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

Abstract

The application relates to a power distribution network energy-saving control method, device and computer equipment for an air conditioning system. It relates to the technical field of power systems. The method comprises the following steps: in a current operation cycle of a power distribution network for an air conditioning system, obtaining predicted data of load power and distributed resource output of a previous operation cycle of the power distribution network; inputting the predicted data into a trained scheduling model to obtain a first scheduling plan of the previous operation cycle; obtaining a scheduling plan value at a preset time point, and controlling the power distribution network to operate at the preset time point corresponding to the current operation cycle; obtaining each node voltage value of the power distribution network at the preset time point in the current operation cycle; in the case that at least one node voltage value exceeds a preset node voltage value range, correcting the first scheduling plan based on a preset correction strategy to obtain a second scheduling plan after correction, and then controlling the power distribution network to operate. The method can guarantee the regulation and control efficiency of the power distribution network when the air conditioning load is high.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a distribution network energy-saving control method, device and computer equipment for air conditioning systems. Background Technology

[0002] With global warming and accelerated urbanization, the proportion of air conditioning load in the power system is gradually increasing. Due to its concentrated usage periods and large load fluctuations, air conditioning affects the stable operation of the power grid and the rational and efficient use of energy. Therefore, how to achieve energy-saving operation of air conditioning has become a problem to be studied.

[0003] Current energy-saving control of the power distribution network during air conditioning operation involves reducing peak grid load and optimizing air conditioning load. However, due to the presence of rectifier capacitors, the air conditioning load is less affected by grid voltage fluctuations. Relying solely on CVR (Conservation Voltage Reduction) technology has limited effectiveness in regulating air conditioning load and cannot cope with the severe challenges posed to the power grid by the surge in air conditioning load during the high-temperature summer period. Therefore, there is currently a problem of low distribution network control efficiency when air conditioning load is high. Summary of the Invention

[0004] Therefore, it is necessary to address the technical problem of low distribution network control efficiency when the air conditioning load is high by providing a distribution network energy-saving control method, device, computer equipment, computer-readable storage medium, and computer program product for air conditioning systems.

[0005] In a first aspect, this application provides a power distribution network energy-saving control method for air conditioning systems, comprising:

[0006] In the current operating cycle of the distribution network used for air conditioning systems, obtain the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle;

[0007] The load power and the predicted data are input into the trained scheduling model to obtain the first scheduling plan for the previous operating cycle of the distribution network.

[0008] 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 operating cycle;

[0009] The voltage values ​​of each node in the current operating cycle of the power distribution network at the preset time are obtained. If the voltage value of at least one node exceeds the preset node voltage value range, the first scheduling plan is modified based on a preset correction strategy to obtain the modified second scheduling plan.

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

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

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

[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: acquiring 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 the at least one branch at the preset time, and the load power of at least one node in the node set after implementing voltage reduction energy-saving measures; and determining the minimum daily energy consumption based on the second impact data.

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

[0015] In one embodiment, the step of modifying the first scheduling plan based on a preset correction strategy to obtain a modified second scheduling plan includes: based on the first scheduling plan, adopting a group-based rotation control strategy to regulate the air conditioning system; the first scheduling plan adopting a group-based rotation control strategy to regulate the air conditioning system includes: in the first-level group-based rotation control strategy, dividing multiple air conditioners into different groups and marking them according to a preset initial temperature, so that the power distribution network can synchronously regulate the multiple air conditioners according to the markings, and regulate the temperature of the multiple air conditioners to the maximum value of a preset temperature range; in the second-level group-based rotation control strategy, dividing the multiple air conditioners in the same group into multiple subgroups according to the single controlled duration and controlled time interval of the multiple air conditioners in the same group, so that the power distribution network can rotate and regulate the multiple subgroups according to a preset time interval and a preset power adjustment strategy.

[0016] In one embodiment, when the voltage value of at least one of the nodes exceeds a preset node voltage value range, the step of correcting the first scheduling plan based on a preset correction strategy includes: obtaining the voltage sensitivity vector between at least one node in the distribution network and the remaining nodes at the current time; determining the coupling degree 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] Secondly, this application also provides an energy-saving control device for power distribution networks in air conditioning systems, comprising:

[0018] The data acquisition module is used to acquire the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle of the distribution network used for the air conditioning system under the current operating cycle.

[0019] The data processing module is used to input the load power and the predicted data into the trained scheduling model to obtain the first scheduling plan for the previous operating cycle of the distribution network.

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

[0021] The correction module is used to obtain the voltage values ​​of each node in the current operating cycle of the distribution network at the preset time, and when at least one node voltage value exceeds the 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] Thirdly, this application also provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0024] In the current operating cycle of the distribution network used for air conditioning systems, obtain the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle;

[0025] The load power and the predicted data are input into the trained scheduling model to obtain the first scheduling plan for the previous operating cycle of the distribution network.

[0026] 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 operating cycle;

[0027] The voltage values ​​of each node in the current operating cycle of the power distribution network at the preset time are obtained. If the voltage value of at least one node exceeds the preset node voltage value range, the first scheduling plan is modified based on a preset correction strategy to obtain the modified second scheduling plan.

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

[0029] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0030] In the current operating cycle of the distribution network used for air conditioning systems, obtain the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle;

[0031] The load power and the predicted data are input into the trained scheduling model to obtain the first scheduling plan for the previous operating cycle of the distribution network.

[0032] 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 operating cycle;

[0033] The voltage values ​​of each node in the current operating cycle of the power distribution network at the preset time are obtained. If the voltage value of at least one node exceeds the preset node voltage value range, the first scheduling plan is modified based on a preset correction strategy to obtain the modified second scheduling plan.

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

[0035] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, performs the following steps:

[0036] In the current operating cycle of the distribution network used for air conditioning systems, obtain the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle;

[0037] The load power and the predicted data are input into the trained scheduling model to obtain the first scheduling plan for the previous operating cycle of the distribution network.

[0038] 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 operating cycle;

[0039] The voltage values ​​of each node in the current operating cycle of the power distribution network at the preset time are obtained. If the voltage value of at least one node exceeds the preset node voltage value range, the first scheduling plan is modified based on a preset correction strategy to obtain the modified second scheduling plan.

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

[0041] The aforementioned 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 distribution networks for air conditioning systems: First, under the current operating cycle of the distribution network for the air conditioning system, the predicted data of 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; next, 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 values ​​of each node in the current operating cycle of the distribution network at the preset time are obtained, and if the voltage value of at least one node 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 operation of the distribution network is controlled based on the second scheduling plan. In the above process, selecting an appropriate operating cycle helps to more accurately predict load and resource output. Inputting this data into the trained scheduling model yields a more precise first scheduling plan. Real-time monitoring of node voltages allows for timely adjustments 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, when the air conditioning system load is high, this method can ensure the efficiency of distribution network regulation. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating a power distribution network energy-saving control method for an air conditioning system in one embodiment.

[0044] Figure 2 This is a schematic diagram of the controlled air conditioning layer in a power distribution network energy-saving control method for an air conditioning system in one embodiment.

[0045] Figure 3 This is a detailed schematic diagram illustrating the steps of a power distribution network energy-saving control method for an air conditioning system in one embodiment;

[0046] Figure 4 This is a schematic diagram of the system architecture for simulation verification in one embodiment;

[0047] Figure 5This is a schematic diagram of the optimal adjustment level of the OLTC after implementing CVR measures in one embodiment;

[0048] Figure 6 This is a schematic diagram of the system voltage after measures were taken in one embodiment;

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

[0050] Figure 8 This is a schematic diagram of the total power reduction of the system after adjusting using a group rotation control strategy in one embodiment;

[0051] Figure 9 This is a schematic diagram of the voltage of each node before and after multi-timescale optimization of the system at 14:00 in one embodiment;

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

[0053] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] In one embodiment, such as Figure 1 As shown, an energy-saving control method for power distribution networks in air conditioning systems is provided. This embodiment illustrates the method by applying it to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0056] Step S102: Under the current operating cycle of the distribution network used for the air conditioning system, obtain the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle.

[0057] Among them, the distribution network is the power network that transmits electrical energy from substations to air conditioning systems, and may include transformers, distribution lines and switching equipment; the operating cycle is the time period during which the distribution network is 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 sources during a specific time period.

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

[0059] Step S104: Input the load power and forecast data into the trained scheduling model to obtain the first scheduling plan for the previous operating cycle of the distribution network.

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

[0061] Step S106: 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 operating cycle.

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

[0063] Step S108: Obtain the voltage values ​​of each node in the current operating cycle of the distribution network at a preset time. If the voltage value of at least one node exceeds the preset node voltage value range, modify the first scheduling plan based on the preset correction strategy to obtain the modified 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 the power generation, changing the load distribution, or introducing backup power sources.

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

[0066] As an example, taking a one-day operating cycle as an example, firstly, the load demand and distributed resource output forecast for the day are predicted. Then, the predicted data is input into the trained scheduling model to obtain the first scheduling plan. Then, the operation of the distribution network is controlled according to the first scheduling plan and the voltage value of each node in the distribution network is monitored 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. The operation of the distribution network is then controlled according to the second scheduling plan.

[0067] In the aforementioned energy-saving control method for distribution networks used in air conditioning systems, firstly, under the current operating cycle of the distribution network used for the air conditioning system, the predicted data of load power and distributed resource output of the previous operating cycle of the distribution network 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; next, 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 values ​​of each node in the current operating cycle of the distribution network at the preset time are obtained, and if the voltage value of at least one node exceeds the preset node voltage value range, the first scheduling plan is corrected based on a pre-set 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 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 node voltage, the first scheduling plan can be corrected in a timely manner 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 correction. Therefore, when the air conditioning system is under high load, the above methods can ensure the control efficiency of the power distribution network.

[0068] In an exemplary embodiment, the power distribution network energy-saving control method for an air conditioning system further includes: acquiring first impact data of the power distribution network before the implementation of preset voltage reduction energy-saving measures in the previous operating cycle; the first impact data includes the node voltage value of at least one 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, acquiring the second load active power and the second load reactive power of the nodes at preset times after the implementation of voltage reduction energy-saving measures in the previous operating cycle.

[0069] Among them, Conservation voltage reduction (CVR) refers to the method of reducing the voltage level of the distribution network to reduce transmission and distribution losses, reduce load power, and achieve energy-saving effects. 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. First load active power represents the active power actually consumed by the node in the previous operating cycle. First load reactive power represents the reactive power used to maintain the stability of the node voltage in the previous operating cycle. Load ratio corresponding to load characteristics includes ZIP (static load model) load ratio. Second load active power and second load reactive power refer to the load power at a preset time after the implementation of voltage reduction energy-saving measures. Preset time refers to the time point selected at a specific time based on load characteristics and distribution network conditions for collecting load power data.

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

[0071] As an example, V i,t V is the voltage at node i after the voltage reduction regulation measure. i,0 The voltage at node i before the voltage reduction regulation measure, P i,t The active power of the first load, Q i,t Let αi, αi, and αpi be the ZIP load ratio of node i, respectively, and let PCVRi,t be the active power of the second load and QCVRi,t be the reactive power of the second load. The expressions corresponding to the above data are as follows:

[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 nodes before implementing voltage reduction energy-saving measures. By comparing the changes in active and reactive power of the load before and after the implementation of voltage reduction 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 to optimize the operation of the distribution network, improve energy utilization efficiency, and also ensure the stability and reliability of the distribution network.

[0074] Further, 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 a preset time, and the load power of at least one node in the node set after implementing voltage reduction energy-saving measures; and determining the minimum daily energy consumption based on the second impact data.

[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 power; 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 certain 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 day's operating cycle after optimized scheduling and voltage reduction measures.

[0076] As an example, Ω L For branch set, Ω N For the set of nodes, r ij The resistance in branch ij is the resistance in at least one branch of the branch set, I. ij,t Let be the current flowing into branch ij at time t, i.e., the input current of at least one branch at a preset time; and let PCVR j,t be the load power of each node after CVR measures are implemented, i.e., the load power of at least one node in the node set after voltage reduction and energy saving measures are implemented. The expression corresponding to the above data is:

[0077]

[0078] In this embodiment, by acquiring the second impact data, the distribution network can gain a more comprehensive understanding of the operating status after the implementation of the voltage reduction and energy-saving measures. Furthermore, 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 dispatch strategy, improving energy utilization efficiency, and reducing energy consumption.

[0079] In one embodiment, the step of determining the minimum daily energy consumption further includes: acquiring 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 power 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 ranges for the voltage values ​​of each node in the node set, the branch currents in the node set, and preset threshold ranges for the branch currents; the distributed resource output constraints are determined based on preset threshold ranges for the distributed generation output power, distributed active power, and distributed reactive power of at least one node in the node set; the reactive power compensation device constraints are determined based on preset threshold ranges for the reactive power compensation amount and compensation capacity of the reactive power compensation device of at least one node in the node set; and the on-load transformer regulation constraints are determined based on the substation voltage before and after on-load transformer regulation, and multiple data corresponding to the on-load transformer regulation level.

[0080] As an example, the system's forward and backward power flow constraints are based on the network branch set Ψ with j as the starting point. b The active power P of the first segment of the branch (j,k) with branch j is... j,k The active power P of the load at node j L,j The set of network branches Ψ ending with j c The active power P of the first segment of branch (i,j) i,j The reactive power Q of the first segment 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 at node j DG,j The reactive power Q of the first segment of the branch (j,k) with branch j as the first segment. j,k The reactive power Q of the load at node j L,j The reactance x of branch (i,j) i,j The reactive power Q emitted by the DG at node j is determined. DG,j The specific expression is:

[0081]

[0082] More specifically, node voltage and branch current constraints are determined based on preset threshold ranges for the voltage values ​​of each node in the node set, the branch currents in the node set, and preset threshold ranges for the branch currents, where V imin With V imax These are the upper and lower limits of the voltage at each node, i.e., the preset threshold range of the voltage value at each node; I ij Let I be the current between branches ij, i.e., the branch current in the node set; ijmin with I ijmax These represent the upper and lower limits of the current in each branch, i.e., the preset threshold range of the branch current, and their specific expressions are as follows:

[0083]

[0084] Furthermore, the distributed resource output constraint is determined based on the distributed generation output power of at least one node in the node set, a preset threshold range for distributed active power, and a preset threshold range for distributed reactive power, where P DG,i Let be the power output of the DG at node i, i.e., the distributed generation power output of at least one node; PminDG,i and PmaxDG,i are the upper and lower limits of the active power output of each node's DG, i.e., the preset threshold range of distributed active power; QminDG,i and QmaxDG,i are the upper and lower limits of the reactive power output of each node's DG, i.e., the preset threshold range of distributed reactive power, and their specific expressions are as follows:

[0085]

[0086] Furthermore, the reactive power compensation device constraint is determined based on a preset threshold range of the reactive power compensation amount of the reactive power compensation device at least one node in the node set and the compensation capacity of the reactive power compensation device, wherein Q C,mLet Cm be the reactive power compensation amount of the reactive power compensation device at node m, i.e., the reactive power compensation amount of the reactive power compensation device at at least one node; QminCm and QmaxCm are the minimum and maximum values ​​of the compensation capacity of the reactive power compensation device at node m, i.e., the preset threshold range of the compensation capacity of the reactive power compensation device, and their specific expressions are as follows:

[0087]

[0088] Furthermore, the on-load transformer regulation constraints are determined based on the substation voltage before and after on-load transformer regulation, as well as multiple data points corresponding to the on-load transformer regulation taps, where V ss,1 This refers to the substation voltage after OLTC regulation, i.e., the substation voltage before and after on-load transformer regulation; multiple data points corresponding to the on-load transformer regulation settings include: the substation voltage V before OLTC regulation. ss,0 OLTC adjustment level λ, OLTC adjustment voltage ω for each level, OLTC adjustment level upper and lower limits λ min With λ max OLTC adjustment times ξ λ OLTC maximum number of adjustments ξ 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 safe range, reducing power quality issues; by constraining the output of distributed generation, energy is rationally allocated, improving resource utilization efficiency; by comprehensively considering the above constraints, the daily energy consumption of the distribution network can be effectively reduced, achieving a dual improvement in economic and environmental benefits.

[0091] More specifically, in one embodiment, the first scheduling plan is modified based on a pre-set modification strategy to obtain a modified second scheduling plan, including: based on the first scheduling plan, a group-based rotation control strategy is adopted to regulate the air conditioning system; the first scheduling plan, adopting a group-based rotation control strategy to regulate the air conditioning system, includes: in the first-level group-based 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 markings, and regulate the temperature of the multiple air conditioners to the maximum value of the preset temperature range; in the second-level group-based rotation control strategy, multiple air conditioners in the same group are divided into multiple subgroups according to the single controlled duration and controlled time interval of multiple air conditioners in the same group, so that the distribution network can rotate and regulate the multiple subgroups according to a preset time interval and a preset power adjustment strategy.

[0092] As an example, such as Figure 2As shown, the total number of controlled air conditioners includes a first layer and a second layer. In the first layer grouping strategy, based on the preset initial temperature, the air conditioning cluster consisting of N controllable air conditioners is divided into different groups, labeled as S1, S2...S... n Assuming the human body's comfortable temperature perception range [T] min T max [This refers to a preset temperature range, where all air conditioners are uniformly set to temperature T after being regulated.] max This refers to the maximum value within the preset temperature range. Therefore, air conditioning units with the same initial set temperature will operate synchronously at the lowest possible frequency, ensuring consistent control timing. During demand response periods, all air conditioning units will be simultaneously controlled, collectively reducing to their minimum operating power.

[0093] More specifically, in the second-level grouping strategy, to balance user comfort, a rotating control strategy is implemented for air conditioners within the same group. Taking group S1 as an example, assuming the single controlled duration of the inverter air conditioners in the group is Δt, and the controlled time interval for each air conditioner is set to φ, the inverter air conditioners in this group can be divided into φ / Δt subgroups for rotating control. Specifically, S... 11 Subgroup 1 reduces power to a minimum during the first Δt period and restores it to normal operating power during the second Δt period; Subgroup 2 maintains normal power during the first Δt period, reduces power during the second Δt period, and then restores stable operating power during the third Δt period; S 13 ~S 1n The subgroups follow the same pattern, taking turns to regulate according to predetermined 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 start-up and shutdown of air conditioners can be reduced, energy consumption can be lowered, and energy utilization efficiency can be improved. The rotation control strategy can ensure that air conditioners in the same group take turns cooling at different time periods, avoiding user discomfort caused by simultaneous cooling. The unified set temperature and synchronous control strategy ensure the consistency of control time for all air conditioners, simplifying the management process and improving the effectiveness of control. Therefore, through hierarchical and refined group control, not only can the adjustment effect of air conditioning load 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 modified based on a preset modification strategy, including: obtaining the voltage sensitivity vector between at least one node and the remaining nodes in the distribution network at the current time; determining the coupling degree between at least one node and the remaining nodes based on the voltage sensitivity vector; and modifying the first scheduling plan according to the coupling degree.

[0096] As an example, real-time monitoring of the distribution network's operation is performed daily. When a voltage exceedance occurs, an optimized daily operation strategy is adopted. Based on the electrical distance between nodes, distributed resources with strong coupling are selected for adjustment to achieve rapid recovery of node voltage. In a distribution system containing m nodes, the voltage amplitude change ΔU at each node satisfies the following relationship with the changes in active power ΔP and reactive power ΔQ:

[0097]

[0098]

[0099] Where ΔP and ΔQ are the changes in active power and reactive power injected at the node, respectively; This represents the change in the node voltage amplitude per unit of active power injected into the node; This represents the change in the node voltage amplitude per unit of reactive power injected into the node.

[0100] Therefore, according to the above expression, changes in the injected power at each node will affect the voltage of a single node. When the voltage of a node exceeds its limit, the voltage sensitivity vector between that 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 more flexible and adjustable resources of that node become the priority control targets. The distribution network optimization objective will change from minimizing electricity consumption to minimizing the reverse flow of active and reactive power injected by flexible and adjustable resource nodes to achieve rapid voltage recovery, thereby enhancing the stability of grid operation. The original constraints of the mathematical model remain unchanged, and the objective function is set as follows:

[0101]

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

[0103] In this embodiment, by implementing the first and second layer grouping strategies, the air conditioning cluster control not only optimizes the energy efficiency, but also integrates the distribution network energy-saving control technology of voltage and air conditioning active regulation, thus 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 an energy-saving control method for power distribution networks used in air conditioning systems. To better understand the process of the above-described energy-saving control method for power distribution networks used in air conditioning systems, combined with... Figure 3 As shown below, the specific process of a power distribution network energy-saving control method for air conditioning systems according to this application is described in detail, including the following steps:

[0105] Step S302: Obtain the predicted 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 the day-ahead dispatch plan.

[0107] Step S306: Develop a grouped rotation control strategy for variable frequency air conditioners.

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

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

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

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

[0112] As an example, a simulation verification was performed using an improved IEEE 33-bus system, with the system structure as follows: Figure 4As shown, the system voltage reference value is 12.66kV, the power reference value is 1MVA, and the total active power and reactive power of the system are 3715kW and 2300kVar (Kilovolt-Ampere Reactive), respectively. The allowable fluctuation range of node voltage is [0.94, 1.06] pu (per unit). The maximum branch current is set to 500A. The OLTC is connected to the branch of node 1 connected to the upper-level grid, with 12 adjustment levels, an adjustment step size of 0.01, an adjustment range of [0.94, 1.06], and a maximum number of adjustments of 5. The SVC (Static Var Compensator) is connected to nodes 6, 16, and 32, with a reactive power adjustment range of [-100kVar, 300kVar]. The capacitor bank (Capacitor) Bank (CB) access nodes 6 and 16, with a maximum of 10 groups in operation, each group 100kVar, and a maximum switching frequency of 5; energy storage access nodes 16 and 33, both with a rated capacity of 2000kWh, rated active power of 300kW and 200kW respectively, capacity upper and lower limits of 90% and 20%, and charge / discharge efficiency of 0.9; wind turbine access nodes 18 and 33, both with a capacity of 1000kW; considering the high proportion of air conditioning load in summer, which is approximately a constant power load, this invention sets the ZIP load model ratio of each node to 3:2:5; based on the total power demand of the system, it is assumed that 90 controllable variable frequency air conditioners are connected to each of 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 a distribution network energy-saving control technology that integrates voltage and air conditioning active regulation to optimize the energy saving of the distribution network system, and obtains the optimal OLTC adjustment level and system voltage after taking CVR measures as follows. Figure 5 and Figure 6 As shown, the total power requirement of the system is as follows: Figure 7 As shown, the total system power before CVR optimization and the total system power after CVR optimization are included.

[0113] from Figure 6 It can be seen that the per-unit voltage values ​​of each node after optimization are still above 0.94, meeting the system power supply voltage standard. The system daily energy consumption before optimization was 54.7565 MW·h, and the system daily energy consumption after optimization is 53.2772 MW·h (Note: These two data are relative to...). Figure 7(The figure is obtained by integrating the bar chart), resulting in a 2.701% reduction in daily energy consumption. Since the load output factor is greater than 0.9 between 19:00 and 22:00, which is the peak summer load period, a variable frequency air conditioner grouping and rotation control strategy was adopted to further reduce the total power demand during this period. The air conditioners were grouped according to their initial set temperature and controlled duration, and the set temperatures of different groups of variable frequency air conditioners were adjusted sequentially to their maximum set temperatures. The total power reduction of the adjusted system is shown below. Figure 8 As shown.

[0114] More Figure 8 This includes the original power demand, the power demand after CVR optimization, and the power demand after CVR and air conditioning control. Figure 8 It can be seen that during the period from 19:00 to 22:00, the original system 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 users' 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%. The above results show that, under the condition of sufficient voltage margin, the multi-time-scale optimization strategy for distribution networks considering CVR and air conditioning load regulation proposed in this invention can effectively reduce the total system energy consumption and achieve peak load reduction.

[0115] To further verify the feasibility of the proposed strategy during voltage over-limit periods, it is assumed that at 14:00, there is a significant deviation between the daytime load forecast and the actual daytime load, with the output factor increasing sharply from 0.68 to 1.5, leading to a surge in load power demand at each node of the distribution network and causing the system voltage to drop below the safe operating range. In this scenario, the intraday optimized operation strategy responds rapidly, increasing the OLTC level and optimizing distributed resources based on electrical distance to achieve rapid voltage recovery and ensure optimal power control of the controlled resources. The voltages of each node before and after multi-timescale optimization at 14:00 are shown below. Figure 9 As shown, this 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, such as Figure 9 As shown, the voltage of all nodes has been restored to the specified range. Compared with the initial CVR optimization strategy, the intraday optimization operation strategy adjusts the OLTC level from -4 to +5. At the same time, the SVC reactive power 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 scheduling plan, effectively reduce the dependence on real-time scheduling correction, and thus optimize the overall operating efficiency of the system.

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

[0118] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

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

[0120] In one exemplary embodiment, such as Figure 10 As shown, a power 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 predicted data of load power and distributed resource output of the distribution network in the previous operating cycle of the distribution network used for the air conditioning system under the current operating cycle.

[0122] The data processing module 1002 is used to input load power and forecast data into the trained scheduling model to obtain the first scheduling plan for the previous operating 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 operating cycle.

[0124] The correction module 1004 is used to obtain the voltage values ​​of each node in the current operating cycle of the distribution network at a preset time. If the voltage value of at least one node exceeds the preset node voltage value range, the first scheduling plan is corrected based on a preset correction strategy to obtain the 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 acquire first impact data of the distribution network before the implementation of preset voltage reduction energy-saving measures in the previous operating cycle; the first impact data includes the node voltage value of at least one 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 after the implementation of voltage reduction energy-saving measures are acquired at preset times.

[0127] Furthermore, in one embodiment, the data processing module 1002 is also used to acquire 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 a preset time, and the load power of at least one node in the node set after implementing voltage reduction energy-saving measures; and determines the minimum daily energy consumption based on the second impact data.

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

[0129] Furthermore, in one embodiment, the correction module 1004 is further configured 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-based rotation control strategy to regulate the air conditioning system; the first scheduling plan adopting a group-based rotation control strategy to regulate the air conditioning system includes: in the first-level group-based rotation control strategy, dividing multiple air conditioners into different groups and marking them according to a preset initial temperature, so that the distribution network can synchronously regulate multiple air conditioners according to the markings, and regulate the temperature of multiple air conditioners to the maximum value of a preset temperature range; in the second-level group-based rotation control strategy, dividing multiple air conditioners in the same group into multiple subgroups according to the single controlled duration and controlled time interval of multiple air conditioners in the same group, so that the distribution network can rotate and regulate multiple subgroups according to a preset time interval and a 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 at the current time; determine the coupling degree between at least one node and the remaining nodes based on the voltage sensitivity vector; and correct the first scheduling plan according to the coupling degree.

[0131] The modules in the aforementioned power distribution network energy-saving control device for air conditioning systems can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0132] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores energy-saving control data for the power distribution network of the air conditioning system. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an energy-saving control method for the power distribution network of an air conditioning system.

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

[0134] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0135] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

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

[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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0138] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, 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 many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0139] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A power distribution network energy-saving control method for air conditioning systems, characterized in that, The method includes: Under the current operating cycle of the distribution network used for air conditioning systems, obtain the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle; The load power and the predicted data are input into the trained scheduling model to obtain the first scheduling plan for the previous operating cycle of the distribution network; the objective function of the trained scheduling model is the minimum daily energy consumption of the distribution network. The steps for determining the minimum daily energy consumption include: The system acquires second impact data and multiple constraints 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 the at least one branch at a preset time, and the load power of at least one node in the node set after implementing voltage reduction and energy-saving measures. The multiple constraints include system forward and backward power flow constraints, node voltage and branch current constraints, distributed resource output constraints, reactive power 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 based on multiple data corresponding to at least one node in the node set. The preset threshold ranges for voltage values ​​at each node, the branch currents in the node set, and the preset threshold ranges for the branch currents are determined; the distributed resource output constraints are determined based on the preset threshold ranges for distributed generation output power, distributed active power, and distributed reactive power of at least one node in the node set; the reactive power compensation device constraints are determined based on the preset threshold ranges for the reactive power compensation amount of the reactive power compensation device of at least one node in the node set and the compensation capacity of the reactive power compensation device; the on-load transformer regulation constraints are determined based on the substation voltage before and after on-load transformer regulation, and multiple data corresponding to the on-load transformer regulation levels. Based on the second impact data and the multiple constraints, the minimum daily energy consumption is determined; Obtain the scheduling plan value of 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 operating cycle; The voltage values ​​of each node in the current operating cycle of the distribution network at the preset time are obtained. If the voltage value of at least one node exceeds the preset node voltage value range, the first scheduling plan is modified based on a preset correction strategy to obtain a modified second scheduling plan. The operation of the distribution network is controlled based on the second scheduling plan.

2. The method according to claim 1, characterized in that, The method further includes: The first impact data of the distribution network before the pre-set voltage reduction energy-saving measures were implemented in the previous operating cycle were obtained respectively; the first impact data includes the node voltage value of at least one 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 at the preset time are obtained respectively after the node implements the voltage reduction and energy saving measures in the previous operating cycle.

3. The method according to claim 1, characterized in that, The step of revising the first scheduling plan based on a preset revision strategy to obtain a revised second scheduling plan includes: Based on the first scheduling plan, a group-based round-robin control strategy is adopted to regulate the air conditioning system; The first scheduling plan employs a group-based round-robin control strategy to regulate the air conditioning system, including: In the first-level grouping and control strategy, multiple air conditioners are divided into different groups and marked according to the preset initial temperature, so that the power distribution network can synchronously regulate the multiple air conditioners according to the markings and regulate the temperature of the multiple air conditioners to the maximum value of the preset temperature range. In the second-level grouping and rotational control strategy, the multiple air conditioners in the same group are divided into multiple subgroups according to the single controlled duration and controlled time interval of the multiple air conditioners in the same group, so that the power distribution network can take turns controlling the multiple subgroups according to the preset time interval and preset power adjustment strategy.

4. The method according to claim 1, characterized in that, The step of correcting the first scheduling plan based on a preset correction strategy when at least one of the node voltage values ​​exceeds a preset node voltage value range includes: Obtain the voltage sensitivity vector between at least one node in the distribution network and the remaining nodes at the current time. Based on the voltage sensitivity vector, the degree of coupling between the at least one node and the remaining nodes is determined; The first scheduling plan is modified based on the degree of coupling.

5. An energy-saving control device for power distribution networks in air conditioning systems, characterized in that, The device includes: The data acquisition module is used to acquire the predicted data of load power and distributed resource output of the distribution network in the previous operating cycle of the distribution network used for the air conditioning system under the current operating cycle. The data processing module is used to input the load power and the predicted data into a trained scheduling model to obtain a first scheduling plan for the previous operating cycle of the distribution network. The objective function of the trained scheduling model is the minimum daily energy consumption of the distribution network. The steps for determining the minimum daily energy consumption include: acquiring second influence data and multiple constraints of the distribution network; the second influence data includes a branch set, a node set, the resistance of at least one branch in the branch set, the input current of the at least one branch at a preset time, and the load power of at least one node in the node set after implementing voltage reduction and energy-saving measures; the multiple constraints include system forward and backward power flow constraints, node voltage and branch current constraints, distributed resource output constraints, reactive power compensation device constraints, and on-load transformer regulation constraints; the system forward and backward power flow constraints are based on at least one node in the node set. Multiple data points corresponding to a node are determined; the node voltage and branch current constraints are determined based on preset threshold ranges for the voltage values ​​of each node in the node set, the branch currents in the node set, and the preset threshold ranges for the branch currents; the distributed resource output constraints are determined based on preset threshold ranges for the distributed generation output power, distributed active power, and distributed reactive power of at least one node in the node set; the reactive power compensation device constraints are determined based on preset threshold ranges for the reactive power compensation amount and compensation capacity of the reactive power compensation device of at least one node in the node set; the on-load transformer regulation constraints are determined based on the substation voltage before and after on-load transformer regulation, and multiple data points corresponding to the on-load transformer regulation levels; the minimum daily energy consumption is determined based on the second influence data and the multiple constraints. The first control module is used to obtain the scheduling plan value of the preset time in the first scheduling plan, and control the distribution network to operate at the preset time corresponding to the current operating cycle based on the scheduling plan value; The correction module is used to obtain the voltage values ​​of each node in the current operating cycle of the distribution network at the preset time, and when at least one node voltage value exceeds the 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.

6. The apparatus according to claim 5, characterized in that, The data acquisition module is also used to acquire the first impact data of the distribution network before the pre-set voltage reduction energy saving measures are implemented in the previous operating cycle; the first impact data includes the node voltage value, first load active power, first load reactive power of at least one node in each node, 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 at the preset time are obtained respectively after the node implements the voltage reduction and energy saving measures in the previous operating cycle.

7. The apparatus according to claim 5, characterized in that, The correction module is also used to regulate the air conditioning system based on the first scheduling plan by adopting a group-based round-robin control strategy; The first scheduling plan adopts a group-based rotation control strategy to regulate the air conditioning system, including: in the first-level group-based rotation control strategy, multiple air conditioners are divided into different groups and marked according to a preset initial temperature, so that the power distribution network can synchronously regulate the multiple air conditioners according to the markings, and regulate the temperature of the multiple air conditioners to the maximum value of the preset temperature range; in the second-level group-based rotation control strategy, multiple air conditioners in the same group are divided into multiple subgroups according to the single controlled duration and controlled time interval of multiple air conditioners in the same group, so that the power distribution network can rotate and regulate the multiple subgroups according to a preset time interval and a preset power adjustment strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images