Power distribution network energy-saving control method and device for air conditioning system and computer equipment

Abstract

The invention relates to a power distribution network energy-saving control method and device for an air conditioning system and computer equipment. Relates to the technical field of power systems. The method comprises the steps that under the current operation period of a power distribution network used for the air conditioning system, load power of one operation period on the power distribution network and prediction data of distributed resource output are obtained; inputting the first scheduling plan into a trained scheduling model to obtain a first scheduling plan of a previous operation cycle; obtaining a scheduling plan value at a preset moment, and controlling the power distribution network to operate at the preset moment corresponding to the current operation cycle; and obtaining node voltage values of the current operation period of the power distribution network at a preset moment, correcting the first scheduling plan based on a preset correction strategy under the condition that at least one node voltage value exceeds a preset node voltage value range, and after a corrected second scheduling plan is obtained, controlling the operation of the power distribution network. The method can guarantee the regulation and control efficiency of the power distribution network when the air conditioner load is high.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a distribution network energy-saving control method, device, and computer equipment for air-conditioning systems. Background Art

[0002] With global warming and accelerating urbanization, air conditioners are increasingly accounting for a growing share of power load in power systems. Due to their concentrated usage and high load volatility, these loads impact the stable operation of power grids and the efficient and effective use of energy. Therefore, achieving energy-efficient air conditioner operation has become a key research topic.

[0003] Currently, energy-saving control of distribution networks during air conditioning operation is achieved by reducing peak grid load and optimizing the air conditioning load. However, due to the presence of rectifier capacitors, air conditioning loads are less susceptible to grid voltage fluctuations. Relying solely on CVR (Conservation Voltage Reduction) technology has limited energy regulation for air conditioning loads and is unable to address the severe challenges posed to the grid by the surge in air conditioning loads during high summer temperatures. Consequently, distribution network regulation efficiency is currently low when air conditioning loads are high. Summary of the Invention

[0004] Based on this, it is necessary to provide a distribution network energy-saving control method, device, computer equipment, computer-readable storage medium and computer program product for an air-conditioning system to address the technical problem of low distribution network regulation efficiency when the air-conditioning load is high.

[0005] In a first aspect, the present application provides a distribution network energy-saving control method for an air-conditioning system, comprising:

[0006] Under the current operation cycle of the distribution network used for the air conditioning system, obtain the load power and the forecast data of the distributed resource output during the previous operation cycle of the distribution network;

[0007] Inputting the load power and the forecast data into a trained scheduling model to obtain a first scheduling plan for a previous operation cycle of the distribution network;

[0008] Obtaining a scheduling plan value at a preset time in the first scheduling plan, and controlling the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle;

[0009] Obtaining the voltage value of each node at the preset time in the current operation cycle of the distribution network, and when at least one of the node voltage values exceeds a preset node voltage value range, revising the first scheduling plan based on a preset correction strategy to obtain a revised second scheduling plan;

[0010] The operation of the distribution network is controlled based on the second dispatch plan.

[0011] In one embodiment, the distribution network energy-saving control method for an air-conditioning system further includes: obtaining first impact data of the distribution network in a previous operating cycle before performing a preset voltage reduction energy-saving measure; the first impact data includes the node voltage value, the first load active power, the first load reactive power, and the load ratio corresponding to the plurality of load characteristics of at least one node among the nodes;

[0012] Based on the first impact data, the second load active power and the second load reactive power at the preset moment after the node in the previous operation cycle performs the voltage reduction and energy-saving measures are respectively obtained.

[0013] In one embodiment, the objective function of the trained scheduling model is the minimum daily energy consumption of the distribution network; the step of determining the minimum daily energy consumption includes: obtaining second impact data of the distribution network; the second impact data includes a branch set, a node set, the resistance of at least one branch in the branch set, the input current of at least one branch at the preset time, and the load power of at least one node in the node set after voltage reduction and energy-saving measures are performed; based on the second impact data, the minimum daily energy consumption is determined.

[0014] In one embodiment, the step of determining the minimum daily energy consumption further includes: obtaining multiple constraints and determining the minimum daily energy consumption based on the multiple constraints; wherein the multiple constraints include system forward and backward power flow constraints, node voltage and branch current constraints, distributed resource output constraints, reactive compensation device constraints, and on-load transformer regulation constraints; the system forward and backward power flow constraints are determined based on multiple data corresponding to at least one node in the node set; the node voltage and branch current constraints are determined based on preset threshold intervals of voltage values of each node in the node set, branch currents in the node set, and preset threshold intervals of the branch currents; the distributed resource output constraints are determined based on the preset threshold intervals of the distributed power generation output power, distributed active power, and distributed reactive power of at least one node in the node set; the reactive compensation device constraints are determined based on the reactive compensation amount of the reactive compensation device of at least one node in the node set and the preset threshold interval of the compensation capacity of the reactive compensation device; the on-load transformer regulation constraints are determined based on the substation voltage before and after the on-load transformer is adjusted, and multiple data corresponding to the on-load transformer adjustment gear.

[0015] In one embodiment, the first scheduling plan is corrected based on a preset correction strategy to obtain a corrected second scheduling plan, including: based on the first scheduling plan, a group rotation control strategy is adopted to regulate the air-conditioning system; the first scheduling plan adopts a group rotation control strategy to regulate the air-conditioning system, including: in the first layer of group rotation control strategy, multiple air conditioners are divided into different groups and marked according to a preset initial temperature, so that the distribution network synchronously regulates the multiple air conditioners according to the marks and regulates the temperatures of the multiple air conditioners to the maximum value of the preset temperature range; in the second layer of group rotation control strategy, the multiple air conditioners in the same group are divided into multiple small groups according to the single controlled time and controlled time interval of the multiple air conditioners in the same group, so that the distribution network regulates the multiple small groups in turn according to the preset time interval and preset power adjustment strategy.

[0016] In one embodiment, when at least one of the node voltage values exceeds a preset node voltage value range, the first scheduling plan is corrected based on a preset correction strategy, including: obtaining a voltage sensitivity vector between at least one node and the remaining nodes in the distribution network corresponding to the current moment; determining a degree of coupling between the at least one node and the remaining nodes based on the voltage sensitivity vector; and correcting the first scheduling plan according to the coupling degree.

[0017] In a second aspect, the present application further provides a distribution network energy-saving control device for an air-conditioning system, comprising:

[0018] A data acquisition module is used to obtain the load power and distributed resource output prediction data of the distribution network in the previous operation cycle under the current operation cycle of the distribution network for the air-conditioning system;

[0019] a data processing module, configured to input the load power and the forecast data into a trained scheduling model to obtain a first scheduling plan for a previous operation cycle of the distribution network;

[0020] A first control module is configured to obtain a scheduling plan value at a preset time in the first scheduling plan, and control the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle;

[0021] a correction module, configured to obtain the voltage value of each node at the preset time in the current operation cycle of the distribution network, and, if at least one of the node voltage values exceeds a preset node voltage value range, correct the first scheduling plan based on a preset correction strategy to obtain a corrected second scheduling plan;

[0022] The second control module is used to control the operation of the distribution network based on the second scheduling plan.

[0023] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0024] Under the current operation cycle of the distribution network used for the air conditioning system, obtain the load power and the forecast data of the distributed resource output during the previous operation cycle of the distribution network;

[0025] Inputting the load power and the forecast data into a trained scheduling model to obtain a first scheduling plan for a previous operation cycle of the distribution network;

[0026] Obtaining a scheduling plan value at a preset time in the first scheduling plan, and controlling the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle;

[0027] Obtaining the voltage value of each node at the preset time in the current operation cycle of the distribution network, and when at least one of the node voltage values exceeds a preset node voltage value range, revising the first scheduling plan based on a preset correction strategy to obtain a revised second scheduling plan;

[0028] The operation of the distribution network is controlled based on the second dispatch plan.

[0029] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the following steps:

[0030] Under the current operation cycle of the distribution network used for the air conditioning system, obtain the load power and the forecast data of the distributed resource output during the previous operation cycle of the distribution network;

[0031] Inputting the load power and the forecast data into a trained scheduling model to obtain a first scheduling plan for a previous operation cycle of the distribution network;

[0032] Obtaining a scheduling plan value at a preset time in the first scheduling plan, and controlling the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle;

[0033] Obtaining the voltage value of each node at the preset time in the current operation cycle of the distribution network, and when at least one of the node voltage values exceeds a preset node voltage value range, revising the first scheduling plan based on a preset correction strategy to obtain a revised second scheduling plan;

[0034] The operation of the distribution network is controlled based on the second dispatch plan.

[0035] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0036] Under the current operation cycle of the distribution network used for the air conditioning system, obtain the load power and the forecast data of the distributed resource output during the previous operation cycle of the distribution network;

[0037] Inputting the load power and the forecast data into a trained scheduling model to obtain a first scheduling plan for a previous operation cycle of the distribution network;

[0038] Obtaining a scheduling plan value at a preset time in the first scheduling plan, and controlling the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle;

[0039] Obtaining the voltage value of each node at the preset time in the current operation cycle of the distribution network, and when at least one of the node voltage values exceeds a preset node voltage value range, revising the first scheduling plan based on a preset correction strategy to obtain a revised second scheduling plan;

[0040] The operation of the distribution network is controlled based on the second dispatch plan.

[0041] The above-mentioned distribution network energy-saving control method, device, computer equipment, storage medium and computer program product for air-conditioning systems have the following beneficial effects in the process of energy-saving control of the distribution network of air-conditioning systems: first, in the current operation cycle of the distribution network for the air-conditioning system, the load power and the predicted data of the distributed resource output of the distribution network in the previous operation cycle are obtained; then the load power and the predicted data are input into the trained scheduling model to obtain the first scheduling plan of the previous operation cycle of the distribution network; then the scheduling plan value at the preset time in the first scheduling plan is obtained, and the distribution network is controlled based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle; then the voltage value of each node at the preset time in the current operation cycle of the distribution network is obtained, and when at least one node voltage value exceeds the preset node voltage value range, the first scheduling plan is corrected based on the preset correction strategy to obtain a corrected second scheduling plan; finally, the operation of the distribution network is controlled based on the second scheduling plan. In this process, selecting the appropriate operating cycle helps more accurately predict load and resource output. Inputting these into the trained scheduling model yields a more accurate first scheduling plan. Real-time monitoring of node voltages allows timely implementation of corrections to the first scheduling plan, resulting in a second scheduling plan. This further enhances the flexibility and stability of the distribution network and effectively reduces its reliance on real-time scheduling corrections. Therefore, this method ensures efficient distribution network control when the air conditioning system is under high load. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 1 is a flow chart of a method for controlling energy-saving in a distribution network of an air-conditioning system according to an embodiment;

[0044] Figure 2 A schematic diagram of controlled air conditioner layers in a distribution network energy-saving control method for an air-conditioning system according to an embodiment;

[0045] Figure 3 Detailed steps of a power distribution network energy-saving control method for an air-conditioning system according to an embodiment;

[0046] Figure 4 A schematic diagram of a system structure for simulation verification in one embodiment;

[0047] Figure 5Schematic diagram of the optimal adjustment gear position of OLTC after taking CVR measures in one embodiment;

[0048] Figure 6 A schematic diagram of system voltage after measures are taken in one embodiment;

[0049] Figure 7 is a schematic diagram of the total power requirement of the system in one embodiment;

[0050] Figure 8 A schematic diagram of total system power reduction after adjusting by adopting the group round-robin control strategy in one embodiment;

[0051] Figure 9 Schematic diagram of voltages at various nodes before and after system multi-time-scale optimization at 14:00 in one embodiment;

[0052] Figure 10 This is a structural block diagram of a distribution network energy-saving control device for an air-conditioning system in one embodiment;

[0053] Figure 11 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0055] In one embodiment, Figure 1 As shown, a distribution network energy-saving control method for an air-conditioning system is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0056] Step S102 : in the current operation cycle of the distribution network for the air-conditioning system, obtaining the load power and the prediction data of the output of the distributed resources in the previous operation cycle of the distribution network.

[0057] Among them, the distribution network is the power network that transmits electricity from the substation to the air-conditioning system, which may include transformers, distribution lines, and switchgear, etc.; the operating cycle is the time period for the distribution network to be dispatched and controlled; the load power is the power demand of the air-conditioning system in the distribution network during a specific time period; and the distributed resource output can be the power generation capacity of distributed energy within a specific time period.

[0058] Optionally, the operating cycle can be one day, 12 hours or other customized time periods; the forecast data of distributed resource output can include the expected power generation of various distributed energy sources in a specific time period, the forecast value of electricity demand near the distributed resources, and forecast information on electricity price changes.

[0059] Step S104: input the load power and the forecast data into the trained scheduling model to obtain a first scheduling plan for the last operation cycle of the distribution network.

[0060] Among them, the dispatching model can be a mathematical or computational model, mainly used to optimize the operation of the distribution network; the first dispatching plan is a preliminary dispatching plan generated based on the load power and forecast data of the previous operating cycle, and also includes OLTC (On load tap changer) gear adjustment.

[0061] Step S106: Obtain the scheduling plan value at the preset time in the first scheduling plan, and control the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle.

[0062] The scheduling plan value is the load power and resource configuration value in the first scheduling plan at a specific preset moment, which is used to control the operation of the distribution network.

[0063] Step S108, obtaining the voltage value of each node at a preset time in the current operation cycle of the distribution network. When at least one node voltage value exceeds the preset node voltage value range, the first scheduling plan is corrected based on a preset correction strategy to obtain a corrected second scheduling plan.

[0064] Among them, the node voltage value is the voltage level of each node in the distribution network; the correction strategy is the adjustment measures taken when the node voltage value exceeds the preset node voltage value range, which may include adjusting power generation, changing load distribution, or introducing backup power supply.

[0065] Step S110: Control the operation of the distribution network based on the second scheduling plan.

[0066] As an example, taking the operating cycle as one day, first predict the load demand and distributed resource output within one day, then input the predicted data into the trained scheduling model to obtain the first scheduling plan, and then control the operation of the distribution network according to the first scheduling plan and monitor the voltage values of each node of the distribution network in real time. When it is detected that the voltage value of a node exceeds the preset node voltage value range, the preset value correction strategy is activated to adjust the output of each distributed resource to obtain the second scheduling plan, and continue to control the operation of the distribution network according to the second scheduling plan.

[0067] In the above-mentioned distribution network energy-saving control method for an air-conditioning system, first, in the current operating cycle of the distribution network for the air-conditioning system, predicted data of the load power and distributed resource output of the distribution network in the previous operating cycle are obtained; then, the load power and predicted data are input into a trained scheduling model to obtain a first scheduling plan for the previous operating cycle of the distribution network; then, the scheduling plan value at a preset time in the first scheduling plan is obtained, and the distribution network is controlled based on the scheduling plan value to operate at the preset time corresponding to the current operating cycle; then, the voltage value of each node at the preset time in the current operating cycle of the distribution network is obtained. If at least one node voltage value exceeds the preset node voltage value range, the first scheduling plan is corrected based on a preset correction strategy to obtain a corrected second scheduling plan; finally, the distribution network operation is controlled based on the second scheduling plan. In the above process, by selecting an appropriate operating cycle, it is helpful to more accurately predict the load and resource output, and inputting them into the trained scheduling model can obtain a more accurate first scheduling plan; by real-time monitoring of the node voltage, the correction strategy can be timely implemented on the first scheduling plan to obtain the second scheduling plan, further enhancing the flexibility and stability of the distribution network and effectively reducing the distribution network's dependence on real-time scheduling corrections. Therefore, when the load of the air-conditioning system is high, the control efficiency of the distribution network can be guaranteed by the above method.

[0068] In an exemplary embodiment, the distribution network energy-saving control method for an air-conditioning system further includes: respectively obtaining first impact data of the distribution network in the previous operating cycle before performing preset voltage reduction and energy-saving measures; the first impact data includes the node voltage value, the first load active power, the first load reactive power, and the load ratio corresponding to multiple load characteristics of at least one node in each node; based on the first impact data, respectively obtaining the second load active power and the second load reactive power of the nodes in the previous operating cycle at a preset moment after performing voltage reduction and energy-saving measures.

[0069] Among them, conservation voltage reduction (CVR) refers to a method of reducing transmission and distribution losses, lowering load power, and achieving energy-saving effects by lowering the voltage level of the distribution network. It is usually used to alleviate power supply pressure and reduce energy consumption; node voltage value: refers to the voltage level of each node in the distribution network, reflecting the power quality of the grid; the first load active power represents the active power actually consumed by the node in the previous operating cycle; the first load reactive power represents the reactive power used by the node to maintain node voltage stability in the previous operating cycle; the load ratio corresponding to the load characteristics includes the ZIP (static load model) load ratio; the second load active power and the second load reactive power refer to the load power at the preset time after the implementation of the conservation voltage reduction measure; the preset time refers to the time point for collecting load power data at a specific time selected according to the load characteristics and distribution network conditions.

[0070] More commonly, Z can represent impedance load, which means that the power demand of the load is proportional to the square of the voltage; I can represent current load, which means that the power demand of the load is proportional to the voltage; P can represent constant power load, which means that the power demand of the load remains unchanged within a certain range and does not change with the voltage.

[0071] As an example, V i,t is the voltage of node i after the step-down regulation, V i,0 is the voltage of node i before the step-down regulation, P i,t is the active power of the first load, Q i,t is the reactive power of the first load, αZ i, αI i, and αP i are the ZIP load proportions of node i, PCVR i,t is the active power of the second load, and QCVRi,t is the reactive power of the second load. The corresponding expressions for the above data are:

[0072]

[0073] In this embodiment, by monitoring and analyzing the first impact data, the distribution network can understand the actual power demand and status of the node before implementing the voltage reduction and energy-saving measures. By comparing the changes in load active and reactive power before and after the implementation of the voltage reduction and energy-saving measures, the effectiveness of the energy-saving measures and their impact on the performance of the distribution network can be judged, which helps optimize the operation of the distribution network, improves energy utilization efficiency, and ensures the stability and reliability of the distribution network.

[0074] Furthermore, in one embodiment, the objective function of the trained scheduling model is the minimum daily energy consumption of the distribution network; the step of determining the minimum daily energy consumption includes: obtaining second impact data of the distribution network; the second impact data includes a branch set, a node set, the resistance in at least one branch in the branch set, the input current of at least one branch at a preset time, and the load power of at least one node in the node set after voltage reduction and energy-saving measures are performed; based on the second impact data, the minimum daily energy consumption is determined.

[0075] Among them, the branch set refers to the set of power branches connecting different nodes in the distribution network, and the branches are responsible for the transmission and distribution of electricity; the node set refers to the set of various electrical nodes in the distribution network, including substations, distribution boxes and user access points; the resistance in the branch refers to the electrical characteristics of at least one branch in the distribution network. Resistance is an important factor affecting current flow and power loss. The larger the resistance value, the more energy is lost in the current flow; input current: refers to the current value flowing into a branch at a preset time. The magnitude of the current directly affects the power transmission and energy consumption of the branch; the minimum daily energy consumption refers to the lowest energy consumption of the distribution network within a one-day operating cycle after optimized scheduling and voltage reduction measures.

[0076] As an example, Ω L is the branch set, Ω N is the node set, r ij is the resistance in branch ij, that is, the resistance in at least one branch in the branch set, I ij,t is the current flowing into branch ij at time t, that is, the input current of at least one branch at the preset time, PCVR j,t is the load power of each node after taking CVR measures, that is, the load power after at least one node in the node set takes voltage reduction and energy saving measures. The corresponding expression of the above data is:

[0077]

[0078] In this embodiment, by obtaining the second impact data, the distribution network can more comprehensively understand the operating status after the implementation of the voltage reduction and energy-saving measures, and the second image data not only reflects the electrical characteristics of the distribution network, but also shows the changes in load demand. By analyzing these data, the minimum daily energy consumption can be determined, thereby optimizing the power dispatching strategy, improving energy utilization efficiency, and reducing energy consumption.

[0079] In one embodiment, the step of determining the minimum daily energy consumption also includes: obtaining multiple constraints and determining the minimum daily energy consumption based on the multiple constraints; wherein the multiple constraints include system forward-backward flow constraints, node voltage and branch current constraints, distributed resource output constraints, reactive compensation device constraints and on-load transformer regulation constraints; the system forward-backward flow constraints are determined based on multiple data corresponding to at least one node in the node set; the node voltage and branch current constraints are determined based on the preset threshold intervals of the voltage values of each node in the node set, the branch currents in the node set and the preset threshold intervals of the branch currents; the distributed resource output constraints are determined based on the distributed power generation output power, the preset threshold intervals of the distributed active power and the preset threshold intervals of the distributed reactive power of at least one node in the node set; the reactive compensation device constraints are determined based on the reactive compensation amount of the reactive compensation equipment of at least one node in the node set and the preset threshold intervals of the compensation capacity of the reactive compensation equipment; the on-load transformer regulation constraints are determined based on the substation voltage before and after the on-load transformer is adjusted, and multiple data corresponding to the on-load transformer adjustment gear.

[0080] As an example, the system forward and backward power flow constraint is based on the network branch set Ψ with j as the head end b , with j as the first active power P of branch (j, k) j,k , node j load active power P L,j , the network branch set Ψ with j as the terminal c , the first active power P of branch (i, j) i,j , the first section reactive power Q of branch (i, j)i,j , the resistance r of branch (i, j) i,j , the actual voltage V between node i and node j i 、V j , the active power P emitted by the DG of node j DG,j ; Take j as the first section reactive power Q of branch (j, k) j,k , node j load reactive power Q L,j , reactance x of branch (i, j) i,j , the reactive power generated by the DG at node j determines Q DG,j , the specific expression is:

[0081]

[0082] Furthermore, the node voltage and branch current constraints are determined based on the preset threshold intervals of the node voltage values in the node set, the branch currents in the node set, and the preset threshold intervals of the branch currents, wherein V imin With V imax , are the upper and lower limits of each node voltage, i.e., the preset threshold interval of each node voltage value; I ij is the current between branches ij, that is, the branch current in the node set; I ijmin with I ijmax are the upper and lower limits of each branch current, that is, the preset threshold range of the branch current. The specific expression is:

[0083]

[0084] Furthermore, the distributed resource output constraint is determined based on the distributed generation output power, the preset threshold interval of the distributed active power, and the preset threshold interval of the distributed reactive power of at least one node in the node set, wherein P DG,i is the DG output power of the i-th node, that is, the distributed generation output power of at least one node; Pmin DG,i and Pmax DG,i are the upper and lower limits of the active power emitted by each node DG, that is, the preset threshold interval of distributed active power; Qmin DG,i and Qmax DG,i are the upper and lower limits of the reactive power emitted by each node DG, that is, the preset threshold interval of distributed reactive power. The specific expression is:

[0085]

[0086] In addition, the reactive compensation device constraint is determined based on the reactive compensation amount of the reactive compensation device of at least one node in the node set and the preset threshold interval of the compensation capacity of the reactive compensation device, wherein Q C,mis the reactive compensation amount of the reactive compensation device at node m, that is, the reactive compensation amount of the reactive compensation device at at least one node; Qmin C,m and Qmax C,m are the minimum and maximum compensation capacities of the reactive compensation device at node m, that is, the preset threshold ranges of the compensation capacity of the reactive compensation device. The specific expression is:

[0087]

[0088] Moreover, the on-load transformer regulation constraint is determined based on the substation voltage before and after the on-load transformer regulation, and a plurality of data corresponding to the on-load transformer regulation gear, wherein V ss,1 The substation voltage after OLTC regulation, that is, the substation voltage before and after the on-load transformer regulation; the multiple data corresponding to the on-load transformer regulation gear include: the substation voltage V before OLTC regulation ss,0 , OLTC adjustment gear λ, OLTC each gear adjustment voltage ω, OLTC adjustment gear upper and lower limits λ min and λ max , OLTC adjustment times ξ λ , OLTC maximum adjustment timesξ max , the specific expression is:

[0089]

[0090] In this embodiment, by controlling the node voltage and branch current, the voltage is ensured to remain within a preset safety range, thereby reducing power quality issues; by constraining the output of distributed power generation, energy is rationally allocated and resource utilization efficiency is improved; by comprehensively considering the above-mentioned multiple constraints, the daily energy consumption of the distribution network can be effectively reduced, achieving a dual improvement in economic and environmental benefits.

[0091] Furthermore, in one embodiment, the first scheduling plan is corrected based on a preset correction strategy to obtain a corrected second scheduling plan, including: based on the first scheduling plan, adopting a group rotation control strategy to regulate the air-conditioning system; the first scheduling plan adopts a group rotation control strategy to regulate the air-conditioning system, including: in the first layer of group rotation control strategy, multiple air conditioners are divided into different groups and marked according to a preset initial temperature, so that the distribution network can synchronously regulate the multiple air conditioners according to the marks, and regulate the temperatures of the multiple air conditioners to the maximum value of the preset temperature range; in the second layer of group rotation control strategy, multiple air conditioners in the same group are divided into multiple small groups according to the single controlled time and controlled time interval of the multiple air conditioners in the same group, so that the distribution network can regulate the multiple small groups in turn according to the preset time interval and the preset power adjustment strategy.

[0092] As an example, Figure 2As shown, the total number of controlled air conditioners includes the first layer and the second layer. In the first layer grouping strategy, the air conditioner cluster consisting of N controllable air conditioners is divided into different groups according to the preset initial temperature, which are marked as S1, S2...S n Assuming that the human body's comfortable temperature perception range [T min , T max ], that is, the preset temperature range, then all air conditioners are uniformly set to the temperature T after being regulated. max , which is the maximum value of the preset temperature range. This allows groups of air conditioners with the same initial set temperature to operate synchronously at the minimum frequency, achieving consistent control timing. During demand response periods, all air conditioners in the group are controlled synchronously, collectively reducing their operating power to the minimum.

[0093] Furthermore, in the second-level grouping strategy, in order to take into account user comfort, a rotation control strategy is implemented for the air conditioners in the same group. Taking the S1 group as an example, assuming that the single control duration of the variable frequency air conditioner in the group is Δt, and the control time interval of each air conditioner is set to φ, the variable frequency air conditioners in the group can be evenly divided into φ / Δt sub-groups to implement rotation control. Specifically, S 11 The subgroup reduces the power to the minimum during the first Δt period and recovers to the normal operating power during the second Δt period; the second subgroup maintains the normal power during the first Δt period, performs power reduction during the second Δt period, and then recovers the stable operating power during the third Δt period; S 13 ~S 1n The sub-groups follow this analogy and take turns to perform control according to the established time intervals and power adjustment strategies.

[0094] In this embodiment, by dividing air conditioners with the same initial set temperature into different groups and setting a unified temperature, the frequent starting and stopping of air conditioners can be reduced, energy consumption can be reduced, and energy utilization efficiency can be improved; the rotation control strategy can ensure that the air conditioners in the same group take turns to cool down at different time periods, avoiding user discomfort caused by simultaneous cooling; the unified set temperature and synchronous control strategy ensure the consistency of the control time of all air conditioners, simplify the management process, and improve the effectiveness of control; therefore, through hierarchical and refined group control, not only the adjustment effect of the air conditioning load can be optimized, but also the efficiency of demand response implementation can be maximized.

[0095] In an exemplary embodiment, when the voltage value of at least one node exceeds a preset node voltage value range, the first scheduling plan is corrected based on a preset correction strategy, including: obtaining a voltage sensitivity vector between at least one node and the remaining nodes in the distribution network corresponding to the current moment; based on the voltage sensitivity vector, determining the degree of coupling between at least one node and the remaining nodes; and correcting the first scheduling plan according to the coupling degree.

[0096] As an example, the distribution network's operating conditions are monitored in real time during the day. When a voltage limit is exceeded, an optimized daily operation strategy is implemented. Distributed resources with strong coupling are selected based on the electrical distance between nodes to achieve rapid node voltage recovery. In a distribution system consisting of m nodes, the change in voltage amplitude ΔU at each node satisfies the following relationship with the change in active power ΔP and reactive power ΔQ:

[0097]

[0098]

[0099] Among them, ΔP and ΔQ are the changes in active power and reactive power injected into the node respectively; Indicates the change in node voltage amplitude per unit active power injected into the node; Indicates the change in node voltage amplitude when unit reactive power is injected into the node.

[0100] Therefore, according to the above expression, the change of the injected power of each node will affect the voltage of a single node. When the voltage of a node exceeds the limit, the voltage sensitivity vector between the node and other nodes is calculated. and The larger the value in the vector, the stronger the electrical coupling between the node and the node, and the flexible adjustable resource of the node becomes the priority regulation target. The distribution network optimization goal will be changed from minimizing power consumption to minimizing the active and reactive reverse flow injected by the flexible adjustable resource node to achieve rapid voltage recovery, thereby enhancing the stability of the grid operation. The original constraints of the mathematical model remain unchanged, and the objective function is set as:

[0101]

[0102] Where, Ω M is the set of nodes containing flexible adjustable resources, ΔQ i With ΔP i are the reactive power and active power changes injected by the adjustable resources connected to node i, ΔV is the difference between the lowest voltage of the system node and the lower voltage limit, and δ1, δ2 and δ3 are the corresponding weight coefficients after normalized weighting processing.

[0103] In this embodiment, through the implementation of the first and second layer grouping strategies, the air conditioning cluster control not only optimizes the energy utilization efficiency, but also integrates the distribution network energy-saving control technology of active voltage and air conditioning adjustment, achieving the technical effect of ensuring the regulation efficiency of the distribution network when the load of the air conditioning system is high.

[0104] This application provides a distribution network energy-saving control method for an air-conditioning system. In order to better understand the process of the distribution network energy-saving control method for an air-conditioning system, combined with Figure 3 As shown, the following describes in detail a specific process of the distribution network energy-saving control method for the air-conditioning system of the present application, including the following steps:

[0105] Step S302: Obtain forecast data of the day-ahead load power and distributed resource output of the distribution network.

[0106] Step S304: Take voltage reduction and energy-saving measures to obtain a day-ahead scheduling plan.

[0107] Step S306: Formulate a group rotation control strategy for the variable frequency air conditioners.

[0108] Step S308: delivering the scheduling plan at time t to each distributed resource, on-load transformer, and controlled air conditioner.

[0109] Step S310: collecting voltage data of each node in the distribution network at time t and determining whether the node voltage exceeds a limit.

[0110] Step S312: If the node voltage exceeds the limit, the day-ahead scheduling plan is corrected based on a correction strategy of a preset value.

[0111] Among them, the day before is the previous operation cycle; the day before scheduling plan is the first scheduling plan; time t is the preset time; and the limit-out refers to the node voltage value exceeding the preset node voltage value range.

[0112] As an example, the improved IEEE33 node system is used for simulation verification. The system structure is as follows: Figure 4As shown in the figure, the system voltage reference value is 12.66 kV, the power reference value is 1 MVA, the total system active power and reactive power are 3715 kW and 2300 kVar (Kilovolt-Ampere Reactive), respectively; the node voltage fluctuation range is allowed to be [0.94, 1.06] pu (per unit), and the maximum branch current is set to 500 A; the OLTC is connected to the branch connected to the upper power grid at node 1, with a total of 12 adjustment gears, an adjustment step of 0.01, an adjustment range of [0.94, 1.06], and a maximum adjustment number of 5; the SVC (Static Var Compensator) is connected to nodes 6, 16, and 32, and the reactive adjustment range is [-100 kVar, 300 kVar]; the capacitor bank (Capacitor The energy storage is connected to nodes 16 and 33, with a rated capacity of 2000kWh and a rated active power of 300kW and 200kW respectively. The upper and lower limits of the capacity are 90% and 20%, and the charge and discharge efficiency is 0.9. The wind turbines are connected to nodes 18 and 33, with a capacity of 1000kW. Considering that the air conditioning load accounts for a high proportion in summer and is approximately a constant power load, the present invention sets the ZIP load model ratio of each node to 3:2:5. According to the total power demand of the system, it is assumed that 90 controllable variable frequency air conditioners are connected to nodes 2 to 33, and the user sets the air conditioning temperature to be evenly distributed between 24℃ and 26℃. To meet user comfort, the maximum set temperature after the air conditioning load is controlled in summer is 28℃. Based on this, this example adopts the distribution network energy-saving control technology that integrates voltage and air conditioning active regulation to optimize the distribution network system for energy saving, and obtains the optimal OLTC adjustment gear and system voltage after taking CVR measures. Figure 5 and Figure 6 As shown in the figure, the total power requirement of the system is as follows Figure 7 As shown, it includes the total system power before CVR optimization and the total system power after CVR optimization.

[0113] from Figure 6 It can be seen that after optimization, the voltage per unit value of each node is still above 0.94, which meets the system power supply voltage standard. The daily energy consumption of the system before optimization is 54.7565MW·h, and the daily energy consumption of the system after optimization is 53.2772MW·h (Note: These two data are for Figure 7(integrated from the middle bar graph), daily energy consumption decreased by 2.701%. Since the load output coefficient is greater than 0.9 from 19:00 to 22:00, which is the peak load period in summer, to further reduce the total load power demand during this period, a variable frequency air conditioner grouping rotation control strategy is adopted. The air conditioners are grouped according to their initial set temperature and controlled duration, and the set temperatures of the variable frequency air conditioners in different groups are adjusted to the maximum set temperature in turn. The total system power reduction after adjustment is as follows: Figure 8 shown.

[0114] More, Figure 8 Including the original power demand, the power demand after CVR optimization and the power demand after CVR and air conditioning regulation, Figure 8 It can be seen that during the period from 7:00 PM to 10:00 PM, the system's original energy consumption was 11.5973 MW·h. By implementing CVR measures, the total system energy consumption was reduced to 11.4432 MW·h. Furthermore, by adjusting the set temperature of user variable-frequency air conditioners, the total system energy consumption was reduced by an additional 0.44226 MW·h, achieving a peak reduction rate of 5.142%. These results demonstrate that, given sufficient voltage margin, the proposed multi-time-scale distribution network optimization strategy, which considers CVR and air conditioning load control, can effectively reduce the system's total energy consumption and achieve peak load reduction.

[0115] To further verify the feasibility of the strategy proposed in this invention at the time of voltage exceeding the limit, it is assumed that there is a significant deviation between the load forecast value before the day and the actual load value during the day at 14:00, and the output coefficient increases sharply from 0.68 to 1.5, resulting in a surge in the load power demand of each node in the distribution network, and the system voltage drops below the safe operating range. In this scenario, the intraday optimization operation strategy responds quickly, the OLTC gear is upgraded, and the distributed resources are preferentially regulated according to the electrical distance to achieve rapid voltage recovery and ensure the optimization of the regulated power of the controlled resources. The voltages of each node before and after the multi-time scale optimization of the system at 14:00 are shown in the figure below. Figure 9 As shown, it includes the node voltage corresponding to the predicted load, the node voltage corresponding to the actual load, and the node voltage after collaborative optimization.

[0116] In the optimized power distribution system, if Figure 9 As shown in the figure, the voltages of all nodes have returned to the specified range. Compared with the initial CVR optimization strategy, the OLTC gear is adjusted from -4 to +5 in the intraday optimization operation strategy. At the same time, the SVC reactive compensation capacity of node 32 is optimized from 281.375kVar to 466.746kVar, while the output configuration of other distributed resources remains unchanged. The above adjustments significantly improve the flexibility of the intraday dispatch plan and effectively reduce the dependence on real-time dispatch corrections, thereby optimizing the overall operation efficiency of the system.

[0117] Through the above embodiments, based on the existing CVR technology, the potential for regulating air conditioning loads is fully exploited, and a distribution network energy-saving control technology that integrates voltage and active air conditioning regulation is proposed. Given that variable-frequency air conditioning loads are less sensitive to voltage fluctuations, the above-mentioned group rotation control strategy effectively reduces the total power demand and reduces load peaks by combining CVR technology with air conditioning load cluster regulation, significantly improving the regulation capability of the distribution network. While reducing the total energy consumption of the system, it effectively reduces the reliance on real-time scheduling corrections, enhancing the stability and robustness of the distribution network operation.

[0118] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0119] Based on the same inventive concept, embodiments of the present application also provide a distribution network energy-saving control device for an air-conditioning system, which is used to implement the aforementioned distribution network energy-saving control method for an air-conditioning system. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the distribution network energy-saving control device for an air-conditioning system provided below can be found in the aforementioned limitations of the distribution network energy-saving control method for an air-conditioning system, and will not be repeated here.

[0120] In an exemplary embodiment, Figure 10 As shown, a distribution network energy-saving control device for an air-conditioning system is provided, comprising: a data acquisition module 1001, a data processing module 1002, a first control module 1003, a correction module 1004, and a second control module 1005, wherein:

[0121] The data acquisition module 1001 is used to acquire the load power and the prediction data of the output of distributed resources in the previous operation cycle of the distribution network used for the air-conditioning system in the current operation cycle of the distribution network.

[0122] The data processing module 1002 is used to input the load power and prediction data into the trained scheduling model to obtain the first scheduling plan of the last operation cycle of the distribution network.

[0123] The first control module 1003 is used to obtain the scheduling plan value at a preset time in the first scheduling plan, and control the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle.

[0124] The correction module 1004 is used to obtain the voltage value of each node at a preset time in the current operation cycle of the distribution network. When at least one node voltage value exceeds the preset node voltage value range, the first scheduling plan is corrected based on a preset correction strategy to obtain a corrected second scheduling plan.

[0125] The second control module 1005 is used to control the operation of the distribution network based on the second scheduling plan.

[0126] Furthermore, in one embodiment, the data acquisition module 1001 is also used to respectively obtain the first impact data of the distribution network in the previous operating cycle before the preset voltage reduction and energy-saving measures are implemented; the first impact data includes the node voltage value of at least one node in each node, the first load active power, the first load reactive power, and the load ratio corresponding to multiple load characteristics; based on the first impact data, the second load active power and the second load reactive power of the nodes in the previous operating cycle at the preset moment after the voltage reduction and energy-saving measures are implemented are respectively obtained.

[0127] Furthermore, in one embodiment, the data processing module 1002 is also used to obtain second impact data of the distribution network; the second impact data includes a branch set, a node set, the resistance in at least one branch in the branch set, the input current of at least one branch at a preset time, and the load power of at least one node in the node set after voltage reduction and energy-saving measures are taken; based on the second impact data, the minimum daily energy consumption is determined.

[0128] Furthermore, in one embodiment, the data processing module 1002 is also used to obtain multiple constraints and determine the minimum daily energy consumption based on the multiple constraints; wherein the multiple constraints include system forward and backward flow constraints, node voltage and branch current constraints, distributed resource output constraints, reactive compensation device constraints and on-load transformer regulation constraints; the system forward and backward flow constraints are determined based on multiple data corresponding to at least one node in the node set; the node voltage and branch current constraints are determined based on the preset threshold intervals of the voltage values of each node in the node set, the branch currents in the node set and the preset threshold intervals of the branch currents; the distributed resource output constraints are determined based on the distributed power generation output power, the preset threshold intervals of the distributed active power and the preset threshold intervals of the distributed reactive power of at least one node in the node set; the reactive compensation device constraints are determined based on the reactive compensation amount of the reactive compensation device of at least one node in the node set and the preset threshold intervals of the compensation capacity of the reactive compensation device; the on-load transformer regulation constraints are determined based on the substation voltage before and after the on-load transformer is adjusted, and multiple data corresponding to the on-load transformer adjustment gear.

[0129] Furthermore, in one embodiment, the correction module 1004 is also used to correct the first scheduling plan based on a preset correction strategy to obtain a corrected second scheduling plan, including: based on the first scheduling plan, adopting a group rotation control strategy to regulate the air-conditioning system; the first scheduling plan, adopting a group rotation control strategy to regulate the air-conditioning system, including: in the first layer of group rotation control strategy, multiple air conditioners are divided into different groups and marked according to the preset initial temperature, so that the distribution network can synchronously regulate the multiple air conditioners according to the marks, and regulate the temperatures of the multiple air conditioners to the maximum value of the preset temperature range; in the second layer of group rotation control strategy, multiple air conditioners in the same group are divided into multiple small groups according to the single controlled time and controlled time interval of the multiple air conditioners in the same group, so that the distribution network can regulate the multiple small groups in turn according to the preset time interval and the preset power adjustment strategy.

[0130] Furthermore, in one embodiment, the correction module 1004 is also used to obtain the voltage sensitivity vector between at least one node and the remaining nodes in the distribution network corresponding to the current moment; based on the voltage sensitivity vector, determine the coupling degree between the at least one node and the remaining nodes; and correct the first scheduling plan according to the coupling degree.

[0131] Each module in the aforementioned power distribution network energy-saving control device for an air conditioning system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0132] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 11 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store distribution network energy-saving control data for air-conditioning systems. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a distribution network energy-saving control method for air-conditioning systems is implemented.

[0133] Those skilled in the art will understand that Figure 11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0134] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0135] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0136] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0137] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0138] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0139] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0140] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A distribution network energy-saving control method for an air-conditioning system, characterized in that: The method comprises: Under the current operation cycle of the distribution network used for the air conditioning system, obtain the load power and the forecast data of the distributed resource output during the previous operation cycle of the distribution network; Inputting the load power and the forecast data into a trained scheduling model to obtain a first scheduling plan for a previous operation cycle of the distribution network; Obtaining a scheduling plan value at a preset time in the first scheduling plan, and controlling the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle; Obtaining the voltage value of each node at the preset time in the current operation cycle of the distribution network, and when at least one of the node voltage values exceeds a preset node voltage value range, revising the first scheduling plan based on a preset correction strategy to obtain a revised second scheduling plan; The operation of the distribution network is controlled based on the second dispatch plan.

2. The method according to claim 1, characterized in that The method further comprises: Obtaining first impact data of the distribution network in a previous operating cycle before performing a preset voltage reduction and energy-saving measure; the first impact data includes the node voltage value, the first load active power, the first load reactive power, and the load ratio corresponding to the plurality of load characteristics of at least one node among the nodes; Based on the first impact data, the second load active power and the second load reactive power at the preset moment after the node in the previous operation cycle performs the voltage reduction and energy-saving measures are respectively obtained.

3. The method according to claim 1, characterized in that The objective function of the trained scheduling model is the minimum daily energy consumption of the distribution network; The step of determining the minimum daily energy consumption includes: Obtaining second impact data of the distribution network; the second impact data includes a branch set, a node set, a resistance in at least one branch in the branch set, an input current of the at least one branch at the preset time, and a load power of at least one node in the node set after voltage reduction and energy saving measures are performed; The minimum daily energy consumption is determined according to the second impact data.

4. The method according to claim 3, characterized in that The step of determining the minimum daily energy consumption also includes: Acquire multiple constraints, and determine the minimum daily energy consumption according to the multiple constraints; The multiple constraints include system forward and backward power flow constraints, node voltage and branch current constraints, distributed resource output constraints, reactive compensation device constraints, and on-load transformer regulation constraints; The forward and backward power flow constraints of the system are determined based on a plurality of data corresponding to at least one node in the node set; The node voltage and branch current constraints are determined based on a preset threshold interval of each node voltage value in the node set, a branch current in the node set, and a preset threshold interval of the branch current; The distributed resource output constraint is determined based on a preset threshold range of distributed power generation output, distributed active power, and distributed reactive power of at least one node in the node set; The reactive compensation device constraint is determined based on a reactive compensation amount of a reactive compensation device of at least one node in the node set and a preset threshold interval of a compensation capacity of the reactive compensation device; The on-load transformer regulation constraint is determined based on the substation voltage before and after the on-load transformer is regulated, and a plurality of data corresponding to the regulation gear of the on-load transformer.

5. The method according to claim 1, wherein The step of modifying the first scheduling plan based on a preset modification strategy to obtain a modified second scheduling plan includes: Based on the first scheduling plan, adopting a group rotation control strategy to regulate the air-conditioning system; The first scheduling plan adopts a group rotation control strategy to regulate the air-conditioning system, including: In the first-level group rotation control strategy, multiple air conditioners are divided into different groups according to preset initial temperatures and marked, so that the distribution network can synchronously control the multiple air conditioners according to the marks and adjust the temperatures of the multiple air conditioners to the maximum value of the preset temperature range; In the second-level group rotation control strategy, the multiple air conditioners in the same group are divided into multiple groups based on the single control duration and controlled time interval of the multiple air conditioners in the same group, so that the distribution network can rotate and control the multiple groups according to the preset time interval and preset power adjustment strategy.

6. The method according to claim 1, characterized in that When at least one of the node voltage values exceeds a preset node voltage value range, modifying the first scheduling plan based on a preset modification strategy includes: Obtaining a voltage sensitivity vector between at least one node and the remaining nodes in the distribution network corresponding to a current moment; determining, based on the voltage sensitivity vector, a degree of coupling between the at least one node and the remaining nodes; The first scheduling plan is modified according to the coupling degree.

7. A distribution network energy-saving control device for an air-conditioning system, characterized in that: The device comprises: A data acquisition module is used to obtain the load power and distributed resource output prediction data of the distribution network in the previous operation cycle under the current operation cycle of the distribution network for the air-conditioning system; a data processing module, configured to input the load power and the forecast data into a trained scheduling model to obtain a first scheduling plan for a previous operation cycle of the distribution network; A first control module is configured to obtain a scheduling plan value at a preset time in the first scheduling plan, and control the distribution network based on the scheduling plan value to operate at the preset time corresponding to the current operation cycle; a correction module, configured to obtain the voltage value of each node at the preset time in the current operation cycle of the distribution network, and, if at least one of the node voltage values exceeds a preset node voltage value range, correct the first scheduling plan based on a preset correction strategy to obtain a corrected second scheduling plan; The second control module is used to control the operation of the distribution network based on the second scheduling plan.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images