Air conditioner supply and demand collaborative optimization scheduling method

Abstract

The invention discloses an air conditioner supply and demand collaborative optimization scheduling method, which relates to the technical field of air conditioner supply and demand scheduling, and comprises a sensing prediction module, an acquisition comparison module, a deviation correction driving module, a control adjustment module, a cold source control module, a strategy adjustment module and an anomaly detection module. When the abnormality detection module detects that the air conditioner terminal breaks down, the control adjusting module enhances the power of the peripheral equipment to fill the cooling capacity gap, if the water chilling unit breaks down, the cold source control module starts the standby unit to switch the cooling capacity output path, and when the cooling capacity is insufficient, the control adjusting module is in linkage to reduce the air volume of the low-priority area to preferentially guarantee cooling of the core area; meanwhile, a strategy adjusting module automatically matches a predefined strategy chain according to the fault type, for example, global average temperature control is switched when temperature control fails, a load balancing strategy is triggered to be distributed to a standby unit when equipment is overloaded, and the strategy is gradually rolled back to the optimal strategy based on historical data after the fault is repaired; and strategy conflicts and equipment fluctuations are avoided through progressive improvement of cold energy supply.

Description

Technical Field

[0001] The present invention relates to the technical field of air-conditioning supply and demand scheduling, and specifically provides an air-conditioning supply and demand collaborative optimization scheduling method. Background Art

[0002] With the acceleration of the urbanization process and the continuous growth of building energy consumption, as the main component of building energy consumption, the supply and demand scheduling efficiency of the air-conditioning system directly affects the energy utilization rate and user comfort. Traditional air-conditioning systems mostly adopt fixed threshold or periodic adjustment modes, and control the cooling capacity supply through preset temperature and humidity parameters. However, these methods have significant deficiencies:

[0003] 1. Existing technologies rely on real-time monitoring data of environmental sensors, but lack the ability to predict dynamic factors such as personnel flow distribution and meeting reservations, resulting in insufficient prediction accuracy of cooling load demand. When the actual personnel flow suddenly increases (such as during a meeting peak) or environmental parameters fluctuate, the system is difficult to adjust the cooling capacity supply in a timely manner, often resulting in problems of over-supply or under-supply of cooling, causing energy waste or a decline in comfort.

[0004] 2. Traditional air-conditioning systems usually adopt a single operation strategy (such as a full-course energy-saving mode or a comfort-priority mode), and cannot dynamically switch according to scenario requirements. For example, they still maintain high-power operation during low-load periods, or lack a backup device linkage mechanism during emergencies, making it difficult to balance energy efficiency and equipment reliability.

[0005] 3. When existing systems encounter equipment failures (such as chiller overload, temperature control failure), they mostly rely on manual intervention or simple shutdown protection, lacking automated fault isolation, redundant switching, and cooling capacity compensation mechanisms. This may lead to cooling interruption in the core area or too long a recovery time, affecting the user experience.

[0006] 4. Frequent start-stop of cold source equipment (such as chillers, water pumps) not only increases energy consumption but also accelerates equipment aging. In existing technologies, the application of energy storage equipment (such as ice storage) is mostly limited to peak-valley electricity price management and is not combined with a real-time correction mechanism, unable to effectively buffer sudden cooling demand or store redundant cooling capacity.

[0007] In recent years, in response to the above problems, although some studies have tried to optimize cooling load prediction through intelligent algorithms or introduce multi-objective control strategies, there are generally problems such as insufficient module coordination and disconnection between prediction and execution. For example, the prediction model is not combined with a real-time correction closed-loop, the strategy switching lacks a dynamic threshold design, and the abnormal recovery still relies on a fixed strategy fallback, resulting in limited overall optimization effect of the system. Summary of the Invention

[0008] The purpose of the present invention is to provide an air-conditioning supply and demand collaborative optimization scheduling method to solve the problems raised in the above background art.

[0009] To achieve the above object, the present invention provides the following technical solutions: An air-conditioning supply-demand collaborative optimization scheduling method, including a perception and prediction module, which obtains the personnel flow distribution data in the floor through an access control system, a video recognition system, and a meeting reservation system. After obtaining the personnel flow distribution data, the perception and prediction module predicts the cooling load demand of each area on the floor according to the personnel flow distribution data, and controls the air-conditioning equipment to cool each area according to the cooling load demand;

[0010] A collection and comparison module: obtains environmental sensor data, identifies the temperature, humidity, and CO2 concentration parameters of each area to obtain real-time monitoring data, and compares and analyzes the real-time monitoring data with the perception and prediction module to determine whether the deviation between the actual monitoring data and the predicted data exceeds a set threshold;

[0011] A deviation correction and drive module: obtains the cooling capacity supply-demand deviation rate (DR). When the deviation exceeds the threshold, the collection and comparison module sends a signal to the deviation correction and drive module to trigger the deviation correction mechanism of the deviation correction and drive module. The deviation correction and drive module dynamically adjusts the cooling load demand of the perception and prediction module according to the degree of deviation to make it meet the actual cooling load demand of the floor. At the same time, the deviation correction and drive module will record this deviation correction behavior in a log, and when encountering a similar situation later, the deviation correction and drive module will send this log to the perception and prediction module as a reference for cooling load demand prediction;

[0012] A control and adjustment module: controls the air-conditioning equipment to adjust the air volume and cooling capacity supply according to the cooling load demand predicted by the perception and prediction module;

[0013] A cold source control module: collects and summarizes the cooling load of all currently operating cold source equipment, and compares it with the cooling load demand predicted by the perception and prediction module, and flexibly adjusts the cold source operation parameters such as the start and stop of the chiller and the pump frequency to achieve supply based on demand;

[0014] A strategy adjustment module: constructs an operation strategy according to the actual situation of the floor. The operation strategy is divided into energy conservation priority, comfort priority, equipment protection, and area priority;

[0015] An anomaly detection module, which is used to monitor anomalies such as temperature control failure and equipment overload during the operation of the system in real time. When an anomaly event occurs, the anomaly detection module will send the anomaly status to the strategy adjustment module, and the strategy adjustment module will adjust the strategy according to the actual situation or switch redundant equipment;

[0016] The strategy adjustment module receives the cold load demand prediction curve and the trend of people flow distribution from the perception and prediction module, constructs in advance the strategy combinations for future periods. For example, it pre-loads the "comfort priority + area priority" strategy one hour before the peak of the meeting, and automatically adjusts the strategy switching threshold according to the predicted amplitude of cold load fluctuation. For example, when the increase in the number of people exceeds 30%, the comfort priority strategy is forcibly locked. In addition, the strategy adjustment module can dynamically adjust the strategy switching sensitivity according to the cold quantity supply-demand deviation rate (DR) fed back by the deviation correction drive module, maintain the current strategy at low deviation (DR ≤ 5%) and only fine-tune the terminal control parameters, switch to the energy-saving priority mode at medium deviation (5% < DR ≤ 15%) to reduce the cold quantity supply in non-core areas, and emergently enable the combined strategy of equipment protection + area priority at high deviation (DR > 15%).

[0017] Furthermore, the control and regulation module is linked with the anomaly detection module. If the anomaly detection module detects a failure of an air-conditioning terminal, the control and regulation module will fill the cold quantity gap by enhancing the output power of the surrounding equipment.

[0018] Furthermore, the cold source control module receives the cold load demand prediction curve from the perception and prediction module, adjusts in advance the operating state of the cold source equipment, and reduces the delay in cold quantity supply. For example, it obtains the changes in the number of people in each area in the next 1 hour and starts the preheating of the chiller 10 minutes in advance.

[0019] Furthermore, the cold source control module is linked with the strategy adjustment module and the perception and prediction module, and dynamically allocates the output ratio of the cold source equipment according to the area priority and the cold load prediction. For example, it preferentially allocates cold quantity to the meeting room area during the peak period of the meeting room.

[0020] Furthermore, the cold source control module is linked with the deviation correction drive module. When the deviation correction drive module corrects the cold load demand, the cold source control module synchronously adjusts the parameters of the cold source equipment such as the pump frequency and the cold water temperature, and calculates the cold quantity supply-demand deviation rate according to the cold quantity supply-demand deviation rate (DR) formula, and feeds it back to the strategy adjustment module to optimize the global strategy.

[0021] Furthermore, the cold source control module uses energy storage equipment such as ice storage to temporarily store the redundant cold quantity generated by the deviation correction for subsequent emergency use, and avoids frequent start-stop of the cold source equipment.

[0022] Furthermore, the cold quantity supply-demand deviation rate (DR) formula is as follows:

[0023]

[0024] Where Q demand is the required cold quantity (unit: kW), provided by the perception and prediction module or the deviation correction drive module, and predicted based on the people flow data and the environmental parameters;

[0025] Q actual is the actual cooling capacity (unit: kW), which is measured in real time by the sensors of the cold source equipment. The calculation formula is: Q actual = ρ·c·V·ΔT

[0026] ρ: fluid density (kg / m 3 )

[0027] c: specific heat capacity of the fluid (kJ / (kg·°C))

[0028] V: fluid volume flow rate (m 3 / s)

[0029] ΔT: temperature difference between supply and return water (°C).

[0030] Furthermore, the cold source control module is linked with the anomaly detection module. When the anomaly detection module reports a fault in a certain chiller, the cold source control module automatically activates the standby unit and redistributes the cold output path. If the fault results in a cold gap, the cold source control module will link and control the adjustment module to temporarily reduce the air volume in the low-priority area to ensure the cooling supply in the core area first.

[0031] Furthermore, when the strategy adjustment module selects comfort priority, the cold source control module will achieve high-precision temperature control by reducing the temperature fluctuation range of the chilled water. When the strategy adjustment module switches to energy-saving priority, the cold source control module will adopt a strategy of stepped cold supply by adjusting the chilled water temperature according to demand in different time periods. In addition, the strategy adjustment module will dynamically rotate the cold source equipment according to the operation duration of the strategy to avoid long-term high-load operation of a single unit and extend the overall equipment life.

[0032] Furthermore, the strategy adjustment module is linked with the anomaly detection module. According to the fault type reported by the anomaly detection module, it automatically matches the predefined strategy chain. For example, when the temperature control fails, the strategy adjustment module switches to the global average temperature control strategy. When the equipment is overloaded, it triggers the load balancing strategy to reduce the operation intensity of the same group of equipment and distribute it to the standby unit. After the fault is repaired, the strategy adjustment module will automatically roll back to the optimal strategy based on the historical operation data.

[0033] The present invention provides an air-conditioning supply-demand collaborative optimization scheduling method, which has the following beneficial effects:

[0034] 1. The acquisition and comparison module of the present invention obtains real-time monitoring data of each area through environmental sensors, and compares and analyzes it with the cold load prediction value of the perception prediction module. When the deviation between the actual data and the predicted value exceeds the set threshold, the module sends a signal to the correction drive module to trigger the correction mechanism. The latter dynamically corrects the cold load demand prediction value according to the degree of deviation to make it fit the actual demand. At the same time, the correction behavior is recorded in the log as a prediction reference for subsequent similar scenarios. This process constructs a closed-loop control of data acquisition-deviation analysis-strategy adjustment. Compared with the traditional periodic adjustment mode, it significantly improves the system response speed and the matching accuracy of cold supply and demand.

[0035] 2. The strategy adjustment module of the present invention builds a strategy combination in advance (such as preloading comfort priority + regional priority strategy before the meeting peak) based on the cold load demand forecast curve and the flow distribution trend provided by the perception prediction module, reduces the strategy switching delay and improves the response efficiency, and automatically adjusts the threshold according to the fluctuation amplitude of the cold load (such as forcibly locking the comfort priority strategy when the flow increase exceeds 30%) to avoid the influence of strategy lag on comfort. In addition, combined with the cold supply and demand deviation rate (DR) fed back by the correction drive module, the sensitivity is dynamically adjusted: when the deviation is low (DR≤5%), the terminal parameters are fine-tuned to maintain stability, and when the deviation is medium (5%), the terminal parameters are fine-tuned to maintain stability.<DR≤15%)时切换至节能优先模式以平衡能效,高偏差(DR> The "equipment protection + area priority" combined strategy is urgently activated when the temperature drops by 15% to give priority to cooling in core areas and prevent equipment overload. This design solves the pain points of traditional air conditioning, such as delayed response, rigid strategies, and imbalance between energy efficiency and comfort, through the deep coordination of predictive data and real-time monitoring.

[0036] 3. In the present invention, when the abnormal detection module detects a fault in the air-conditioning terminal, the control and regulation module fills the cooling gap by enhancing the power of the peripheral equipment. If the chiller fails, the cold source control module enables the spare unit and switches the cooling output path. When the cooling capacity is insufficient, the linkage control and regulation module reduces the air volume in the low-priority area to give priority to the cooling supply in the core area. At the same time, the strategy adjustment module automatically matches the predefined strategy chain according to the fault type (such as switching to the global average temperature control when the temperature control fails, and triggering the load balancing strategy to allocate to the spare unit when the equipment is overloaded), and gradually rolls back to the optimal strategy based on historical data after the fault is repaired. Through phased parameter adjustment (such as gradual increase in cooling supply), strategy conflicts and equipment fluctuations are avoided to achieve a smooth transition.

[0037] 4. The control and regulation module of the present invention is linked with the abnormal detection module. When the air-conditioning terminal failure is detected, the cooling capacity gap is filled by enhancing the power of the peripheral equipment. The cold source control module dynamically allocates the cold source output ratio (such as giving priority to cooling in the peak hours of the conference room) based on the regional priority provided by the strategy adjustment module and the cold load prediction data of the perception prediction module, and uses ice storage and other energy storage devices to store redundant cooling capacity for sudden demand, avoiding frequent start and stop of equipment. If the abnormal detection module reports the failure of the chiller unit, the cold source control module automatically enables the standby unit and switches the output path. When the cooling capacity is insufficient, the linkage control and regulation module reduces the air volume in the low priority area to ensure the cooling of the core area. When the strategy switching module selects "comfort priority", the cold source control module realizes high-precision temperature control by reducing the fluctuation range of the cold water temperature. When it switches to "energy saving priority", the cold water temperature is adjusted in different time periods as needed to realize step cooling. In addition, the cold source equipment dynamically rotates the main and standby roles according to the operation time of the strategy, avoiding long-term high-load operation of a single machine, thereby extending the overall life. Through deep collaboration between modules, the system realizes accurate matching of cooling capacity, rapid response to faults and continuous optimization of energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of a real-time monitoring and deviation correction process of an air conditioning supply and demand collaborative optimization scheduling method of the present invention;

[0039] Figure 2 A schematic diagram of a strategy formulation and dynamic switching process of an air conditioning supply and demand collaborative optimization scheduling method of the present invention;

[0040] Figure 3 A schematic diagram of an abnormality detection and emergency response process of an air conditioning supply and demand collaborative optimization scheduling method of the present invention. DETAILED DESCRIPTION

[0041] See also Figures 1 to 3 , the present invention provides a technical solution: an air conditioning supply and demand coordinated optimization scheduling method, including a perception prediction module, which obtains the crowd distribution data in the floor through the access control system, the video recognition system, and the conference reservation system. After obtaining the crowd distribution data, the perception prediction module predicts the cooling load demand of each area on the floor according to the crowd distribution data, and controls the air conditioning equipment to cool each area according to the cooling load demand;

[0042] Collection and comparison module: obtains environmental sensor data, identifies the temperature, humidity, and CO2 concentration parameters of each area, obtains real-time monitoring data, compares and analyzes the real-time monitoring data with the perception prediction module, and determines whether the deviation between the actual monitoring data and the predicted data exceeds the set threshold;

[0043] Deviation correction drive module: Obtain the cooling capacity supply-demand deviation rate (DR). When the deviation exceeds the threshold, the acquisition and comparison module sends a signal to the deviation correction drive module, triggering the deviation correction mechanism of the deviation correction drive module. The deviation correction drive module dynamically adjusts the cooling load demand of the perception and prediction module according to the degree of deviation, so that it matches the actual cooling load demand of the floor;

[0044] Control and regulation module: According to the cooling load demand predicted by the perception and prediction module, control the air-conditioning equipment to adjust the air volume and cooling capacity supply;

[0045] Chilled water source control module: Collect and summarize the cooling load of all currently operating chilled water source equipment, and compare it with the cooling load demand predicted by the perception and prediction module. Flexibly adjust the chilled water source operation parameters such as the start and stop of the chiller and the pump frequency to achieve supply based on demand;

[0046] Strategy adjustment module: Construct an operation strategy according to the actual situation of the floor. The operation strategy is divided into energy conservation priority, comfort priority, equipment protection, and area priority;

[0047] Abnormality detection module, used to monitor abnormal phenomena such as temperature control failure and equipment overload during the operation of the system in real time. When an abnormal event occurs, the abnormality detection module sends the abnormal state to the strategy adjustment module, and the strategy adjustment module will adjust the strategy or switch redundant equipment according to the actual situation.

[0048] The specific operation is as follows. When the system starts, the perception and prediction module, acquisition and comparison module, deviation correction drive module, control and regulation module, chilled water source control module, strategy adjustment module, and abnormality detection module enter the normal working state. The perception and prediction module starts to work. Through the access control system, video recognition system, and meeting reservation system, it obtains the real-time personnel flow distribution data in the floor. The perception and prediction module uses the built-in algorithm to predict the cooling load demand of each area of the floor according to the collected personnel flow distribution data. The control and regulation module controls the air-conditioning equipment to adjust the air volume and cooling capacity supply according to the prediction result of the perception and prediction module to meet the initially predicted cooling load demand;

[0049] During the continuous operation of the system, the acquisition and comparison module works. Using the environmental sensors located in the floors, it continuously monitors the temperature, humidity, and CO2 concentration parameters in each floor area to obtain real-time monitoring data. The acquisition and comparison module compares and analyzes the real-time monitoring data with the predicted data of the perception and prediction module to determine whether the deviation between the actual monitoring data and the predicted data exceeds the set threshold. If the deviation is within the set threshold, the current scheduling strategy is continued. When the deviation exceeds the threshold, the acquisition and comparison module sends a signal to the correction drive module to trigger the correction mechanism. The correction drive module dynamically adjusts the predicted value of the cooling load demand of the perception and prediction module according to the degree of deviation to make it meet the actual cooling load demand of the floor. At the same time, the correction drive module will record this correction behavior in the log. When encountering a similar situation later, it can send this log to the perception and prediction module as a reference for the prediction of the cooling load demand. Through the above operations, the system can build an execution closed-loop from data acquisition - deviation calculation - strategy adjustment, enabling the air conditioning system to have the ability of real-time dynamic correction. Compared with the periodic adjustment mode of traditional air conditioners, it can effectively improve the response speed and the matching accuracy of the cooling supply and demand;

[0050] In addition, the strategy adjustment module constructs operation strategies according to the actual situation of the floors, including energy-saving priority, comfort priority, equipment protection, and area priority strategies. The strategy adjustment module receives the predicted curve of the cooling load demand and the trend of the personnel flow distribution of the perception and prediction module, and constructs the strategy combination for the future period in advance. For example, one hour before the peak of the meeting, it preloads the "comfort priority + area priority" strategy. This enables the system to significantly reduce the strategy switching delay compared with the passive scheduling method adopted by traditional air conditioners and effectively improve the system response efficiency. In addition, the strategy adjustment module can automatically adjust the strategy switching threshold according to the predicted amplitude of the cooling load fluctuation of the perception and prediction module. For example, when the increase in the personnel flow exceeds 30%, the comfort priority strategy is forcibly locked. This can avoid the strategy lag caused by sudden demands and affect the comfort in the space. In addition, the strategy switching module can dynamically adjust the strategy switching sensitivity according to the cooling supply and demand deviation rate (DR) fed back by the correction drive module. When the deviation is low (DR ≤ 5%), the current strategy is maintained, and only the terminal control parameters are slightly adjusted to maintain the stability of the strategy. When the medium deviation (5% < DR ≤ 15%) occurs, it switches to the energy-saving priority mode to reduce the cooling supply in the non-core areas and achieve the balance of energy efficiency and demand. When the high deviation (DR > 15%) occurs, the strategy switching module will urgently enable the equipment protection + area priority combination strategy to give priority to ensuring the cooling supply in the core areas and prevent equipment overload. Through the above operations, both equipment damage is avoided and the comfort of key areas is ensured, solving the drawback that traditional single strategies cannot balance safety and efficiency. By deeply binding the predicted data, real-time monitoring, and dynamic strategies, the system solves the problems of lagging response, rigid strategies, and difficulty in balancing energy efficiency and comfort in traditional air conditioning systems through forward-looking preloading, hierarchical response, and multi-strategy collaboration;

[0051] During the operation of the system, the anomaly detection module can monitor the anomalies during system operation in real time, such as temperature control failure, equipment overload, etc. When the anomaly detection module detects a fault in the air-conditioning terminal, the control and regulation module can fill the cooling capacity gap by increasing the output power of the peripheral equipment. When the anomaly detection module detects a fault in the chiller, the cold source control module automatically activates the standby unit and reallocates the cooling capacity output path. If the fault results in a cooling capacity gap, the control and regulation module is linked to temporarily reduce the air volume in the low-priority area to prioritize the cooling supply in the core area. In addition, according to the fault type reported by the anomaly detection module, the policy adjustment module will automatically match the predefined policy chain. For example, when the temperature control fails, the policy switching module switches to the global average temperature control policy. When the equipment is overloaded, the load balancing policy is triggered to reduce the operating intensity of the same group of equipment and allocate it to the standby unit, and automatically roll back to the optimal policy based on historical operation data after the fault is repaired. This can effectively prevent policy conflicts. For example, during a fault, an emergency policy of equipment protection + area priority is temporarily enabled, and directly switching back to the normal policy may cause sudden changes in the supply and demand of cooling capacity. The automatic rollback can smoothly transition to the optimal policy by gradually adjusting parameters (increasing the cooling capacity supply in stages), avoiding frequent start-stop of equipment or fluctuations in temperature and humidity;

[0052] In addition, the control and regulation module can be linked with the anomaly detection module. If the anomaly detection module detects a fault in an air-conditioning terminal, the control and regulation module will fill the cooling capacity gap by increasing the output power of the peripheral equipment. The cold source control module can be linked with the policy adjustment module and the perception and prediction module to dynamically allocate the output ratio of the cold source equipment according to the area priority and the cooling load prediction. For example, during the peak period of the meeting room, the cooling capacity is preferentially allocated to the meeting room area. At the same time, the cold source control module uses energy storage equipment such as ice storage to temporarily store the redundant cooling capacity generated by correction for subsequent emergency use, avoiding frequent start-stop of the cold source equipment. In addition, the cold source control module can be linked with the anomaly detection module. When the anomaly detection module reports a fault in a certain chiller, the cold source control module automatically activates the standby unit and reallocates the cooling capacity output path. If the fault results in a cooling capacity gap, the cold source control module will be linked to the control and regulation module to temporarily reduce the air volume in the low-priority area to prioritize the cooling supply in the core area. When the policy switching module selects comfort priority, the cold source control module will achieve high-precision temperature control by reducing the range of cold water temperature fluctuations. When the policy switching module switches to energy-saving priority, the cold source control module will adopt a strategy of stepped supply of cooling capacity by adjusting the cold water temperature according to demand in different time periods. In addition, the policy switching module will dynamically rotate the cold source equipment according to the operation duration of the policy, avoiding long-term high-load operation of a single unit and extending the overall equipment life. Through the above operations, the system can achieve continuous optimization and energy efficiency improvement through the mutual cooperation of modules.

[0053] It should be noted that in this text, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article or device.

[0054] In this text, specific examples are used to illustrate the principles and implementation manners of the present invention. The description of the above examples is only for helping to understand the method of the present invention and its core idea. The above description is only the preferred implementation manner of the present invention. It should be noted that due to the limited nature of literal expression and objectively infinite specific structures, for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements, retouches or changes can be made, or the above technical features can be combined in an appropriate manner; these improvements, retouches, changes or combinations, or directly applying the concept and technical solution of the invention to other occasions without improvement, shall all be regarded as the protection scope of the present invention.

Claims

1. An air conditioner supply-demand collaborative optimization scheduling method, characterized in that, The method includes: A perception and prediction module, which obtains the people flow distribution data within the floor through the access control system, video recognition system, and meeting reservation system. After obtaining the people flow distribution data, the perception and prediction module predicts the cooling load demand of each area on the floor based on the people flow distribution data, and controls the air conditioning equipment to cool each area according to the cooling load demand; A strategy adjustment module: constructs an operation strategy according to the actual situation of the floor. The operation strategies are divided into energy conservation priority, comfort priority, equipment protection, and area priority; The strategy adjustment module receives the cooling load demand prediction curve and people flow distribution trend of the perception and prediction module, constructs a strategy combination for the future period in advance, pre-loads the "comfort priority + area priority" strategy one hour before the meeting peak, automatically adjusts the strategy switching threshold according to the predicted cooling load fluctuation range, and forcibly locks the comfort priority strategy when the people flow increase exceeds 30%. In addition, the strategy adjustment module can dynamically adjust the strategy switching sensitivity according to the cooling capacity supply-demand deviation rate fed back by the deviation correction driving module, maintain the current strategy when the low deviation DR ≤ 5%, only fine-tune the terminal control parameters, switch to the energy conservation priority mode when the medium deviation 5% < DR ≤ 15%, reduce the cooling capacity supply in the non-core area, and emergently enable the equipment protection + area priority combined strategy when the high deviation DR > 15%; Among them, the formula for the cooling capacity supply-demand deviation rate DR is: Among which Q demand is the required cooling capacity, provided by the perception prediction module or the correction driving module, and predicted based on the pedestrian flow data and environmental parameters; Q actual is the actual cooling capacity, which is measured in real time by the sensors of the cold source equipment, and the calculation formula is: Q actual = ρ·c·V·ΔT ρ: fluid density c: specific heat capacity of the fluid V: fluid volume flow rate ΔT: supply and return water temperature difference.

2. The air conditioner supply-demand collaborative optimization scheduling method according to claim 1, characterized in that An acquisition and comparison module: obtains the environmental sensor data, identifies the temperature, humidity, and CO2 concentration parameters of each area to obtain real-time monitoring data, and compares and analyzes the real-time monitoring data with the perception and prediction module to determine whether the deviation between the actual monitoring data and the predicted data exceeds the set threshold; A deviation correction driving module: obtains the cooling capacity supply-demand deviation rate DR. When the deviation exceeds the threshold, the acquisition and comparison module sends a signal to the deviation correction driving module to trigger the deviation correction mechanism of the deviation correction driving module. The deviation correction driving module dynamically adjusts the cooling load demand of the perception and prediction module according to the deviation degree to make it meet the actual cooling load demand of the floor; A control and regulation module: controls the air conditioning equipment to adjust the air volume and cooling capacity supply according to the cooling load demand predicted by the perception and prediction module; A cold source control module: collects and summarizes the cooling load of all currently operating cold source equipment, and compares it with the cooling load demand predicted by the perception and prediction module, and flexibly adjusts the cold source operation parameters such as the start and stop of the chiller and the pump frequency to achieve supply based on demand; An anomaly detection module, which is used to monitor anomalies such as temperature control failure and equipment overload in real time during the operation of the system. When an anomaly event occurs, the anomaly detection module sends the anomaly status to the strategy adjustment module, and the strategy adjustment module will adjust the strategy or switch redundant equipment according to the actual situation.

3. The air conditioner supply-demand collaborative optimization scheduling method according to claim 2, wherein The control and regulation module is linked with the anomaly detection module. If the anomaly detection module detects a failure of an air conditioning terminal, the control and regulation module will fill the cooling capacity gap by increasing the output power of the surrounding equipment.

4. The air conditioner supply-demand collaborative optimization scheduling method according to claim 2, characterized in that, The cold source control module receives the cold load demand prediction curve of the perception and prediction module, adjusts the operating state of the cold source equipment in advance, and reduces the delay of cold supply. For example, it obtains the changes in the number of people in each area in the next hour and starts the preheating of the chiller 10 minutes in advance.

5. The air conditioner supply-demand collaborative optimization scheduling method according to claim 2, wherein The cold source control module is linked with the strategy adjustment module and the perception and prediction module, and dynamically allocates the output ratio of the cold source equipment according to the regional priority and cold load prediction. For example, it preferentially allocates cold to the meeting room area during the peak period of the meeting room.

6. The air conditioner supply-demand collaborative optimization scheduling method according to claim 2, wherein, The cold source control module is linked with the deviation correction drive module. When the deviation correction drive module corrects the cold load demand, the cold source control module synchronously adjusts the parameters of the cold source equipment such as the pump frequency and the cold water temperature, calculates the cold supply and demand deviation rate according to the cold supply and demand deviation rate formula, and feeds it back to the strategy adjustment module to optimize the global strategy. The cold source control module uses energy storage equipment such as ice storage to temporarily store the redundant cold generated by the deviation correction for subsequent emergency needs, and avoids frequent start and stop of the cold source equipment.

7. A method for collaborative optimization scheduling of air conditioner supply and demand according to claim 2, characterized in that The cold source control module is linked with the anomaly detection module. When the anomaly detection module reports a fault in a certain chiller, the cold source control module automatically activates the standby unit and reallocates the cold output path. If the fault causes a cold gap, the cold source control module will link with the control and regulation module to temporarily reduce the air volume in the low-priority area and give priority to ensuring the cold supply in the core area.

8. The air conditioner supply-demand collaborative optimization scheduling method according to claim 2, wherein When the strategy adjustment module selects comfort priority, the cold source control module will achieve high-precision temperature control by reducing the cold water temperature fluctuation range. When the strategy adjustment module switches to energy-saving priority, the cold source control module will adopt a strategy of stepped cold supply by adjusting the cold water temperature according to demand in different time periods. In addition, the strategy adjustment module will dynamically rotate the cold source equipment according to the running duration of the strategy to avoid long-term high-load operation of a single unit and extend the overall equipment life.

9. The air conditioner supply-demand collaborative optimization scheduling method according to claim 2, wherein The strategy adjustment module is linked with the anomaly detection module. According to the fault type reported by the anomaly detection module, it automatically matches the predefined strategy chain. For example, when the temperature control fails, the strategy adjustment module switches to the global average temperature control strategy. When the equipment is overloaded, it triggers the load balancing strategy to reduce the running intensity of the same group of equipment and allocate it to the standby unit. After the fault is repaired, the strategy adjustment module will automatically roll back to the optimal strategy based on the historical operation data.

Images