A temperature control-industrial load aggregated scheduling analysis method, system, device and medium

Abstract

The present disclosure relates to a temperature control-industrial load aggregation scheduling analysis method, system, device and medium, belonging to the technical field of power grid analysis, the method comprising the following steps: constructing a double-layer optimization model considering air conditioning load participating in steel load peak shaving; the double-layer optimization model comprises an upper model and a lower model; when the flexibility resource on the power supply side cannot meet the safe and economic operation of the power grid, the upper model takes ensuring that the air conditioning load aggregation regulates and controls the maximum steel load as the objective function; the lower model takes the minimum total cost as the objective function under the condition of meeting the shortage of flexibility resource of the upper model; the double-layer optimization model is solved to obtain an optimal scheduling strategy. The present disclosure improves the system flexibility and response speed, and provides a new idea and technical means for realizing the effective participation of large-scale load resources in demand response.

Description

Technical Field

[0001] This disclosure belongs to the field of power grid analysis technology, and in particular relates to a temperature control-industrial load aggregation dispatch analysis method, system, equipment and medium. Background Technology

[0002] Currently, innovation in demand-side load management and power supply-demand balance strategies is urgently needed, with a particular focus on the development of new power load management strategies. Large industrial loads, with their significant capacity advantages and adjustment flexibility, have become important targets for optimizing power dispatch. At the same time, the large-scale air conditioning load groups in industrial parks present significant challenges due to their data density and high computational load, easily leading to communication bottlenecks and response delays. This limits the ability of air conditioning users to participate in demand response (DR) in real time, and both factors increase the overall control difficulty.

[0003] In the context of vast industrial parks with densely packed air conditioning equipment, traditional centralized control models face challenges and limited effectiveness when aggregating air conditioning loads to participate in grid peak shaving. Given the impact of the diversity of resource characteristics and spatiotemporal differences on the accuracy of overall load regulation, relying solely on centralized control cannot guarantee regulation efficiency and accuracy, while distributed control may weaken the potential for cross-regional energy synergy optimization.

[0004] Therefore, it is necessary to provide a new method, system, equipment, and medium for temperature control-industrial load aggregation scheduling analysis to solve the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method, system, device, and medium for temperature control-industrial load aggregation scheduling analysis in order to solve the above-mentioned problems.

[0006] This disclosure achieves the above objectives through the following technical solutions: A method for temperature control-industrial load aggregation scheduling analysis includes the following steps: A two-layer optimization model is constructed that considers the participation of air conditioning load in peak shaving of steel load. The two-layer optimization model includes an upper-layer model and a lower-layer model. When the power supply flexibility resources cannot meet the requirements for safe and economical operation of the power grid, the upper-layer model takes the maximum target function of ensuring the aggregation and regulation of steel load by air conditioning load. The lower-layer model takes the minimum total cost as the target function, while satisfying the flexibility resource shortage of the upper-layer model. The optimal scheduling strategy is obtained by solving the two-layer optimization model.

[0007] As a further optimization of this disclosure, a two-level optimization model considering the participation of air conditioning load in steel load peak shaving is constructed, including: Model the air conditioning system and aggregate the air conditioning load; Model the steel industry within the park to obtain the aggregation power of the steel industry; An upper-level model is constructed based on the air conditioning load and the aggregated power of the steel industry.

[0008] As a further optimization of this disclosure, air conditioning modeling and aggregating air conditioning loads are performed, including: Model the individual air conditioner to obtain the total load power of the individual air conditioner; The air conditioning load is aggregated based on the air conditioning on / off time and the total load power of the individual air conditioners.

[0009] As a further optimization of this disclosure, the steel industry within the industrial park is modeled to obtain the aggregation power of the steel industry, including: Model the steel industry within the park, calculate continuous impact load, intermittent impact load, and stable load. The aggregate power of the steel industry is the sum of the continuous impact load, the intermittent impact load, and the stable load.

[0010] As a further optimization of this disclosure, an upper-level model is constructed based on the air conditioning load and the aggregated power of the steel industry, including: The upper-level model is the difference between the aggregate power of the steel industry and the air conditioning load.

[0011] As a further optimization of this disclosure, a two-level optimization model considering the participation of air conditioning load in steel load peak shaving is constructed, which also includes: By aggregating the regulation capabilities of steel enterprises and air conditioning users in industrial parks, the relationship between the power grid company's incentive-based demand-side costs and the load reduction amount of users can be obtained. Based on the relationship between the power grid company's incentive-based demand-side costs and the load reduction of users, the load reduction of steel plants and air conditioners in the industrial park is regarded as a virtual power plant. The objective function and constraints for the load reduction of all equipment are obtained, thus obtaining the lower-level model.

[0012] As a further optimization of this disclosure, the constraints include power balance constraints and upper and lower limits constraints for load reduction.

[0013] As a further optimization of this disclosure, the two-level optimization model is solved to obtain the optimal scheduling scheme, including: The Monte Carlo tree search optimization algorithm is used to solve the two-level optimization model to obtain the optimal scheduling strategy.

[0014] A temperature control-industrial load aggregation scheduling and analysis system, comprising: The model building module is used to construct a two-layer optimization model that considers the participation of air conditioning load in steel load peak shaving. The two-layer optimization model includes an upper-layer model and a lower-layer model. When the power supply flexibility resources cannot meet the requirements for safe and economical operation of the power grid, the upper-layer model takes the maximum steel load as the objective function to ensure the aggregation and regulation of air conditioning load. The lower-layer model takes the minimum total cost as the objective function to meet the flexibility resource shortage of the upper-layer model. The model solving module is used to solve the two-layer optimization model to obtain the optimal scheduling strategy.

[0015] As a further optimization of this disclosure, the model building module constructs a two-layer optimization model that considers the participation of air conditioning load in steel load peak shaving, including: Model the air conditioning system and aggregate the air conditioning load; Model the steel industry within the park to obtain the aggregation power of the steel industry; An upper-level model is constructed based on the air conditioning load and the aggregated power of the steel industry.

[0016] As a further optimization of this disclosure, air conditioning modeling and aggregating air conditioning loads are performed, including: Model the individual air conditioner to obtain the total load power of the individual air conditioner; The air conditioning load is aggregated based on the air conditioning on / off time and the total load power of the individual air conditioners.

[0017] As a further optimization of this disclosure, the steel industry within the industrial park is modeled to obtain the aggregation power of the steel industry, including: Model the steel industry within the park, calculate continuous impact load, intermittent impact load, and stable load. The aggregate power of the steel industry is the sum of the continuous impact load, the intermittent impact load, and the stable load.

[0018] As a further optimization of this disclosure, an upper-level model is constructed based on the air conditioning load and the aggregated power of the steel industry, including: The upper-level model is the difference between the aggregate power of the steel industry and the air conditioning load.

[0019] As a further optimization of this disclosure, the model building module constructs a two-layer optimization model that considers the participation of air conditioning load in steel load peak shaving, and further includes: By aggregating the regulation capabilities of steel enterprises and air conditioning users in industrial parks, the relationship between the power grid company's incentive-based demand-side costs and the load reduction amount of users can be obtained. Based on the relationship between the power grid company's incentive-based demand-side costs and the load reduction of users, the load reduction of steel plants and air conditioners in the industrial park is regarded as a virtual power plant. The objective function and constraints for the load reduction of all equipment are obtained, thus obtaining the lower-level model.

[0020] An electronic device is characterized in that it includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to execute the program stored in the memory to implement the temperature control-industrial load aggregation scheduling analysis method.

[0021] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the temperature control-industrial load aggregation scheduling analysis method.

[0022] The beneficial effects of this disclosure are as follows: This disclosure constructs a hierarchical control architecture and a multi-agent collaborative communication network model for large-scale air conditioning and industrial load management, aiming to achieve precise and efficient overall load regulation. By analyzing the relationship between demand-side load reduction costs of power grid companies and users, and based on the Monte Carlo tree search optimization algorithm, it can promote the optimal allocation of cross-regional energy resources while ensuring regulation accuracy. This disclosure improves system flexibility and response speed, providing new ideas and technical means for realizing the effective participation of large-scale load resources in demand response. Attached Figure Description

[0023] Figure 1 This is a flowchart of a method in an embodiment of this disclosure; Figure 2 This is a system structure block diagram of an embodiment of this disclosure; Figure 3 This is a block diagram of the device structure in an embodiment of this disclosure. Detailed Implementation

[0024] The present application will now be described in further detail with reference to the accompanying drawings. It should be noted that the following specific embodiments are only used to further illustrate the present application and should not be construed as limiting the scope of protection of the present application. Those skilled in the art can make some non-essential improvements and adjustments to the present application based on the above application content.

[0025] like Figure 1 As shown, a temperature control-industrial load aggregation scheduling analysis method includes the following steps: A two-layer optimization model is constructed that considers the participation of air conditioning load in peak shaving of steel load. The two-layer optimization model includes an upper-layer model and a lower-layer model. When the power supply flexibility resources cannot meet the requirements for safe and economical operation of the power grid, the upper-layer model takes the maximum aggregation regulation of steel load by air conditioning load as the objective function to derive the demand-side flexibility requirements. The lower-layer model, under the condition of meeting the flexibility resource shortage of the upper-layer model, takes the minimum total cost as the objective function and derives the aggregation response potential based on the load that can be reduced and transferred. The optimal scheduling strategy is obtained by solving the two-layer optimization model.

[0026] In this embodiment, a two-layer optimization model considering the participation of air conditioning load in steel load peak shaving is constructed, including: Step 1: First, model the air conditioner. Since the air conditioner load accounts for the largest proportion of electricity consumption and is highly controllable, the thermodynamic equivalent method is often used for individual air conditioner modeling. The total load power of a single air conditioner is: (1) (2) In the formula: and These represent the real-time indoor and outdoor temperatures (°C), respectively. Equivalent heat capacity (kW·h / °C); Equivalent thermal resistance (°C / kW); The power rating (kW) of the air conditioner; The variables 0 and 1 represent the on / off state of the air conditioner, with 1 indicating that the air conditioner is on and 0 indicating that the air conditioner is off. and Upper and lower limits of indoor temperature variation (°C); This is due to time lag. Next, the air conditioner switching time can be determined by solving the first-order ordinary differential equation shown in equation (1), and the aggregated air conditioner load is: (3) ; (4) (5) In the formula: and This refers to the on / off time of the air conditioner; This represents the total load of the air conditioning system (kW). This refers to the usage of air conditioners; For air conditioner operating rate; To set the temperature to The probability of; Set the temperature to The air conditioner power at that time. This is a temperature dead zone. For the number of residents, Air conditioner ownership per 100 households Set the air conditioner to turn on; Step 2: Next, model the steel industry within the park. The steel loads are continuous impact load, intermittent impact load, and stable load. Consider that the steel billet is processed by multiple roughing mills and finishing mills. Each roughing mill... implement Rolling passes. The overall power analysis of the steel rolling process is as follows: (6) Where: Where: For steel billet No. The moment when the i-th roughing mill is entered; For the j-th time the steel billet passes through the first time The time taken by each roughing mill; For steel billet No. The average power of the i-th roughing mill. This indicates the number of equipment units used in steel rolling production. This indicates the total processing time for steel rolling. The total power consumed in roughing.

[0027] so Power of steel billets completing the rolling process As shown in the following formula: (7) The formula illustrates the production process of rolled steel products. , The power of roughing and finishing rolling, as well as the time interval sequence of the billet entering the two stages, are used to simulate the power change of the production line at a certain time. The number of equipment for finishing rolling. and These represent the time taken to pass through the finishing mill and the roughing mill, respectively.

[0028] In the steel industry, intermittent impact loads are typically found in refining furnaces, whose core function is to heat a mixture of molten iron and scrap iron to remove impurities and produce high-quality steel, as shown in the following formula: (8) In the formula: For impact load power, Time required for the electric arc furnace to reach steady-state power after startup; The time required for the electric arc furnace to stop power to zero. This is the rated operating power value; This represents the random fluctuation in steady state. and These represent the maximum and minimum durations of continuous operation of the electric arc furnace, respectively.

[0029] Aside from the significant load fluctuations in rolling mills and electric arc furnaces, other auxiliary equipment in the steel industry, such as pump units, blower systems, dust removal equipment, and conveying devices, exhibit relatively stable operating power. Without manual adjustments, the power consumption of these devices can be considered essentially constant over short to medium-term timeframes, with minimal fluctuations, approximating a constant power operation mode. The stable load expression is as follows: (9) In the formula, To stabilize load power, Represents the sum of the rated power of other types of loads; for Random variables within an interval reflect minor fluctuations during stable load operation.

[0030] Next, starting from the power changes of a single steel rolling production line and a single electric arc furnace, the aggregate power of the steel industry is derived: (10) Step 3: In the upper interval, the main objective function for adjusting the air conditioning load to compensate for the peak steel load is obtained by subtracting equation (5) from equation (10): (11) Step 4: The goal of the lower-level interval is to minimize grid costs. Load aggregators effectively leverage the flexible adjustment capabilities of steel plants and air conditioning users in industrial parks to precisely regulate grid supply and demand. When grid power is strained, steel plants and air conditioning units reduce their loads to alleviate grid pressure and avoid power shortages. When grid capacity is surplus, the loads of steel plants and air conditioning units are intelligently increased to efficiently absorb excess power. Before the industrial park equipment responds, the grid company's revenue... for: (12) In the formula: This represents the total number of devices; The electricity price is for the retail side; This represents the electrical load.

[0031] The cost of demand-side management for power grid companies is reflected in the rewards and incentives for users' load shedding behavior, denoted by a quadratic cost function: (13) In the formula To participate in the secondary costs of demand-side, and These are price coefficients, and The primary and secondary costs of load participation in demand response, The reward for reducing user load is z, where z is the number of resources involved and h is the response time to the request. Indicates the types of resources required to respond to a demand; Indicates the response time to the demand. (14) In the formula and These represent the costs and revenues of the power grid companies participating in demand response.

[0032] Following the demand response in the industrial park, the power grid company's revenue is: (15) In the formula and These represent the changes in load before and after the demand response.

[0033] The incentive-based demand-side cost of the power grid company is a quadratic function of the load shedding amount by users: (16) In the formula and The price coefficient for incentive-driven demand-side costs. For other expenses, and The coefficient that excites the load parameter demand response.

[0034] Treating the load reduction of steel plants and air conditioning units in the industrial park as virtual power plants, the objective function and constraints for load reduction of all equipment are as follows: (17) (18) In the formula: The total cost incurred by the power grid company for user participation in demand response; Reduce load costs for each device; Reduce the load on each device; The number of equipment within the industrial park; This represents the total active power deficit of the system. and These are the upper and lower limits (kW) of the load that can be reduced by the industrial air conditioning system; the constraint (18) is the power balance constraint and the upper and lower limits of the load reduction constraint.

[0035] Step 5: Construct the objective function corresponding to the two-level interval: (18) (19) Solving the two-layer optimization model yields the optimal scheduling strategy, which in this embodiment specifically includes: The Monte Carlo Tree Search (MCTS) algorithm is used to optimize the above equation, and then applied to solve the optimal scheduling problem. The MCTS algorithm treats the decision-making process as a sequential Markov chain, where each step is based on the current environment state, reflecting the wisdom of dynamic decision-making. The strategy is envisioned as being built on an n-layer state framework, with each layer containing k potential actions. The state set E = {E1, E2, ..., En} forms the foundation of the decision path. The formation of the strategy involves selecting the optimal sequence from these actions, resulting in a wide combinatorial space. k n This presents several possibilities. Through simulation and evaluation cycles, the layout of the search tree is continuously optimized. When encountering seemingly effective strategy fragments, MCTS can quickly deepen its exploration, as detailed below: Each node in MCTS is mapped to an action decision point in the current state, where A / B indicates that the action was executed B times, and that the final policy reached the ideal or optimal standard A times out of B attempts. The starting root node, such as 12 / 21, means that the predetermined optimal standard was reached 12 times out of a total of 21 simulations.

[0036] The first step in MCTS is the "Selection" process, which begins at the root node and proceeds along the path of the "most promising" child nodes until a node that has not yet been fully explored (i.e., has "unexpanded child nodes") is encountered, as shown in the 3 / 3 node. This signifies that there are still untried follow-up strategies in the current situation.

[0037] The expansion phase then begins, adding a new 0 / 0 child node to the previously unexpanded node. This represents a completely new, untried decision option.

[0038] The next step is simulation. Starting from this new node, a rollout policy is employed. This policy, while having a limited search depth, is fast and aims to quickly arrive at a final policy evaluation. This step typically involves only one simulation to balance accuracy and efficiency. While multiple simulations can improve accuracy, they significantly reduce the simulation frequency per unit time, thus affecting overall search performance.

[0039] Finally, the backpropagation process feeds back the simulation results to all involved parent nodes. If the simulation result is 0 / 1, it means that the optimal standard has not been reached. This information will be passed up layer by layer to update the statistical information of each node.

[0040] When selecting nodes, MCTS employs a probability-based selection mechanism that optimizes the selection process through random sampling and dynamic adjustment of policy value. Specifically, while randomly selecting actions, it dynamically adjusts the probability of each action being selected based on its historical performance (i.e., expected reward), making high-performing strategies more likely to be explored repeatedly. Through numerous repeated random simulations, MCTS can gradually identify and strengthen the optimal policy path, as shown in the following formula:

[0041] In the formula, S1 and S2 are the current optimal node values ​​of the two objective functions; This is the current optimal probability estimate of the node, estimated in increments of 10% from [25%, 85%] using the interval estimation method, N. c It represents the number of times a node is visited; z is a constant, the larger z is, the more it leans towards breadth-first search, and the smaller z is, the more it leans towards depth-first search.

[0042] The optimal parameters are obtained by using the Monte Carlo tree search optimization algorithm, and the optimal trading strategy is obtained.

[0043] This disclosure presents a hierarchical and partitioned dynamic architecture-based temperature control-industrial load aggregation scheduling analysis method, which has the following characteristics: (1) Design of a hierarchical and partitioned dynamic architecture: Based on the actual needs of the power system, a two-layer dynamic architecture is designed. This architecture should be able to support the effective aggregation and dispatch of temperature-controlled loads and industrial loads. Within the framework, the LA (Lower Layout) effectively aggregates the flexible adjustment capabilities of steel plants and air conditioning users in industrial parks, precisely controlling the power grid supply and demand relationship. When the power grid is under pressure, the load of steel plants and air conditioning units is reduced to alleviate grid pressure and avoid power shortages. When the grid has surplus capacity, the load of steel plants and air conditioning units is intelligently increased to efficiently absorb excess power, while ensuring the system's safety and economy, achieving efficient load aggregation and dispatch.

[0044] (2) The convergence of temperature control load and industrial load: Effectively combining temperature-controlled air conditioning loads with industrial loads from steel plants requires considering the characteristics and demands of the loads and designing a reasonable combination strategy to ensure the stability and controllability of the combined loads.

[0045] (3) Scheduling optimization algorithm: To achieve optimal scheduling of aggregated loads, considering factors such as power system supply and demand balance, load forecasting, and constraints, a Monte Carlo Tree Search (MCTS) optimization algorithm is employed. This algorithm optimizes the selection process through random sampling and dynamic adjustment of strategy value. The probability of selection for each action is dynamically adjusted based on its historical performance (i.e., expected return), making high-performing strategies more likely to be explored repeatedly. Through numerous repeated random simulations, MCTS gradually identifies and strengthens the optimal strategy path, thereby achieving optimal strategy selection.

[0046] This disclosure reduces system operating costs and volatility. An objective function model minimizing operating costs and wind / solar curtailment is established, and an efficient solution method combining a two-layer structure and an innovative genetic algorithm is developed to determine the system's coordinated control scheme. After optimization, wind / solar curtailment is significantly reduced, and operating costs are substantially lowered, achieving good economic and social benefits. Nevertheless, this research still has room for improvement. In particular, the model construction stage focuses only on the temporal dimension of energy, neglecting its spatial characteristics; that is, the geographical location of both supply and demand sides is equally important in energy coordination. Therefore, future research will focus on incorporating the spatial characteristics of energy to further improve the practicality and effectiveness of this control strategy.

[0047] like Figure 2 As shown, embodiments of this disclosure provide a temperature control-industrial load aggregation scheduling and analysis system, including: The model building module is used to construct a two-layer optimization model that considers the participation of air conditioning load in steel load peak shaving. The two-layer optimization model includes an upper-layer model and a lower-layer model. When the power supply flexibility resources cannot meet the requirements for safe and economical operation of the power grid, the upper-layer model takes the maximum steel load as the objective function to ensure the aggregation and regulation of air conditioning load. The lower-layer model takes the minimum total cost as the objective function to meet the flexibility resource shortage of the upper-layer model. The model solving module is used to solve the two-layer optimization model to obtain the optimal scheduling strategy.

[0048] The implementation process of the functions and roles of each module in the above system is detailed in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0049] See Figure 3 The electronic device provided in the embodiments of this disclosure includes a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120 and the memory 1130 communicate with each other through the communication bus 1140. Memory 1130 is used to store computer programs; The processor 1110, when executing the program stored in the memory 1130, implements the above-described temperature control-industrial load aggregation scheduling analysis method. The aforementioned communication bus 1140 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, it is represented by only one thick line in the figure, but this does not indicate that there is only one bus or one type of bus.

[0050] The communication interface 1120 is used for communication between the above-mentioned electronic device and other devices.

[0051] The memory 1130 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1130 may also be at least one storage device located remotely from the aforementioned processor 1110.

[0052] Embodiments of this disclosure also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the temperature control-industrial load aggregation scheduling analysis method as described above.

[0053] The embodiments described above are merely examples of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these modifications and improvements all fall within the protection scope of this disclosure.

Claims

1. A method for temperature control-industrial load aggregation scheduling analysis, characterized in that, Includes the following steps: A two-layer optimization model is constructed that considers the participation of air conditioning load in peak shaving of steel load. The two-layer optimization model includes an upper-layer model and a lower-layer model. When the power supply flexibility resources cannot meet the requirements for safe and economical operation of the power grid, the upper-layer model takes the maximum target function of ensuring the aggregation and regulation of steel load by air conditioning load. The lower-layer model takes the minimum total cost as the target function, while satisfying the flexibility resource shortage of the upper-layer model. Solving the two-layer optimization model yields the optimal scheduling strategy; Among them, a two-level optimization model considering the participation of air conditioning load in steel load peak shaving is constructed, including: Model the air conditioning system and aggregate the air conditioning load; Modeling the steel industry within the industrial park yields the aggregated power of the steel industry, including: modeling the steel industry within the park with steel loads categorized as continuous impact loads, intermittent impact loads, and stable loads. Power of steel billets completing the rolling process As shown in the following formula: ； In the formula, , These are the roughing rolling power and the finishing rolling power, respectively. The number of equipment for finishing rolling. and These refer to the time taken to pass through the finishing mill and the roughing mill, respectively. In the steel industry, intermittent impact load power As shown in the following formula: ； In the formula, For intermittent impact load power, Time required for the electric arc furnace to reach steady-state power after startup; The time required for the electric arc furnace to stop power to zero. This is the rated operating power value; This refers to the random fluctuation in steady state. and These represent the maximum and minimum durations of continuous operation of the electric arc furnace, respectively. Stable load power of other auxiliary equipment in the steel industry The expression is as follows: ； In the formula, To stabilize load power, Represents the sum of the rated power of other types of loads; for Random variables within an interval reflect minute fluctuations during stable load operation; Next, starting from the power changes of a single steel rolling production line and a single electric arc furnace, the aggregate power of the steel industry is derived: ； An upper-level model is constructed based on the air conditioning load and the aggregate power of the steel industry; the upper-level model is the difference between the aggregate power of the steel industry and the air conditioning load.

2. The temperature control-industrial load aggregation scheduling analysis method according to claim 1, characterized in that, Model the air conditioning system and aggregate the air conditioning load, including: Model the individual air conditioner to obtain the total load power of the individual air conditioner; The air conditioning load is aggregated based on the air conditioning on / off time and the total load power of the individual air conditioners.

3. The temperature control-industrial load aggregation scheduling analysis method according to claim 1, characterized in that, The construction of a two-level optimization model that considers the participation of air conditioning load in peak shaving of steel load also includes: By aggregating the regulation capabilities of steel enterprises and air conditioning users in industrial parks, the relationship between the power grid company's incentive-based demand-side costs and the load reduction amount of users can be obtained. Based on the relationship between the power grid company's incentive-based demand-side costs and the load reduction of users, the load reduction of steel plants and air conditioning units in the industrial park is regarded as a virtual power plant. The objective function and constraints for the load reduction of all equipment are obtained, thus obtaining the lower-level model.

4. The temperature control-industrial load aggregation scheduling analysis method according to claim 3, characterized in that, The constraints include power balance constraints and upper and lower limits for load reduction.

5. The temperature control-industrial load aggregation scheduling analysis method according to claim 1, characterized in that, Solving the two-level optimization model yields the optimal scheduling scheme, including: The Monte Carlo tree search optimization algorithm is used to solve the two-level optimization model to obtain the optimal scheduling strategy.

6. A temperature control-industrial load aggregation scheduling and analysis system, characterized in that, include: The model building module is used to construct a two-layer optimization model that considers the participation of air conditioning load in steel load peak shaving. The two-layer optimization model includes an upper-layer model and a lower-layer model. When the power supply flexibility resources cannot meet the requirements for safe and economical operation of the power grid, the upper-layer model takes the maximum steel load as the objective function to ensure the aggregation and regulation of air conditioning load. The lower-layer model takes the minimum total cost as the objective function to meet the flexibility resource shortage of the upper-layer model. The model solving module is used to solve the two-layer optimization model to obtain the optimal scheduling strategy; The model building module constructs a two-layer optimization model that considers the participation of air conditioning load in steel load peak shaving, including: Model the air conditioning system and aggregate the air conditioning load; Modeling the steel industry within the industrial park yields the aggregated power of the steel industry, including: modeling the steel industry within the park with steel loads categorized as continuous impact loads, intermittent impact loads, and stable loads. Power of steel billets completing the rolling process As shown in the following formula: ； In the formula, , These are the roughing rolling power and the finishing rolling power, respectively. The number of equipment for finishing rolling. and These refer to the time taken to pass through the finishing mill and the roughing mill, respectively. In the steel industry, intermittent impact load power As shown in the following formula: ； In the formula, For intermittent impact load power, Time required for the electric arc furnace to reach steady-state power after startup; The time required for the electric arc furnace to stop power to zero. This is the rated operating power value; This refers to the random fluctuation in steady state. and These represent the maximum and minimum durations of continuous operation of the electric arc furnace, respectively. Stable load power of other auxiliary equipment in the steel industry The expression is as follows: ； In the formula, To stabilize load power, Represents the sum of the rated power of other types of loads; for Random variables within an interval reflect minute fluctuations during stable load operation; Next, starting from the power changes of a single steel rolling production line and a single electric arc furnace, the aggregate power of the steel industry is derived: ； An upper-level model is constructed based on the air conditioning load and the aggregate power of the steel industry; the upper-level model is the difference between the aggregate power of the steel industry and the air conditioning load.

7. The temperature control-industrial load aggregation scheduling and analysis system according to claim 6, characterized in that, Model the air conditioning system and aggregate the air conditioning load, including: Model the individual air conditioner to obtain the total load power of the individual air conditioner; The air conditioning load is aggregated based on the air conditioning on / off time and the total load power of the individual air conditioners.

8. The temperature control-industrial load aggregation scheduling and analysis system according to claim 6, characterized in that, The model building module constructs a two-layer optimization model that considers the participation of air conditioning load in steel load peak shaving, and also includes: By aggregating the regulation capabilities of steel enterprises and air conditioning users in industrial parks, the relationship between the power grid company's incentive-based demand-side costs and the load reduction amount of users can be obtained. Based on the relationship between the power grid company's incentive-based demand-side costs and the load reduction of users, the load reduction of steel plants and air conditioning units in the industrial park is regarded as a virtual power plant. The objective function and constraints for the load reduction of all equipment are obtained, thus obtaining the lower-level model.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor is used to execute a program stored in a memory to implement the temperature control-industrial load aggregation scheduling analysis method according to any one of claims 1-5.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the temperature control-industrial load aggregation scheduling analysis method as described in any one of claims 1-5.

Images