A Multi-Objective Optimization and Cooperative Control Method and System for Air Conditioning Load Based on Network-Load Interaction

Abstract

The application relates to a kind of air conditioner load multi-objective optimization collaborative control method and system based on net load interaction, belong to load management field.Therein, the method includes collecting net load interaction data, introducing dynamic priority classification mechanism based on the net load interaction data, and obtaining priority control set and double-target optimization set;Based on the priority control set and the double-target optimization set, a multi-objective optimization collaborative control model is constructed, the multi-objective optimization collaborative control model includes a priority control model and a double-target optimization model, and the air conditioner temperature is regulated based on the multi-objective optimization collaborative control model;The air conditioners in the priority control set and the double-target optimization set are aggregated to form a virtual energy pool, and the air conditioner load is adjusted through load translation and power smoothing.The application realizes the fusion of power grid load emergency, user sensitivity and temperature deviation, real-time division of priority control set and double-target optimization set, and improves the regulation accuracy.

Description

Technical Field

[0001] This invention belongs to the field of load management technology, specifically relating to a multi-objective optimization and collaborative control method and system for air conditioning load based on grid-load interaction. Background Technology

[0002] With accelerated urbanization and surging electricity demand, power grid load management faces significant challenges, especially in areas where air conditioning load accounts for a large proportion. Air conditioning, as a typical temperature-controlled load, has a significant impact on grid stability due to its start-up, shutdown, and power fluctuations. Traditional power grid load management technologies mainly include: Demand response mechanisms: guiding users to adjust their electricity consumption behavior through electricity price incentives or direct control, such as time-of-use pricing and load interruption compensation. Static priority control: prioritizing loads based on fixed rules (such as equipment type and user contract level), prioritizing the disconnection of low-priority equipment. Single-objective optimization: using grid economics (such as peak shaving and valley filling) or user comfort (such as temperature deviation) as a single optimization objective. These existing technologies currently have many shortcomings, such as: poor dynamic adaptability: static priority control cannot dynamically adjust priorities based on real-time grid conditions (such as load urgency) and user behavior (such as the frequency of manual adjustments), resulting in low control efficiency. Sacrificing user comfort: traditional demand response often forcibly adjusts air conditioning at the expense of users' perceived temperature, leading to user complaints (such as sudden temperature changes and frequent start-ups and shutdowns). Lack of synergistic optimization: Existing methods mostly focus on a single objective (such as grid economy) and lack systematic modeling for the synergistic optimization of the "grid-user" dual objectives, making it difficult to balance the interests of both. Risk of load surges: Simultaneous start-up and shutdown of clustered air conditioners can easily cause power surges, threatening grid stability (such as voltage drops and frequency fluctuations). Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, this invention provides a multi-objective optimization and collaborative control method and system for air conditioning load based on grid-load interaction.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] A multi-objective optimization and collaborative control method for air conditioning load based on grid-load interaction, the implementation of which includes the following steps:

[0006] S1: Collect network-load interaction data, introduce a dynamic priority classification mechanism based on the network-load interaction data, and obtain a priority control set and a bi-objective optimization set;

[0007] S2: Construct a multi-objective optimization cooperative control model based on the priority control set and the dual-objective optimization set. The multi-objective optimization cooperative control model includes a priority control model and a dual-objective optimization model. Adjust the air conditioning temperature based on the multi-objective optimization cooperative control model.

[0008] S3: Aggregate the air conditioners in the priority control set and the dual-objective optimization set to form a virtual energy pool, and adjust the air conditioner load through load shifting and power smoothing.

[0009] Preferably, step S1 specifically includes:

[0010] S101: Collect the grid-load interaction data, which includes user-side data and grid-side data;

[0011] S102: Calculate a priority index based on the network-load interaction data, which is used to introduce the dynamic priority classification mechanism;

[0012] S103: Obtain the priority control set and the bi-objective optimization set based on the priority index.

[0013] Preferably, the formula for calculating the priority index in step S102 is as follows: Where P is the priority index, α, β, and γ are the weights for temperature deviation, user sensitivity, and grid urgency, respectively, and T is the priority index. real For the true temperature, T set To set the temperature, S represents user sensitivity, and L... emergency This refers to the urgency level of the power grid load.

[0014] Preferably, step S2 specifically includes:

[0015] S201: Obtain the priority control adjustment value, and construct the priority control model based on the priority control adjustment value and the priority control set;

[0016] S202: Obtain the predicted temperature parameters and construct the bi-objective optimization model based on the bi-objective optimization set.

[0017] Preferably, the construction of the priority control model in step S201 specifically includes:

[0018] Obtain the user comfort deviation, which is the difference between the actual temperature and the set temperature. Calculate the priority control adjustment value based on the user comfort deviation and construct the priority control model.

[0019] Preferably, the formula for calculating the priority control adjustment value is as follows: , among which, T adj To prioritize the control adjustment value, δ and ε are dynamic weighting coefficients, and ΔT comfort The temperature of the priority control central air conditioning system is adjusted according to the priority control adjustment value based on the user comfort deviation.

[0020] Preferably, the acquisition of the predicted temperature parameters in step S202 specifically includes:

[0021] The cooling power of the dual-objective optimized centralized air conditioning system, along with the corresponding regional height and area, are obtained. Spatiotemporal temperature field prediction is then performed to obtain predicted temperature parameters. The mathematical description of these predicted temperature parameters is... ,in, T represents the predicted temperature parameter after time Δt. real For the actual temperature, ΔT out Let Δt be the change in outdoor temperature after time Δt, I be the air conditioning efficiency coefficient, and Q be... AC Here, ρ is the air conditioning cooling power, Δt is the prediction time step, ρ is the air density, c is the specific heat capacity of air, H is the region height, and Area is the region area. Where is the thermal diffusivity, The second derivative of temperature in the X direction. This is the second derivative of temperature in the Y direction.

[0022] Preferably, the construction of the bi-objective optimization model in step S202 specifically includes:

[0023] Based on the predicted temperature parameters, a bi-objective optimization model is constructed, and the temperature of the bi-objective optimized centralized air conditioning system is adjusted. Mathematically, this is described as follows: Where n is the number of centralized air conditioners required for the bi-objective optimization. Let J be the power change of air conditioner i during the adjustment process, and J be the stage electricity price. To regulate the duration, S i For the user sensitivity of the area corresponding to air conditioner i, [T] min ,T max [] represents the preset upper and lower thresholds.

[0024] Preferably, step S3 specifically includes:

[0025] S301: The load shift is carried out by cooling and energy storage, that is, cooling in advance when the grid load is low and storing cold energy;

[0026] S302: By suppressing peak start-up and shutdown of air conditioners through cluster power fluctuations, load abrupt changes are eliminated, thus achieving the power smoothing.

[0027] A multi-objective optimization and collaborative control system for air conditioning load based on grid-load interaction is used to execute the aforementioned multi-objective optimization and collaborative control method for air conditioning load, including a priority division module, a collaborative control module, and a virtual adjustment module;

[0028] The priority classification module is used to collect network-load interaction data, introduce a dynamic priority classification mechanism based on the network-load interaction data, and obtain a priority control set and a bi-objective optimization set.

[0029] The coordinated control module is used to construct a multi-objective optimization coordinated control model based on the priority control set and the dual-objective optimization set. The multi-objective optimization coordinated control model includes a priority control model and a dual-objective optimization model. The air conditioning temperature is controlled based on the multi-objective optimization coordinated control model.

[0030] The virtual adjustment module is used to aggregate the air conditioners in the priority control set and the dual-objective optimization set to form a virtual energy pool, and adjust the air conditioner load through load shifting and power smoothing.

[0031] The beneficial effects of this invention are as follows:

[0032] (1) By using a dynamic priority classification mechanism to accurately identify high-value control objects, the grid demand can be responded to quickly with the least user perception cost. At the same time, efficiency can be improved through hierarchical control. The priority control set can alleviate grid pressure through rapid temperature regulation, thus buying time for the refined control of the dual-objective optimization set and avoiding "one-size-fits-all" global control.

[0033] (2) User comfort is guaranteed by dynamic compensation of comfort deviation, which is significantly better than the traditional forced temperature control strategy. Furthermore, the change in air conditioning power is optimized by predicting the spatiotemporal temperature field, ensuring a balance between stage electricity cost and user sensitivity weighted comfort. Attached Figure Description

[0034] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0035] Figure 1 This is a flowchart illustrating the steps of a multi-objective optimization and collaborative control method for air conditioning load based on grid-load interaction according to the present invention. Detailed Implementation

[0036] To better understand the invention, various aspects of the invention will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of the invention and are not intended to limit the scope of the invention in any way. Throughout the specification, the expression "and / or" includes any and all combinations of one or more of the associated listed items. As used herein, the terms "approximately," "about," and similar terms are used as expressions of approximation, not as expressions of degree, and are intended to describe inherent deviations in measured or calculated values ​​that will be recognized by those skilled in the art. Furthermore, the order in which the steps are described in this invention does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.

[0037] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of the invention, the word "may" is used to mean "one or more embodiments of the invention." And the term "exemplary" is intended to refer to examples or illustrations.

[0038] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formalized sense.

[0039] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0040] Example 1:

[0041] Please see Figure 1 A multi-objective optimization and collaborative control method for air conditioning load based on grid-load interaction includes:

[0042] S1: Collect network-load interaction data, introduce a dynamic priority classification mechanism based on the network-load interaction data, and obtain a priority control set and a bi-objective optimization set;

[0043] S2: Construct a multi-objective optimization cooperative control model based on the priority control set and the dual-objective optimization set. The multi-objective optimization cooperative control model includes a priority control model and a dual-objective optimization model. Adjust the air conditioning temperature based on the multi-objective optimization cooperative control model.

[0044] S3: Aggregate the air conditioners in the priority control set and the dual-objective optimization set to form a virtual energy pool, and adjust the air conditioner load through load shifting and power smoothing.

[0045] In this embodiment, grid-load interaction data is collected, and a dynamic priority classification mechanism is introduced based on the grid-load interaction data to obtain a priority control set and a dual-objective optimization set. This can be implemented through the following steps:

[0046] S101: Collect the grid-load interaction data, which includes user-side data and grid-side data. The user-side data includes the real-time status of the air conditioner and user sensitivity (the ratio of the number of times the user manually adjusted the temperature to the total number of times the temperature was adjusted in the past seven days). The real-time status of the air conditioner includes the actual temperature, set temperature, and operating mode. The grid-side data includes the urgency of the grid load and the phased electricity price.

[0047] S102: Calculate a priority index based on the network-load interaction data, which is used to introduce the dynamic priority classification mechanism. The calculation formula is as follows: Where P is the priority index, α, β, and γ are the weights for temperature deviation, user sensitivity, and grid urgency, respectively, with typical values ​​of 0.5, 0.3, and 0.2, and T... real For the true temperature, T set To set the temperature, S represents user sensitivity, and L... emergency The urgency level of the power grid load (the value ranges from [0.1], and the higher the value, the greater the pressure on the power grid).

[0048] S103: Based on the priority index, the priority control set and the dual-objective optimization set are obtained. Specifically, multiple air conditioners with higher priority indices are selected to form the priority control set, prioritizing temperature control to temporarily alleviate grid pressure and allow time for subsequent measures. The remaining air conditioners form the dual-objective optimization set. Example: An office has two air conditioners, and the grid load is extremely high (grid load urgency = 1). Air conditioner X: T real -T set =3℃, S=0.2 (low sensitivity), then P X =0.5×3 / 5 + 0.3×(1-0.2) + 0.2×1 = 0.74; Air conditioner Y:T real -T set =1℃, S=0.6 (high sensitivity), then P Y =0.5×1 / 5 + 0.3×(1-0.6) + 0.2×1 = 0.445. At this time, air conditioner X is included in the priority control set for priority temperature setting, and air conditioner Y is included in the dual-objective optimization set.

[0049] In this embodiment, a multi-objective optimization cooperative control model is constructed based on the priority control set and the dual-objective optimization set, which can be implemented through the following steps:

[0050] S201: Obtain the priority control adjustment value, and construct the priority control model based on the priority control adjustment value and the priority control set:

[0051] Obtain the user comfort deviation, which is the difference between the actual temperature and the set temperature. Calculate the priority control adjustment value based on the user comfort deviation and construct the priority control model. The calculation formula is as follows: , among which, T adj To prioritize the control adjustment value, δ and ε are dynamic weighting coefficients, and ΔT comfort To adjust the temperature of the prioritized central air conditioning system according to the prioritized control adjustment value based on the user comfort deviation, thereby alleviating grid pressure while reducing the impact on user comfort. Example: Grid load surge (L emergency =1), but the actual temperature in the user's room is consistent with the set value (△T). comfort =0℃), at this time T adj = 26 + 0.5×1 + 0.3×0 = 26.5℃. The air conditioner in this room automatically raises the temperature by 0.5℃, which not only relieves the pressure on the power grid but also does not affect the user's comfort.

[0052] S202: After adjusting the temperature of the priority-controlled central air conditioning system, obtain the predicted temperature parameters and construct the dual-objective optimization model based on the dual-objective optimization set;

[0053] S202-1: Obtain the air conditioning cooling power of the dual-objective optimized centralized air conditioning system, as well as the corresponding area height (e.g., room height) and area, perform spatiotemporal temperature field prediction, and obtain predicted temperature parameters. The mathematical description of the predicted temperature parameters is... ,in, T represents the predicted temperature parameter after time Δt. real For the actual temperature, ΔT out Let Δt be the change in outdoor temperature after time Δt, I be the air conditioning efficiency coefficient, determined by equipment parameters, and the unit be m²·℃ / J. AC The unit is air conditioning cooling power in watts, Δt is the prediction time step, ρ is air density, c is specific heat capacity of air, H is the area height, and Area is the area of ​​the region. This is the thermal diffusivity, expressed in m² / s. This is the second derivative of temperature in the X direction, with units of °C / m². Let T be the second derivative of temperature in the Y direction; Example: Predict the temperature of an office in 30 minutes, initial condition: T real = 28℃, △T out = +3℃, I=1.2×e -6 m²·℃ / J, Q AC = 3000W (air conditioner running at full speed), △t = 1800 seconds (30 minutes), room size: 10m × 8m × 3m (Area = 80m², H = 3m), temperature gradient detected on the west wall: = 0.2℃ / m², then the predicted temperature of the room will drop to 28 + 0.7 × 3 + [(1.2e -6 [×3000×1800) / (1.225×1005×3×80)]-0.02×1800×0.2=22.92℃, which may indicate overcooling.

[0054] S202-2: Based on the predicted temperature parameters, construct the dual-objective optimization model and adjust the temperature of the dual-objective optimized centralized air conditioning system to balance power grid economy and user comfort. Mathematically, this is described as follows: Where n is the number of centralized air conditioners required for the bi-objective optimization. Let J be the power change of air conditioner i during the adjustment process, and J be the stage electricity price. To regulate the duration, S i For the user sensitivity of the area corresponding to air conditioner i, [T] min ,T max [] represents the preset upper and lower thresholds.

[0055] In this embodiment, the air conditioners in the priority control set and the dual-objective optimization set are aggregated to form a virtual energy pool. The air conditioner load is adjusted through load shifting and power smoothing, which can be implemented through the following steps:

[0056] S301: The load shift is achieved through cooling and energy storage, that is, cooling in advance and storing cold energy when the grid load is low; Example: Set the air conditioner to 22°C (lower than the daytime temperature) 2 hours in advance; turn off the compressor during peak hours and maintain the room temperature only by relying on the pre-stored cold energy;

[0057] S302: By suppressing peak-hour start-up and shutdown of air conditioners through cluster power fluctuation suppression, load abrupt changes are eliminated, thus achieving the power smoothing described above. The mathematical description of the cluster power fluctuation suppression is: D≤0.3×(1-L) emergency )×D total Where D is the number of air conditioners that can be started and stopped simultaneously. total L represents the total number of air conditioners. emergency This represents the urgency level of the power grid load. Example: In a certain area, there are 100 air conditioners. When L=0.8, the number of air conditioners that can be started and stopped simultaneously is D≤0.3×(1-0.8)×100=6, to avoid the power grid being impacted by the simultaneous restart of 100 air conditioners.

[0058] Example 2:

[0059] A multi-objective optimization and collaborative control system for air conditioning load based on grid-load interaction includes a priority division module, a collaborative control module, and a virtual adjustment module.

[0060] The priority classification module is used to collect grid-load interaction data, introduce a dynamic priority classification mechanism based on the grid-load interaction data, and obtain a priority control set and a dual-objective optimization set. Specifically, the grid-load interaction data is collected, which includes user-side data and grid-side data. The user-side data includes the real-time status of air conditioners and user sensitivity. The real-time status of air conditioners includes actual temperature, set temperature, and operating mode, etc. The grid-side data includes the urgency of grid load and phased electricity prices, etc. A priority index is calculated based on the grid-load interaction data, which is used to introduce the dynamic priority classification mechanism. The priority control set and the dual-objective optimization set are obtained based on the priority index. That is, multiple air conditioners with higher priority indices are selected to form the priority control set, and their temperature settings are adjusted first to temporarily alleviate grid pressure and allow time for subsequent treatment measures. The remaining air conditioners form the dual-objective optimization set.

[0061] The coordinated control module is used to construct a multi-objective optimization coordinated control model based on the priority control set and the dual-objective optimization set. The multi-objective optimization coordinated control model includes a priority control model and a dual-objective optimization model. The air conditioning temperature is controlled based on the multi-objective optimization coordinated control model, specifically: (1) Obtain the priority control adjustment value and construct the priority control model based on the priority control adjustment value and the priority control set: Obtain the user comfort deviation, which is the difference between the actual temperature and the set temperature. Calculate the priority control adjustment value based on the user comfort deviation and construct the priority control model. Adjust the temperature of the priority control centralized air conditioner based on the priority control adjustment value to alleviate grid pressure and reduce the impact on user comfort. (2) After controlling the temperature of the priority control centralized air conditioner, obtain the predicted temperature parameters and construct the dual-objective optimization model based on the dual-objective optimization set: Obtain the air conditioning cooling power of the dual-objective optimized centralized air conditioner and the corresponding regional height and area, perform spatiotemporal temperature field prediction, and obtain the predicted temperature parameters. Construct the dual-objective optimization model based on the predicted temperature parameters and adjust the temperature of the dual-objective optimized centralized air conditioner to balance grid economy and user comfort.

[0062] The virtual regulation module is used to aggregate the air conditioners in the priority control set and the dual-objective optimization set to form a virtual energy pool. It regulates the air conditioner load through load shifting and power smoothing. Specifically, the load shifting is performed by cooling and energy storage, that is, cooling in advance when the grid load is low to store cold energy; the power smoothing is achieved by suppressing peak start-up and shutdown of air conditioners through cluster power fluctuations to eliminate load abrupt changes.

[0063] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for multi-objective optimization and collaborative control of air conditioning load based on net energy interaction, characterized in that, The implementation of the air conditioner load multi-objective optimization collaborative control method comprises the following steps: S1: Collecting grid-load interaction data, introducing a dynamic priority classification mechanism based on the grid-load interaction data, and obtaining a priority control set and a double-objective optimization set; the priority control set is a set composed of a preset number or a preset proportion of air conditioners with the highest priority index; the double-objective optimization set is a set composed of the remaining air conditioners after excluding the priority control set from all air conditioners to be controlled; The calculation formula of the priority index is Wherein, P is the priority index, a, β and γ are respectively the temperature deviation weight, the user sensitivity weight and the power grid emergency degree weight, T real is the real temperature, T set is the set temperature, S is the user sensitivity, L emergency is the power grid load emergency degree; S2: Constructing a multi-objective optimization collaborative control model based on the priority control set and the double-objective optimization set, the multi-objective optimization collaborative control model comprising a priority control model and a double-objective optimization model, and controlling air conditioner temperature based on the multi-objective optimization collaborative control model; the double-objective comprises minimizing energy consumption cost and minimizing temperature deviation; S3: Aggregating air conditioners in the priority control set and the double-objective optimization set to form a virtual energy pool, and adjusting air conditioner load through load shifting and power smoothing.

2. The air conditioning load multi-objective optimization collaborative control method according to claim 1, characterized in that, The step S1 specifically comprises: S101: Collecting the grid-load interaction data, the grid-load interaction data comprising user-side data and grid-side data; S102: Calculating a priority index based on the grid-load interaction data, for introducing the dynamic priority classification mechanism; S103: Obtaining the priority control set and the double-objective optimization set based on the priority index.

3. The air conditioning load multi-objective optimization collaborative control method according to claim 1, characterized in that, The step S2 specifically comprises: S201: Obtaining a priority control adjustment value, and constructing the priority control model based on the priority control adjustment value and the priority control set; S202: Obtaining a predicted temperature parameter and constructing the double-objective optimization model according to the double-objective optimization set.

4. The air conditioning load multi-objective optimization collaborative control method according to claim 3, characterized in that, The construction of the priority control model in the step S201 specifically comprises: Obtaining a user comfort deviation, the user comfort deviation being a difference between a real temperature and a set temperature, calculating the priority control adjustment value according to the user comfort deviation, and constructing the priority control model.

5. The air conditioning load multi-objective optimization collaborative control method according to claim 4, characterized in that, The calculation formula of the priority control adjustment value is Wherein, T adj is the priority control adjustment value, δ and ε are dynamic weight coefficients, and △T comfort is the user comfort deviation degree, and the temperature of the central air conditioner is adjusted according to the priority control adjustment value.

6. The air conditioning load multi-objective optimization collaborative control method according to claim 5, characterized in that, The obtaining of the predicted temperature parameter in the step S202 specifically comprises: The air conditioner refrigeration power of the dual-target optimization set, the area height and the area area of the corresponding area are acquired, time-space temperature field prediction is performed, and a predicted temperature parameter is obtained, and the mathematical description of the predicted temperature parameter is wherein, is the predicted temperature parameter after △t time, T real is the real temperature, △T out is the outdoor temperature change after △t time, I is the air conditioner efficiency coefficient, Q AC is the air conditioner refrigeration power, △t is the prediction time step, ρ is the air density, c is the air specific heat capacity, H is the area height, Area is the area area, is the thermal diffusion coefficient, is the X-direction temperature second-order derivative, is the Y-direction temperature second-order derivative.

7. The air conditioning load multi-objective optimization collaborative control method according to claim 6, characterized in that, The construction of the double-objective optimization model in the step S202 specifically comprises: constructing the double-target optimization model based on the predicted temperature parameter and adjusting the temperature of the central air conditioner in the double-target optimization, which is mathematically described as wherein n is the number of central air conditioners in the double-target optimization, is the power variation of the air conditioner i in the adjustment process, J is the stage electricity price, is the regulation duration, S i is the user sensitivity of the area corresponding to the air conditioner i, [T min ,T max ] is the preset upper and lower limits of the threshold.

8. The air conditioning load multi-objective optimization collaborative control method of claim 1, wherein, The step S3 specifically comprises: S301: Performing the load shifting through cooling energy storage, that is, pre-cooling when the grid load is low to store cold energy; S302: Inhibiting peak-shaving start-stop air conditioners through cluster power fluctuation to eliminate load mutation and realize power smoothing.

9. A multi-objective optimization collaborative control system for air conditioning load based on net energy interaction, characterized in that, The system is applied to the air conditioner load multi-objective optimization collaborative control method as claimed in any one of claims 1-8, comprising a priority division module, a collaborative control module, and a virtual adjustment module; The priority division module is used for collecting grid-load interaction data, introducing a dynamic priority classification mechanism based on the grid-load interaction data, and obtaining a priority control set and a double-objective optimization set; The collaborative control module is used for constructing a multi-objective optimization collaborative control model based on the priority control set and the double-objective optimization set, the multi-objective optimization collaborative control model comprising a priority control model and a double-objective optimization model, and controlling air conditioner temperature based on the multi-objective optimization collaborative control model; The virtual adjustment module is used to aggregate the air conditioners in the priority control set and the double-target optimization set to form a virtual energy pool, and to adjust the air conditioner load through load shifting and power smoothing.

Images