Energy consumption detection method based on multi-parameter fusion and related device
By collecting multi-parameter fusion data from air conditioning equipment and using a reinforcement learning decision engine to dynamically adjust the operation of the air conditioning, the problems of inaccurate assessment and lack of adaptive control strategies in traditional air conditioning energy consumption management are solved, and accurate assessment and adaptive optimization of air conditioning energy consumption are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- QINGDAO HAIER AIR CONDITIONING ELECTRONICS CO LTD
- Filing Date
- 2026-02-13
- Publication Date
- 2026-06-05
AI Technical Summary
Traditional air conditioning energy management relies on basic electricity consumption data, which leads to inaccurate energy consumption assessment and a lack of adaptive control strategies, affecting the effectiveness of energy efficiency optimization.
By collecting multi-parameter fusion data from air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters, and using a reinforcement learning decision engine to output optimization strategies, the operation of the air conditioning is dynamically adjusted to minimize total energy consumption.
It enables accurate assessment and adaptive optimization of air conditioning energy consumption, effectively reducing energy consumption and improving energy efficiency.
Smart Images
Figure CN122149057A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of air conditioning energy management technology, and in particular to an energy consumption detection method and related device based on multi-parameter fusion. Background Technology
[0002] Air conditioning energy management is a key measure for energy efficiency optimization. Traditional solutions mainly rely on basic electricity consumption. This single data collection method can easily lead to inaccurate energy consumption assessment and a lack of adaptive control strategies, thus limiting the effectiveness of energy efficiency optimization. Summary of the Invention
[0003] In view of the above problems, this application provides an energy consumption detection method and related apparatus based on multi-parameter fusion, so as to achieve energy consumption assessment and adaptive control based on multi-parameter fusion. The specific solution is as follows: The first aspect of this application provides an energy consumption detection method based on multi-parameter fusion, the energy consumption detection method based on multi-parameter fusion comprising: Collect the operating parameters of the air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters; Based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the current time, determine the actual comprehensive energy consumption evaluation coefficient at the current time; If the actual comprehensive energy consumption evaluation coefficient at the current time meets the corresponding high energy consumption condition, with the goal of minimizing total energy consumption, the reinforcement learning decision engine outputs the target instruction optimization strategy at the current time, and drives the executor to run according to the target instruction optimization strategy at the current time.
[0004] In one possible implementation, the equipment parameters include supply water temperature, return water temperature, water circulation flow rate and main unit input power; the environmental parameters include cooling area, indoor and outdoor temperature difference and ambient humidity; and the operating status parameters include compressor actual input power and continuous operating time. The step of determining the actual comprehensive energy consumption assessment coefficient for the current time based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment includes: The energy efficiency ratio at the current time is determined based on the supply water temperature, return water temperature, water circulation flow rate, and main unit input power at the current time. The actual energy consumption at the current time is determined based on the energy efficiency ratio, the actual input power of the compressor, and the continuous operating time at the current time. The required energy consumption at the current time is determined using the area of the cooling zone, the indoor-outdoor temperature difference, and the ambient humidity. Based on the actual energy consumption and demand energy consumption at the current time, determine the actual comprehensive energy consumption evaluation coefficient at the current time.
[0005] In one possible implementation, the operating status parameters also include the actual CPU load; The determination of the actual comprehensive energy consumption assessment coefficient for the current time based on the actual energy consumption and demand energy consumption at the current time includes: Obtain the learning parameters output by the reinforcement learning decision engine in the previous time step. The learning parameters are output simultaneously with the target instruction optimization strategy in the previous time step and include the optimal CPU load and load weight coefficient. Based on the actual CPU load at the current time, and the optimal CPU load and load weight coefficient at the previous time, determine the load coupling term at the current time; The actual comprehensive energy consumption evaluation coefficient for the current time is determined by using the actual energy consumption, demand energy consumption, and load coupling term at the current time.
[0006] In one possible implementation, the step of minimizing total energy consumption and outputting the target instruction optimization strategy for the current time through a reinforcement learning decision engine includes: Obtain the policy constraints and the actual absolute energy consumption of the air conditioning equipment at the current time; The reinforcement learning decision engine searches for candidate instruction optimization strategies that satisfy the policy constraints, and predicts the target comprehensive energy consumption evaluation coefficient and target absolute energy consumption of the candidate instruction optimization strategies in the next time step. The strategy with the smallest overall target energy consumption evaluation coefficient and the smallest absolute target energy consumption is selected from the candidate instruction optimization strategies as the target instruction optimization strategy for the current time. The overall target energy consumption evaluation coefficient of the target instruction optimization strategy for the current time is less than the actual overall target energy consumption evaluation coefficient for the current time, and the absolute target energy consumption of the target instruction optimization strategy for the current time is less than the actual absolute energy consumption for the current time.
[0007] In one possible implementation, the energy consumption detection method based on multi-parameter fusion further includes: When the actuator finishes operating, the actual comprehensive energy consumption assessment coefficient for the next time is determined based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the next time. The actual absolute energy consumption of the air conditioning equipment at the next time is obtained, and the effectiveness of the target instruction optimization strategy at the current time is evaluated by comparing the actual comprehensive energy consumption evaluation coefficient and the actual absolute energy consumption at the current time with those at the next time. If the target instruction optimization strategy at the current time is invalid, the executor is driven to roll back.
[0008] In one possible implementation, the energy consumption detection method based on multi-parameter fusion further includes: Based on the effectiveness of the target instruction optimization strategy at the current time, a learning experience is constructed, and the reinforcement learning decision engine is retrained using the learning experience.
[0009] A second aspect of this application provides an energy consumption detection device based on multi-parameter fusion, the energy consumption detection device based on multi-parameter fusion comprising: The data acquisition module is used to collect the operating parameters of the air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters. The energy consumption detection module is used to determine the actual comprehensive energy consumption evaluation coefficient at the current time based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the current time. If the actual comprehensive energy consumption evaluation coefficient at the current time meets the corresponding high energy consumption condition, the module outputs the target instruction optimization strategy at the current time through the reinforcement learning decision engine with the goal of minimizing total energy consumption, and drives the actuator to run according to the target instruction optimization strategy at the current time.
[0010] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the energy consumption detection method based on multi-parameter fusion described in the first aspect or any implementation thereof.
[0011] A fourth aspect of this application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the energy consumption detection method based on multi-parameter fusion of the first aspect or any implementation thereof described above.
[0012] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the energy consumption detection method based on multi-parameter fusion described in the first aspect or any implementation thereof.
[0013] By employing the above technical solution, this application provides an energy consumption detection method and related apparatus based on multi-parameter fusion, comprising: collecting operating parameters of air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters; determining the actual comprehensive energy consumption evaluation coefficient at the current time based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the current time; if the actual comprehensive energy consumption evaluation coefficient at the current time meets the corresponding high energy consumption condition, with the goal of minimizing total energy consumption, outputting the target instruction optimization strategy at the current time through a reinforcement learning decision engine, and driving the actuator to run according to the target instruction optimization strategy at the current time. This application accurately evaluates the actual comprehensive energy consumption of air conditioning equipment at the current time through multi-parameter fusion, and adaptively optimizes when energy consumption is high, thereby effectively reducing air conditioning energy consumption and ensuring energy efficiency optimization results. Attached Figure Description
[0014] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.
[0015] Figure 1 A flowchart illustrating an energy consumption detection method based on multi-parameter fusion provided in this application embodiment; Figure 2 A partial flowchart illustrating an energy consumption detection method based on multi-parameter fusion provided in this application embodiment; Figure 3 This is another schematic flowchart of an energy consumption detection method based on multi-parameter fusion provided in an embodiment of this application; Figure 4 This is another schematic flowchart of an energy consumption detection method based on multi-parameter fusion provided in an embodiment of this application; Figure 5 A schematic diagram of the structure of an energy consumption detection device based on multi-parameter fusion provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0016] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.
[0017] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.
[0018] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.
[0019] This application provides an energy consumption detection method based on multi-parameter fusion, which achieves global energy consumption optimization of air conditioning equipment through a dynamic comprehensive energy consumption assessment strategy and a reinforcement learning decision engine. The energy consumption detection method based on multi-parameter fusion of this application will be described in detail below with reference to the accompanying drawings.
[0020] See Figure 1 , Figure 1 This is a flowchart illustrating an energy consumption detection method based on multi-parameter fusion, provided as an embodiment of this application. Figure 1 As shown in the figure, the energy consumption detection method based on multi-parameter fusion provided in this application embodiment may include steps S101 to S103, which are described in detail below.
[0021] S101 collects the operating parameters of the air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters.
[0022] In this embodiment of the application, relevant sensors are deployed in the air conditioning equipment to collect the operating parameters of the air conditioning equipment. These operating parameters include equipment parameters, environmental parameters, and operating status parameters. Among them, the equipment parameters can characterize the efficiency of the air conditioning equipment in converting electrical energy into cooling capacity, the environmental parameters can characterize the building environment where the air conditioning equipment is located and its cooling capacity requirements, and the operating status parameters can characterize the real-time operating status of the air conditioning equipment.
[0023] S102, Based on the equipment parameters, environmental parameters and operating status parameters of the air conditioning equipment at the current time, determine the actual comprehensive energy consumption assessment coefficient at the current time.
[0024] In this embodiment, by continuously collecting the operating parameters of the air conditioning equipment at different times, the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the current time can be determined, thereby obtaining a profile of the air conditioning equipment at the current time. Furthermore, data preprocessing is performed on the equipment parameters, environmental parameters, and operating status parameters at the current time, including outlier filtering, data standardization, and missing value imputation. Specifically, outlier filtering uses threshold methods (e.g., temperature > 50℃) or statistical methods (3σ principle) to remove sensor fault data. Data standardization normalizes parameters with different dimensions, such as temperature, power, and flow rate, to the [0,1] interval. Missing value imputation uses linear interpolation or the last valid value to fill in data lost during brief communication. Furthermore, the actual comprehensive energy consumption of the air conditioning equipment can be evaluated based on the preprocessed equipment parameters, environmental parameters, and operating status parameters at the current time, thereby obtaining an actual comprehensive energy consumption evaluation coefficient at the current time. The larger the actual comprehensive energy consumption evaluation coefficient, the higher the comprehensive energy consumption of the air conditioning equipment.
[0025] In one possible implementation, a comprehensive energy consumption assessment coefficient model can be established, comprehensively considering three categories of parameters: equipment parameters, environmental parameters, and operating status parameters, to determine the actual comprehensive energy consumption assessment coefficient at the current time. In this regard, an embodiment of this application provides an energy consumption detection method based on multi-parameter fusion, wherein the equipment parameters include supply water temperature, return water temperature, water circulation flow rate, and main unit input power; the environmental parameters include cooling area area, indoor-outdoor temperature difference, and ambient humidity; and the operating status parameters include the compressor's actual input power and continuous operating time.
[0026] Specifically, contact or insertion temperature sensors are deployed at the supply and return pipes of the cooling water system to measure the supply and return water temperatures; flow meters are deployed on the main pipeline of the cooling water system to measure the water circulation flow rate; power meters are deployed on the power supply lines of the air conditioning unit (such as compressors and condensers) to measure the unit's input power; based on test data, the cooling area is assessed according to the cooling or heating efficiency of the air conditioning equipment; indoor and outdoor temperature sensors are deployed to measure the indoor and outdoor temperature difference; humidity sensors are deployed at key locations in the air-conditioned service area (such as the center of the room and near the return air vent) to measure the ambient humidity; the actual input power of the compressor can be obtained from the unit's input power through model separation or direct measurement; the continuous operating time can be obtained by accumulating the equipment's operating status through the system clock. Furthermore, in practical applications, power meters can be deployed on the power supply lines of the cooling water circulating pump to measure the pump's input power, and power meters can be deployed on the power supply lines of auxiliary equipment such as cooling tower fans, fresh air units, and air handling unit fans to measure the auxiliary equipment's input power. Therefore, the total energy consumption of the air conditioning equipment can be comprehensively calculated based on the cumulative values of the main unit's input power, the pump's input power, and the auxiliary equipment's input power. Thus, this application enables the construction of a panoramic, quantifiable energy consumption and operational status monitoring network that surpasses the capabilities of the air conditioner's built-in control board.
[0027] See Figure 2 , Figure 2 This is a partial flowchart illustrating an energy consumption detection method based on multi-parameter fusion, provided as an embodiment of this application. Figure 2 As shown in the embodiment of this application, an energy consumption detection method based on multi-parameter fusion is provided. Step S102, "determine the actual comprehensive energy consumption evaluation coefficient at the current time based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the current time", may include steps S201 to S204. These steps are described in detail below.
[0028] S201 determines the energy efficiency ratio for the current time based on the supply water temperature, return water temperature, water circulation flow rate, and main unit input power at the current time.
[0029] In this embodiment of the application, the energy efficiency ratio at the current time can be calculated using the following formula (1): (1) in, Indicates the energy efficiency ratio; Indicates cooling capacity; Indicates the host input power; This indicates the specific heat capacity of water; Indicates the density of water; Indicates the water circulation flow rate; This indicates the temperature difference between the supply water temperature and the return water temperature.
[0030] S202, determine the actual energy consumption at the current time based on the energy efficiency ratio, the actual input power of the compressor, and the continuous running time at the current time.
[0031] In this embodiment of the application, the actual energy consumption at the current time can be calculated using the following formula (2): (2) in, Indicates actual energy consumption; This indicates the actual input power of the compressor; Indicates the duration of continuous operation.
[0032] S203 determines the required energy consumption at the current time by using the area of the cooling zone, the indoor-outdoor temperature difference, and the ambient humidity.
[0033] In this embodiment of the application, the energy consumption demand at the current time can be calculated according to the following formula (3): (3) in, Indicates energy demand; Indicates the area of the refrigerated zone; Indicates the temperature difference between indoors and outdoors; Indicates ambient humidity.
[0034] S204, Based on the actual energy consumption and demand energy consumption at the current time, determine the actual comprehensive energy consumption assessment coefficient at the current time.
[0035] In this embodiment of the application, the ratio of actual energy consumption to demand energy consumption at the current time can be used as the actual comprehensive energy consumption evaluation coefficient at the current time.
[0036] In one possible implementation, to accurately assess the actual comprehensive energy consumption of air conditioning equipment, a load coupling term for the CPU load can be introduced to obtain an accurate evaluation coefficient for the actual comprehensive energy consumption. See also Figure 3 , Figure 3 This is another schematic flowchart illustrating an energy consumption detection method based on multi-parameter fusion, provided as an embodiment of this application. Figure 3 As shown in the embodiment of this application, an energy consumption detection method based on multi-parameter fusion is provided. The operating status parameters also include the actual CPU load. Step S204, "determine the actual comprehensive energy consumption evaluation coefficient at the current time based on the actual energy consumption and demand energy consumption at the current time", may include steps S301 to S303. These steps are described in detail below.
[0037] S301, obtain the learning parameters output by the reinforcement learning decision engine in the previous time step. The learning parameters are output simultaneously with the target instruction optimization strategy in the previous time step, and include the optimal CPU load and load weight coefficient.
[0038] In this embodiment, the reinforcement learning engine, while inputting target instruction optimization strategies at different times, also outputs learning parameters at different times. These learning parameters include optimal CPU load and load weight coefficients. Optimal CPU load represents the level of CPU load with the highest energy efficiency, and the load weight coefficient represents the proportion of load coupling terms in the actual comprehensive energy consumption evaluation process. Therefore, the learning parameters from the previous time period, including optimal CPU load and load weight coefficients, can be obtained.
[0039] S302, based on the actual CPU load at the current time, and the optimal CPU load and load weight coefficient at the previous time, determine the load coupling term at the current time.
[0040] In this embodiment of the application, the load coupling term at the current time can be calculated according to the following formula (4): (4) in, Indicates load coupling terms; Indicates the load weighting coefficient; Indicates the actual CPU load; This indicates the optimal CPU load.
[0041] S303, using the actual energy consumption, demand energy consumption and load coupling terms at the current time, determines the actual comprehensive energy consumption evaluation coefficient at the current time.
[0042] In this embodiment of the application, the actual comprehensive energy consumption assessment coefficient at the current time can be calculated according to the following formula (5): (5) in, This represents the actual comprehensive energy consumption assessment coefficient.
[0043] S103, if the actual comprehensive energy consumption evaluation coefficient at the current time meets the corresponding high energy consumption condition, with the goal of minimizing total energy consumption, the reinforcement learning decision engine outputs the target instruction optimization strategy at the current time, and drives the executor to run according to the target instruction optimization strategy at the current time.
[0044] In this embodiment, the actual comprehensive energy consumption assessment coefficient is a comprehensive, dimensionless energy efficiency health index that can be used to quickly diagnose system status. Specifically, corresponding coefficient ranges can be set for different energy consumption modes such as high, medium, and low. If the actual comprehensive energy consumption assessment coefficient at the current time falls within the coefficient range corresponding to the high energy consumption mode, then the high energy consumption condition is determined to be met. Once the high energy consumption condition is determined to be met, the optimization process is initiated, specifically to minimize the total power consumption (i.e., With the objective of [specific objective], a reinforcement learning engine outputs a target instruction optimization strategy for the current time. This strategy includes specific equipment control instructions, such as increasing the host set temperature by 0.8℃ and reducing the opening of the damper in zone 1 to 70%. By analyzing historical and real-time data, the reinforcement learning engine can find the optimal combination of equipment operating parameters. Finally, the actuator is driven to run according to the target instruction optimization strategy for the current time.
[0045] In practical applications, sensors deployed in air conditioning equipment to collect operating parameters can act as data acquisition nodes. These nodes transmit the collected parameters to the central gateway via IoT communication protocols (such as ZigBee and LoRa). The central data unit adopts a cloud-edge collaborative structure, with edge nodes responsible for real-time control and the cloud platform handling big data analysis and iterative training of the reinforcement learning engine. The cloud platform then transmits the model parameters obtained from the iterative training to the edge nodes through the central gateway, enabling the edge nodes to synchronously update the reinforcement learning engine. The edge nodes determine the comprehensive energy consumption evaluation coefficient for the current time and, when high energy consumption conditions are met, output the target instruction optimization strategy for the current time through the reinforcement learning engine. This strategy drives the actuators, which connect to the air conditioning equipment to achieve precise control. The actuators can include a PLC (Programmable Logic Controller) and a relay array. The PLC receives target instruction optimization strategies from edge nodes and converts them into specific, time-controlled control signal sequences, which are then sent to the relay array or the air conditioner's main control board. The relay array acts as a high-voltage control switch, receiving low-voltage, low-current control signals from the PLC to directly connect or disconnect high-voltage, high-current circuits connected to the air conditioner's main unit, water pump, fan, and other equipment, thereby achieving equipment start-up and shutdown control. For continuous adjustments (such as inverter frequency and damper opening), the PLC controls via analog output or communication protocols (such as Modbus). Through the PLC and relay array, lower-level control beyond the original air conditioner remote control or panel is achieved, such as time-segmented and zoned control, pre-cooling strategies based on actual comprehensive energy consumption assessment coefficients, and dynamic adjustment of water pump frequency in conjunction with the main unit's operating mode, achieving system-level energy saving.
[0046] In one possible implementation, executable instruction optimization strategies can be searched within a safe and comfortable range for the user by configuring policy constraints. During this process, by simulating and verifying changes in the actual comprehensive energy consumption assessment coefficient and absolute energy consumption, an instruction optimization strategy is selected that significantly reduces both the actual comprehensive energy consumption assessment coefficient and absolute energy consumption. See also Figure 4 , Figure 4 This is another schematic flowchart illustrating an energy consumption detection method based on multi-parameter fusion, provided as an embodiment of this application. Figure 4 As shown in the embodiment of this application, an energy consumption detection method based on multi-parameter fusion is provided. In step S103, "with the goal of minimizing total energy consumption, the target instruction optimization strategy at the current time is output through the reinforcement learning decision engine" can include steps S401 to S403. These steps are described in detail below.
[0047] S401, obtain the policy constraints and obtain the actual absolute energy consumption of the air conditioning equipment at the current time.
[0048] In this embodiment, policy constraints can be set regarding user-defined temperature, ambient humidity, and actual CPU load. For example, the user-defined temperature can be between 18°C and 25°C, the ambient humidity between 40% and 60%, and the actual CPU load between 0% and 95%. Furthermore, based on the actual input power of the compressor in the operating status parameters at the current time, the absolute energy consumption of the air conditioning unit from the previous time to the current time can be determined as the actual absolute energy consumption at the current time.
[0049] S402 uses a reinforcement learning decision engine to search for candidate instruction optimization strategies that satisfy policy constraints, and predicts the target comprehensive energy consumption evaluation coefficient and target absolute energy consumption of the candidate instruction optimization strategies in the next time step.
[0050] In this embodiment, a reinforcement learning engine searches for at least one instruction optimization strategy that satisfies the policy constraints as a candidate instruction optimization strategy. The system then predicts the equipment parameters, environmental parameters, and operating status parameters of the air conditioning unit after executing the candidate instruction optimization strategy, thereby determining the target comprehensive energy consumption evaluation coefficient for the next time period. The process of determining the target comprehensive energy consumption evaluation coefficient for the next time period based on the predicted equipment parameters, environmental parameters, and operating status parameters can be found in step S102, and will not be elaborated here. Additionally, the absolute energy consumption of the air conditioning unit from the current time to the next time period can be determined based on the actual input power of the compressor in the predicted operating status parameters, serving as the target absolute energy consumption for the next time period.
[0051] S403: Select the strategy with the smallest target comprehensive energy consumption evaluation coefficient and the smallest target absolute energy consumption from the candidate instruction optimization strategies as the target instruction optimization strategy for the current time. The target comprehensive energy consumption evaluation coefficient corresponding to the target instruction optimization strategy for the current time is less than the actual comprehensive energy consumption evaluation coefficient for the current time, and the target absolute energy consumption corresponding to the target instruction optimization strategy for the current time is less than the actual absolute energy consumption for the current time.
[0052] In this embodiment, the strategy with the smallest overall target energy consumption evaluation coefficient and the smallest target absolute energy consumption can be selected from the candidate instruction optimization strategies as the target instruction optimization strategy for the current time. The overall target energy consumption evaluation coefficient corresponding to the target instruction optimization strategy for the current time is less than the actual overall target energy consumption evaluation coefficient for the current time, thereby significantly reducing the overall energy consumption evaluation coefficient. In addition, the target absolute energy consumption corresponding to the target instruction optimization strategy for the current time is less than the actual absolute energy consumption for the current time, thereby reducing the absolute energy consumption.
[0053] In one possible implementation, after the actuator starts running, the changes in the actual comprehensive energy consumption evaluation coefficient and the actual absolute energy consumption can be continuously monitored to determine whether the target instruction optimization strategy is effective at the current time, and to roll back the settings if it is ineffective. To this end, an energy consumption detection method based on multi-parameter fusion provided in this application embodiment further includes the following steps: When the actuator finishes running, the actual comprehensive energy consumption assessment coefficient for the next time is determined based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the next time. The actual absolute energy consumption of the air conditioning equipment at the next time is obtained, and the effectiveness of the target instruction optimization strategy at the current time is evaluated by comparing the actual comprehensive energy consumption assessment coefficient and the actual absolute energy consumption at the current time with those at the next time. If the target instruction optimization strategy at the current time is invalid, the actuator is driven to roll back and return to the state before the target instruction optimization strategy was executed.
[0054] In one possible implementation, learning experience can be constructed based on the effectiveness of the target instruction optimization strategy at the current time, driving the reinforcement learning decision engine to repeatedly learn, thus enabling the reinforcement learning decision engine to adapt to user habits. In this regard, an energy consumption detection method based on multi-parameter fusion provided in this application embodiment further includes the following steps: Based on the effectiveness of the target instruction optimization strategy at the current time, a learning experience is constructed, and the reinforcement learning decision engine is retrained using the learning experience.
[0055] In this embodiment, the current image of the air conditioning equipment is used as the state, the current target instruction optimization strategy is used as the action, and the immediate reward is calculated according to the following formula (6) to construct the learning experience: (6) in, Indicates an immediate reward; This indicates a reduction in the total energy consumption of air conditioning equipment as a reward. This represents the total energy consumption during the period from the current time to the next time. This indicates a penalty for thermal comfort deviation. The average vote is a function of temperature and humidity. This indicates the penalty imposed for any behavior that violates the policy constraints; , and Preset weights.
[0056] Specifically, if the target instruction optimization strategy is effective at the current time, the "state-action-reward" sequence at the current time is used as positive learning experience; if the target instruction optimization strategy is ineffective at the current time, the "state-action-reward" sequence at the current time is used as negative learning experience. Furthermore, the reinforcement learning decision engine is retrained according to the above learning experience. After long-term online or offline training, the reinforcement learning decision engine ultimately predicts the globally optimal energy-saving action in any state, achieving adaptive and refined control.
[0057] Based on the above description, the energy consumption detection method based on multi-parameter fusion provided in this application embodiment accurately evaluates the actual comprehensive energy consumption of air conditioning equipment at the current time through multi-parameter fusion, and adaptively optimizes when energy consumption is high, thereby effectively reducing air conditioning energy consumption and ensuring energy efficiency optimization effect.
[0058] The above describes an energy consumption detection method based on multi-parameter fusion provided by the embodiments of this application. The following describes the apparatus for performing the above-described energy consumption detection method based on multi-parameter fusion.
[0059] See Figure 5 , Figure 5 This is a schematic diagram of the structure of an energy consumption detection device based on multi-parameter fusion, provided as an embodiment of this application. Figure 5 As shown in the figure, this application provides an energy consumption detection device based on multi-parameter fusion, including: The data acquisition module 501 is used to acquire the operating parameters of the air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters. The energy consumption detection module 502 is used to determine the actual comprehensive energy consumption evaluation coefficient at the current time based on the equipment parameters, environmental parameters and operating status parameters of the air conditioning equipment at the current time. If the actual comprehensive energy consumption evaluation coefficient at the current time meets the corresponding high energy consumption condition, the module outputs the target instruction optimization strategy at the current time through the reinforcement learning decision engine with the goal of minimizing total energy consumption, and drives the actuator to run according to the target instruction optimization strategy at the current time.
[0060] In one possible implementation, the equipment parameters include supply water temperature, return water temperature, water circulation flow rate and main unit input power; the environmental parameters include cooling area area, indoor and outdoor temperature difference and ambient humidity; and the operating status parameters include compressor actual input power and continuous running time. The energy consumption detection module 502 is used to determine the actual comprehensive energy consumption assessment coefficient of the air conditioning equipment at the current time based on the equipment parameters, environmental parameters, and operating status parameters at the current time. Specifically, it is used for: Based on the supply water temperature, return water temperature, water circulation flow rate, and main unit input power at the current time, determine the energy efficiency ratio at the current time; based on the energy efficiency ratio at the current time, the actual input power of the compressor, and the continuous running time, determine the actual energy consumption at the current time; using the cooling area area, indoor and outdoor temperature difference, and ambient humidity at the current time, determine the required energy consumption at the current time; based on the actual energy consumption and required energy consumption at the current time, determine the actual comprehensive energy consumption evaluation coefficient at the current time.
[0061] In one possible implementation, the runtime status parameters also include the actual CPU load; The energy consumption detection module 502, used to determine the actual comprehensive energy consumption evaluation coefficient based on the actual energy consumption and demand energy consumption at the current time, is specifically used for: Obtain the learning parameters output by the reinforcement learning decision engine in the previous time step. The learning parameters and the target instruction optimization strategy in the previous time step are output simultaneously, and include the optimal CPU load and load weight coefficient. Based on the actual CPU load in the current time step, as well as the optimal CPU load and load weight coefficient in the previous time step, determine the load coupling term in the current time step. Using the actual energy consumption, required energy consumption, and load coupling term in the current time step, determine the actual comprehensive energy consumption evaluation coefficient in the current time step.
[0062] In one possible implementation, the energy consumption detection module 502, which optimizes the target instruction at the current time by outputting the target instruction optimization strategy through a reinforcement learning decision engine with the goal of minimizing total energy consumption, is specifically used for: Obtain the policy constraints and the actual absolute energy consumption of the air conditioning equipment at the current time; use a reinforcement learning decision engine to search for candidate instruction optimization strategies that meet the policy constraints, and predict the target comprehensive energy consumption evaluation coefficient and target absolute energy consumption of the candidate instruction optimization strategies at the next time; select the strategy with the smallest target comprehensive energy consumption evaluation coefficient and the smallest target absolute energy consumption from the candidate instruction optimization strategies as the target instruction optimization strategy at the current time. The target comprehensive energy consumption evaluation coefficient of the target instruction optimization strategy at the current time is less than the actual comprehensive energy consumption evaluation coefficient at the current time, and the target absolute energy consumption of the target instruction optimization strategy at the current time is less than the actual absolute energy consumption at the current time.
[0063] In one possible implementation, the energy consumption detection module 502 is also used for: When the actuator finishes running, the actual comprehensive energy consumption assessment coefficient for the next time is determined based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the next time. The actual absolute energy consumption of the air conditioning equipment at the next time is obtained, and the effectiveness of the target instruction optimization strategy at the current time is evaluated by comparing the actual comprehensive energy consumption assessment coefficient and the actual absolute energy consumption at the current time with those at the next time. If the target instruction optimization strategy at the current time is invalid, the actuator is driven to roll back.
[0064] In one possible implementation, the energy consumption detection module 502 is also used for: Based on the effectiveness of the target instruction optimization strategy at the current time, a learning experience is constructed, and the reinforcement learning decision engine is retrained using the learning experience.
[0065] It should be noted that the detailed functions of each module in the embodiments of this application can be found in the corresponding disclosure of the above-mentioned embodiment of the energy consumption detection method based on multi-parameter fusion, and will not be repeated here.
[0066] This application also provides an electronic device in its embodiments. See also... Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device in this embodiment may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0067] like Figure 6As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. When the electronic device is powered on, the RAM 603 also stores various programs and data required for the operation of the electronic device. The processing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0068] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, memory cards, hard drives, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.
[0069] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the energy consumption detection methods based on multi-parameter fusion provided in this application.
[0070] This application also provides a computer-readable storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the energy consumption detection methods based on multi-parameter fusion provided in this application.
[0071] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.
[0072] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0073] In the above embodiments, the implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, in the form of a computer program product.
[0074] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).
Claims
1. An energy consumption detection method based on multi-parameter fusion, characterized in that, The energy consumption detection method based on multi-parameter fusion includes: Collect the operating parameters of the air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters; Based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the current time, determine the actual comprehensive energy consumption evaluation coefficient at the current time; If the actual comprehensive energy consumption evaluation coefficient at the current time meets the corresponding high energy consumption condition, with the goal of minimizing total energy consumption, the reinforcement learning decision engine outputs the target instruction optimization strategy at the current time, and drives the executor to run according to the target instruction optimization strategy at the current time.
2. The energy consumption detection method based on multi-parameter fusion according to claim 1, characterized in that, The equipment parameters include supply water temperature, return water temperature, water circulation flow rate, and main unit input power; the environmental parameters include cooling area, indoor and outdoor temperature difference, and ambient humidity; and the operating status parameters include compressor actual input power and continuous operating time. The step of determining the actual comprehensive energy consumption assessment coefficient for the current time based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment includes: The energy efficiency ratio at the current time is determined based on the supply water temperature, return water temperature, water circulation flow rate, and main unit input power at the current time. The actual energy consumption at the current time is determined based on the energy efficiency ratio, the actual input power of the compressor, and the continuous operating time at the current time. The required energy consumption at the current time is determined using the area of the cooling zone, the indoor-outdoor temperature difference, and the ambient humidity. Based on the actual energy consumption and demand energy consumption at the current time, determine the actual comprehensive energy consumption evaluation coefficient at the current time.
3. The energy consumption detection method based on multi-parameter fusion according to claim 2, characterized in that, The operating status parameters also include the actual CPU load; The determination of the actual comprehensive energy consumption assessment coefficient for the current time based on the actual energy consumption and demand energy consumption at the current time includes: Obtain the learning parameters output by the reinforcement learning decision engine in the previous time step. The learning parameters are output simultaneously with the target instruction optimization strategy in the previous time step and include the optimal CPU load and load weight coefficient. Based on the actual CPU load at the current time, and the optimal CPU load and load weight coefficient at the previous time, determine the load coupling term at the current time; The actual comprehensive energy consumption evaluation coefficient for the current time is determined by using the actual energy consumption, demand energy consumption, and load coupling term at the current time.
4. The energy consumption detection method based on multi-parameter fusion according to claim 1, characterized in that, The optimization strategy for the target instruction at the current time, which aims to minimize total energy consumption and outputs the target instruction through a reinforcement learning decision engine, includes: Obtain the policy constraints and the actual absolute energy consumption of the air conditioning equipment at the current time; The reinforcement learning decision engine searches for candidate instruction optimization strategies that satisfy the policy constraints, and predicts the target comprehensive energy consumption evaluation coefficient and target absolute energy consumption of the candidate instruction optimization strategies in the next time step. The strategy with the smallest overall target energy consumption evaluation coefficient and the smallest absolute target energy consumption is selected from the candidate instruction optimization strategies as the target instruction optimization strategy for the current time. The overall target energy consumption evaluation coefficient of the target instruction optimization strategy for the current time is less than the actual overall target energy consumption evaluation coefficient for the current time, and the absolute target energy consumption of the target instruction optimization strategy for the current time is less than the actual absolute energy consumption for the current time.
5. The energy consumption detection method based on multi-parameter fusion according to claim 4, characterized in that, The energy consumption detection method based on multi-parameter fusion also includes: When the actuator finishes operating, the actual comprehensive energy consumption assessment coefficient for the next time is determined based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the next time. The actual absolute energy consumption of the air conditioning equipment at the next time is obtained, and the effectiveness of the target instruction optimization strategy at the current time is evaluated by comparing the actual comprehensive energy consumption evaluation coefficient and the actual absolute energy consumption at the current time with those at the next time. If the target instruction optimization strategy at the current time is invalid, the executor is driven to roll back.
6. The energy consumption detection method based on multi-parameter fusion according to claim 5, characterized in that, The energy consumption detection method based on multi-parameter fusion also includes: Based on the effectiveness of the target instruction optimization strategy at the current time, a learning experience is constructed, and the reinforcement learning decision engine is retrained using the learning experience.
7. An energy consumption detection device based on multi-parameter fusion, characterized in that, The energy consumption detection device based on multi-parameter fusion includes: The data acquisition module is used to collect the operating parameters of the air conditioning equipment, including equipment parameters, environmental parameters, and operating status parameters. The energy consumption detection module is used to determine the actual comprehensive energy consumption evaluation coefficient at the current time based on the equipment parameters, environmental parameters, and operating status parameters of the air conditioning equipment at the current time. If the actual comprehensive energy consumption evaluation coefficient at the current time meets the corresponding high energy consumption condition, the module outputs the target instruction optimization strategy at the current time through the reinforcement learning decision engine with the goal of minimizing total energy consumption, and drives the actuator to run according to the target instruction optimization strategy at the current time.
8. A computer program product, characterized in that, It includes computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the energy consumption detection method based on multi-parameter fusion as described in any one of claims 1 to 6.
9. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the energy consumption detection method based on multi-parameter fusion as described in any one of claims 1 to 6.
10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the energy consumption detection method based on multi-parameter fusion as described in any one of claims 1 to 6.