Air conditioner cold storage electric power intelligent scheduling method for virtual power grid transaction

Abstract

The invention relates to the technical field of power dispatching, in particular to an air conditioner cold storage power intelligent dispatching method for virtual power grid transaction. According to the method, the periodically acquired data information is preprocessed, so that time synchronization of the data information can be realized, and the acquired data is more effective; and environment modeling is completed based on the preprocessed data information, so that the change of the state is represented more accurately by using the environment modeling based on the periodically updated data information, and the scheduling proportion output after the environment modeling is input to the deep reinforcement learning agent is more accurate. And the dispatching state of the electric power is determined based on the cold storage characterization value, and relevant parameters are adjusted based on the dispatching state, so that the dispatching of the cold storage and transaction electric quantity is more effective. According to the invention, the problem of low power dispatching efficiency caused by the fact that the electric quantity for cold storage and transaction cannot be reasonably dispatched in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the technical field of power dispatching, and in particular to a smart dispatching method for air conditioning cold storage power for virtual grid trading. Background Technology

[0002] With the deepening of power market reform and the increasing penetration of new energy sources, virtual grid trading has become a key means of balancing power supply and demand. Air conditioning cold storage technology, with its load regulation potential, is being integrated into this system through intelligent dispatch. The core background of this technology can be summarized in three aspects: First, the demand for flexible resources in the power system has surged, with air conditioning load accounting for more than 30% of peak electricity consumption; its cold storage characteristics can achieve load transfer within 6-8 hours. Second, breakthroughs in virtual power plant aggregation technology enable distributed resources to participate in spot market trading. Third, the development of intelligent algorithms has shortened the response time of air conditioning cold storage systems from hours to minutes, achieving optimal operating strategies in conjunction with electricity price signals.

[0003] Chinese Patent Publication No. CN112032882B discloses a scheduling method for an ice storage air conditioning system, comprising: acquiring real-time system operation data, load forecast data, equipment operation and maintenance plan data, and system equipment parameters; determining the boundary conditions for optimized scheduling; performing optimized scheduling calculations using a pre-determined optimized scheduling model, with the goal of minimizing system operating costs during the scheduling period, based on the boundary conditions for optimized scheduling, to obtain the hourly start-up number of base-load units and dual-condition units, as well as the hourly load of ice melting; determining the load level during the optimized period based on the optimized scheduling results; and adjusting the equipment start-up and shutdown periods according to a preset equipment start-up and shutdown adjustment strategy and the determined load level, in order to reduce the number of equipment start-ups and shutdowns during the optimized period.

[0004] It is evident that existing technologies have the following problems: they cannot rationally allocate electricity for cold storage and trading, resulting in low power dispatch efficiency. Summary of the Invention

[0005] Therefore, this invention provides an intelligent dispatching method for air conditioning cold storage power for virtual grid trading, in order to overcome the problem that the power used for cold storage and trading cannot be reasonably dispatched in the prior art, resulting in low power dispatching efficiency.

[0006] To achieve the above objectives, the present invention provides a method for intelligent dispatching of air conditioning cold storage power for virtual grid trading, comprising: Periodically acquire data information, including power generation data, cold storage status, load data, environmental parameters, and electricity price information; The acquired data information is preprocessed to enable time synchronization and create a unified timestamp. Construct a single-cycle environment model using preprocessed data; The environmental model for each cycle is input into a deep reinforcement learning agent, and the scheduling ratio of energy storage and electricity sales corresponding to the cycle is output. Deployment is carried out based on the scheduling ratio, and the cold storage characterization value is calculated within a preset time after deployment. The cold storage characterization value is the average value of the cold storage capacity ratio over multiple cycles, and the cold storage capacity ratio is the ratio of the current actual cold storage capacity to the total cold storage capacity that the cold storage tank can store. The scheduling status is determined by using the cold storage characterization value, and the scheduling ratio is adjusted based on the scheduling status. If the adjusted scheduling status is not qualified, the scheduling ratio or the cold release rate of the cold storage equipment is determined based on the plotted power-cycle curve.

[0007] Furthermore, when the scheduling state is determined to be the first state based on the cold storage characterization value, the proportion of traded electricity in the electricity sales is calculated; if the proportion of traded electricity is less than the preset traded electricity proportion, the scheduling ratio is adjusted based on the difference between the preset traded electricity proportion and the proportion of traded electricity; wherein, the first state is the state corresponding to when the cold storage characterization value is less than the preset average value, and the proportion of traded electricity is the ratio of sold electricity to recycled electricity.

[0008] Furthermore, the scheduling ratio is increased based on the difference between the preset transaction electricity ratio and the already traded electricity ratio, and the increase in the scheduling ratio is proportional to the difference.

[0009] Furthermore, the scheduling status after adjusting the scheduling ratio is re-detected. If the scheduling status is the first status, the scheduling ratio is adjusted at least once until the number of adjustments is less than the preset number and the scheduling status is the first status or the number of adjustments is equal to the preset number, at which point the adjustment is stopped. The scheduling status after the adjustment is stopped is detected. If the scheduling status is the first status, the sold electricity-cycle curve is plotted, and the corresponding adjustment method is determined based on whether the curve has regularity.

[0010] Furthermore, the process of determining the corresponding adjustment method based on whether the curve has a regularity includes: using an adaptive function to determine whether the curve has a regularity; if the curve has a regularity, then calculating the curve slope; and adjusting the scheduling ratio based on the curve slope.

[0011] Furthermore, the scheduling ratio is increased based on the slope of the curve, and the increase in the scheduling ratio is inversely proportional to the slope of the curve.

[0012] Furthermore, the process of determining the corresponding adjustment method based on whether the curve has regularity also includes: if the curve does not have regularity, the cold release rate of the cold storage device is reduced based on the difference between the preset average value and the cold storage characterization value, and the reduction in the cold release rate is proportional to the difference.

[0013] Furthermore, the cooling time is increased based on the cooling rate, and the increase in cooling time is inversely proportional to the cooling rate.

[0014] Furthermore, the scheduling status after adjusting the cooling release time is re-checked. If the scheduling status is the first state, the variance of the proportion of cold storage capacity in multiple cycles is calculated. If the variance is less than the preset variance, the cooling power is increased based on the ratio of the variance to the preset variance, and the increase in cooling power is inversely proportional to the ratio.

[0015] Furthermore, the scheduling status after adjusting the cooling release time is re-checked. If the scheduling status is the first state, the data acquisition cycle is reduced based on the difference between the preset cold storage capacity ratio and the cold storage capacity ratio, and the reduction in cycle is proportional to the difference.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: By preprocessing periodically acquired data, this invention enables time synchronization of the data, making the acquired data more effective; and by performing environmental modeling based on the preprocessed data, it allows for a more accurate representation of state changes using periodically updated data, resulting in a more accurate scheduling ratio output after inputting the environmental model into the deep reinforcement learning agent; and by determining the power scheduling state based on cold storage characterization values ​​and adjusting relevant parameters based on the scheduling state, the scheduling of cold storage and trading power becomes more efficient. This invention solves the problem of low power scheduling efficiency in existing technologies due to the inability to rationally schedule power used for cold storage and trading.

[0017] Furthermore, by determining whether to adjust the dispatch ratio based on the proportion of traded electricity in the electricity sales when the dispatch state is determined to be in the first state, the present invention can more accurately determine the reason for the dispatch state being in the first state and more accurately determine whether to adjust the dispatch ratio, thereby more rationally dispatching the electricity used for cold storage and trading, and further improving the efficiency of power dispatch.

[0018] Furthermore, the present invention adjusts the dispatch ratio based on the difference between the preset trading electricity ratio and the already traded electricity ratio, which can more effectively adjust the dispatch ratio, thereby more rationally dispatching the electricity used for cold storage and trading, and further improving the efficiency of power dispatch.

[0019] Furthermore, this invention, by repeatedly adjusting the scheduling ratio and when the scheduling state is in the first state, determines the corresponding adjustment method based on whether the plotted electricity sales-cycle curve has regularity. This allows for a more accurate determination of the corresponding adjustment method based on the regularity of the electricity sales, and enables more effective subsequent adjustments. This results in a more rational scheduling of electricity used for cold storage and trading, thereby further improving power dispatch efficiency.

[0020] Furthermore, by adjusting the dispatch ratio based on the slope of the electricity sold-period curve when the curve is regular, this invention can more accurately adjust the dispatch ratio when the electricity sold ratio is periodic, thereby more rationally dispatching the electricity used for cold storage and trading, and further improving the efficiency of power dispatch.

[0021] Furthermore, by adjusting the release rate of the cold storage device based on the difference between the preset average value and the cold storage characterization value when the curve is not regular, the present invention can reduce energy consumption and further reduce the electricity used for cold storage when the room temperature is close to the target value, thereby improving the cold storage characterization value and further improving the efficiency of power dispatch.

[0022] Furthermore, by adjusting the cooling release time through the cooling release rate, the present invention can further reduce energy consumption through more accurate cooling release time, thereby further reducing the electricity used for cold storage, improving the cold storage performance value, and further improving power dispatch efficiency.

[0023] Furthermore, this invention adjusts the cooling power based on the ratio of the variance of the cold storage capacity ratio over multiple cycles to a preset variance. This enables the cold storage system to more effectively balance the power load and cooling demand when the power demand is consistently much greater than the cold storage capacity, thereby further improving the efficiency of power dispatch.

[0024] Furthermore, the present invention adjusts the data acquisition cycle based on the difference between the preset cold storage capacity ratio and the cold storage capacity ratio. This allows for a more accurate capture of data changes through a more precise data acquisition cycle, thereby making the subsequently determined scheduling ratio more accurate and further improving power dispatch efficiency. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of the structure of an intelligent dispatching system for air conditioning cold storage power for virtual power grid transactions according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the steps of an intelligent dispatching method for air conditioning cold storage power for virtual grid trading according to an embodiment of the present invention. Figure 3 This is a flowchart illustrating the steps for determining the comparison results between the cold storage characterization value and the preset average value in an embodiment of the present invention. Figure 4 This is a flowchart illustrating the steps of generating a corresponding processing method based on the scheduling state after repeated adjustment of the scheduling ratio in an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0027] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0028] It should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0029] Please see Figure 1 As shown, it is a structural schematic diagram of an intelligent dispatching system for air conditioning cold storage power used in virtual power grid transactions according to an embodiment of the present invention.

[0030] The system includes a data acquisition unit, a data preprocessing unit, an environment modeling unit, a scheduling ratio output unit, a calculation unit, and an analysis unit.

[0031] The data acquisition unit is used to periodically acquire data information, including power generation data, cold storage status, load data, environmental parameters, and electricity price information; The data preprocessing unit is connected to the data acquisition unit and is used to preprocess the acquired data information so that the acquired data information can be synchronized in time and a unified timestamp can be created. The environment modeling unit is connected to the data preprocessing unit, and it is used to construct a single-cycle environment model using the preprocessed data information. The scheduling ratio output unit is connected to the environment modeling unit, and is used to input the environment modeling of each cycle into the deep reinforcement learning agent and output the scheduling ratio of energy storage and power sales corresponding to the cycle. The calculation unit is connected to the scheduling ratio output unit, and is used to deploy based on the scheduling ratio and calculate the cold storage characterization value within a preset time after deployment. The cold storage characterization value is the average value of the cold storage capacity ratio over multiple cycles, and the cold storage capacity ratio is the ratio of the current actual cold storage capacity to the total cold storage capacity that the cold storage tank can store. The analysis unit is connected to the calculation unit. It is used to determine the scheduling state using the cold storage characterization value, adjust the scheduling ratio based on the scheduling state, and determine whether to adjust the scheduling ratio or the cold release rate of the cold storage equipment based on the plotted power-cycle curve if the adjusted scheduling state is not qualified.

[0032] Specifically, the process of constructing environmental modeling involves using preprocessed data to build a state space, action space, and reward function for a single cycle to complete environmental modeling for each cycle. This process includes: constructing the state space by integrating preprocessed data and defining system state vectors, such as current cooling capacity, electricity price periods, and load forecasts; setting executable operations in the action space, such as starting and stopping the cooling system and adjusting power levels; and setting multi-objective optimization indicators in the reward function, such as economic benefits from electricity price differences and grid friendliness contributed by peak shaving and valley filling. This process is existing technology and will not be elaborated further.

[0033] Please see Figure 2 The diagram shown is a flowchart of the steps of the intelligent dispatching method for air conditioning cold storage power for virtual power grid transactions according to an embodiment of the present invention.

[0034] The specific steps of the intelligent dispatching method for air conditioning cold storage power used in virtual grid trading are as follows: S1 periodically acquires data information through the data acquisition unit, including power generation data, cold storage status, load data, environmental parameters, and electricity price information; S2, the acquired data information is preprocessed by the data preprocessing unit connected to the data acquisition unit so that the acquired data information is time-synchronized and a unified timestamp is created; S3, the environment modeling unit connected to the data preprocessing unit constructs a single-cycle environment model using the preprocessed data information; S4, the environment modeling of each cycle is input to the deep reinforcement learning agent through the scheduling ratio output unit connected to the environment modeling unit, and the scheduling ratio of energy storage and power sales corresponding to the cycle is output. S5, the calculation unit connected to the scheduling ratio output unit deploys based on the scheduling ratio and calculates the cold storage characterization value within a preset time after deployment, wherein the cold storage characterization value is the average value of the cold storage capacity ratio over multiple cycles, and the cold storage capacity ratio is the ratio of the current actual cold storage capacity to the total cold storage capacity that the cold storage tank can store. S6, the analysis unit connected to the computing unit uses the cold storage characterization value to determine the scheduling state, and adjusts the scheduling ratio based on the scheduling state. If the adjusted scheduling state is not qualified, it determines whether to adjust the scheduling ratio or the cold release rate of the cold storage device based on the plotted power-cycle curve.

[0035] Please see Figure 3 The diagram shows a flowchart illustrating the steps of determining the cold storage characterization value based on a comparison with a preset average value in an embodiment of the present invention. When the scheduling state is determined to be in the first state based on the cold storage characterization value, the proportion of traded electricity in the electricity sales is calculated. If the proportion of traded electricity is less than a preset traded electricity proportion, the scheduling ratio is adjusted based on the difference between the preset traded electricity proportion and the proportion of traded electricity. Here, the first state is the state corresponding to when the cold storage characterization value is less than the preset average value, and the proportion of traded electricity is the ratio of sold electricity to recycled electricity.

[0036] Specifically, if the preset average value L0 = 0.3, the comparison process between the cold storage characterization value L and the preset average value L0 is as follows: If the cold storage characterization value L is greater than or equal to the preset average value L0, it indicates that the remaining cold storage capacity in the cold storage tank is sufficient, that is, the scheduling ratio setting is qualified, and the scheduling status is qualified. If the cold storage characterization value L is less than the preset average value L0, it indicates that the remaining cold storage capacity in the cold storage tank is low, that is, the dispatch ratio setting is too low and the dispatch status is unqualified. Then, the dispatch status is marked as the first status, and the proportion of traded electricity in the electricity sales is calculated. If the proportion of traded electricity is less than the preset traded electricity ratio, it indicates that the electricity consumption is high and the electricity sold is low, so there is a problem with the dispatch ratio. Therefore, the dispatch ratio is adjusted based on the difference between the preset traded electricity ratio and the traded electricity ratio.

[0037] Specifically, if the preset difference P0 between the preset transaction volume ratio and the already traded volume ratio is 0.1, then the comparison process between the preset difference P and the preset difference P0 is as follows: If the difference P between the preset transaction volume ratio and the already traded volume ratio is less than or equal to the preset difference P0, the scheduling ratio will be adjusted to 1.3 times the original scheduling ratio. If the difference P between the preset transaction volume ratio and the already traded volume ratio is greater than the preset difference P0, the scheduling ratio will be adjusted to 2.1 times the original scheduling ratio.

[0038] Please see Figure 4 The diagram shows the steps of generating a corresponding processing method based on the scheduling state after repeated adjustment of the scheduling ratio in an embodiment of the present invention. In this embodiment, the scheduling state after adjusting the scheduling ratio is re-detected. If the scheduling state is the first state, the scheduling ratio is repeatedly adjusted at least once until the number of adjustments is less than a preset number and the scheduling state is the first state, or the number of adjustments equals the preset number, at which point the adjustment stops. The scheduling state after stopping the adjustment is detected. If the scheduling state is the first state, the sold electricity volume-cycle curve is plotted, and the corresponding adjustment method is determined based on whether the curve has a regularity.

[0039] Specifically, after adjusting the dispatch ratio, the dispatch status is re-checked. If the dispatch status is in the first state, i.e., the dispatch status is unqualified, the dispatch ratio is adjusted again. After stopping the adjustment, if the dispatch status is still in the first state, the sold electricity-cycle curve is plotted. Based on whether the curve has regularity, it is determined whether the sold electricity has regularity, so as to more accurately determine the reason for the unqualified dispatch status.

[0040] Specifically, the process of determining whether a curve exhibits regularity using an adaptive function includes: first, dynamically normalizing the time-series electricity sales data; then, using variable bandwidth kernel density estimation to adaptively adjust the smoothing parameters, narrowing the bandwidth during peak electricity price periods to capture fluctuation details, and widening the bandwidth during off-peak periods to enhance trend characteristics. Next, a two-dimensional verification system is constructed: first, in the time dimension, instantaneous periodic components are extracted using an improved Local Mean Decomposition (LMD); when the contribution rate of the main periodic component exceeds 70%, a significant regularity is determined; second, in the spatial dimension, fractal dimension analysis (FD>1.5 indicates strong regularity) is used, combined with a change point detection algorithm to identify abnormal fluctuations. Finally, a comprehensive judgment is made based on entropy values ​​(approximate entropy <0.2) and dynamic thresholds (fluctuation coefficient <15%). This process is existing technology and will not be elaborated further.

[0041] Specifically, if the electricity sales-cycle curve is regular, the slope of the curve is calculated, and the dispatch ratio is adjusted based on the curve slope. The preset slope Q0 = 0. The comparison process between the curve slope Q and the preset slope Q0 is as follows: If the curve slope Q is less than or equal to the preset slope Q0, the scheduling ratio will be adjusted to 1.8 times the original scheduling ratio. If the slope Q of the curve is greater than the preset slope Q0, the scheduling ratio will be adjusted to 1.2 times the original scheduling ratio.

[0042] Specifically, if the electricity sales-cycle curve is not regular, it indicates that the air conditioner continuously releases cold near the set temperature. Therefore, when the room temperature approaches the target value (e.g., temperature difference ≤ 2℃), reducing the cold release rate can maintain stable cooling and prevent frequent compressor start-stop. Continuous low-speed operation is more energy-efficient than repeated speed increases and decreases, with energy consumption per unit time only 50% of the start-stop mode. Therefore, the cold release rate of the cold storage device is adjusted based on the difference between the preset average value and the cold storage characterization value. The preset difference between the preset average value and the cold storage characterization value is R0 = 0.05. The comparison process between the preset average value and the cold storage characterization value R and the preset difference R0 is as follows: If the difference R between the preset average value and the cold storage characterization value is less than or equal to the preset difference R0, the cold release rate will be adjusted to 0.9 times the original cold release rate. If the difference R between the preset average value and the cold storage characterization value is greater than the preset difference R0, the cold release rate will be adjusted to 0.6 times the original cold release rate.

[0043] Specifically, after adjusting the cooling rate, extending the cooling time can improve the utilization rate of cooling capacity, thereby reducing energy consumption. Therefore, the cooling time is adjusted based on the cooling rate, where the preset cooling rate T0 = 100 kW / m³. The comparison process between the cooling rate T and the preset cooling rate T0 is as follows: If the cooling rate T is less than or equal to the preset cooling rate T0, the cooling time will be adjusted to 2.7 times the original cooling time. If the cooling rate T is greater than the preset cooling rate T0, the cooling time will be adjusted to 1.5 times the original cooling time.

[0044] Specifically, in this embodiment of the invention, the scheduling state after adjusting the cooling release time is re-detected. If the scheduling state is the first state, the variance of the proportion of cold storage capacity in multiple cycles is calculated. If the variance is less than the preset variance, the cooling power is increased based on the ratio of the variance to the preset variance, and the increase in cooling power is inversely proportional to the ratio.

[0045] Specifically, if the variance is less than the preset variance, it indicates that the long-term electricity consumption / cold storage ratio is too high (i.e., electricity demand consistently far exceeds cold storage capacity). This means that the existing cold storage system cannot effectively balance the power load and cooling demand, leading to a decrease in system economy and stability. In this case, it is necessary to increase the cooling power to shorten the cold storage time and store a larger capacity during limited off-peak electricity periods, thereby increasing the proportion of cold storage capacity. Therefore, the cooling power is adjusted based on the ratio of the variance to the preset variance, where the preset ratio U0 = 0.7. The comparison process between the ratio U0 and the preset ratio U0 is as follows: If the ratio U of the variance to the preset variance is less than or equal to the preset ratio U0, the cooling power will be adjusted to 1.97 times the original cooling power. If the ratio U of the variance to the preset variance is greater than the preset ratio U0, the cooling power will be adjusted to 1.42 times the original cooling power.

[0046] Specifically, in this embodiment of the invention, the scheduling status after adjusting the cooling release time is re-detected. If the scheduling status is the first state, the data acquisition cycle is reduced based on the difference between the preset cold storage capacity ratio and the cold storage capacity ratio, and the reduction in cycle is proportional to the difference.

[0047] Specifically, after re-testing the dispatch status after adjusting the cooling release time, if the dispatch status is still unqualified (i.e., the first state), it indicates that the sampling frequency is too low (e.g., 1 hour / time) and cannot capture the rapid fluctuations in power generation and load, resulting in a mismatch between the dispatch ratio and the current power situation. In this case, it is necessary to adjust the data acquisition cycle. Therefore, the data acquisition cycle is adjusted based on the difference between the preset cooling storage ratio and the preset difference V0 = 0.04. The comparison process between the preset cooling storage ratio and the preset difference V0 is as follows: If the difference V between the preset cold storage capacity ratio and the cold storage capacity ratio is less than or equal to the preset difference V0, the data acquisition period will be adjusted to 0.94 times the original period. If the difference V between the preset cold storage capacity ratio and the cold storage capacity ratio is greater than the preset difference V0, the data acquisition period will be adjusted to 0.71 times the original period.

[0048] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0049] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent dispatching of air conditioning cold storage power for virtual power grid trading, characterized in that, include: Periodically acquire data information, including power generation data, cold storage status, load data, environmental parameters, and electricity price information; The acquired data information is preprocessed to enable time synchronization and create a unified timestamp. Construct a single-cycle environment model using preprocessed data; The environmental model for each cycle is input into a deep reinforcement learning agent, and the scheduling ratio of energy storage and electricity sales corresponding to the cycle is output. Deployment is carried out based on the scheduling ratio, and the cold storage characterization value is calculated within a preset time after deployment. The cold storage characterization value is the average value of the cold storage capacity ratio over multiple cycles, and the cold storage capacity ratio is the ratio of the current actual cold storage capacity to the total cold storage capacity that the cold storage tank can store. The scheduling status is determined by using the cold storage characterization value, and the scheduling ratio is adjusted based on the scheduling status. If the adjusted scheduling status is not qualified, the scheduling ratio or the cold release rate of the cold storage equipment is determined based on the plotted power-cycle curve.

2. The intelligent dispatching method for air conditioning cold storage power for virtual power grid trading according to claim 1, characterized in that, When the scheduling state is determined to be the first state based on the aforementioned cold storage characterization value, the proportion of traded electricity in electricity sales is calculated. If the proportion of traded electricity is less than the preset proportion of traded electricity, the scheduling ratio is adjusted based on the difference between the preset proportion of traded electricity and the proportion of traded electricity. The first state is the state corresponding to when the cold storage characterization value is less than the preset average value, and the proportion of traded electricity is the ratio of sold electricity to recycled electricity.

3. The intelligent dispatching method for air conditioning cold storage power for virtual power grid trading according to claim 2, characterized in that, The scheduling ratio is increased based on the difference between the preset transaction volume ratio and the already traded volume ratio, and the increase in the scheduling ratio is proportional to the difference.

4. The intelligent dispatching method for air conditioning cold storage power for virtual power grid trading according to claim 3, characterized in that, Re-detect the scheduling status after adjusting the scheduling ratio. If the scheduling status is the first status, repeat the adjustment of the scheduling ratio at least once until the number of adjustments is less than the preset number and the scheduling status is the first status or the number of adjustments is equal to the preset number, then stop adjusting. The scheduling status after the adjustment is stopped is detected. If the scheduling status is the first state, the electricity sold-cycle curve is plotted, and the corresponding adjustment method is determined based on whether the curve has regularity.

5. The intelligent dispatching method for air conditioning cold storage power for virtual power grid trading according to claim 4, characterized in that, The process of determining the corresponding adjustment method based on whether the curve has a regularity includes: Use adaptive functions to determine whether a curve exhibits regularity; If the curve exhibits a regularity, then calculate the slope of the curve; The scheduling ratio is adjusted based on the curve slope.

6. The intelligent dispatching method for air conditioning cold storage power for virtual grid trading according to claim 5, characterized in that, The scheduling ratio is increased based on the slope of the curve, and the increase in the scheduling ratio is inversely proportional to the slope of the curve.

7. The intelligent dispatching method for air conditioning cold storage power for virtual grid trading according to claim 5, characterized in that, The process of determining the corresponding adjustment method based on whether the curve has a regularity also includes: If the curve does not have a regularity, the cold release rate of the cold storage device will be reduced based on the difference between the preset average value and the cold storage characterization value, and the reduction in the cold release rate will be proportional to the difference.

8. The intelligent dispatching method for air conditioning cold storage power for virtual grid trading according to claim 7, characterized in that, The cooling time is increased based on the cooling rate, and the increase in cooling time is inversely proportional to the cooling rate.

9. The intelligent dispatching method for air conditioning cold storage power for virtual grid trading according to claim 8, characterized in that, Re-check the scheduling status after adjusting the cooling release time. If the scheduling status is the first state, calculate the variance of the proportion of cold storage capacity in multiple cycles. If the variance is less than the preset variance, the cooling power is increased based on the ratio of the variance to the preset variance, and the increase in cooling power is inversely proportional to the ratio.

10. The intelligent dispatching method for air conditioning cold storage power for virtual grid trading according to claim 9, characterized in that, The scheduling status after adjusting the cooling release time is re-checked. If the scheduling status is the first state, the data acquisition cycle is reduced based on the difference between the preset cold storage capacity ratio and the cold storage capacity ratio, and the reduction in cycle is proportional to the difference.

Images