Multi-zone-area interconnection model predictive control system and method based on side-end interoperation

Abstract

The invention discloses a multi-zone-area interconnection model prediction control system and method based on side-end interoperation, relates to the technical field of power distribution automation, and comprises the steps of designing an interconnection system, configuring equipment to realize system architecture construction, optimizing a communication architecture, realizing real-time information interaction, and performing collaborative optimization based on model control prediction. According to the method, by adopting a model predictive control (MPC) strategy, energy dynamic distribution and load balancing between transformer areas are achieved, and the power quality problem caused by load fluctuation and distributed energy access can be effectively solved; the optimized communication architecture enables the real-time information interaction to be more efficient, and the cooperative control capability among the transformer areas is improved; through the flexible direct current interconnection technology, the problems of difficulty in capacity increase and point distribution and voltage quality difference of a traditional power distribution network are solved, and the stability and the safety of the power distribution network are improved. And meanwhile, the flexibility of cooperative operation of multiple transformer areas is improved, and the self-recovery capability of the system under the fault condition is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of power distribution automation technology, and in particular to a multi-station area interconnection model predictive control system and method based on edge-end interoperability. Background Art

[0002] The high penetration rate of distributed photovoltaic access has caused the low-voltage distribution network to face load imbalance, and some substations have reverse overload, three-phase imbalance, overvoltage and other problems. The temporal and spatial characteristics of the distributed power sources in the distribution substation are quite different from those of the traditional loads. The excess photovoltaic output in some substations during the day needs to be reversed to the upper power grid through transformers, and then transmitted to other substations for consumption, which puts higher requirements on the safety and flexibility of the distribution system and will also increase the operating network loss of the distribution network; on the other hand, the peak period of electric vehicle charging overlaps with the peak period of conventional load, making it easier for the transformers in the substation to have instantaneous heavy load / overload, which is not conducive to the safe and economic operation of the substation. In order to ensure the safety and stability of the low-voltage distribution network, the conventional control and regulation strategy must limit the power generation of photovoltaics, making it impossible to fully consume distributed photovoltaics.

[0003] The flexible interconnection system of the substation area realizes the interconnection and mutual supply between distribution stations through flexible DC technology, which can optimize the load distribution between different substations and effectively reduce the operating loss of the interconnection system. At the same time, the substations with different temporal and spatial characteristics of load complement each other to achieve dynamic capacity expansion of equipment under the premise of safe and stable distribution system. Therefore, it is necessary to study the energy dispatching system and control method between substations to realize the optimal dispatching of substation energy. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing low-voltage distribution station interval energy interaction method has low energy utilization, low load balancing efficiency, poor voltage quality, difficulty in accessing distributed energy, and how to achieve multi-station interval collaborative optimization and dynamic load regulation. In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-station area interconnection model predictive control method based on edge-end interoperability, including realizing system architecture construction by designing an interconnection system and configuring equipment;

[0006] Optimize communication architecture to achieve real-time information interaction;

[0007] Collaborative optimization of model-based control predictions.

[0008] As a preferred solution of the multi-station area interconnection model predictive control method based on edge-end interoperability described in the present invention, wherein: a first execution state is acquired to construct a first object;

[0009] collecting various parameters of the first object in the first execution state;

[0010] According to the first execution state, performing a first adjustment process on the parameter data in the first object;

[0011] The execution process of the first object is optimized.

[0012] As a preferred solution of the multi-station interconnection model predictive control method based on edge interoperability described in the present invention, wherein: the first execution state includes the state switching result obtained when the state of the first object is switched during operation.

[0013] The constructing the first object includes systematically constructing the first object according to the first target requirement.

[0014] As a preferred solution of the multi-station interconnection model predictive control method based on edge interoperability described in the present invention, wherein: the various parameters include the operating parameters of each sub-part of the first object during operation.

[0015] As a preferred solution of the multi-station interconnection model predictive control method based on edge-end interoperability described in the present invention, wherein: the first adjustment processing includes filtering the operating parameters of the sub-part.

[0016] As a preferred solution of the multi-station interconnection model predictive control method based on edge interoperability described in the present invention, the optimization process includes adjusting each parameter in the first object through a first adjustment process to make the first goal more accurately achieved.

[0017] As a preferred solution of the multi-station interconnected model predictive control method based on edge interoperability described in the present invention, the filtering process includes comparing the collected data with the results when the first object executes the first goal, and screening out the parameters that affect the first goal.

[0018] As a preferred scheme of the multi-station interconnection model predictive control method based on edge interoperability described in the present invention, wherein: the optimization link includes adjusting the various operating parameters when the first object executes the first goal, ensuring the coordination of the operating parameters between the first objects, thereby achieving the adjustment of the first goal.

[0019] Another object of the present invention is to provide a multi-station interconnected model predictive control system based on edge interoperability, which can realize dynamic load regulation and energy optimization distribution between stations through the combination of DC voltage balancing control and multi-converter collaborative optimization control, and solve the problems of current low-voltage distribution station energy interaction technology containing load imbalance, low energy utilization and unstable voltage quality.

[0020] As a preferred solution of the multi-station area interconnected model predictive control system based on edge-end interoperability described in the present invention, it includes: a system architecture module, a collection and communication module, and a prediction and optimization module;

[0021] The system architecture module is used for hardware layout and basic function implementation;

[0022] The acquisition and communication module is used for data acquisition, strategy management and communication interaction;

[0023] The prediction and optimization module is used for data-based intelligent control and global optimization.

[0024] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a multi-station interconnection system and method.

[0025] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a system and method for interconnecting multiple zones.

[0026] Beneficial effects of the present invention: The model predictive control method for interconnecting multiple substations based on edge-end interoperability provided by the present invention realizes dynamic optimization distribution of energy between substations through DC voltage balancing control, thereby improving the load balancing capability of the system. The voltage quality problem under the condition of high penetration of distributed energy is solved through flexible DC interconnection technology. By combining the rolling optimization strategy of model predictive control, the response speed of the system in dynamic load change scenarios is improved. The present invention has achieved better results in improving energy utilization efficiency, voltage stability of the distribution system, and load balancing between multiple substations. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0028] Figure 1 An overall flow chart of a multi-station interconnected model predictive control method based on edge interoperability provided for the first embodiment of the present invention.

[0029] Figure 2 A primary architecture diagram of a substation flexible interconnection system for a multi-substation interconnection model predictive control method based on edge-end interoperability provided in the first embodiment of the present invention.

[0030] Figure 3A diagram of a flexible interconnection communication architecture for a multi-station interconnection model predictive control method based on edge-end interoperability provided in the first embodiment of the present invention.

[0031] Figure 4 The first embodiment of the present invention provides an energy mutual assistance flexible control strategy for a multi-station interconnected model predictive control method based on edge interoperability. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0033] Example 1, reference Figure 1-4 , is an embodiment of the present invention, and provides a multi-station interconnection model predictive control method based on edge-end interoperability, comprising:

[0034] S1: Obtain a first execution state to construct a first object.

[0035] Specifically: the first execution state includes the state switching result obtained when the first object switches state during operation. In this embodiment: the first object is specifically a multi-station interconnection system, and a multi-port station low-voltage flexible DC interconnection system is constructed through the operation state of the multi-station interconnection system.

[0036] In this embodiment, the first object refers to a multi-port area low-voltage flexible DC interconnection system. Further, the multi-port area low-voltage flexible DC interconnection system includes an input port and an output port of the interconnection system. The input port includes performance parameters, operating state parameters, adjustment methods, etc. The output port includes performance parameters, operating state parameters, control methods, etc.

[0037] In an optional embodiment, the first object may also be a multi-port area low-voltage flexible DC interconnection system or a distributed energy system. For these two systems, the quantitative characteristic data may include the following performance parameters and operating state parameters: Multi-port area low-voltage flexible DC interconnection system, performance parameters: input voltage, current, power, output power, load balance, etc. Operating state parameters: current fluctuation, power fluctuation, frequency fluctuation, voltage regulation, etc. Distributed energy system, performance parameters: power generation power, output voltage, power quality, grid-connected power, etc. Operating state parameters: grid-connected state, voltage fluctuation, frequency deviation, load fluctuation, etc.

[0038] S2: Collect various parameters of the first object in the first execution state.

[0039] Specifically: the various parameters include the various subroutine parameters and the first object's own parameter data when the first object is running in the first execution state. In this embodiment: the collected subroutine parameters are the load of the platform area, the flexible interconnection APP parameters, etc. The first object's own parameter data is the voltage, current, power switch status and other information during operation.

[0040] In this embodiment, each parameter refers to the operation status data of the substation, and further, the operation status data includes the voltage data and current data of the substation. The voltage data includes steady-state voltage, transient voltage, maximum voltage amplitude, minimum voltage amplitude, etc. The current data includes steady-state current, transient current, load current, overload current, etc.

[0041] In an optional embodiment, the operating parameter may also be temperature data or humidity data. For these two types of data, the quantitative characteristic data may include the following performance parameters and operating state parameters: Temperature data, performance parameters: maximum temperature, minimum temperature, temperature change rate, temperature fluctuation range, etc. Operating state parameters: temperature stability, temperature gradient, temperature control accuracy, etc. Humidity data, performance parameters: relative humidity, absolute humidity, humidity fluctuation rate, humidity stability, etc. Operating state parameters: humidity control accuracy, humidity change rate, humidity adjustment frequency, etc.

[0042] S3: performing a first adjustment process on parameter data in the first object according to the first execution state.

[0043] Specifically: the first adjustment process includes adjusting the parameter data of the first object according to the operating state of the first object. In this embodiment; when the multi-port area low-voltage flexible DC interconnection system is in operation, it monitors its own parameter data in real time, and focuses on observing the parameters that affect the prediction obtained through the simulation process of the collected data, and makes real-time adjustments.

[0044] In this embodiment, the first adjustment process refers to adjusting various parameters when the first object is running. Furthermore, the first adjustment process includes voltage regulation and power balance of the multi-port area low-voltage flexible DC interconnection system. Voltage regulation includes performance parameters: voltage fluctuation range, voltage stability, regulation accuracy, etc. Power balance includes performance parameters: power error, power regulation rate, power adjustment amplitude, etc.

[0045] In an optional embodiment, the first adjustment process may also be voltage adjustment or power adjustment. For these two adjustment processes, the quantitative characteristic data may include the following performance parameters and operating state parameters: voltage adjustment, performance parameters: voltage stability, adjustment accuracy, response speed, etc. Operating state parameters: adjustment mode, response time, adjustment amplitude, etc. Power adjustment, performance parameters: power adjustment accuracy, power adjustment rate, adjustment amplitude, etc. Operating state parameters: power allocation strategy, load monitoring, adjustment frequency, etc.

[0046] S4: Optimizing the execution process of the first object.

[0047] Specifically: the optimization process includes re-adjusting each parameter according to the requirements of each part when executing the first object, and optimizing the allocation ratio. In this embodiment, the power allocation ratio is optimized and adjusted according to the DC bus voltage, load requirements and power generation prediction results.

[0048] In this embodiment, the optimization process refers to re-adjusting each parameter according to the requirements of each part when executing the first object, and optimizing the allocation ratio. Further, the optimization process includes input parameters and output results of the power allocation optimization. Input parameters include DC bus voltage, load demand, power generation prediction results, etc. Output results include optimized power allocation ratio, adjustment strategy, etc.

[0049] In an optional embodiment, the optimization process may also be power dispatch optimization or load balancing optimization. For these two optimization processes, the quantitative characteristic data may include the following performance parameters and operating state parameters: Power dispatch optimization, performance parameters: power dispatch accuracy, power response time, dispatch stability, etc. Operating state parameters: dispatch strategy, power adjustment range, dispatch frequency, etc. Load balancing optimization, performance parameters: load balance, response speed, balancing efficiency, etc. Operating state parameters: load distribution ratio, load fluctuation amplitude, adjustment accuracy, etc.

[0050] Embodiment 2 is an embodiment of the present invention, which supplements a multi-station interconnection model predictive control method based on edge-end interoperability, including:

[0051] B1: Build an interconnected system with DC bus as the core, with multiple AC / DC converters connecting the AC ends of various low-voltage distribution stations. Configure AC incoming line switches, DC switches and other equipment to ensure system stability and flexibility. Implement main functions through functional modules, including power management, heavy load transfer, load balancing, power failure support, source-load transfer, fault isolation and dynamic networking.

[0052] Furthermore, in order to address the problem of capacity expansion and site layout in substations, a flexible interconnection structure is designed to solve the voltage quality problems caused by distributed energy access through the DC bus, and to deal with common problems such as uneven load rates between substations and terminal voltage drops.

[0053] MPC is a model-based closed-loop optimization control method, and the core idea of ​​its algorithm is the receding horizon strategy. This strategy mainly includes the following steps: at the current time k and the current state x(k), based on a certain prediction model, predict the future state of the system, while considering the current and future constraints, and by solving the optimization problem, obtain the control instruction sequence for the future k+1, k+2, k+N moments, apply the first value of the control instruction sequence to the control system, and at the k+1 moment, update the state to x(k+1), and repeat the above steps. It can be seen that MPC is an alternating process of continuously rolling local optimization and continuously rolling implementation of control actions, and MPC control is used to compensate for the uncertainty of system output after large-scale photovoltaic access.

[0054] B2: The fusion terminal is responsible for collecting substation information (voltage, current, power, switch status, etc.) and transmitting it to the cloud master station, exchanging information with adjacent substation terminals to achieve strategy coordination.

[0055] Furthermore, a flexible interconnection APP is deployed on the converged terminal to implement the following strategies.

[0056] Load balancing: transferring part of the load in the overloaded area through the DC bus;

[0057] Power outage support: quickly provide energy to power outage areas;

[0058] Source-load transfer: dynamic allocation between distributed energy sources such as photovoltaics and loads;

[0059] Fault isolation: Isolate the faulty area and rebuild the system topology;

[0060] It should be noted that the two-way communication architecture of the cloud master station and the substation fusion terminal is adopted to realize real-time monitoring and dynamic adjustment of the substation operation status. The substation mutual assistance system includes photovoltaic, load, converter and other equipment. Considering the maximum absorption target of photovoltaic, the main control method is to adjust the converter power to realize power dispatch between substations. According to the power balance equation of the substation mutual assistance system in each period, the substation grid connection point power and flexible direct current converter power are selected to form the state vector x(k).

[0061] x(k)=[P pcc1 (k),P pcs1 (k),P pcc2 (k),P pcs2 (k)…] T

[0062] The power increment of the adjustable flexible DC converter constitutes the control vector u(k).

[0063] u(k)=[ΔP pcs1 (k),ΔP pcs2 (k)…] T

[0064] The vector composed of the ultra-short-term predicted power increment of load and photovoltaic is used as the disturbance output r(k).

[0065] r(k)=[ΔP load (k),ΔP PV (k)…] T

[0066] The grid-connected power of the substation is the output variable y(k).

[0067] y(k)=[P pcc1 (k),P pcc2 (k)…] T

[0068] The following multi-input and multi-output state space model can be established, defining the converter current from AC to DC as the positive direction, m is the number of interconnected stations, and the state space equation is:

[0069]

[0070]

[0071] The constraints are:

[0072] -S N ≤P pccN (k)≤S N

[0073] -S pcsN ≤S pcsN (k)≤S pcsN

[0074] B3: Each converter is equipped with a DC virtual inertia control loop to achieve coordinated control of active power and DC bus voltage. Smooth the power impact caused by load fluctuations in the system. Model predictive control (MPC) deployment, using edge devices to perform MPC rolling optimization based on real-time load and PV forecast data.

[0075] Furthermore, the converter output power is dynamically adjusted with the goal of power flow optimization, and dynamic regulation is performed in multiple operating modes.

[0076] In the heavy load transfer mode, energy is allocated to high load areas first;

[0077] In load balancing mode, power is evenly distributed to optimize bus voltage;

[0078] In power failure support mode, it provides energy support to the power failure area;

[0079] In the source-load transfer mode, the power of distributed energy is dynamically allocated.

[0080] The allocation strategy optimizes and adjusts the power allocation ratio according to the DC bus voltage, load demand and power generation prediction results to ensure efficient energy transmission and stable power distribution in the system under different operating scenarios.

[0081] It should be noted that the allocation strategy optimizes and adjusts the power allocation ratio according to the DC bus voltage, load demand and power generation prediction results to ensure that the system can achieve efficient energy transmission and stable power allocation under different operating scenarios. With the goal of minimizing the power deviation of the grid-connected point in the substation, the substation flexible control is converted into a quadratic programming problem, and its objective function is as follows:

[0082]

[0083] Where P r is the target matrix; N is the prediction interval of model predictive control; Q N is the authority matrix of the state matrix, which determines the priority of the state quantity; R N The matrix is ​​the authority matrix of the control matrix, which determines the priority of the control parameter selection.

[0084]

[0085] When the AC load in the substation is overloaded, the edge computing terminal receives the command from the main station to start AC transfer. Combined with the supporting capacity of the local substation, it supports the substation by controlling the output power of the flexible DC port to prevent overload of the substation distribution transformer.

[0086] The target power of the area optimization control P rn The calculation formula is:

[0087] P rn (k) = εS n

[0088] ε is the target load factor for load reduction control in the overload area.

[0089] When the load rate deviation of each substation is greater than the starting set value, the load balancing control is started. By obtaining the real-time load rate of each substation and taking the load rate balance of each substation as the goal, the active power of the AC-DC converters of all operable substations is adjusted to achieve load balance in each substation and ensure the stable operation of the system.

[0090] The target power of the area optimization control P rn The calculation formula is:

[0091] P rn (k) = μS n

[0092]

[0093] μ is the average load rate of the system, P n is the current grid-connected power of area n, S n is the rated power of the station n.

[0094] Example 3 is an embodiment of the present invention, which provides a multi-station interconnection model predictive control method based on edge interoperability. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0095] First, in order to verify the innovation and advantages of the multi-area interconnection system and method based on model predictive control (MPC) in the aspects of power management, load balancing, power failure support and source-load transfer, an experiment was conducted. The experiment simulated a multi-area interconnection system, including three areas, each of which was equipped with an AC / DC converter and interconnected through a DC bus. The main equipment of the system includes AC incoming line switch, DC switch, fusion terminal and flexible interconnection APP. The area contains distributed photovoltaic power generation equipment and loads, and simulates the fluctuations of load and photovoltaic power generation in different time periods.

[0096] The test process is divided into the following steps:

[0097] Configure multiple AC / DC converters to connect the AC ends of different low-voltage distribution substations. All converters share a DC bus to achieve flexible interconnection. By setting up DC switches and AC incoming line switches, ensure that the system can isolate the problem substation in the event of a fault and improve system stability. At the same time, deploy fusion terminals to collect voltage, current, power and switch status data of each substation and upload them to the cloud master station.

[0098] Flexible interconnection APP is deployed on the integrated terminal to realize real-time information interaction and control strategy execution. The terminal communicates with the cloud master station in two directions to dynamically monitor the operation status of the substation. According to real-time information, the terminal prioritizes energy allocation to high-load substations in heavy-load transfer mode; evenly adjusts the power between substations in load balancing mode; provides energy support for power outage substations in power outage support mode; and dynamically allocates distributed energy power in source-load transfer mode.

[0099] Based on the real-time load and photovoltaic forecast data of the substation, the MPC rolling optimization method is used to dynamically allocate the output power of the converter. For different operation modes, the objective function takes the minimum grid-connected power deviation of the substation as the optimization goal. Through the DC virtual inertia control loop, the power impact caused by load fluctuation is smoothed to ensure efficient energy transmission and stable power distribution of the system.

[0100]

[0101] Embodiment 4 is an embodiment of the present invention, which provides a multi-station interconnected model predictive control system based on edge interoperability, including a system architecture module, a collection and communication module, and a prediction optimization module.

[0102] The system architecture module is used for hardware layout and basic function implementation, specifically to build a multi-station interconnection structure based on a DC bus and support multi-port connection.

[0103] Equipped with key equipment such as AC / DC converter, AC incoming line switch, DC switch, etc.

[0104] Provides flexible DC interconnection functions, including power management, heavy load transfer, load balancing, power failure support, source-load transfer and dynamic networking.

[0105] It supports energy interaction between low-voltage substations, solving problems such as difficult substation layout, uneven load, distributed energy access, and reduced voltage quality.

[0106] The acquisition and communication module is used for data acquisition, strategy management and communication interaction, specifically, the fusion terminal acquires real-time operation information such as voltage, current, power, switch status, etc. in the station area.

[0107] Realize information exchange between stations and communicate and synchronize data with the cloud master station.

[0108] Deploy a flexible interconnection APP to manage substation operation strategies and support different control modes (load balancing, power failure support, and source-load transfer).

[0109] Provide intelligent control of the entire station control layer to ensure the stability and real-time performance of the coordinated operation of multiple intervals.

[0110] The prediction and optimization module is used for data-based intelligent control and global optimization, specifically based on the model predictive control (MPC) method, combined with real-time load prediction and photovoltaic power prediction, to optimize the power flow distribution between stations.

[0111] The DC virtual inertia control loop is used to achieve dual control of DC bus voltage stability and active power.

[0112] Dynamically allocate converter output power and support flexible adjustment in multiple operating modes.

[0113] Improve the substation's ability to carry impact power and high-power source loads, and enhance the system's dynamic response efficiency and stability.

[0114] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0115] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0116] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0117] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-station interconnected model predictive control method based on edge-end interoperability, characterized in that: include: Acquire a first execution state and construct a first object; collecting various parameters of the first object in the first execution state; According to the first execution state, performing a first adjustment process on the parameter data in the first object; The execution process of the first object is optimized.

2. The multi-station interconnection model predictive control method based on edge-end interoperability according to claim 1, characterized in that: The first execution state includes a state switching result obtained when the state of the first object is switched during the running process; The constructing the first object includes systematically constructing the first object according to the first target requirement.

3. The multi-station interconnection model predictive control method based on edge-end interoperability according to claim 2 is characterized in that: The parameters include operating parameters of each sub-part of the first object during operation.

4. The multi-station interconnection model predictive control method based on edge-end interoperability according to claim 3 is characterized in that: The first adjustment process includes performing a filtering operation on the operating parameters of the sub-part.

5. The multi-station interconnection model predictive control method based on edge-end interoperability according to claim 4 is characterized in that: The optimization process includes adjusting various parameters in the first object through a first adjustment process so that the first goal is achieved more accurately.

6. The multi-station interconnection model predictive control method based on edge-end interoperability according to claim 5 is characterized in that: The filtering process includes comparing the collected data with the result when the first object executes the first goal, and screening out parameters that affect the first goal.

7. The multi-station interconnection model predictive control method based on edge-end interoperability according to claim 6 is characterized in that: The optimization step includes adjusting various operating parameters when the first object executes the first goal to ensure the coordination of operating parameters between the first objects, thereby achieving the adjustment of the first goal.

8. A system using the multi-station interconnection model predictive control method based on edge-end interoperability as claimed in any one of claims 1 to 7, characterized in that: Including system architecture module, acquisition communication module, prediction and optimization module; The system architecture module is used for hardware layout and basic function implementation; The acquisition and communication module is used for data acquisition, strategy management and communication interaction; The prediction and optimization module is used for data-based intelligent control and global optimization.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images