main display of the non-real-time system transparently transmitted by the display card, and the other displays are used as extension desktops, and in the non-real-time system transparently transmitted by the PCIE display card, the other non-real-time systems may be opened by using a corresponding software tool through a VNC method, and then are respectively placed in the extension desktops corresponding to the non-real-time systems. And the transparent transmission non-real-time system can be operated by a set of USB external equipment corresponding to each non-real-time system.
Fig. 2 is a schematic diagram illustrating a connection between a USB external device, a non-real-time system, and a real-time control system according to an embodiment of the present invention. For example, the non-real-time environment in fig. 2 includes 3 USB external devices, 3 first-type non-real-time systems and a second-type non-real-time system, and the real-time environment in fig. 2 includes 3 Virtualization program Logic controllers (vplmcs) for illustration. Each first type non-real-time system corresponds to one USB external device. As shown in fig. 2, the first type non-real-time system may be a Fedora system, and exemplarily, the first type non-real-time system 1 is a Fedora system 1, the first type non-real-time system 2 is a Fedora system 2, the first type non-real-time system 3 is a Fedora system 3, and the second type non-real-time system may be a win10 system. The first type non-real-time system 1 corresponds to the USB controller 1, the first type non-real-time system 2 corresponds to the USB controller 2, and the first type non-real-time system 3 corresponds to the USB controller 3. In this embodiment, the video card is transmitted to the second type non-real-time system, and the three desktop systems, i.e., the first type non-real-time system 1, the first type non-real-time system 2, and the first type non-real-time system 3, are accessed to the second type non-real-time system by the control of the remote desktop.
According to the technical scheme, the real-time control system sends the actual motion parameters to the corresponding real-time control system through the first type non-real-time system, so that the real-time control system drives the motor to operate according to the actual motion parameters, the real-time control system collects the energy consumption actual values of the corresponding motor to serve as original training data to be fed back to the second type non-real-time system and the corresponding first type non-real-time system, the first type non-real-time system creates the corresponding non-joint learning model according to the original training data, the second type non-real-time system creates the corresponding joint learning model according to the original training data of each real-time control system, the set of equipment simultaneously builds the operating environment of the joint learning model and the non-joint learning model, the energy consumption of the motor is accurately predicted, and the working efficiency is improved.
In one embodiment, the energy consumption prediction system further comprises: at least two motor controllers and at least two electric meters; the motor controllers and the electric meters are in one-to-one correspondence with the motors 140; the input end of the motor controller and the output end of the electric meter are connected with the real-time control system 130, and the output end of the motor controller is respectively connected with the motor 140 and the input end of the electric meter;
the real-time control system 130 sends the actual motion parameters to the corresponding motor controllers, so that the motor controllers drive the corresponding motors 140 to operate according to the actual motion parameters, and the electric meters collect the actual energy consumption values of the corresponding motors 140 and feed the actual energy consumption values back to the corresponding real-time control system 130.
The motor controller may be a controller for controlling the motor, and the motor controller may perform command execution and feedback of actual motion parameters of the motor 140. The electric meter is used for acquiring an actual energy consumption value of the corresponding motor 140 and transmitting the corresponding actual energy consumption value to the real-time control system 130.
In this embodiment, the motor controller may be one of a dc speed regulator, a frequency converter, a step driver, and a servo driver, and each motor controller has a corresponding motor, so that the types of the motor controllers are multiple, and the types of the corresponding motors may also be multiple. It should be noted that the motor controller may control the speed of different types of motors, either directly or indirectly. It will be appreciated that when the motor controller is a dc speed regulator, the corresponding motor may be a dc motor, i.e. the dc speed regulator is used directly to control the speed of the dc motor. When the motor controller is a frequency converter, a servo driver or a stepping driver, the speed of the corresponding type of motor can be indirectly controlled. Specifically, when the motor controller is a frequency converter, the corresponding motor may be a variable frequency motor, and the frequency converter may be configured to provide alternating currents of different powers to control the speed of the variable frequency motor; when the motor controller is a stepping driver, the corresponding motor can be a stepping motor, and the stepping driver can be used for providing different pulse currents so as to control the speed of the stepping motor; when the motor controller is a servo driver, the corresponding motor can be a servo motor, and the servo driver can also be used for providing different pulse currents so as to control the speed of the servo motor.
In this embodiment, the energy consumption prediction system includes at least two motor controllers and at least two electric meters, each of the motor controllers and the electric meters has a corresponding motor 140, so as to drive the motor 140 to operate through the motor controllers, and directly measure the electric energy of the motor 140 output by the motor controllers through the electric meters. For example, the electric meter corresponding to the motor controller 1 is the electric meter 1, the corresponding motor is the motor 1, the motor controller 1 drives the motor 1 to operate, different motion parameters generated after the motor 1 moves are obtained, for example, the weight of a weight, a motion mode and the like, the energy consumption of the motor 1 corresponding to the different motion parameters is different, and the electric meter 1 can obtain an actual energy consumption value generated by the corresponding motor 1 in the moving process.
It should be noted that, in the aspect of measuring the actual energy consumption value corresponding to the motor 140, an electric meter with a lower resolution may be used to measure the input electric energy of the corresponding motor controller, so that it is ensured that the actual energy consumption value may conform to the normal distribution under the same motion parameter.
In this embodiment, the input end of the motor controller and the output end of the electric meter are connected to the real-time control system 130, the output end of the motor controller is connected to the input ends of the motor 140 and the electric meter, the real-time control system 130 can send the actual motion parameters of the motor 140 to the corresponding motor controller, so that the motor controller can drive the corresponding motor 140 to operate according to the actual motion parameters of the motor 140, and meanwhile, the electric meter can collect the actual energy consumption value of the corresponding motor 140 and feed the actual energy consumption value back to the corresponding real-time control system 130.
In an embodiment, to facilitate better understanding of the energy consumption prediction system, fig. 3 is a schematic structural diagram of another energy consumption prediction system according to an embodiment of the present invention. Illustratively, the energy consumption prediction system in the present embodiment includes: four non-real-time systems, three real-time control systems, three motor controllers, three electric meters and three motors are taken as examples to explain the connection relationship among the modules.
As shown in fig. 3, four non-real-time systems include: three first-type non-real-time systems 320 and one second-type non-real-time system 310, the three first-type non-real-time systems 320 may be a Fedora system 1, a Fedora system 2, and a Fedora system 3, and the one second-type non-real-time system 310 may be a win10 system. Each first-type non-real-time system 320 is connected to the second-type non-real-time system 310 in a remote desktop control mode, and each real-time control system 330 corresponds to one motor controller 340, one motor 350 and one electric meter 360, as shown in fig. 3, a real-time control system 1 corresponds to a motor controller 1, an electric meter 1 and a motor 1, a real-time control system 2 corresponds to a motor controller 2, an electric meter 2 and a motor 2, and a real-time control system 3 corresponds to a motor controller 3, an electric meter 3 and a motor 3.
In this embodiment, the first type non-real-time system 320 sends the actual motion parameters of the corresponding motor 350 to the corresponding real-time control system 330, the real-time control system 330 sends the actual motion parameters to the corresponding motor controller 340, so that the motor controller 340 drives the corresponding motor 350 to operate according to the actual motion parameters, and the electric meter 360 collects the actual energy consumption value of the corresponding motor 350 and feeds the actual energy consumption value back to the corresponding real-time control system 330, and at the same time, the real-time control system 330 feeds the actual energy consumption value as the original training data to the corresponding first type non-real-time system 320, so that the first type non-real-time system 320 creates the corresponding non-joint learning model according to the original training data of the corresponding motor 350, and the real-time control system 330 feeds the actual energy consumption value as the original training data to the second type non-real-time system 310, so that the second type non-real-time system 310 creates the corresponding joint learning model according to the original training data of the motor 350 corresponding to each real-time control system 330.
In an embodiment, in order to facilitate understanding of energy consumption prediction performed when the energy consumption prediction is applied to different scenarios, the embodiment takes a control system scenario of an elevator as an example for description, and fig. 4 is a control system scenario diagram of an elevator according to an embodiment of the present invention. The motor control elevator in the elevator in this embodiment moves, as shown in fig. 4, contains product installation version, status light, promotion straight line module and weight in the elevator scene, and this embodiment utilizes the actual motion parameter of motor in the elevator through the removal of weight control elevator to obtain the energy consumption actual value of current motor, in order to be used for follow-up energy consumption prediction condition to joint learning model and non-joint learning model to carry out the analysis.
In an embodiment, fig. 5 is a flowchart of an energy consumption prediction method according to an embodiment of the present invention, where the embodiment is applicable to a situation when energy consumption of motors in various devices is predicted, and the method may be executed by an energy consumption prediction system, where the energy consumption prediction system may be implemented in a form of hardware and/or software, and the energy consumption prediction system may be configured in an electronic device. As shown in fig. 5, the method includes:
and S510, acquiring actual motion parameters of at least two motors.
S520, inputting the actual motion parameters into a pre-established joint learning model and a corresponding non-joint learning model to obtain a corresponding energy consumption predicted value; wherein, the motor is in one-to-one correspondence with the non-joint learning model.
The joint learning model can be created by the second type non-real-time system comprehensively according to the original training data of each real-time control system, and the first type non-real-time system of the non-joint learning model is created according to the corresponding original training data.
In this embodiment, the obtained actual motion parameters corresponding to the motor are input into a pre-created joint learning model and a corresponding non-joint learning model, so as to obtain the predicted energy consumption value of the corresponding motor. It should be noted that there is only one joint learning model, there are a plurality of non-joint learning models, and each non-joint learning model corresponds to one motor.
For example, the learning process may be to learn, for the second type non-real-time system, each database data in the first type non-real-time system, where each first type non-real-time system forms a non-joint learning model of its own system, and becomes joint learning once integrated with the first type non-real-time system, in this embodiment, the original training data in the first type non-real-time system is learned together to form a joint learning model. The second type of non-real time system may be a win10 system and the first type of non-real time system may be a fedora system.
S530, determining the energy consumption prediction capability of the joint learning model and each non-joint learning model according to the energy consumption prediction value and the energy consumption actual value obtained in advance.
In this embodiment, a corresponding energy consumption difference value is determined by the energy consumption predicted value and the energy consumption actual value, and then the energy consumption prediction capability between the joint learning model and each non-joint learning model can be determined according to the energy consumption difference value.
In one embodiment, determining the energy consumption prediction capability of the joint learning model and each non-joint learning model according to the energy consumption prediction value and the energy consumption actual value obtained in advance comprises:
determining an energy consumption difference value according to the energy consumption predicted value and the energy consumption actual value;
and determining the energy consumption prediction capability between the joint learning model and each non-joint learning model according to the energy consumption difference value.
In this embodiment, a corresponding energy consumption difference value may be determined by using the energy consumption predicted value and the energy consumption actual value of the corresponding motor, and the energy consumption prediction capability between the joint learning model and each non-joint learning model may be determined according to the energy consumption difference value.
Illustratively, the first type of non-real-time system is a fedora system, the second type of non-real-time system is a win10 system for illustration, the win10 system has a plurality of sets of non-joint learning models and a set of joint learning models, the two sets of non-joint learning models are communicated with each fedora system, each fedora system can manually input corresponding motor operation parameters in a parameter setting interface, energy consumption values of joint learning and non-joint learning prediction output by the models can be displayed in the interface, equipment can move through corresponding operation, a real energy consumption value can be displayed, so that an energy consumption difference value of a predicted value and a real value is obtained, and the energy consumption prediction capability between the joint learning models and each non-joint learning model is determined through the energy consumption difference value. Wherein the motor operating parameters may include: weight, run time, mode of running each segment, etc.
It should be noted that, for the explanation of the actual motion parameters, the actual energy consumption values, and other parameters in the energy consumption prediction method in this embodiment, see the description of the corresponding parameters in the energy consumption prediction system in the above embodiment, which is not described in detail here.
In an embodiment, fig. 6 is a flowchart of another energy consumption prediction method according to an embodiment of the present invention, and the present embodiment explains the construction of a joint learning model and a non-joint learning model on the basis of the foregoing embodiments. As shown in fig. 6, the method includes:
s610, respectively acquiring original training data corresponding to at least two first type non-real-time systems; the first type of non-real-time system corresponds to the motors one by one.
S620, constructing a non-joint learning model corresponding to the first type non-real-time system according to the original training data collected by each first type non-real-time system and a pre-established machine learning model.
S630, performing integrated training on all the original training data acquired by the first type non-real-time system, and constructing a corresponding joint learning model.
In this embodiment, a non-joint learning model corresponding to each first-type non-real-time system is constructed according to original training data acquired by each first-type non-real-time system and a pre-created machine learning model, and a corresponding joint learning model is constructed by performing integrated training on the original training data acquired by all first-type non-real-time systems, so that the difference between the joint learning model and the non-joint learning model can be displayed, and the actual energy consumption value of the motor under various control strategies can be predicted more accurately.
It should be noted that, the original training data includes weight, movement time range, time increment, movement mode, and the like, during training, corresponding parameters may be artificially input in the first-type non-real-time control system, for example, weight, movement time range, and time increment, in this embodiment, the input weight is consistent with the actual weight, otherwise, accuracy of the model is affected, then, a training process is started, the VPLC in the actual environment may drive the motor to operate according to a predetermined movement mode from the minimum time within the time range, and at the same time, the VPLC measures power loss through the electric meter during this process, the VPLC transmits and stores single-training data to the database in the first-type non-real-time system, then, the training continues by adding a time increment value, and sequentially progresses until the whole training ends, a large amount of training data may exist in the database in the first-type non-real-time system. More randomness is increased by adopting the effect of the low-sampling and low-real-time-rate electric meter, the electric meter actually integrates voltage and current after multiplying the motor with time, the power difference is large when the motor is started instantly, accelerated, decelerated and at a constant speed, the instantaneous current and voltage value at the moment of metering and sampling by the electric meter has a lot of uncertainty and randomness, and the energy consumption value also has a lot of randomness. In the actual operation process, the weight on the motor can be manually placed on the energy consumption prediction demonstration device by an operator. Of course, in order to realize automatic control, weights can be automatically placed on the energy consumption prediction demonstration device in other modes, the weight of the input weights is consistent with the actual weight, and otherwise the accuracy of the model is influenced.
And S640, acquiring actual motion parameters of at least two motors.
S650, inputting the actual motion parameters into a pre-established joint learning model and a corresponding non-joint learning model to obtain a corresponding energy consumption prediction value; wherein, the motor is in one-to-one correspondence with the non-joint learning model.
And S660, determining the energy consumption prediction capability of the joint learning model and each non-joint learning model according to the energy consumption prediction value and the energy consumption actual value obtained in advance.
According to the technical scheme in the embodiment, on the basis of the embodiment, the original training data corresponding to at least two first-type non-real-time systems are respectively obtained, the non-joint learning model corresponding to the first-type non-real-time systems is constructed according to the original training data collected by each first-type non-real-time system and the pre-established machine learning model, all the original training data collected by the first-type non-real-time systems are subjected to integrated training, the corresponding joint learning model is constructed, and the non-joint learning model and the joint learning model are created.
In an embodiment, fig. 7 is a block diagram of an energy consumption prediction apparatus according to an embodiment of the present invention, which is suitable for use in predicting energy consumption of motors in various devices, and the apparatus may be implemented by hardware/software. The energy consumption prediction method can be configured in the electronic device to implement the energy consumption prediction method in the embodiment of the invention. As shown in fig. 7, the apparatus includes: an acquisition module 710, an input module 720, and a determination module 730.
The obtaining module 710 is configured to obtain actual motion parameters of at least two motors;
an input module 720, configured to input the actual motion parameter into a pre-created joint learning model and a corresponding non-joint learning model to obtain a corresponding energy consumption prediction value; the motor corresponds to the non-joint learning model one by one;
and the determining module 730 is configured to determine the energy consumption prediction capabilities of the joint learning model and each non-joint learning model according to the energy consumption prediction value and a pre-obtained energy consumption actual value.
According to the technical scheme, the obtaining module is used for obtaining the actual motion parameters of at least two motors, the input module is used for inputting the actual motion parameters into the pre-created joint learning model and the corresponding non-joint learning model to obtain the corresponding energy consumption predicted values, and the determining module is used for determining the energy consumption prediction capabilities of the joint learning model and each non-joint learning model according to the energy consumption predicted values and the pre-obtained energy consumption actual values, so that the running environments of the joint learning model and the non-joint learning model are built simultaneously through one set of hardware equipment, the energy consumption prediction situations of the joint learning model and the non-joint learning model are conveniently analyzed and checked, and the working efficiency is improved; and moreover, the energy consumption of the motor can be predicted more accurately by adopting the joint learning model.
In one embodiment, the determining module 730 includes:
the difference value determining unit is used for determining an energy consumption difference value according to the energy consumption predicted value and the energy consumption actual value;
and the capacity determining unit is used for determining the energy consumption prediction capacity between the joint learning model and each non-joint learning model according to the energy consumption difference value.
In an embodiment, the energy consumption prediction apparatus further includes:
the training data acquisition module is used for respectively acquiring original training data corresponding to at least two first type non-real-time systems before acquiring actual motion parameters of at least two motors; the first type non-real-time system corresponds to the motors one by one.
And the model construction module is used for constructing a corresponding joint learning model and a non-joint learning model corresponding to each first type non-real-time system according to the original training data.
In one embodiment, a model building module comprises:
the first model building unit is used for building a non-joint learning model corresponding to each first type non-real-time system according to original training data acquired by each first type non-real-time system and a pre-created machine learning model;
and the second model construction unit is used for performing integrated training on the original training data acquired by all the first type non-real-time systems and constructing a corresponding joint learning model.
The energy consumption prediction device provided by the embodiment of the invention can execute the energy consumption prediction method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
In an embodiment, fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 8, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as the energy consumption prediction method.
In some embodiments, the energy consumption prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the energy consumption prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the energy consumption prediction method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. An energy consumption prediction system, comprising: at least two non-real time systems and at least two real time control systems; wherein the non-real time system comprises: a first type of non-real time system and a second type of non-real time system;
each first type non-real-time system is accessed to the second type non-real-time system in a remote desktop control mode; the first type non-real-time system is connected with the real-time control system in a one-to-one correspondence manner; the second type non-real-time system is connected with each real-time control system;
sending actual motion parameters to a corresponding real-time control system through the first type non-real-time system so that the real-time control system drives a motor to operate according to the actual motion parameters, and acquiring actual energy consumption values of the corresponding motor through the real-time control system to serve as original training data to be fed back to the second type non-real-time system and the corresponding first type non-real-time system;
and the first type non-real-time system creates a corresponding non-joint learning model according to the original training data, and the second type non-real-time system creates a corresponding joint learning model according to the original training data of each real-time control system.
2. The system of claim 1, wherein the energy consumption prediction system further comprises: at least two motor controllers and at least two electric meters; the motor controllers and the electric meters are in one-to-one correspondence with the motors; the input end of the motor controller and the output end of the electric meter are connected with the real-time control system, and the output end of the motor controller is respectively connected with the motor and the input end of the electric meter;
and sending the actual motion parameters to the corresponding motor controllers through the real-time control system, so that the motor controllers drive the corresponding motors to operate according to the actual motion parameters, and collecting the energy consumption actual values of the corresponding motors through the electric meters and feeding the energy consumption actual values back to the corresponding real-time control system.
3. The system according to claim 1 or 2, wherein the non-real-time system is connected to at least two USB controllers in a PCIE card manner, and the non-real-time system and the USB controllers are in one-to-one correspondence.
4. The system according to claim 1 or 2, wherein all of said non-real time systems are connected to a USB controller, and each of said non-real time systems is allocated a set of USB peripheral devices.
5. A method of energy consumption prediction, comprising:
acquiring actual motion parameters of at least two motors;
inputting the actual motion parameters into a pre-established joint learning model and a corresponding non-joint learning model to obtain a corresponding energy consumption predicted value; the motor corresponds to the non-joint learning model one by one;
and determining the energy consumption prediction capability of the joint learning model and each non-joint learning model according to the energy consumption prediction value and the pre-acquired energy consumption actual value.
6. The method according to claim 5, wherein determining the energy consumption prediction capability of the joint learning model and each of the non-joint learning models according to the energy consumption prediction value and the pre-obtained energy consumption actual value comprises:
determining an energy consumption difference value according to the energy consumption predicted value and the energy consumption actual value;
and determining the energy consumption prediction capability between the joint learning model and each non-joint learning model according to the energy consumption difference value.
7. The method of claim 5, further comprising, prior to said obtaining actual motion parameters of at least two motors:
respectively acquiring original training data corresponding to at least two first-type non-real-time systems; the first type non-real-time system corresponds to the motors one by one;
and constructing a corresponding joint learning model and a non-joint learning model corresponding to each first type non-real-time system according to the original training data.
8. The method according to claim 7, wherein the constructing of the corresponding joint learning model and the corresponding non-joint learning model for each of the first-type non-real-time systems according to the original training data comprises:
constructing a non-joint learning model corresponding to each first type non-real-time system according to original training data acquired by each first type non-real-time system and a pre-established machine learning model;
and performing integrated training on all the original training data acquired by the first type non-real-time system to construct a corresponding joint learning model.
9. An energy consumption prediction apparatus, comprising:
the acquisition module is used for acquiring actual motion parameters of at least two motors;
the input module is used for inputting the actual motion parameters into a pre-established joint learning model and a corresponding non-joint learning model so as to obtain a corresponding energy consumption predicted value; the motor corresponds to the non-joint learning model one by one;
and the determining module is used for determining the energy consumption prediction capability of the joint learning model and each non-joint learning model according to the energy consumption prediction value and the pre-acquired energy consumption actual value.
10. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the energy consumption prediction method of any one of claims 5-8.
11. A computer-readable storage medium storing computer instructions for causing a processor to implement the energy consumption prediction method of any one of claims 5-8 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210945157.6A CN115310698A (en) | 2022-08-08 | 2022-08-08 | Energy consumption prediction system, method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210945157.6A CN115310698A (en) | 2022-08-08 | 2022-08-08 | Energy consumption prediction system, method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115310698A true CN115310698A (en) | 2022-11-08 |
Family
ID=83860475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210945157.6A Pending CN115310698A (en) | 2022-08-08 | 2022-08-08 | Energy consumption prediction system, method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115310698A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116633233A (en) * | 2023-06-08 | 2023-08-22 | 南京欧陆电气股份有限公司 | Frequency converter energy-saving control system and method based on voltage scanning technology |
-
2022
- 2022-08-08 CN CN202210945157.6A patent/CN115310698A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116633233A (en) * | 2023-06-08 | 2023-08-22 | 南京欧陆电气股份有限公司 | Frequency converter energy-saving control system and method based on voltage scanning technology |
| CN116633233B (en) * | 2023-06-08 | 2024-01-23 | 南京欧陆电气股份有限公司 | Frequency converter energy-saving control system and method based on voltage scanning technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11784489B2 (en) | Supply and demand adjustment monitoring device of power grid and supply and demand adjustment monitoring method for power grid | |
| US10838850B2 (en) | Robotic regression testing for smart devices | |
| CN111209609A (en) | Production parameter determination method, device, system, storage medium and electronic equipment | |
| CN102279796A (en) | Method and device for testing software compatibility | |
| CN112446976A (en) | Inspection robot, inspection system and inspection method | |
| CN115310698A (en) | Energy consumption prediction system, method, device, equipment and medium | |
| CN112988381A (en) | Method and device for generating optimization information for cloud resources and electronic equipment | |
| US11182689B2 (en) | Adaptive learning rate schedule in distributed stochastic gradient descent | |
| CN112965903A (en) | Test method, test device, electronic equipment and computer readable storage medium | |
| CN108875103B (en) | Power grid online simulation system and method | |
| CN114819385A (en) | Wind power prediction method and device, electronic equipment and storage medium | |
| CN112862222A (en) | Air conditioner return air temperature prediction method, abnormality monitoring method and related device | |
| CN113379153A (en) | Method for predicting power load, prediction model training method and device | |
| CN115586438A (en) | Dual-motor efficiency testing method, system, equipment and storage medium | |
| CN116301916A (en) | Service deployment method, device, electronic equipment and storage medium | |
| CN115599438A (en) | Method, device, equipment and medium for constructing application program publishing package | |
| CN114415691A (en) | Robot scheduling method, scheduling platform and system | |
| CN114165430A (en) | Method, system, equipment and medium for monitoring health of pump based on edge calculation | |
| KR20150116476A (en) | Method And Apparatus for Providing Building Simulation | |
| Dissanayaka et al. | Smart meter based inverter controlling network for demand response applications in smart grids | |
| CN113435718A (en) | Glass generation method and device, electronic device and storage medium | |
| CN114816758B (en) | Resource allocation method and device | |
| CN114397931B (en) | Dehumidification and liquid supplementation integrated tension wire intelligent control method and control device | |
| CN117125566A (en) | Dynamic diagnosis maintenance method, system, electronic equipment and storage medium | |
| CN114217862B (en) | Real-time hybrid test method based on combination of Windows system and real-time hardware 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 |