Building air conditioner double-layer energy-saving optimization operation control system and method

Through a double-layer energy-saving and optimized operation control system, combining the flow data of people and air conditioning historical data, a zoning collaborative temperature control model is established to realize multi-stage temperature control and energy supply flow optimization, solving the problems of energy waste and uneven hot and cold in building air conditioning systems. , improves energy efficiency and user comfort.

CN118935627APending Publication Date: 2024-11-12SHANDONG ZERO CARBON SMART ENERGY TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411057085.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The electricity load of building air conditioning systems increases during peak periods, resulting in waste of energy. The existing technology cannot effectively regulate the fan and water pump loads, resulting in uneven hot and cold heat and low energy efficiency, and lack of optimized control of HVAC systems.

Method used

Adopt a dual-layer energy-saving and optimized operation control system, through the cooperation of the upper and lower body, people flow data are obtained for clustering, and a zoning collaborative temperature control equivalent model is established to realize multi-stage temperature control and energy supply flow optimization, and combined with air conditioning units to start Stop and load rate constraints to achieve differentiated and refined control of building temperature.

Benefits of technology

Differentiated and refined control of building temperatures is achieved, energy consumption of air conditioning systems is reduced, user comfort and energy utilization efficiency are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118935627A_ABST
    Figure CN118935627A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of building air-conditioning systems, and provides a building air-conditioning double-layer energy-saving optimization operation control system and method.The method comprises the steps that a lower layer main body obtains a pedestrian flow sequence of a certain area in a plurality of time periods, clusters the time periods based on the pedestrian flow sequence, and judges the type of the area based on the clustering result; based on the type of the region, performing multi-stage temperature range assignment on each type of time period in the region; for the current moment of the area, temperature parameters and the pedestrian volume are obtained, after the power needed when the indoor temperature is not changed is obtained through the called partition cooperative temperature control equivalent model, the power of the area in the hierarchical control mode is obtained through optimization by combining the multi-stage temperature range and taking the optimal user comfort as the target; and the upper layer main body carries out fine tuning on the power in the hierarchical control mode after solving to obtain the optimal energy supply flow and energy supply power distribution based on the power of all the areas in the hierarchical control mode. And the energy-saving operation of the building air conditioner is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of building air conditioning systems, and in particular relates to a building air conditioning double-layer energy-saving optimized operation control system and method. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The electricity load during peak periods continues to grow, and the sharp increase in air-conditioning load has become the main reason for seasonal power shortages. Taking Shandong as an example, the air-conditioning load accounts for nearly half of the load during the peak period in summer.

[0004] Building air conditioning systems generally account for more than 40% of the energy consumption of various commercial buildings. The main reasons are as follows: the equipment margin is generally around 20% during design and selection, but it rarely operates at full load, resulting in high no-load power consumption; in order to save the primary investment cost, the system lacks control devices, resulting in fans and water pumps operating at maximum flow for a long time, and cannot be effectively adjusted according to the load of actual operating conditions, resulting in unnecessary energy waste; thermostats and sensors respond with delays, resulting in excessive cold air supply, and lack of technical settings to track variable factors, such as the number of people indoors or weather conditions and other related data; there is a lack of understanding of the working principle and energy consumption of the HVAC system, and indoor personnel frequently adjust the temperature, resulting in excessive load on the chiller and boiler.

[0005] Therefore, building air conditioning load is a typical load that can be optimized, and can be optimized in four aspects: operating time, zoning, operating temperature and equipment management of building air conditioning.

[0006] At present, the energy saving of building air conditioning mainly has the following problems:

[0007] (1) Due to the different amounts of solar radiation received by different areas of a building, as well as the uneven and dynamic distribution of internal traffic, there are large differences in the load demand in different areas and at different times. Currently, the regional temperature control adopted by most building air conditioners uses the temperature measured by the thermostat as feedback for bistable control. The adjustment has a large lag and there is no coordination between the zones, resulting in uneven heating and cooling and poor comfort. For example, in summer, the temperature of the sunny side of the building cannot be lowered, while the temperature of the shady side is too low. Even when the air conditioner supply side is running at full load, some areas cannot achieve satisfactory comfort, which also causes a lot of resource waste;

[0008] (2) Most building air conditioners adopt a rough start-stop strategy, with no effective interaction between the source and the load. The start-stop strategy is usually manually modified in different seasons based on experience. This strategy cannot ensure that the air-conditioning unit operates at the optimal load rate, resulting in low energy efficiency of the air-conditioning system. Summary of the invention

[0009] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a double-layer energy-saving optimized operation control system and method for building air conditioners, which realizes energy-saving operation of building air conditioners through the cooperation of an upper main body and a lower main body arranged in various areas in the building.

[0010] In order to achieve the above object, the present invention adopts the following technical solution:

[0011] The first aspect of the present invention provides a building air conditioner double-layer energy-saving optimization operation control system, which includes:

[0012] The upper main body and the lower main body set in various areas of the building;

[0013] The lower layer main body is used to obtain the sequence of human flow in a certain area in several time periods, cluster several time periods based on the human flow sequence, and determine the category of the area based on the clustering result; assign a multi-level temperature range to each time period in the area based on the category of the area; for the current moment of the area, obtain the temperature parameters and human flow, obtain the required power when the indoor temperature remains unchanged by calling the partition collaborative temperature control equivalent model, and then combine the multi-level temperature range to optimize the user comfort and obtain the power of the area under the hierarchical control mode;

[0014] The upper body is used to fine-tune the power in the hierarchical control mode after solving the optimal energy supply flow and energy supply power distribution based on the power of all areas in the hierarchical control mode.

[0015] Further, for a certain area, the time periods are clustered into four categories: stable crowded time period, variable crowded time period, variable sparsely populated time period and stable sparsely populated time period;

[0016] If the proportion of time periods belonging to stable congestion periods and variable congestion periods exceeds the set value, the area is classified as a crowded area; if the proportion of time periods belonging to variable sparsely populated periods and stable sparsely populated periods exceeds the set value, the area is classified as a sparsely populated area; otherwise, the area is classified as a normal flow area.

[0017] Furthermore, the temperature parameters include outdoor temperature, temperature within the area and temperature of adjacent areas.

[0018] Furthermore, for each area, each type of time period corresponds to a zoned collaborative temperature control equivalent model.

[0019] Further, when optimizing the power in the hierarchical control mode, the constraint condition includes a power upper limit constraint, and the power upper limit is determined based on the control mode;

[0020] The control modes include full-speed temperature control, fast temperature control and general temperature control.

[0021] Furthermore, when solving the optimal energy supply flow and energy supply power distribution, the optimization goal is to minimize the overall operating cost of the air-conditioning system.

[0022] Furthermore, when solving the optimal energy supply flow and energy supply power distribution, constraints include: the circulation flow ensures heat exchange in the farthest area, maximizes the satisfaction of heating or cooling needs of each area, the correlation between the circulation flow and energy supply, and the energy consumption characteristics of the air-conditioning unit and the circulation pump.

[0023] Furthermore, the upper body is a controller for a central air conditioner; and the lower body is a data collection and edge control device.

[0024] Furthermore, the partitioned collaborative temperature control equivalent model adopts a convolutional long short-term memory neural network, and a particle swarm algorithm is used to optimize the hyperparameters of the convolutional long short-term memory neural network.

[0025] A second aspect of the present invention provides a building air conditioner double-layer energy-saving optimization operation control method, which includes:

[0026] The lower-level subject obtains the flow sequence of people in a certain area in several time periods, clusters several time periods based on the flow sequence, and determines the category of the area based on the clustering results; assigns a multi-level temperature range to each time period in the area based on the category of the area; obtains the temperature parameters and the flow of people at the current moment of the area, obtains the required power when the indoor temperature remains unchanged by calling the partition collaborative temperature control equivalent model, and then optimizes the power of the area under the hierarchical control mode in combination with the multi-level temperature range with the goal of optimizing user comfort;

[0027] The upper body solves the optimal energy supply flow and energy supply power distribution based on the power of all areas in the hierarchical control mode, and then fine-tunes the power in the hierarchical control mode.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention provides a double-layer energy-saving optimized operation control system for building air conditioners, which realizes differentiated and refined control of building temperature and energy-saving operation of building air conditioners through the cooperation of an upper main body and a lower main body arranged in various areas in the building.

[0030] The present invention divides buildings into areas and time periods based on the building's passenger flow data, and assigns three-level temperature difference control to different types of area time periods, thereby achieving temperature optimization control of the building in different areas and time periods, and achieving differentiated control of the building's temperature.

[0031] The present invention relies on historical air-conditioning data to establish a zoned collaborative temperature control equivalent model, and combines three-level temperature difference control of different zones to achieve refined building temperature control with the goal of optimizing user comfort.

[0032] The upper layer of the present invention takes into account the constraints of start and stop of the air-conditioning unit, load rate and working fluid circulation flow rate, and realizes energy-saving operation of building air conditioning under the premise of satisfying the differentiated and refined control of the temperature of the lower layer building. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 This is an architecture diagram of a building air-conditioning double-layer energy-saving optimization operation control system according to the first embodiment of the present invention;

[0035] Figure 2 This is a flow chart of clustering according to the first embodiment of the present invention. DETAILED DESCRIPTION

[0036] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0037] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0038] Embodiment 1

[0039] This embodiment provides a double-layer energy-saving optimized operation control system for a building air conditioner.

[0040] This embodiment provides a building air conditioning double-layer energy-saving optimization operation control system, such as Figure 1 As shown, it includes a lower body and an upper body.

[0041] The upper body is the controller of the central air conditioner, which is configured as follows: based on the cooling / heating power required for the building in each period calculated by the lower layer, the start and stop of the air-conditioning unit, the load rate and the optimization of the working fluid circulation flow rate are considered, so as to minimize the energy consumption cost or optimize the energy efficiency of the air-conditioning system while meeting the user's comfort.

[0042] The main body of the lower layer is the building intelligent collection and edge control equipment.

[0043] The first stage of the lower-level optimization is configured as follows: collecting pedestrian flow data from multiple areas, multiple days, and multiple time periods in the building to form a pedestrian flow-time graph for each area, and using the K-means clustering method to divide different time periods in each area into four categories: stable crowded time period, variable crowded time period, variable sparsely populated time period, and stable sparsely populated time period.

[0044] The second stage of lower-level optimization is configured as follows: assigning time-divided temperature ranges to building partitions, including set temperature values ​​and three-level temperature limits; full-speed temperature control is adopted when the third-level temperature limit is exceeded; rapid temperature control is adopted when the second-level temperature limit is exceeded; general temperature control is adopted when the first-level temperature limit is exceeded; and the current control state is maintained within the first-level temperature difference limit.

[0045] The third stage of the lower-level optimization is configured as follows: fitting the building's zoned collaborative temperature control equivalent model based on historical data such as the building's air-conditioning system power and indoor and outdoor temperatures.

[0046] The fourth stage of the lower-level optimization is configured as follows: based on the regional and time period classification results and the corresponding temperature limits and temperature setting values, the required cooling / heating power of the building is calculated under the premise of optimizing user comfort, and the adjustment amount is determined by interaction with the upper layer to adjust the regional temperature.

[0047] Step 1: The first stage of the lower layer uses intelligent building collection equipment to collect human flow data and divide buildings into zones, specifically:

[0048] Step 101: Collect historical passenger flow data of each partition m∈{1,2,...,M} of the building, and form M passenger flow-time graphs with one collection point every 15 minutes. Each collection point and the two collection points before and after it form a passenger flow sequence for a period of time.

[0049] Step 102: Data preprocessing: first fill in the abnormal or missing data. If the tth data n m,t Abnormal or missing, t∈{1,2,...T}, then replace the data with (n m,t-1 +n m,t+1 ) / 2, where n m,t Represents the value of the tth collection point in the mth area. The pedestrian flow data of each area is standardized. The mean value of the pedestrian flow of the tth collection point in the mth area during the corresponding period is shown in formula (1), and the standard deviation is shown in formula (2), thus forming the pedestrian flow characteristic sequence x m,t =(μ m,t ,σ m,t ).

[0050]

[0051]

[0052] Step 103: For a certain area, based on the feature sequence of each time period, the K-means clustering method is used to divide the different time periods of the area into four categories: stable crowded time period, variable crowded time period, variable sparsely populated time period, and stable sparsely populated time period. The area where more than 3 / 4 of the time period is a crowded time period is a crowded flow area, the area where more than 3 / 4 of the time period is a sparsely populated time period is a sparsely populated area, and the rest of the area is a normal flow area. Figure 2 As shown, the clustering steps are as follows:

[0053] (1) Randomly select four time period features as the initial centroid, assuming that the initial centroid is Where a∈{1,2,3,4} represents the centroid number; k is the number of iterations, k=0 represents the initial centroid, k=1 represents the first regenerated centroid, and so on; are the mean and standard deviation of the passenger flow corresponding to the ath centroid after the kth iteration respectively.

[0054] (2) Calculate the distance from the sample to each centroid and cluster it according to the centroid closest to itself. As shown in formula (3), the sample belongs to the class of the centroid with the closest distance calculated in formula (4).

[0055]

[0056]

[0057] Among them, d m,t,a,k It represents the distance from the feature sample of the time period corresponding to the tth collection point in the mth region to the ath centroid after k iterations.

[0058] Step 105: For each class, recalculate the center of the class to generate a new centroid. The calculation of the new centroid is shown in formula (5).

[0059]

[0060] Among them, |Ω a,k | indicates the set Ω corresponding to the a-th cluster after k iterations a,k The number of samples in .

[0061] Step 106: Repeat steps 104-105 until the centroid no longer changes, which is counted as

[0062] Step 2: In the second stage of the lower layer, the temperature ranges of the building partitions are assigned in different time periods, specifically:

[0063] Step 201: Assign three-level temperature difference ranges to the four time periods (stable crowded time period, variable crowded time period, variable sparsely populated time period and stable sparsely populated time period) corresponding to the three types of areas (crowded area, normal area and sparsely populated area). The temperature setting value corresponding to the a-time period of the n-th type area is expressed as The corresponding b-th level temperature difference threshold is expressed as

[0064] Step 3: The third stage of the lower layer fits the building's partitioned collaborative temperature control equivalent model based on historical data such as the building's air conditioning system power and indoor and outdoor temperatures. Specifically:

[0065] Step 301: Collect outdoor temperature for the a-time period in area m Temperature in the area Temperature of adjacent areas Traffic volume in the area m and district heating (cooling) power P m Composition time series where Λ a It is the collection time set corresponding to the a-time period.

[0066] Step 302: normalize the time series sample data and divide it into a training set and a test set.

[0067] Step 303: Construct a CNN-LSTM network (convolutional long short-term memory neural network) model. As input quantity, P m,t The PSO algorithm is used to optimize the hyperparameters of CNN-LSTM, including the number of convolution kernels, the number of LSTM neurons, and the dropout regularization rate, to minimize the training mean absolute error.

[0068] Step 304: Use the CNN-LSTM model with the optimal hyperparameters to train and obtain the partitioned collaborative temperature control equivalent model for the region m corresponding to the a-time period:

[0069]

[0070] Step 4: The fourth stage of the lower layer considers the building cooling / heat calculation and regional temperature adjustment for user comfort. The specific steps are as follows:

[0071] Step 401: Collect the current outdoor temperature Temperature in the area Adjacent area temperature Traffic volume m,t According to the temperature setting value of step 201 and temperature difference threshold Determine the regional temperature control mode to adjust the regional water supply valve opening and fan speed. The current temperature in the area If the temperature exceeds the third level, full-speed temperature control is adopted (water valve fully open, fan full speed), if the temperature exceeds the second level, fast temperature control is adopted (water valve adjusted on demand, fan full speed), if the temperature exceeds the first level, general temperature control is adopted (water valve fan adjusted on demand), and the current control state is maintained within the first level temperature difference limit. The upper limit of heating (cooling) power in the corresponding control mode is recorded as

[0072] Step 402: Calculate the heating (cooling) power required to keep the indoor temperature of area m constant according to equation (6), as shown in equation (7).

[0073]

[0074] Step 403: Calculate the heating (cooling) power P of each area under the hierarchical control mode under the premise of optimizing user comfort m,t Taking summer as an example, the cooling power of each area is calculated under the premise of optimal user comfort. The optimization target is shown in formula (8), and the constraints include formula (6), formula (10) to formula (11), etc. The calculated total heating (cooling) power of all areas is shown in formula (12).

[0075]

[0076]

[0077]

[0078]

[0079]

[0080] Among them, β m,t+1 is the weight coefficient of user comfort evaluation in the mth area at time t+1, which is related to the area classification and the time period.

[0081] Step 404: The required heating (cooling) power P of each area in the hierarchical control mode m,t and expected temperature Feedback to the upper controller, waiting for the upper controller to feedback the adjustment amount ΔP m,t , and set P according to the actual heating (cooling) power m,t +ΔP m,t Control the opening of the regional water supply valve and the fan speed.

[0082] Step 5: The upper controller distributes the load rate of the air-conditioning units so that the overall operating cost of the air-conditioning system is the lowest or the energy efficiency is the best, specifically:

[0083] Step 501: The heating (cooling) power P required for each area according to the feedback from step 404 m,t , an air conditioning operation cost optimization control model is constructed. The optimization goal is to minimize the overall operation cost of the air conditioning system, as shown in formula (13). The constraints consider the circulation flow to ensure the heat exchange of the farthest area, as shown in formula (14); to maximize the heating (cooling) demand of each area, as shown in formula (15); and the correlation between the circulation flow and the energy supply and the energy consumption characteristics of the air conditioning unit and the circulation pump, as shown in formulas (16) to (18). The optimization variables include the power of each air conditioning unit and the flow of the circulation pump group.

[0084]

[0085]

[0086]

[0087]

[0088]

[0089]

[0090] Among them, p t is the electricity price in period t, and are the power consumption of the air conditioning unit and the pump unit, N ac With N p are the number of air conditioning units and pump units respectively. i,t is the flow rate of the i-th circulating water pump in period t, F t min In order to ensure the minimum circulation flow of heat exchange in the farthest area with functional needs based on the air-conditioning water supply network structure and the energy supply demand fed back from the lower layer. is the output power of the i-th air-conditioning unit in period t, c 0 is the fitting coefficient of the relationship between the air conditioning system power supply, flow rate, and supply and return water temperature difference, T t sup and T t rec is the air conditioning supply and return water temperature, 0 ~z 3 is the fitting coefficient of the relationship between the circulation pump flow and energy consumption, COP i,t The performance coefficient of the i-th air-conditioning unit during period t.

[0091] Step 502: Perform piecewise linear processing on the nonlinear constraints in the optimization model in step 501 to solve the optimal energy supply flow F i,t Power distribution

[0092] Step 503: According to the optimal energy supply flow and energy supply power, the heating (cooling) power P of each area fed back by the lower layer is m,t Make fine adjustments and adjust the adjustment amount ΔP m,t Feedback to the lower-level control device. Specific adjustment methods include:

[0093] (1) If This indicates that the heating (cooling) demand of each region cannot be fully met. Based on the premise of ensuring that the comfort of users in each region is not reduced, the regional energy supply can be fine-tuned by giving priority to the crowded areas during the period or reducing the energy supply in the same proportion.

[0094] (2) If This indicates that the heating (cooling) demand of each region can be met. Based on the air-conditioning water supply network structure and the optimal energy supply flow, find the energy supply mismatch area and make fine adjustments to it. If the energy supply of each region is balanced and there is no mismatch, no adjustment will be made.

[0095] This embodiment provides a double-layer energy-saving optimized operation control system for building air conditioning, which realizes differentiated and refined control of building temperature and energy-saving operation of building air conditioning through the cooperation of the controller of the upper-layer central air conditioning and the lower-layer building intelligent collection and edge control equipment.

[0096] (1) Buildings are zoned based on the building's passenger flow data, and three-level temperature difference control is assigned to different types of zones to achieve temperature optimization control of building zones and time zones, and to achieve differentiated control of building temperatures.

[0097] (2) Relying on historical air conditioning data, an equivalent model of zoned collaborative temperature control is established, and combined with three-level temperature difference control of different zones, refined control of building temperature with the goal of optimizing user comfort is achieved.

[0098] (3) The upper layer considers the constraints of air-conditioning unit start and stop, load rate and working fluid circulation flow rate, and realizes energy-saving operation of building air conditioning under the premise of satisfying the differentiated and refined control of the temperature of the lower layer building.

[0099] Embodiment 2

[0100] This embodiment provides a building air conditioner double-layer energy-saving optimization operation control method, which specifically includes:

[0101] The lower-level subject obtains the flow sequence of people in a certain area in several time periods, clusters several time periods based on the flow sequence, and determines the category of the area based on the clustering results; assigns a multi-level temperature range to each time period in the area based on the category of the area; obtains the temperature parameters and the flow of people at the current moment of the area, obtains the required power when the indoor temperature remains unchanged by calling the partition collaborative temperature control equivalent model, and then optimizes the power of the area under the hierarchical control mode in combination with the multi-level temperature range with the goal of optimizing user comfort;

[0102] The upper body solves the optimal energy supply flow and energy supply power distribution based on the power of all areas in the hierarchical control mode, and then fine-tunes the power in the hierarchical control mode.

[0103] It should be noted here that the various steps in this embodiment correspond one-to-one to the various steps in Example 1, and the specific implementation process is the same, which will not be repeated here.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A double-layer energy-saving optimization operation control system for building air conditioning, It is characterized in that It includes an upper main body and a lower main body arranged in various areas of the building; The lower layer entity is used to obtain a sequence of human flow in a certain area in several time periods, cluster the several time periods based on the sequence of human flow, and determine the category of the area based on the clustering result; Based on the category of the area, a multi-level temperature range is assigned to each time period in the area; for the current moment of the area, the temperature parameters and the flow of people are obtained, and the required power when the indoor temperature remains unchanged is obtained by calling the partition collaborative temperature control equivalent model. Then, combined with the multi-level temperature range, the power of the area under the hierarchical control mode is optimized with the goal of optimizing user comfort; The upper body is used to fine-tune the power in the hierarchical control mode after solving the optimal energy supply flow and energy supply power distribution based on the power of all areas in the hierarchical control mode.

2. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that For a certain area, the time periods are clustered into four categories: stable crowded time period, variable crowded time period, variable sparsely populated time period and stable sparsely populated time period; If the proportion of stable congestion periods and variable congestion periods exceeds the set value, the area is classified as a crowded flow area; If the proportion of time periods belonging to variable and stable periods of few people exceeds the set value, the area is classified as a sparsely populated area; otherwise, the area is classified as a normal flow area.

3. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that The temperature parameters include outdoor temperature, temperature within the area and temperature of adjacent areas.

4. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that For each area, each time period corresponds to a zoned collaborative temperature control equivalent model.

5. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that When optimizing the power in the hierarchical control mode, the constraint condition includes a power upper limit constraint, and the power upper limit is determined based on the control mode; The control modes include full-speed temperature control, fast temperature control and general temperature control.

6. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that When solving the optimal energy supply flow and energy supply power distribution, the optimization goal is to minimize the overall operating cost of the air-conditioning system.

7. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that When solving the optimal energy supply flow and energy supply power distribution, the constraints include: the circulation flow ensures heat exchange in the farthest area, maximizes the satisfaction of heating or cooling needs of each area, the correlation between the circulation flow and energy supply, and the energy consumption characteristics of the air-conditioning unit and the circulation pump.

8. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that The upper body is the controller of the central air conditioner; the lower body is the acquisition and edge control equipment.

9. A building air conditioning double-layer energy-saving optimization operation control system as claimed in claim 1, It is characterized in that The partitioned collaborative temperature control equivalent model adopts a convolutional long short-term memory neural network, and a particle swarm algorithm is used to optimize the hyperparameters of the convolutional long short-term memory neural network.

10. A double-layer energy-saving optimization operation control method for building air conditioning, It is characterized in that include: The lower-level subject obtains the flow sequence of people in a certain area in several time periods, clusters several time periods based on the flow sequence, and determines the category of the area based on the clustering results; Based on the category of the area, a multi-level temperature range is assigned to each time period in the area; for the current moment of the area, the temperature parameters and the flow of people are obtained, and the required power when the indoor temperature remains unchanged is obtained by calling the partition collaborative temperature control equivalent model. Then, combined with the multi-level temperature range, the power of the area under the hierarchical control mode is optimized with the goal of optimizing user comfort; The upper body solves the optimal energy supply flow and energy supply power distribution based on the power of all areas in the hierarchical control mode, and then fine-tunes the power in the hierarchical control mode.

Citation Information

Cited By

  • Biosafety facility ventilation control system and method

    CN120140918A

  • Building power utilization energy-saving method and system based on big data

    CN120706828A