Park resource regulation method and device, equipment and medium

Abstract

The application relates to a park resource regulation method and device, equipment and medium, and relates to the technical field of power control. The method comprises the following steps: acquiring instruction data of a power grid and submission data corresponding to each target object in a park; wherein the instruction data comprises a response price and a response signal, and the submission data comprises an initial boundary value and a submission offer; inputting the instruction data, the submission data and a preset coupling parameter into a first model to obtain a first price; wherein the first model is a model for solving an equilibrium price by depicting a game coupling relationship between the target objects based on the submission offer and a linkage coupling relationship of the corresponding equipment operation states of the target objects, and a step control optimization algorithm; and issuing corresponding regulation instructions to each target object in the park based on the first price and the response signal. The method can effectively regulate the resources in the park.

Description

Technical Field

[0001] This application relates to the field of power control technology, and in particular to a method, apparatus, equipment and medium for regulating park resources. Background Technology

[0002] Integrated energy systems in industrial parks, serving as a vehicle for integrating multiple energy forms and achieving efficient energy utilization, are gradually becoming a key technological direction for energy transformation and intelligent management. By organically integrating multiple energy types such as electricity, heat, and cooling, and combining them with energy storage technology and flexible load resources (such as electric vehicles, air conditioning systems, and heating equipment), this system can achieve coordinated scheduling and optimized allocation across energy categories. It not only improves energy utilization efficiency and reduces carbon emission intensity but also provides flexible auxiliary services to the power grid, becoming an important support for balancing energy supply and demand and coping with the volatility of new energy sources. It shows broad application prospects in scenarios such as industrial parks and commercial complexes.

[0003] Currently, there are numerous technological studies and practical applications regarding the scheduling optimization and flexibility incentives for integrated energy systems in industrial parks. At the system scheduling level, existing technologies are mostly based on centralized or distributed control architectures, achieving coordinated control of photovoltaic, natural gas, and energy storage equipment by establishing energy conversion and transmission models. Regarding flexibility incentives, existing technologies primarily draw on virtual power plant market theory and demand response mechanisms. Aggregators act as intermediaries, connecting grid operators with distributed resource agents within the park, and formulating price-signal-based incentive strategies. After receiving the grid's response demand, the aggregator issues price guidance signals to each agent, encouraging them to participate in grid services by adjusting their energy consumption behavior or providing adjustable capacity, thereby realizing the exploration and utilization of system flexibility.

[0004] Although existing technologies have made some progress in the scheduling and incentive of integrated energy systems in industrial parks, they still face bottlenecks caused by resource coupling effects, cannot accurately depict the price game logic between agents, and ultimately find it difficult to effectively regulate resources. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and medium for regulating park resources, which can effectively regulate park resources.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] Firstly, this application provides a method for adjusting park resources, including:

[0008] Acquire the power grid's instruction data and the submission data corresponding to each target object in the park; among which, the instruction data includes the response price and response signal, and the submission data includes the initial boundary value and the submitted quotation;

[0009] The instruction data, submission data, and preset coupling parameters are input into the first model to obtain the first price; wherein, the first model is a model that solves the equilibrium price by characterizing the game coupling relationship between each target object based on the submitted bid and the linkage coupling relationship of the corresponding equipment operation status of each target object, as well as the step size control optimization algorithm.

[0010] Based on the first price and response signal, corresponding adjustment instructions are issued to each target object in the park.

[0011] In one embodiment, inputting instruction data, submission data, and preset coupling parameters into a first model to obtain a first price includes:

[0012] The submitted data and preset coupling parameters are input into the first model to determine the influence coefficients and correction matrices between each target object;

[0013] The first price is determined based on the instruction data, influence coefficient, and correction matrix.

[0014] In one embodiment, determining the first price based on instruction data, influence coefficients, and a correction matrix includes:

[0015] Based on the correction matrix, the initial boundary values ​​are corrected to obtain the first boundary values;

[0016] The initial iteration variables are determined based on the response price and the first boundary value;

[0017] Based on the step size control optimization algorithm, the initial iteration variables are updated to obtain the first price.

[0018] In one embodiment, updating the initial iteration variables and determining the first price based on a step-size control optimization algorithm includes:

[0019] Based on the step size control optimization algorithm, the initial iteration variables are updated to obtain the updated iteration variables;

[0020] Based on the updated iteration variables, the influence coefficients and correction matrices among the target objects are updated, and the first price is determined.

[0021] In one embodiment, based on a first price and a response signal, corresponding adjustment instructions are issued to each target object in the park, including:

[0022] Based on the response signal, determine the adjustment direction and adjustment magnitude;

[0023] Based on the adjustment direction, adjustment magnitude, and first price, determine the adjustment information corresponding to each target object;

[0024] Based on the adjustment information corresponding to each target object, corresponding adjustment instructions are issued to each target object in the park.

[0025] In one embodiment, the adjustment information corresponding to each target object is determined based on the adjustment direction, adjustment magnitude, and a first price, including:

[0026] Based on the adjustment direction, adjustment magnitude, and first price, determine the initial adjustment share corresponding to each target object;

[0027] Based on the operational status data of each target object, the initial adjustment share corresponding to each target object is adjusted to obtain the target adjustment share corresponding to each target object;

[0028] Based on the target adjustment share corresponding to each target object, determine the adjustment information corresponding to each target object.

[0029] In one embodiment, the preset coupling parameters include a first coupling parameter and a second coupling parameter. The first coupling parameter is used to characterize the influence of each target object on other target objects when each target object adjusts its own adjustment behavior based on the submitted quotation. The second coupling parameter is used to characterize the degree of mutual influence and time characteristics between the operating states of the corresponding devices of each target object due to physical association or user behavior linkage.

[0030] Secondly, this application provides a park resource adjustment device, comprising:

[0031] The acquisition module is used to acquire the command data of the power grid and the submission data corresponding to each target object in the park; wherein, the command data includes the response price and response signal, and the submission data includes the initial boundary value and the submitted quotation;

[0032] The price determination module is used to input instruction data, submission data and preset coupling parameters into the first model to obtain the first price; wherein, the first model is a model that solves the equilibrium price by describing the game coupling relationship between each target object based on the submitted bid and the linkage coupling relationship of the corresponding equipment operation status of each target object, as well as the step size control optimization algorithm.

[0033] The adjustment module is used to issue corresponding adjustment instructions to each target object in the park based on the first price and the response signal.

[0034] Thirdly, this application provides a computing device, including a memory and a processor;

[0035] The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0036] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0037] Fifthly, this application provides a computer program product comprising one or more computer instructions, wherein when the computer instructions are executed by a computer, the computer performs the method as described in any one of the first aspects.

[0038] As can be seen from the above technical solution, this application has at least the following beneficial effects:

[0039] In this application, by acquiring command data from the power grid, including response prices and response signals, and submission data from each target object in the park, including initial boundary values ​​and submitted bids, a data foundation is provided for subsequently determining the first price. Furthermore, the command data, submission data, and preset coupling parameters are input into a first model that characterizes the game-theoretic coupling relationship between target objects based on submitted bids and the linkage coupling relationship of the corresponding equipment operating states, as well as a step-size control optimization algorithm to solve for the equilibrium price, thus obtaining the first price and providing a basis for issuing adjustment commands. Based on the first price and response signals, corresponding adjustment commands are issued to each target object in the park. This scheme, by introducing a first model, considers the game-theoretic coupling relationship between target objects and the linkage coupling relationship between equipment, providing a way to simulate the park's resource state and ultimately achieving effective regulation of park resources.

[0040] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0041] Figure 1 This is an application environment diagram of a park resource adjustment method provided in the embodiments of this application;

[0042] Figure 2This is a flowchart illustrating a method for adjusting park resources provided in an embodiment of this application;

[0043] Figure 3 This is a schematic diagram of a process for obtaining a first price provided in an embodiment of this application;

[0044] Figure 4 This is a schematic diagram of a process for issuing adjustment instructions provided in an embodiment of this application;

[0045] Figure 5 This is a structural block diagram of a park resource adjustment device provided in the embodiments of this application;

[0046] Figure 6 This is an internal structural diagram of a computer device provided in the embodiments of the application. Detailed Implementation

[0047] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0048] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0049] To ensure clarity and conciseness in the description of the following embodiments, a brief introduction to the related technologies is given first:

[0050] Integrated energy systems in industrial parks, serving as a vehicle for integrating multiple energy forms and achieving efficient energy utilization, are gradually becoming a key technological direction for energy transformation and intelligent management. By organically integrating multiple energy types such as electricity, heat, and cooling, and combining them with energy storage technology and flexible load resources (such as electric vehicles, air conditioning systems, and heating equipment), this system can achieve coordinated scheduling and optimized allocation across energy categories. It not only improves energy utilization efficiency and reduces carbon emission intensity but also provides flexible auxiliary services to the power grid, becoming an important support for balancing energy supply and demand and coping with the volatility of new energy sources. It shows broad application prospects in scenarios such as industrial parks and commercial complexes.

[0051] Currently, there are numerous technological studies and practical applications regarding the scheduling optimization and flexibility incentives for integrated energy systems in industrial parks. At the system scheduling level, existing technologies are mostly based on centralized or distributed control architectures, achieving coordinated control of photovoltaic, natural gas, and energy storage equipment by establishing energy conversion and transmission models. Regarding flexibility incentives, existing technologies primarily draw on virtual power plant market theory and demand response mechanisms. Aggregators act as intermediaries, connecting grid operators with distributed resource agents within the park, and formulating price-signal-based incentive strategies. After receiving the grid's response demand, the aggregator issues price guidance signals to each agent, encouraging them to participate in grid services by adjusting their energy consumption behavior or providing adjustable capacity, thereby realizing the exploration and utilization of system flexibility.

[0052] While existing technologies have made some progress in the scheduling and incentive of integrated energy systems in industrial parks, they still face bottlenecks caused by resource coupling effects, and no effective solution has yet been formed. On the one hand, the impact of behavioral coupling effects is seriously overlooked: there are close physical connections and behavioral linkages between different energy resources and loads within the park. For example, a sudden increase in electric vehicle charging load can directly affect the stability of the power grid voltage, thereby interfering with the normal operation of air conditioning and heating systems; while the grid-connected / off-grid behavior of electric vehicles brought about by user travel can indirectly change the indoor heat load demand, causing dynamic changes in the adjustable boundaries of air conditioning and heating systems. Existing technologies mostly model and schedule various resources independently, without considering the system disturbances and flexibility boundary shifts caused by this behavioral coupling, resulting in insufficient feasibility and accuracy of scheduling schemes. On the other hand, the optimization of price coupling effects is lacking: in the internal market of the park, various agents (such as electric vehicle charging stations, energy storage operators, air conditioning load aggregators, etc.) participate in the game by bidding for capacity, and their bidding strategies will affect each other—a low-price bid by one type of agent may trigger vicious price competition among other agents, while a high-price bid will lead to insufficient market flexibility supply, forming a complex price coupling phenomenon. Existing incentive mechanisms mostly adopt fixed pricing or simple bidding models, which fail to accurately depict the price game logic among agents and make it difficult to effectively guide resource allocation through price signals. This not only affects the participation enthusiasm and fairness of income of each agent, but also restricts the improvement of the overall economy and flexibility of the system.

[0053] To make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are described below with reference to the accompanying drawings. Figure 1 As shown, this figure is an application environment diagram provided by an embodiment of this application.

[0054] In this application scenario, the power grid 104 is responsible for supplying electricity to the park and issuing flexibility adjustment instructions (such as peak shaving and valley filling) based on power grid load fluctuations and new energy consumption needs, and providing feedback on the execution effect of the instructions. The park management system 103 is the energy dispatch and incentive control center within the park, responsible for receiving power grid instructions, processing target object data, formulating adjustment plans and issuing instructions, and is the hub connecting the power grid and target objects. The target object 102 is a distributed resource agent with adjustment capabilities within the park, covering electric vehicle charging stations, energy storage devices, air conditioning systems, production loads, etc., and is the main body for implementing flexibility adjustment, and needs to provide feedback on its own operating status and adjustment response results. Power grid 104 can send standardized flexibility adjustment instructions to park management system 103 through a dedicated power communication network. The instructions can include core parameters such as adjustment direction, adjustment level, response time limit, and compensation benchmark. After receiving the instructions through the communication interface, park management system 103 breaks down the adjustment requirements and, in conjunction with data such as the park's current total load and renewable energy output, makes a preliminary judgment on the feasibility of the adjustment. If the theoretical total capacity of the currently adjustable resources meets the adjustment requirements, the subsequent process is initiated; if insufficient, a partial response request is sent back to power grid 104. Park management system 103 sends collection instructions to all target objects 102 to obtain real-time operating data. Target objects 102 transmit data back to park management system 103 at a frequency of seconds / minutes through terminals such as PLCs (Programmable Logic Controllers) and IoT gateways. Park management system 103 performs calculations and analysis based on the collected data, generates adjustment schemes or adjustment instructions, and sends them to target objects 102.

[0055] To make the technical solution of this application clearer and easier to understand, the following describes a method for adjusting park resources provided in an embodiment of this application, using the park management system 103 as an example, in conjunction with the above application scenario. Figure 2 As shown in the figure, this figure is a flowchart illustrating a method for adjusting park resources provided in an embodiment of this application.

[0056] S201. Obtain the power grid's instruction data and the submission data corresponding to each target object in the park.

[0057] The instruction data, including but not limited to response prices and response signals, refers to structured data issued by the grid operator to the park's integrated energy system management to transmit grid regulation needs and remuneration standards. It serves as the top-level basis for the park management to carry out park resource regulation. The response price is a pricing reference for providing flexible services to the park, determined by the grid operator based on the results of electricity market clearing (i.e., the matching and transaction process in the electricity market) and the grid's operating status. It is usually presented in the form of a time-of-use price curve. The response signal can be used to clarify the specific regulation requirements of the grid for the park, including but not limited to key information such as regulation direction (e.g., load increase, load decrease), regulation magnitude (e.g., reducing 500kW of load), and execution time limit.

[0058] The submitted data may include, but is not limited to, initial boundary values ​​and submitted quotations. It may refer to the data set reported by each target entity within the park (such as electric vehicles, energy storage systems, air conditioning systems, etc.) that reflects its own adjustment capabilities and transaction demands. The initial boundary values ​​may refer to the upper and lower limits of the adjustable capabilities determined by each target entity based on its own equipment rated parameters (such as rated power and capacity) and operating constraints (such as electric vehicle travel plans and air conditioning temperature range) without considering resource coupling effects. The submitted quotations may refer to the expected transaction prices proposed by each target entity for providing flexible services based on its own operating costs and expected revenue. Target entities may also be referred to as resource agents.

[0059] For example, for instruction data, a real-time connection can be established with the dispatch data platform of the power grid operator through an encrypted dedicated communication channel, and a dedicated receiving port for instruction data can be opened. The port can automatically receive data packets sent by the power grid at a fixed frequency (such as once per minute), and parse out details such as the value of the response price and the adjustment instructions of the response signal through preset decoding rules. It can also automatically verify whether the response price is within a reasonable fluctuation range and whether the adjustment level of the response signal exceeds the maximum adjustable capacity of the park. If there is an anomaly, a verification failure prompt will be sent to the power grid immediately, requesting resending.

[0060] Regarding the submitted data, after receiving the grid command data, a data submission trigger command can be sent to each target entity through the park's internal energy management network, specifying the submission deadline (e.g., within 10 minutes). Each target entity can automatically collect initial boundary values ​​(e.g., the upper and lower limits of the state of charge of energy storage systems, and the power adjustment range of air conditioners) through local monitoring devices. Operations personnel or automated algorithms then generate submission quotes, which are integrated into a standardized data format and uploaded through the park's intranet. Upon receiving the submitted data, it can be automatically categorized according to target entity type, such as energy storage, temperature-controlled loads, and electric vehicles, and associated with each target entity's real-time operating status tag (e.g., grid-connected, offline).

[0061] S202. Input the instruction data, submission data and preset coupling parameters into the first model to obtain the first price.

[0062] The first model is a dedicated model for solving the transaction price of flexible services within the park. It is a model that solves the equilibrium price by depicting the game coupling relationship between each target object based on the submitted bids and the linkage coupling relationship of the corresponding equipment operation status of each target object, as well as the step size control optimization algorithm. The first price refers to the final clearing price of the flexible service transaction within the park obtained by the first model, which can balance the interests of all parties and the system adjustment needs.

[0063] Optionally, the preset coupling parameters can refer to a set of parameters that are pre-set based on the operating rules and historical data of the park's energy system and quantify the mutual influence characteristics between various target objects. These parameters include a first coupling parameter and a second coupling parameter. The first coupling parameter is used to characterize the influence characteristics of each target object on other target objects when it adjusts its own adjustment behavior based on the submitted bid. It can capture the coordinated change pattern of the adjustment behavior of each target object under the drive of price signals. The second coupling parameter is used to characterize the degree of mutual influence and time characteristics between the operating states of the corresponding equipment of each target object due to physical association or user behavior linkage.

[0064] For example, instruction data, submission data, and preset coupling parameters can be loaded into the calculation module of the first model through the model interface. Preset operating parameters such as the initial threshold for step size control and iterative convergence conditions can be automatically read, and the target weight for revenue optimization can be set in conjunction with the response price. Furthermore, the calculation can be automatically executed according to the process of modeling coupling relationships, iterative solving, and price convergence judgment. Then, after the solution is completed, the first price and the corresponding calculation log (including the number of iterations, convergence error, etc.) can be automatically output. Further, the price difference range between the first price and the response price, the total adjustment capacity corresponding to the first price, and the magnitude of the response signal can be compared to confirm the fairness and feasibility of the price. Finally, the verified first price can be stored in the transaction database.

[0065] S203. Based on the first price and response signal, issue corresponding adjustment instructions to each target object in the park.

[0066] The target entity can refer to the operating entity within the park that possesses adjustable energy resources (such as electric vehicles, energy storage systems, air conditioning systems, heating systems, etc.), which is responsible for receiving adjustment instructions and executing resource adjustment operations, and is the specific provider of flexibility services; the adjustment instructions can be structured operation instructions issued to each target entity, which may include, but are not limited to, the details of the adjustment tasks that the target entity needs to perform (such as adjustment power, duration, status parameters, etc.) and settlement-related information, and is the direct basis for the target entity to carry out resource adjustment.

[0067] For example, response signals can be automatically read, and the adjustment direction (e.g., load increase / decrease can be distinguished by + / - indicators), adjustment level (e.g., accurate to kW level), and execution time limit can be extracted to generate a demand list and mark priorities (e.g., emergency response, routine adjustment, etc.). It can also combine the resource adjustment economic ranking corresponding to the first price (e.g., priority allocation when the adjustment cost of the air conditioning system is lower than that of the energy storage system) to decompose the overall adjustment level into preliminary allocation shares according to the target object type (electric vehicles, energy storage, air conditioning, heating). The allocation logic takes into account both the potential for resource flexibility and transaction costs. It can also call the historical adjustment data of each target object to predict whether the preliminary allocation share exceeds its conventional adjustable capacity (e.g., the maximum adjustable load of the electric vehicle cluster, the upper limit of the charging and discharging power of the energy storage system). If there is an overspending, a 20% redundancy is reserved in advance for subsequent adjustments.

[0068] Furthermore, status query commands can be issued to each target object through the park's IoT platform to obtain operating parameters in real time. For example, electric vehicles need to return their grid connection status, remaining power and departure time; energy storage systems need to return their state of charge and charging / discharging power; air conditioners need to return their current temperature and set temperature range; and heating systems need to return their supply / return water temperature and indoor / outdoor temperature. Then, the initial allocated share can be compared with the real-time adjustable boundaries of the target object (e.g., electric vehicles need to ensure that the adjusted power meets the departure requirements, and air conditioners need to ensure that the temperature is within the comfortable range). Shares exceeding the boundaries can be re-allocated (e.g., the excess share of electric vehicles can be transferred to the energy storage system) to form the final adjusted share.

[0069] If multiple target objects have insufficient regulation capacity, they can be redistributed according to the principles of grid response priority (e.g., emergency peak shaving takes precedence over regular consumption) and minimizing user impact (e.g., prioritizing industrial load regulation over residential air conditioning), with the reasons for adjustment recorded simultaneously. Finally, based on the final regulation share, differentiated instruction templates can be automatically generated according to the target object type. For example, electric vehicle target objects include target charging / discharging power (kW), regulation start and end time, and minimum power requirement after completion; energy storage system target objects include charging / discharging mode, target power, regulation duration, and SOC control range; air conditioning system target objects include target operating power, temperature regulation upper and lower limits, and start and stop times; heating system target objects include water supply temperature adjustment value, heating capacity, and circulating pump operating frequency. The unit remuneration (yuan / kWh) corresponding to the first price and the regulation calculation method (e.g., based on actual power × duration) can also be added to the regulation instructions to clarify the settlement basis and enhance the target object's willingness to comply.

[0070] The aforementioned park resource regulation method acquires command data from the power grid, including response prices and response signals, and submission data from each target object within the park, including initial boundary values ​​and submitted bids, providing a data foundation for determining the first price. Furthermore, the command data, submission data, and preset coupling parameters are input into a first model that characterizes the game-theoretic coupling relationship between target objects based on submitted bids and the linkage coupling relationship of the corresponding equipment operating states. A step-size control optimization algorithm is then used to solve for the equilibrium price, yielding the first price, which provides a basis for issuing regulation commands. Based on the first price and response signals, corresponding regulation commands are issued to each target object within the park. This scheme, by introducing a first model, considers the game-theoretic coupling relationship between target objects and the linkage coupling relationship between equipment, providing a way to simulate the park resource state and ultimately achieving effective regulation of park resources.

[0071] Based on the above embodiments, this application provides a detailed explanation of S202. Specifically, this application involves the process of obtaining the first price, as follows: Figure 3 As shown, the specific steps include:

[0072] S301. Input the submitted data and preset coupling parameters into the first model to determine the price coupling matrix and behavior coupling matrix between each target object.

[0073] Among them, the price coupling matrix refers to the parameter calculated based on the submitted data and preset coupling parameters, which quantifies the strength of the indirect effect of the adjustment behavior of a certain target object in the park on other target objects. It can be used to characterize the degree of interaction between target objects due to price correlation. Its value can reflect the strength of the influence, and may include, but is not limited to, the price coupling coefficient and the behavior coupling coefficient.

[0074] A behavior coupling matrix is ​​a structured data matrix generated based on preset coupling parameters and the operating characteristics of the target object, used to adjust the initial boundary value. It may include, but is not limited to, price coupling matrix and behavior coupling matrix. The matrix elements correspond to the correction coefficients and time-sensitivity characteristics of different target objects. Its function is to combine the linkage relationship of equipment operating status to dynamically calibrate the initial boundary value and ensure that the corrected boundary conforms to the actual adjustment potential under the resource coupling effect.

[0075] For example, in a multi-objective bidding coupling process, if the set pricing coefficient is high, each object will increase its bidding capacity. However, if each object independently considers the game process, it will reduce its bidding capacity to obtain a higher internal transaction price. To describe the stochastic coupling process of price game among the objectives, this process can be simulated to obtain a price coupling matrix. The simulation process is as follows:

[0076] (1)

[0077] (2)

[0078] (3)

[0079] in, For target object i in Power output after coupling of resource prices at any given time; For target object i in Initial power output of each resource at any given time; For target object i in The price coupling effect matrix among various resources at any given time, i.e., the price coupling matrix; For target object i in electric vehicle resources The price coupling coefficient at time t is 1; For target object i in the energy storage system resources The price coupling coefficient at time t is 1; For target object i in the air conditioning system resources The price coupling coefficient at time t is 1; For target object i in the heating system resources The price coupling coefficient at time t is 1; and Both are between electric vehicle resources and energy storage system resources, with target object i in The price coupling coefficients between resources at any given time are the same for both. and Both are between electric vehicle resources and air conditioning system resources, with target object i in The price coupling coefficients between resources at any given time are the same for both. and Both are between electric vehicle resources and heating system resources, with target object i in The price coupling coefficients between resources at any given time are the same for both. and Both are between energy storage system resources and air conditioning system resources, with target object i in The price coupling coefficients between resources at any given time are the same for both. and Both are between energy storage system resources and heating system resources, with target object i in The price coupling coefficients between resources at any given time are the same for both. and All are resources between heating and air conditioning systems, with target object i in The price coupling coefficients between resources at time t, both have the same value; the price coupling coefficient matrix. In this context, a positive value for an element indicates that the price coupling effect is a price increase; a positive value indicates a price decrease; a zero value indicates no coupling effect; mn represents the resource type, which is a code for four types of bidable resources, specifically corresponding to: ev: Electric Vehicle resource; ess: Energy Storage System resource; tcl: Thermal Conditioning Load resource; hs: Heating System resource; combinations of m and n (such as ev-ess) represent the interaction relationship between two resources. For resource m in target object i The initial bid price at time (the price before coupling effect adjustment); For resource n in target object i The initial bid price at time (the price before coupling effect adjustment); The price coupling coefficient is the coupling matrix. The specific elements in the description of target object i in At any given moment, the strength and direction of the price correlation between resource m and resource n; For resource m in target object i Price change at any given moment (difference form); For resource n in target object i Price change at any given moment; For resource m in target object i The price differential at time (in differential form); For resource n in target object i The price differential at time (in differential form).

[0080] Furthermore, user behavior has a synergistic effect on various resources. For example, when a user parks an electric vehicle at a charging station, if it is winter, the demand for heat load will increase, and the flexibility of adjusting electricity consumption by the heating system will decrease; conversely, if it is summer, the demand for cooling load will increase, and the flexibility of adjusting electricity consumption by the air conditioning system will still decrease. The flexibility of the electric vehicle charging station will increase due to the newly parked electric vehicle connecting to the grid. To address this, the coupling process of user behavior can be simulated to obtain a behavior coupling matrix, as follows:

[0081] (4)

[0082] (5)

[0083] in, For target object i in Power output after coupling user behavior at any given moment; K is the total number of users in target object i; For user k in The initial value at time t, i.e. , For user k in Initial values ​​of electric vehicle resources at any given time; For user k in Initial values ​​of energy storage system resources at any given time; For user k in Initial values ​​of air conditioning system resources at any given time; For user k in Initial values ​​of heating system resources at any given time; For user k in The behavioral coupling effect matrix between resources at each time step, i.e., the behavioral coupling coefficient matrix; For user k in electric vehicle resources The behavioral coupling coefficient at time t is 1; For user k in the energy storage system resources The behavioral coupling coefficient at time t is 1; For user k in the air conditioning system resources The behavioral coupling coefficient at time t is 1; For user k in the heating system resources The behavioral coupling coefficient at time t is 1; and Both are resources between electric vehicles and energy storage systems, with user k in The behavioral coupling coefficients between resources at any given time are the same for both. and All of these are between electric vehicle resources and air conditioning system resources, and user k is in The behavioral coupling coefficients between resources at any given time are the same for both. and Both are between electric vehicle resources and heating system resources, and user k is in The behavioral coupling coefficients between resources at any given time are the same for both. and Both are between energy storage system resources and air conditioning system resources, and user k is in The behavioral coupling coefficients between resources at any given time are the same for both. and Both are resources between energy storage systems and heating systems, and user k is in The behavioral coupling coefficients between resources at any given time are the same for both. and All of these are resources between the heating and air conditioning systems, and user k is in The behavioral coupling coefficients between resources at each time step are the same in both cases; the behavioral coupling coefficient matrix. In this context, a positive value indicates that the linkage effect of behavioral coupling is to promote energy use; a negative value indicates that the linkage effect of behavioral coupling is to reduce energy use; and a zero value indicates that there is no behavioral coupling effect. For user k in time period The values ​​of each resource after coupling can be expressed as:

[0084] (6)

[0085] in, For user k in The electric vehicle resource coupling value at any given time; For user k in The resource coupling value of the energy storage system at any given time; For user k in The resource coupling value of the air conditioning system at any given time; For user k in The resource coupling value of the heating system at any given time.

[0086] S302. Determine the first price based on instruction data, influence coefficients, and correction matrices.

[0087] One possible approach is to correct the initial boundary values ​​based on the correction matrix to obtain the first boundary value; determine the initial iteration variables based on the response price and the first boundary value; and update the initial iteration variables based on the step size control optimization algorithm to obtain the first price.

[0088] Optionally, based on the step size control optimization algorithm, the initial iteration variables are updated to obtain the updated iteration variables; based on the updated iteration variables, the influence coefficients and correction matrices between each target object are updated, and the first price is determined.

[0089] Among them, the first boundary value refers to the parameter that reflects the actual adjustment potential of the target object under the resource coupling effect, obtained by dynamically calibrating the initial boundary value in the submitted data using the correction matrix;

[0090] The initial iteration variables refer to the set of variables set based on the grid response price and the first boundary value, which serve as the starting point for the step size control optimization algorithm. These variables may include, but are not limited to, the initial internal transaction price (determined with reference to the response price) and the initial regulation capacity of each target object (determined based on the first boundary value).

[0091] The updated iteration variable refers to the new variable obtained by adjusting the variable value and step size rule based on the previous round in each iteration of the step size control optimization algorithm. It includes the updated internal transaction price and the adjustment capacity of each target object. Through multiple iterations, it gradually approaches the equilibrium state and provides dynamic data support for the final determination of the first price.

[0092] It should be noted that the structures of equipment in the integrated system of the park vary. For example, the park includes resources such as electric vehicles, energy storage systems, air conditioning, and heating networks. This application embodiment is based on the grid's minute-level control capability assessment requirements, establishing flexibility models for each resource to form a simplified virtual energy storage model with upper and lower boundaries of power and energy as the main technical indicators, encompassing external regulation and internal state estimation. Specifically, it can be represented as:

[0093] (7)

[0094] (8)

[0095] (9)

[0096] in, For target object i in the park at time The energy possessed at that time; For target object i in the park at time The energy possessed at that time; For target object i in the park at time The power it possesses at that time; This is the energy attenuation coefficient for cooling / heating loads, such as in air conditioning and heating systems; This refers to the energy changes of electric vehicles after they are connected to or disconnected from the grid. The time interval between adjacent sampling points; for The lower boundary (minimum) of energy at time i, i.e., the target object i at time i The energy at any given time must not be lower than this value; for The upper energy boundary at time i, i.e., the target object i at time i The energy at any given moment cannot exceed this value; for The lower power boundary at time i, i.e., the target object i at time i The power at any given time must not be lower than this value; for The upper boundary of power at time i, i.e., the target object i at time i The power at any given moment must not exceed this value.

[0097] Optionally, an energy storage system is a fully deployable resource available at all times. Therefore, a simplified virtual model of an energy storage system can be represented as:

[0098] (10)

[0099] (11)

[0100] in, This represents the lower boundary of the energy level of the energy storage system. This represents the upper boundary of the energy level of the energy storage system. This represents the lower boundary of the power of the energy storage system. This represents the upper boundary of the power of the energy storage system. This refers to the rated capacity of the energy storage system. This is the rated power of the energy storage system.

[0101] Electric vehicles are a type of load with high flexibility in terms of time, space, and capacity. The boundary of this flexibility is related to the arrival time of the electric vehicle. The initial charge of the electric vehicle upon arrival Departure time And the expected charge when the electric vehicle leaves Closely related, which can be expressed as:

[0102] (12)

[0103] in, for The lower energy limit of an electric vehicle at any given moment; for The upper limit of the energy of an electric vehicle at any given moment; for The lower bound of the power flexibility of electric vehicles at any given time; for The upper bound of the power flexibility of the electric vehicle at any given time. The boundary value can be specifically expressed as:

[0104] (13)

[0105] (14)

[0106] (15)

[0107] (16)

[0108] (17)

[0109] (18)

[0110] in, For time variables, The time it takes for electric vehicles to reach the power station and connect to the grid. The time it takes for the electric vehicle to leave the power station. This refers to the initial charge of the electric vehicle when it arrives at the power station and connects to the grid. For electric vehicles during the grid connection period ( The function for calculating the upper energy boundary. This represents the upper limit of the rated capacity of electric vehicles. For electric vehicles during the grid connection period ( The function for calculating the lower energy boundary. This is the first constraint term in the calculation of the lower boundary of electric vehicle energy, calculated from the lower boundary of energy at the previous moment and the change in discharge energy. This is the second constraint term in the calculation of the lower boundary of electric vehicle energy, namely the lower boundary of the rated capacity of the electric vehicle. This is the third constraint term in the calculation of the lower boundary of electric vehicle energy, ensuring that the electric vehicle can be fully charged to the desired energy level before leaving the vehicle. For the electric vehicle at the previous moment ( The lower boundary of energy at time ( ), For time step, This represents the lower limit of the rated capacity of electric vehicles. The expected (or target) charge level of the electric vehicle when it leaves the power station. This is the rated charging power of electric vehicles. It is the rated discharge power of the electric vehicle. It refers to the charging efficiency of electric vehicles. The upper limit of power flexibility for electric vehicles The specific value of the time, For the lower boundary of power flexibility of electric vehicles The specific value of the time, This refers to the discharge efficiency of electric vehicles. When assessing the lower limit of an electric vehicle, it is necessary to evaluate whether it can participate in flexibility services at the current moment, that is, whether the electric vehicle can be fully charged to the desired level before the vehicle leaves.

[0111] Electric vehicles' flexibility in service depends on their grid connection status. When they arrive at a power station and connect to the grid, their energy level is the initial charge. After it leaves the power station, its energy value is Specifically, it can be expressed as:

[0112] (19)

[0113] in, For electric vehicles The change in energy at any given moment; This refers to a moment before an electric vehicle arrives at a power station and is connected to the grid.

[0114] As a cooling / heating load, the flexibility of an air conditioning system is closely related to the user's comfort temperature. According to relevant research, the nonlinear electrothermal conversion model of air conditioning can be simplified to a convergent linear model, which can be expressed as:

[0115] (20)

[0116] (twenty one)

[0117] (twenty two)

[0118] (twenty three)

[0119] (twenty four)

[0120] (25)

[0121] in, For the energy of air conditioning The lower boundary of the time; For the energy of air conditioning The upper boundary of time; For the power of the air conditioner The lower boundary of the time; For the power of the air conditioner The upper boundary of time; The coefficient of performance is the heat capacity. The upper limit of the acceptable temperature for users; The lower limit of the temperature acceptable to the user; The loss performance coefficient; Set the temperature for the user; for The outdoor temperature at any given time; This refers to the rated power of the air conditioner. for Real-time power consumption of the air conditioner; This is for thermal resistance.

[0122] In the flexibility model of a heating system, the indoor temperature of the building needs to be considered. With outdoor temperature In the heating system's pipe network, the indoor temperature of the building... With outdoor temperature Subject to the water supply temperature of the heating system and return water temperature The influence of this is considered. Therefore, by simplifying the thermodynamic model, it is found that the upper limit of its adjustability is related to the supply and return water temperatures; the lower limit of its adjustability is the current operating power. The simplified virtual model of the heating system's flexibility can be simplified as follows:

[0123] (26)

[0124] (27)

[0125] (28)

[0126] (29)

[0127] (30)

[0128] in, For the energy of air conditioning The lower boundary of the time; For the energy of air conditioning The upper boundary of time; For the power of the air conditioner The lower boundary of the time; For the power of the air conditioner The upper boundary of time; for The return water temperature at any given time; for The water supply temperature at any given time; This is the upper limit of the water supply temperature; The lower limit of the water supply temperature; The coefficient of performance is the heat capacity. This is the coefficient relating the boiler's heating capacity to the supply and return water temperatures in the heating network. Specific heat capacity of the fluid; For fluid flow rate; This refers to the rated power of the heating system.

[0129] Unlike the real-time balance characteristics of power systems, heating systems exhibit significant thermal inertia. This thermal inertia is strongly coupled with the heating system, piping system, and building structure, and can be described using an Autoregressive Moving Average (ARMA) time series model to account for the water supply temperature of the heating system. Return water temperature Indoor temperature of buildings and outdoor temperature The relationship between them can be specifically represented as:

[0130] (31)

[0131] (32)

[0132] in, for Indoor temperature at any given time for The water supply temperature at any given time, for outdoor temperature at any time for Indoor temperature at any given time for Indoor temperature at any given time for The water supply temperature at any given time, for outdoor temperature at any time , , , , and The thermal inertia parameter of the heating system can be identified through actual data parameters and obtained through data-driven methods; N is the order of the ARMA model, and its physical meaning characterizes the thermal inertia of the system.

[0133] Furthermore, the behavioral coupling matrix in the correction matrix can be used as a basis. The flexibility model of each resource is modified by multiplying the power boundary between each resource by the behavioral coupling matrix to take into account the behavioral coupling effect.

[0134] Furthermore, it is possible to base this on the price coupling matrix in the correction matrix. The data submitted by each resource user is corrected to take into account the price coupling effect between resources. Specifically, this can include three parts: environmental variables of the target object, production and sales decisions, and decision-making actions. This can be represented as follows:

[0135] Environment variables of the target object It can be represented as:

[0136] (33)

[0137] in, O represents the internal transaction price between the park management and the target entity, O represents the set of power equipment operating parameters of the target entity, and D represents the daily power demand of the target entity.

[0138] Based on information perceived from the environment, the target entity arranges its electrical equipment to minimize its electricity costs / maximize its energy trading revenue. This process, known as the production and sales decision-making process, is as follows:

[0139] (34)

[0140] (35)

[0141] in, For target object i at time The amount of electricity submitted; The lower boundary of the target object's flexible power capacity; The upper boundary of the flexibility power of target object i; Price of electricity; This is the price coupling matrix.

[0142] Based on the above formulas (34)-(35), the actions taken by each target object can be derived, which may include, but are not limited to, control signals of controllable electrical equipment, the electricity quantity to be submitted to the park management (i.e., electricity bid value) and the submitted quotation (i.e. price bid value), etc., which can be expressed as:

[0143] (36)

[0144] in, This indicates the decision-making action taken by the target entity.

[0145] Furthermore, using the price coupling matrix Update the electricity submitted by each target object by substituting the submitted electricity into equations (1)-(3) to obtain the submitted electricity considering the price coupling effect, and submit this value to the park management.

[0146] The park management's responsibilities are mainly twofold: first, to receive data submitted by target entities and publish internal prices to them, managing energy trading within the park; second, to represent the entire park in transactions with the power grid, buying or selling electricity to balance the park's energy shortages or surpluses. The park management's work can be divided into three main parts: environmental variables, pricing, and decision-making actions.

[0147] Park management environmental variables It can be represented as:

[0148] (37)

[0149] in, The transaction price between the park management and the power grid; It is a non-dynamic price, meaning it does not change with the real-time exchange of electricity and energy.

[0150] Based on the park management's environmental variables Based on the submitted data of the target objects, the clearing of the internal transaction prices of each target object can be represented as:

[0151] (38)

[0152] in, For internal trading prices; The pricing function can be expressed as:

[0153] (39)

[0154] in, The aggregator's pricing coefficient is positively correlated with the response price published by the grid operator, i.e. , This is the proportionality coefficient; Let I be the capacity declared by the park management to the power grid; let I be the number of target entities; this pricing function represents that the larger the total capacity bid by multiple target entities received by the park management in the internal market, the lower its internal clearing price; the optimization objective is to maximize the park management's profit, and the objective function can be expressed as:

[0155] (40)

[0156] (41)

[0157] The decision-making actions of the park management include the internal prices published by the park management within the park, and the electricity transactions between the park management and multiple target parties within the park. , can be represented as:

[0158] (42)

[0159] in, It is the electricity volume to be traded between the management and the power grid.

[0160] An optimization algorithm based on step size control simulates the coupling behavior and game process between the park management and multiple target objects. Upon algorithm convergence, the Nash equilibrium point is found. Algorithm convergence typically requires alternating iterations between the target object's response capacity and a first price (internal transaction price): each target object adjusts its response capacity according to the first price published by the park management, and the park management then adjusts and publishes a new first price based on the updated response capacity. If this interaction process reaches a stable point after a finite number of iterations, it is considered convergent, and the first price determined at this point is the equilibrium price. The iterative process represents a two-way interaction between the park management and the target objects. Specifically:

[0161] First, the park management releases the first round of internal transaction prices based on the grid response price and the submitted quotations from each target entity. Second, each target entity updates and submits a new response capacity based on the received internal transaction price and its own boundary constraints and coupling relationships. Then, the park management recalculates and adjusts the internal transaction price based on the new response capacity. Finally, steps 2-3 are repeated until the preset convergence conditions are met (such as the upper limit of the number of iterations or the price / capacity change being less than a threshold).

[0162] In this process, the response capacity and the initial price interact in each iteration: capacity changes affect price updates, and the price, in turn, feeds back into the capacity adjustment in the next round. Convergence is defined as the response capacity and the internal price value eventually converging to a fixed point after a finite number of iterations in the interaction between the park management and the target object. To avoid continuous oscillations in price and capacity during iterations, a step size control factor δ is introduced into the algorithm to limit the ramp rate of the target object's bid submission and capacity update in each iteration, so that the price-capacity interaction can gradually converge to a stable fixed point (i.e., the Nash equilibrium point), which can be specifically expressed as:

[0163] (43)

[0164] (44)

[0165] (45)

[0166] (46)

[0167] Where δ is the iteration step size; t is the number of iterations; The quote submitted by the target object at the t-th iteration; For the first The quote submitted by the target object in the next iteration; This is the step size control parameter for the quotation iteration; This represents the lower limit of the price submitted by the target object in the t-th iteration; This represents the upper limit of the price submitted by the target object in the t-th iteration; The step size control parameter for the response capacity iteration; This represents the response capacity at the t-th iteration; For the first Response capacity at the next iteration.

[0168] After reaching the maximum number of iterations or the preset precision, the iteration stops, and the first price is obtained.

[0169] In this embodiment, by introducing an influence coefficient and a correction matrix, the price coupling effect and the behavioral coupling effect are taken into account, making the simulation process of park resources more realistic and ultimately ensuring the accuracy of resource adjustment instructions.

[0170] Based on the above embodiments, this application provides a detailed explanation of S203. Specifically, this application embodiment involves the process of issuing adjustment commands, such as... Figure 4 As shown, the specific steps include:

[0171] S401. Based on the response signal, determine the adjustment direction and adjustment level.

[0172] Among them, the adjustment direction is the trend of the adjustment operation determined based on the response signal, which is divided into positive adjustment (such as increasing production capacity, increasing energy consumption, and increasing output power) and negative adjustment (such as reducing production capacity, reducing energy consumption, and reducing output power); the adjustment magnitude is the specific numerical scale corresponding to the adjustment direction, that is, the total amount of adjustment operation that needs to be performed, such as reducing 100kW of energy consumption or increasing 50kWh of energy storage charging capacity, which is an indicator for measuring the adjustment intensity.

[0173] For example, upon receiving a response signal, the signal type and content can be analyzed. If it is a power grid peak load warning signal, key information such as the warning level and the required load reduction ratio needs to be extracted. If it is a signal indicating excessive energy consumption within the park, the time period of excess and the amount of excess electricity need to be specified. Furthermore, the analyzed signal information is matched with the park's preset control rule library. For example, when the power grid warning level is Level 1, a mandatory load reduction rule is triggered; when the park's energy consumption exceeds the limit by 10%, a comprehensive energy-saving regulation rule is activated; and adjustments can be determined based on the matched rules. In terms of adjustment direction, if the signal requires a reduction in the total load of the park, the adjustment direction is reverse adjustment (reduction); if the signal requires an increase in the charging capacity of energy storage devices to absorb new energy, the adjustment direction is forward adjustment (increase). Furthermore, the adjustment level can be calculated by combining signal parameters and real-time operating data of the park. For example, if the grid requires a 15% reduction in the total load, and the current total load of the park is 1000kW, then the adjustment level is 1000×15%=150kW; if an additional 200kWh of energy storage capacity is needed, and the current remaining energy storage is 120kWh, then the adjustment level is 80kWh.

[0174] S402. Based on the adjustment direction, adjustment magnitude, and first price, determine the adjustment information corresponding to each target object.

[0175] One possible approach is to determine the initial adjustment share corresponding to each target object based on the adjustment direction, adjustment magnitude, and first price; adjust the initial adjustment share corresponding to each target object based on the operating status data of each target object to obtain the target adjustment share corresponding to each target object; and determine the adjustment information corresponding to each target object based on the target adjustment share corresponding to each target object.

[0176] Among them, the adjustment information is data generated for each target object, containing specific adjustment requirements. It mainly consists of the target adjustment share, and in some scenarios, it may also include additional information such as adjustment time limit and priority. The initial adjustment share is the amount of adjustment task initially allocated to each target object based on the adjustment direction, adjustment level, and first price. It does not consider the actual operating capacity of the target object and serves as the initial reference value for the adjustment share. The target adjustment share is the final amount of adjustment task that each target object actually needs to perform, determined after adjustments based on the initial adjustment share and combined with the operating status data of each target object. It is executable and reasonable. The operating status data is real-time data reflecting the current operating status of the target object, which may include key parameters such as equipment load rate, remaining capacity, operating fault status, maximum adjustment capacity, and minimum operating threshold.

[0177] For example, an allocation model can be constructed based on the basic information of each target object (such as rated power and historical regulation contribution), combined with regulation direction, regulation magnitude and first price. For example, using the price weight allocation method, the target object with the higher the first price has a higher initial allocation ratio. Furthermore, the initial regulation share of each target object can be calculated through the allocation model. Assuming the regulation magnitude is 100kW, the price weight of target object A is 30%, target object B is 25%, and target object C is 45%, then the initial regulation shares are 30kW, 25kW and 45kW respectively.

[0178] Furthermore, operational status data of each target object can be collected through devices such as sensors and smart terminals, and abnormal data (such as invalid values ​​caused by sensor failure) can be eliminated to ensure data authenticity. Then, the actual adjustment capability of each target object can be evaluated based on the operational status data. If the current load rate of target object A has reached 90%, the maximum load reduction is only 20kW, and its initial adjustment share of 30kW exceeds the capability range; target object C is in good operating condition, and the maximum load reduction is 50kW, which has the capacity for over-adjustment.

[0179] Furthermore, the initial regulation quota can be adjusted. For example, the 10kW excess quota of target object A can be allocated to target objects B and C according to the remaining regulation capacity of other target objects, ultimately determining the target regulation quota as 20kW for target object A, 30kW for target object B, and 50kW for target object C. Finally, based on the target regulation quota, information such as regulation direction (e.g., reverse regulation) and regulation reference price (based on the actual compensation price after adjustment of the first price) can be added to form a complete target object regulation information package. Moreover, the regulation information can be standardized according to a unified data format to ensure that each target object can accurately identify the information content.

[0180] S403. Based on the adjustment information corresponding to each target object, issue corresponding adjustment instructions to each target object in the park.

[0181] For example, standardized adjustment information can be converted into adjustment instructions that conform to the control protocols of each target object. For instance, for production equipment controlled by a PLC (Programmable Logic Controller), the instruction format is address + operation code + adjustment value; for IoT charging piles, the instruction format is device ID + adjustment type + power parameters, etc. Furthermore, based on the agent's communication method, such as 4G, LoRa (Long Range Radio), or Ethernet, the corresponding transmission channel can be selected. For target objects with high real-time requirements (such as emergency loads), the low-latency Ethernet channel is preferred; for widely distributed target objects (such as streetlights), the LoRa channel with wide coverage is selected. Then, the adjustment instructions can be sent to each target object through the selected channel, and instruction confirmation feedback can be received from the target object. If the target object successfully receives the instruction, it reports successful reception; if the instruction format is incorrect, the feedback instruction is invalid and needs to be reconverted and resent. The progress and status of instruction transmission can be monitored in real time, and retransmission can be retried for target objects that have not successfully received the instruction, ensuring that all target objects receive the corresponding adjustment instructions, laying the foundation for subsequent adjustment execution.

[0182] In this embodiment of the application, by introducing adjustment information, a foundation is laid for performing resource adjustment operations on each target object.

[0183] The above text combined Figures 1 to 4 The method for adjusting park resources provided in the embodiments of this application has been described in detail. The apparatus and equipment provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0184] like Figure 5As shown in the figure, this is a structural block diagram of a park resource adjustment device provided in an embodiment of this application. The park resource adjustment device 500 includes: an acquisition module 501, a price determination module 502, and an adjustment module 503, wherein:

[0185] The acquisition module 501 is used to acquire the instruction data of the power grid and the submission data corresponding to each target object in the park; wherein, the instruction data includes the response price and response signal, and the submission data includes the initial boundary value and the submitted quotation;

[0186] The price determination module 502 is used to input instruction data, submission data and preset coupling parameters into the first model to obtain the first price; wherein, the first model is a model that solves the equilibrium price by describing the game coupling relationship between each target object based on the submitted bid and the linkage coupling relationship of the corresponding equipment operation status of each target object, as well as the step size control optimization algorithm.

[0187] The adjustment module 503 is used to issue corresponding adjustment instructions to each target object in the park based on the first price and the response signal.

[0188] In one embodiment, the price determination module 502 is specifically used for:

[0189] The submitted data and preset coupling parameters are input into the first model to determine the influence coefficients and correction matrices between each target object;

[0190] The first price is determined based on the instruction data, influence coefficient, and correction matrix.

[0191] In one embodiment, the price determination module 502 is specifically used for:

[0192] Based on the correction matrix, the initial boundary values ​​are corrected to obtain the first boundary values;

[0193] The initial iteration variables are determined based on the response price and the first boundary value;

[0194] Based on the step size control optimization algorithm, the initial iteration variables are updated to obtain the first price.

[0195] In one embodiment, the price determination module 502 is specifically used for:

[0196] Based on the step size control optimization algorithm, the initial iteration variables are updated to obtain the updated iteration variables;

[0197] Based on the updated iteration variables, the influence coefficients and correction matrices among the target objects are updated, and the first price is determined.

[0198] In one embodiment, the price determination module 502 is specifically used for:

[0199] Based on the response signal, determine the adjustment direction and adjustment magnitude;

[0200] Based on the adjustment direction, adjustment magnitude, and first price, determine the adjustment information corresponding to each target object;

[0201] Based on the adjustment information corresponding to each target object, corresponding adjustment instructions are issued to each target object in the park.

[0202] In one embodiment, the price determination module 502 is specifically used for:

[0203] Based on the adjustment direction, adjustment magnitude, and first price, determine the initial adjustment share corresponding to each target object;

[0204] Based on the operational status data of each target object, the initial adjustment share corresponding to each target object is adjusted to obtain the target adjustment share corresponding to each target object;

[0205] Based on the target adjustment share corresponding to each target object, determine the adjustment information corresponding to each target object.

[0206] In one embodiment, the preset coupling parameters include a first coupling parameter and a second coupling parameter. The first coupling parameter is used to characterize the influence of each target object on other target objects when each target object adjusts its own adjustment behavior based on the submitted quotation. The second coupling parameter is used to characterize the degree of mutual influence and time characteristics between the operating states of the corresponding devices of each target object due to physical association or user behavior linkage.

[0207] The park resource adjustment device 500 according to the embodiments of this application can correspond to the execution of the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the park resource adjustment device 500 are respectively for implementing Figures 2-4 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0208] This application also provides a computing device. This computing device can be a local computing device or an application server.

[0209] like Figure 6 As shown in the figure, this is an internal structural diagram of a computing device provided in an embodiment of this application. The computing device 700 includes a bus 701, a processor 702, a communication interface 703, and a memory 704. The processor 702, the memory 704, and the communication interface 703 communicate with each other via the bus 701.

[0210] The 701 bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0211] The processor 702 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0212] The communication interface 703 is used for external communication.

[0213] Memory 704 may include volatile memory, such as random access memory (RAM). Memory 704 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0214] The memory 704 stores executable code, and the processor 702 executes the executable code to perform the aforementioned campus resource adjustment method.

[0215] Specifically, in achieving Figure 5 In the case of the illustrated embodiment, and Figure 5 When the modules or units of the park resource adjustment device described in the embodiment are implemented through software, the execution... Figure 5 The software or program code required for the functions of each module / unit can be partially or wholly stored in the memory 704. The processor 702 executes the program code corresponding to each unit stored in the memory 704 to execute the aforementioned campus resource adjustment method.

[0216] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the aforementioned campus resource adjustment method.

[0217] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0218] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0219] When the computer program product is executed by a computer, the computer performs any of the aforementioned park resource adjustment methods. The computer program product can be a software installation package; when any of the aforementioned park resource adjustment methods needs to be used, the computer program product can be downloaded and executed on the computer.

[0220] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0221] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for adjusting park resources, characterized in that, The method includes: Acquire instruction data from the power grid and submission data corresponding to each target object in the park; wherein, the instruction data includes response price and response signal, and the submission data includes initial boundary value and submission quotation; The submitted data and preset coupling parameters are input into the first model to determine the influence coefficients and correction matrices between each target object; Based on the correction matrix, the initial boundary value is corrected to obtain the first boundary value; wherein, the initial boundary value refers to the upper and lower limits of the adjustable capability of each target object based on its own equipment rated parameters and operating constraints without considering resource coupling effects; the first boundary value refers to the parameter that reflects the actual adjustment potential of the target object under resource coupling effects, obtained by dynamically calibrating the initial boundary value in the submitted data using the correction matrix; Based on the response price and the first boundary value, determine the initial iteration variables; Based on the step size control optimization algorithm, the initial iteration variables are updated to obtain the updated iteration variables; Based on the updated iteration variables, the influence coefficients and correction matrices between each target object are updated, and the first price is determined; The first model is a model that solves the equilibrium price by characterizing the game-theoretic coupling relationship between each target object based on the submitted bids and the linkage coupling relationship of the corresponding equipment operating status of each target object, as well as the step size control optimization algorithm. Based on the response signal, the adjustment direction and adjustment level are determined; Based on the adjustment direction, adjustment magnitude, and first price, determine the initial adjustment share corresponding to each target object; Based on the operational status data of each target object, the initial adjustment share corresponding to each target object is adjusted to obtain the target adjustment share corresponding to each target object; Based on the target adjustment share corresponding to each target object, determine the adjustment information corresponding to each target object; Based on the adjustment information corresponding to each target object, corresponding adjustment instructions are issued to each target object in the park.

2. The method according to claim 1, characterized in that, The preset coupling parameters include a first coupling parameter and a second coupling parameter. The first coupling parameter is used to characterize the influence of each target object on other target objects when each target object adjusts its own adjustment behavior based on the submitted quotation. The second coupling parameter is used to characterize the degree and time characteristics of mutual influence between the operating states of the corresponding devices of each target object due to physical association or user behavior linkage.

3. A park resource regulation device, characterized in that, The device includes: The acquisition module is used to acquire instruction data from the power grid and submission data corresponding to each target object in the park; wherein, the instruction data includes response price and response signal, and the submission data includes initial boundary value and submission quotation; The price determination module is used to input the instruction data, submission data and preset coupling parameters into the first model to obtain the first price; wherein, the first model is a model that solves the equilibrium price by characterizing the game coupling relationship between each target object based on the submitted bid and the linkage coupling relationship of the corresponding equipment operation status of each target object, as well as the step size control optimization algorithm. The adjustment module is used to issue corresponding adjustment instructions to each target object in the park based on the first price and the response signal; The price determination module is used to input the submitted data and preset coupling parameters into the first model to determine the influence coefficients and correction matrices between each target object; based on the correction matrix, the initial boundary values ​​are corrected to obtain the first boundary value; wherein, the initial boundary value refers to the upper and lower limits of the adjustable capability of each target object based on its own equipment rated parameters and operating constraints without considering resource coupling effects; the first boundary value refers to the parameter reflecting the actual adjustment potential of the target object under resource coupling effects, obtained by dynamically calibrating the initial boundary values ​​in the submitted data using the correction matrix; based on the response price and the first boundary value, the initial iteration variables are determined; based on the step size control optimization algorithm, the initial iteration variables are updated to obtain the updated iteration variables; based on the updated iteration variables, the influence coefficients and correction matrices between each target object are updated, and the first price is determined; The adjustment module is used to determine the adjustment direction and adjustment level based on the response signal; determine the initial adjustment share corresponding to each target object based on the adjustment direction, adjustment level and first price; adjust the initial adjustment share corresponding to each target object based on the operating status data of each target object to obtain the target adjustment share corresponding to each target object; determine the adjustment information corresponding to each target object based on the target adjustment share corresponding to each target object; and issue corresponding adjustment instructions to each target object in the park based on the adjustment information corresponding to each target object.

4. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 2.

Images