Environment state control method and system, electronic equipment and storage medium

Abstract

The invention relates to an environment state control method and system, electronic equipment and a storage medium. The method comprises the steps of periodically obtaining m pieces of actual environment state information currently collected by m sensors arranged at m point positions in a specified space and current actual total power consumption information of n pieces of controlled equipment; acquiring m initial control signals generated by m controllers; determining a gain matrix and a weight matrix of the current period according to the m pieces of actual environment state information, the target environment state information specified by the m pieces of actual environment state information, the actual total power consumption information and the specified target total power consumption information; according to the gain matrix and the weight matrix of the current period, the m initial control signals are converted into n target control signals, and the n target control signals are used for controlling the n controlled devices to execute corresponding environment state adjustment work in the current period. Therefore, accurate, multi-point combined, self-adaptive and low-energy-consumption environment state control can be realized.

Description

Technical Field

[0001] The present disclosure relates to the field of automation control, and in particular to an environmental state control method and system, an electronic device and a storage medium. Background Art

[0002] With the development of modern industry and technology, the requirements for controlling environmental conditions (such as temperature, humidity, cleanliness, etc.) are increasing. Especially in areas that are sensitive to environmental conditions, such as data centers, stable control strategies are needed to ensure the normal operation of servers and other equipment.

[0003] Among them, the PID (Proportional-Integral-Derivative) control algorithm is a classic control method widely used in the field of industrial control. It performs closed-loop control of the system through a combination of three parts: proportional (P), integral (I) and differential (D) to achieve accurate tracking of the target value. At present, most data centers and computer rooms use traditional PID control algorithms for temperature management. This control method performs closed-loop control of temperature through a combination of three parts: proportional, integral and differential. However, traditional PID control has the following shortcomings: When facing complex and changeable environmental conditions, the adjustment of PID parameters requires a lot of manual intervention, and it is difficult to achieve automatic optimization. Due to fixed parameters, traditional PID control has limited control accuracy and response speed when dealing with nonlinear systems. In addition, traditional PID control has weak adaptability to environmental changes and is difficult to cope with sudden temperature fluctuations and load changes.

[0004] BP (Back Propagation) neural network is a multi-layer feedforward neural network that adjusts the weights and biases of the network through the back propagation algorithm to minimize the output error. BP neural network has the ability to handle complex nonlinear problems, can automatically iterate and adjust parameters, and has the advantages of short training cycle and fast convergence speed. In the field of control, BP neural network can be used to adaptively adjust the parameters of PID controller to improve control accuracy and response speed.

[0005] However, when using existing controllers (such as PID controllers or PID controllers based on BP neural networks, etc.) to control environmental conditions, they often only focus on the average temperature of the entire space, which is difficult to meet the specific temperature requirements of different areas or equipment. Therefore, multi-point environmental condition control technology has emerged. In multi-point environmental condition control, compared with single-target control, multi-point control does not focus on the overall average environmental condition, but controls the specific environmental conditions of multiple points in detail. However, it is often difficult to accurately control the environmental conditions of specific points, and due to the difference in heat dissipation of equipment, the temperature control of different points may interfere with each other, for example, it may cause the system to reach equilibrium at a temperature point other than the target temperature. In addition, considering the energy consumption of equipment such as air conditioners used to adjust environmental conditions, single PID control may lead to additional energy consumption. Therefore, more advanced control strategies are needed to optimize multi-point environmental condition control, reduce energy consumption, and improve the adaptability and control accuracy of environmental condition control. Summary of the invention

[0006] In view of this, the present disclosure proposes an environmental state control method and system, an electronic device and a storage medium, which can achieve high-precision control of the environmental state in spaces such as data centers and computer rooms and meet energy efficiency requirements. Through a self-learning control method, accurate, multi-point joint, adaptive and low-energy consumption environmental state control can be achieved.

[0007] According to one aspect of the present disclosure, there is provided an environment state control method, comprising: periodically acquiring m actual environment state information currently collected by m sensors set at m points in a specified space and current actual total power consumption information of n controlled devices set in the specified space, wherein the controlled devices are used to adjust the environment state, and m and n are positive integers; acquiring m initial control signals generated by m controllers connected to the m sensors, wherein the i-th initial control signal is generated by the i-th controller based on the actual environment state information currently collected by the i-th sensor and the target environment state information specified at the i-th point, 1≤i≤m; and generating a control signal based on the actual environment state information currently collected by the i-th sensor and the target environment state information specified at the i-th point according to the m actual environment state information and the target environment state information. The target environmental state information specified by each of the m points, as well as the actual total power consumption information and the specified target total power consumption information, are used to determine the gain matrix and the weight matrix of the current cycle, wherein the gain matrix is ​​used to indicate the mapping relationship between the m controllers and the n controlled devices, and the weight matrix is ​​used to indicate the rate of change of the environmental state of the m points; according to the gain matrix and the weight matrix of the current cycle, the m initial control signals are converted into n target control signals, and the n target control signals are used to respectively control the n controlled devices to perform corresponding environmental state adjustment work in the current cycle, so that the environmental state of each point can reach the target environmental state.

[0008] In a possible implementation, the gain matrix and weight matrix of the current cycle are determined based on the m actual environmental state information and the target environmental state information specified by each of the m points, as well as the actual total power consumption information and the specified target total power consumption information, including: determining the gain matrix of the current cycle based on the state error between the m actual environmental state information and the target environmental state information specified by each of the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signals generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle; determining the weight matrix of the current cycle based on the m actual environmental state information currently collected by the m sensors and the m actual environmental state information collected by the m sensors in the previous cycle, and the weight matrix of the previous cycle.

[0009] In a possible implementation, the gain matrix of the current cycle is determined based on the state error between the m actual environmental state information and the target environmental state information specified by each of the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signal generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle, including: determining the first partial derivative of a preset system error function for each of the m actual environmental state information according to the state error between the m actual environmental state information and the target environmental state information specified by each of the m points; wherein the system error function represents the weighted sum between the state error and the power consumption error; determining each actual environmental state according to the partial derivative of the target control signal generated in the previous cycle, the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle, and the preset first mapping model. The invention relates to a method for determining a target environment state information of a first embodiment of the present invention, wherein the first mapping model is used to indicate the mapping relationship between the target control signal and the actual environment state information; the third partial derivative of the system error function to the actual total power consumption information is determined according to the power consumption error between the actual total power consumption information and the specified target total power consumption information; the fourth partial derivative of the actual total power consumption information to the gain matrix is ​​determined according to the partial derivative of the target control signal generated in the previous cycle by the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle and the preset second mapping model; the second mapping model is used to indicate the mapping relationship between the target control signal and the actual total power consumption information; the target partial derivative of the system error function to the gain matrix is ​​determined according to the first partial derivative, the second partial derivative, the third partial derivative and the fourth partial derivative; the gain matrix of the previous cycle is updated based on the target partial derivative and the preset learning rate to obtain the gain matrix of the current cycle.

[0010] In a possible implementation, the system error function E is expressed as:

[0011]

[0012] Among them, T i represents the actual environmental status information collected by the i-th sensor, T target Represents the target environment status information of the i-th point; P total Represents the actual total power consumption information, P target Represents the target total power consumption information, λ i represents the weighting coefficient corresponding to the i-th sensor, and γ represents the weighting coefficient corresponding to the power consumption error;

[0013] The first partial derivative of the system error function with respect to the actual environmental state information collected by the i-th sensor is expressed as:

[0014]

[0015] The second partial derivative of the actual environmental state information collected by the i-th sensor to the gain matrix K[i,j] is expressed as:

[0016]

[0017] Where f(·) represents the first mapping model, u r-1 represents the target control signal of the previous cycle, t represents time, and W r-1 Represents the weight matrix of the previous cycle, du r-1 represents the column vector of the m initial control signals generated in the previous cycle, and j represents the jth element in the matrix;

[0018] The third partial derivative of the system error function with respect to the actual total power consumption information is expressed as:

[0019]

[0020] The fourth partial derivative of the actual total power consumption information to the gain matrix is ​​expressed as:

[0021]

[0022] Wherein, g(·) represents the second mapping model;

[0023] The target partial derivative of the system error function with respect to the gain matrix is ​​expressed as:

[0024]

[0025] The gain matrix K[i,j] of the current cycle r It is expressed as:

[0026]

[0027] Among them, K[i,j] r-1 represents the gain matrix of the previous cycle, and η represents the preset learning rate.

[0028] In a possible implementation, the weight matrix of the current cycle is determined based on the m actual environmental status information currently collected by the m sensors, the m actual environmental status information collected by the m sensors in the previous cycle, and the weight matrix of the previous cycle, including: for the i-th sensor among the m sensors, determining the change rate from the actual environmental status information collected by the i-th sensor in the previous cycle to the actual environmental status information currently collected by the i-th sensor; when the change rate is greater than a preset rate threshold, multiplying the i-th weight value in the weight matrix of the previous cycle by a first coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the first coefficient is less than 1, and the i-th weight value is the weight value corresponding to the i-th point; when the change rate is less than or equal to the preset rate threshold, multiplying the i-th weight value in the weight matrix of the previous cycle by a second coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the second coefficient is greater than 1.

[0029] In one possible implementation, the m initial control signals are represented as m×1 column vectors, the gain matrix is ​​represented as an n×m matrix, and the weight matrix is ​​represented as an m×m diagonal matrix; wherein, converting the m initial control signals into n target control signals based on the gain matrix and weight matrix of the current cycle includes: matrix multiplying the column vectors of the m initial control signals with the weight matrix of the current cycle and the gain matrix of the current cycle to obtain the n target control signals.

[0030] In a possible implementation, the environmental status information includes at least one of temperature, humidity, and cleanliness; the controlled device includes an air-conditioning device, and the air-conditioning device is used to adjust at least one of temperature, humidity, and cleanliness.

[0031] According to another aspect of the present disclosure, an environmental state control system is provided, comprising: a first acquisition module, used to periodically acquire m actual environmental state information currently collected by m sensors set at m points in a specified space and current actual total power consumption information of n controlled devices set in the specified space, wherein the controlled devices are used to adjust the environmental state, and m and n are positive integers; a second acquisition module, used to acquire m initial control signals generated by m controllers connected to the m sensors, wherein the i-th initial control signal is generated by the i-th controller based on the actual environmental state information currently collected by the i-th sensor and the target environmental state information specified by the i-th point, 1≤i≤m; a matrix update module, used to acquire the m initial control signals generated by the m controllers connected to the m sensors according to the m actual environmental state information currently collected by the i-th sensor and the target environmental state information specified by the i-th point, and 1≤i≤m; The actual environmental state information and the target environmental state information specified by each of the m points, as well as the actual total power consumption information and the specified target total power consumption information, determine the gain matrix and the weight matrix of the current cycle, the gain matrix is ​​used to indicate the mapping relationship between the m controllers and the n controlled devices, and the weight matrix is ​​used to indicate the environmental state change rate of the m points; a signal conversion module is used to convert the m initial control signals into n target control signals according to the gain matrix and weight matrix of the current cycle, and the n target control signals are used to respectively control the n controlled devices to perform corresponding environmental state adjustment work in the current cycle, so that the environmental state of each point can reach the target environmental state.

[0032] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0033] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0034] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0035] According to various aspects of the present disclosure, by acquiring actual environmental status information and target environmental status information of multiple points and actual total power consumption information and target total power consumption information of multiple controlled devices, the initial control signals generated by multiple controllers are converted into multiple target control signals to control multiple controlled devices to perform corresponding environmental status adjustment tasks. The initial control signals output by the controllers can be automatically and dynamically adaptively adjusted according to real-time data to achieve joint and precise control of multi-point environmental status, and the power consumption of the controlled devices can be managed more effectively so that each point can reach its respective target environmental status at the same time as much as possible, and the power consumption of the controlled devices can be reduced, reducing operating costs and maintenance costs, thereby achieving precise, multi-point joint, adaptive and low-energy environmental status control as a whole.

[0036] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0038] Figure 1 A schematic diagram showing an application scenario according to an embodiment of the present disclosure.

[0039] Figure 2 A flow chart of an environmental state control method according to an embodiment of the present disclosure is shown.

[0040] Figure 3 A schematic diagram of an environmental state control system according to an embodiment of the present disclosure is shown.

[0041] Figure 4 A flow chart of an environmental status control system according to an embodiment of the present disclosure is shown.

[0042] Figure 5 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0043] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0044] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0045] The term "and / or" herein is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent any one or more elements selected from the set consisting of A, B, and C. In the description of the present disclosure, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0046] It should be understood that the terms "first", "second", etc. in the claims, specifications and drawings of the present disclosure are used to distinguish different objects rather than to describe a specific order. The terms "include" and "comprise" used in the specifications and claims of the present disclosure indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0047] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0048] The environmental state control method of the embodiment of the present disclosure can be deployed on various terminal devices through software or hardware modification. The terminal device involved in the embodiment of the present disclosure may refer to a device with a wireless connection function and / or a wired connection function. The wireless connection function refers to the ability to connect to other devices through wireless connection methods such as wifi and Bluetooth. The terminal device involved in the embodiment of the present disclosure may also communicate with other devices through a wired connection function. The terminal device involved in the embodiment of the present disclosure may be a touch screen, a non-touch screen, or a screenless terminal device. The touch screen terminal device can be controlled by clicking and sliding on the display screen with a finger or a stylus. The non-touch screen device can be connected to an input device such as a mouse, a keyboard, a touch panel, and the terminal device is controlled through the input device. For example, the device without a screen may be a Bluetooth speaker without a screen. For example, the terminal device of the present application may include but is not limited to a user equipment (UE), a mobile device, a user terminal, a handheld device, a tablet computer, a laptop, a PDA, a computing device, etc.

[0049] The environmental state control method of the embodiment of the present disclosure can also be deployed on a server, which can be located in the cloud or locally, and can be a physical device or a virtual device, such as a virtual machine, a container, etc., with a wireless communication function, wherein the wireless communication function can be set in the chip (system) or other parts or components of the server. It can refer to a device with a wireless connection function, and the function of wireless connection refers to the ability to connect to other servers or terminal devices through wireless connection methods such as Wi-Fi, Bluetooth, etc. The server involved in the embodiment of the present disclosure can also have a function of communicating through a wired connection. For example, the server of the embodiment of the present disclosure can be located in the cloud, communicate with the terminal device, receive the actual environmental state information, the actual total power consumption information and the m initial control signals generated by the controller sent by the terminal device, and use the environmental state control method deployed on the server based on the actual environmental state information, the actual total power consumption information and the m initial control signals generated by the controller to generate n target control signals, and return them to the terminal device, so as to control the n controlled devices to perform the corresponding environmental state adjustment work in the current cycle based on the n target control signals through the terminal device.

[0050] To facilitate understanding of the environmental status method of the present embodiment, the present embodiment provides Figure 1 A schematic diagram of an application scenario is shown, such as Figure 1 As shown, multiple sensors, such as temperature sensors, humidity sensors, etc., can be arranged at different locations in a space such as a data center or a computer room. Each sensor can collect various types of environmental status information, such as temperature, humidity, etc. The environmental status information collected by the sensor can be transmitted to the central control unit through a communication controller (Communication Control Unit, CCU). The central control unit can be deployed with the environmental status control method of the embodiment of the present disclosure. By executing the environmental status control method of the embodiment of the present disclosure, a target control signal can be sent to the local control units of n air conditioners (such as actor1, actor2,..., actor_n), such as a target control signal for setting the temperature, a target control signal for setting the wind speed, etc., and then the set temperature and set wind speed of the air conditioner can be adjusted to control each air conditioner to perform corresponding environmental adjustment work, for example, lowering the cooling temperature, increasing the cooling wind speed, etc., which is not limited by the embodiment of the present disclosure.

[0051] Figure 2 FIG. 1 is a flow chart showing a method for controlling an environmental state according to an embodiment of the present disclosure. Figure 2 As shown, the method includes: step S11 to step S14.

[0052] In step S11, m actual environmental status information currently collected by m sensors set at m points in the specified space and the current actual total power consumption information of n controlled devices set in the specified space are periodically obtained. The controlled devices are used to adjust the environmental status. m and n are positive integers.

[0053] The designated space can be understood as a space where the environmental state needs to be controlled, such as a data center, a computer room, etc. The points in the designated space can be understood as spatial locations. It should be understood that the user can set sensors at multiple points in the designated space, and at least one sensor can be set at the same point. The sensors can include, for example, temperature sensors, humidity sensors, cleanliness sensors, etc., which are used to monitor actual environmental state information (such as temperature, humidity, cleanliness, etc.), that is, the environmental state information can include at least: at least one of temperature, humidity, and cleanliness. The embodiments of the present disclosure do not limit the types and quantities of sensors set in the designated space.

[0054] Taking into account the situation that in actual situations there may be a large number of sensors in a designated space and the positions of multiple sensors of the same type are close to each other, it is also possible to equate multiple sensors of the same type and located close to each other into a single sensor, and perform weighted summation on the environmental state information collected by multiple sensors of the same type and located close to each other to obtain weighted environmental state information and use it as the actual environmental state information of the single sensor to which the multiple sensors of the same type and located close to each other are equivalent. In this way, when there are a large number of sensors in the designated space, the amount of actual environmental state information processed can be reduced, which is beneficial to improving data processing efficiency and further improving environmental state control efficiency.

[0055] Among them, the controlled device may include, for example, an air conditioning device, which can be used to adjust at least one of temperature, humidity and cleanliness; of course, it may also include other devices capable of adjusting the environmental state, such as a blower device, a fan device, a water cooling device, etc., which is not limited in the embodiments of the present disclosure. It should be understood that at least one controlled device may be set in a designated space, and the number of controlled devices and the number of sensors in the designated space may be the same or different, depending on the actual application scenario, which is not limited in the embodiments of the present disclosure.

[0056] In practical applications, the current power consumption (i.e., power consumption) of each controlled device can be obtained through serial communication, and the current actual total power consumption information is the sum of the current power consumptions of n controlled devices. It should be understood that those skilled in the art can use any serial communication technology known in the art to obtain the power consumption of each controlled device, and the embodiments of the present disclosure are not limited to this.

[0057] Among them, in order to control the environmental state in the designated space in real time, the actual environmental state information and the actual total power consumption information can be periodically obtained, so as to timely control the controlled device to adjust the environmental state according to the actual environmental state information and the actual total power consumption information. It should be understood that those skilled in the art can set the control period (i.e., the sampling period) according to actual needs. For example, it can be set to obtain the actual environmental state information and the actual total power consumption information every 30 seconds, so that the environmental state control method can be executed every 30 seconds to effectively realize accurate environmental state control and ensure that the environmental state of the designated space reaches the target environmental state.

[0058] In step S12, m initial control signals generated by m controllers connected to m sensors are obtained, wherein the i-th initial control signal is generated by the i-th controller based on the actual environmental state information currently collected by the i-th sensor and the target environmental state information specified by the i-th point, 1≤i≤m.

[0059] In practical applications, the controller can adopt any known controller with output in the art, for example, a controller with a proportional P-integral I-differential D control algorithm. The PID controller can be a hardware device or a software program, and the embodiments of the present disclosure do not limit this. Among them, each sensor in the specified space can be configured with a PID controller respectively, and the PID controller can use the PID control algorithm to generate an initial control signal (that is, generate a PID control signal) according to the actual environmental state information collected by the sensor and the target environmental state information. The embodiments of the present disclosure do not limit the process of the PID controller generating the initial control signal.

[0060] Optionally, the controller may include a PID controller based on a feedforward neural network (such as a BP-PID controller), that is, each point to be controlled is equipped with a BP-PID controller connected to a sensor. The BP-PID controller uses a BP neural network to optimize and adjust the PID control coefficients (i.e., Kp, Ki, and Kd). Optimizing the PID control coefficients by using a BP neural network can dynamically adjust the PID control coefficients according to the environmental state error, which is beneficial to improving the control accuracy of the PID controller. Among them, the input layer of the BP neural network includes 4 neurons, which correspond to the target environmental state information, the actual environmental state information, the environmental state error (i.e., the error between the actual environmental state information and the target environmental state information) and the stability parameter (a preset constant parameter). The output layer includes 3 neurons, which correspond to the three control coefficients of the PID controller, i.e., the proportional coefficient (Kp), the integral coefficient (Ki), and the differential coefficient (Kd).

[0061] For example, the PID controller can use formula (1-1) and formula (1-2) to calculate the specific value of the initial control signal:

[0062]

[0063] in, Represents the initial control signal output by the PID controller in the current cycle, Represents the initial control signal output by the PID controller in the previous cycle, Represents the current output of the incremental PID controller, where Kp, Ki, and Kd are the control coefficients of the BP-PID controller in the current cycle, and e r represents the environmental state error of the current cycle (that is, the error between the actual environmental state information currently obtained and the target environmental state information), e r-1 represents the environmental state error of the previous cycle (i.e., the error between the actual environmental state information obtained last time and the target environmental state information), e r-2 Represents the environmental state error of the previous cycle (i.e., the error between the actual environmental state information obtained last time and the target environmental state information).

[0064] It should be understood that the above-mentioned control algorithms using the BP-PID controller and formulas (1-1) and (1-2) are some possible implementation methods provided by the embodiments of the present disclosure. In fact, those skilled in the art can adopt any other known controllers in the art, such as sliding mode controller (SMC), model predictive controller (MPC), reinforcement learning controller (RLC), etc., to generate m initial control signals based on the actual environmental state information currently collected by m sensors and the target environmental state information specified by m points. The embodiments of the present disclosure are not limited to this.

[0065] In step S13, the gain matrix and weight matrix of the current cycle are determined based on the m actual environmental state information and the target environmental state information specified by the m points, as well as the actual total power consumption information and the specified target total power consumption information. The gain matrix is ​​used to indicate the mapping relationship between the m controllers and the n controlled devices, and the weight matrix is ​​used to indicate the environmental state change rate of the m points.

[0066] In actual applications, users can customize the target environmental state information to be achieved at each point in the specified space according to actual needs, for example, the target temperature reaches 25°C; the target environmental state information specified by different points can be the same or different, that is, users can set the corresponding target environmental state information for each point respectively, and this embodiment of the present disclosure is not limited to this. In addition, users can customize the target total power consumption information that should be generated by n controlled devices in the current cycle according to actual needs, and this embodiment of the present disclosure is not limited to this.

[0067] It should be understood that different target environmental status information and different target total power consumption information can be set at different times (such as different periods of a day, different months of a year, etc.). Therefore, a schedule can be preset, and the preset schedule can record the target environmental status information of each point at different times and the target total power consumption information at different times. For example, the target temperature of each point from 8:00 to 11:00 is recorded as 24°C in the schedule, and the target temperature of each point from 11:00 to 14:00 is 22°C. In this way, the target environmental status information and target total power consumption information at the current time can be obtained from the schedule to realize automatic control of the environmental status of each point. By automatically realizing the environmental status control of multiple points at different times according to the preset schedule, it is possible to automatically reduce the power consumption generated by the controlled device and control the controlled device to achieve the best working state, so that each point reaches the target environmental state.

[0068] As described above, in order to achieve accurate environmental state control, multiple sensors can be used to monitor the environmental state in real time, and the power consumption of the controlled device can be obtained through the serial port, and a controller can be arranged for each sensor to be monitored. In order to map the initial control signal output by the controller to each controlled device, and try to make each point reach its corresponding target environmental state at the same time, a gain matrix can be used to control the mapping relationship between m controllers and n controlled devices, and a weight matrix can be used to control the environmental state change rate of each point. That is, by controlling the mapping relationship between m controllers and n controlled devices through the gain matrix, the m initial control information output by the m controllers can be mapped into n target control signals for controlling n controlled devices, and the environmental state change rate of each point can be controlled through the weight matrix (equivalent to controlling the environmental state adjustment speed of each controlled device) to make each point reach its corresponding target environmental state at the same time, thereby helping to reduce the mutual interference of the environmental state control process of each point, so that the environmental state of each point can efficiently and accurately reach its corresponding target environmental state.

[0069] Among them, the weight matrix can be used to assign priorities to different targets or points in the control process, and the gain matrix can be used to map the adjustment strength of the control signal to the specific controlled equipment (such as the set temperature and wind speed of the air conditioner). In addition, due to the self-learning ability of the gain matrix, it can also converge to a stable state through gradient updating in complex mapping relationships, which is universal.

[0070] In actual applications, when the control method of the embodiment of the present invention is used to start controlling the environmental state, the gain matrix and the weight matrix can be initialized. Thereafter, each cycle can update the gain matrix and the weight matrix of the previous cycle based on the m actual environmental state information obtained in the current cycle and the target environmental state information specified for each of the m points, as well as the actual total power consumption information obtained in the current cycle and the specified target total power consumption information to obtain the gain matrix and the weight matrix of the current cycle. That is, the gain matrix and the weight matrix can be iteratively updated by self-learning and adaptively until each point reaches the target environmental state that it needs to achieve.

[0071] Specifically, the above step S13, according to the m actual environmental state information and the target environmental state information respectively specified by the m points, as well as the actual total power consumption information and the specified target total power consumption information, determines the gain matrix and the weight matrix of the current cycle, which may include:

[0072] Step S131, determining a gain matrix of the current cycle according to the state errors between the m actual environmental state information and the target environmental state information respectively specified by the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signal generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle;

[0073] Step S132, determining a weight matrix of the current cycle according to the m actual environment status information currently collected by the m sensors, the m actual environment status information collected by the m sensors in the previous cycle, and the weight matrix of the previous cycle.

[0074] Among them, in step S131, according to the state error between the m actual environmental state information and the target environmental state information specified by each of the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signal generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle, the gain matrix of the current cycle is determined, which may include:

[0075] Step S1311, determining a first partial derivative of a preset system error function with respect to each of the m actual environmental state information according to a state error between the m actual environmental state information and the target environmental state information respectively specified by the m points;

[0076] Step S1312, determining the second partial derivative of each actual environment state information with respect to the gain matrix according to the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle, and the partial derivative of the target control signal generated in the previous cycle by the preset first mapping model; wherein the first mapping model is used to indicate the mapping relationship between the target control signal and the actual environment state information;

[0077] Step S1313, determining a third partial derivative of the system error function with respect to the actual total power consumption information according to the power consumption error between the actual total power consumption information and the specified target total power consumption information;

[0078] Step S1314, determining a fourth partial derivative of the actual total power consumption information with respect to the gain matrix according to the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle, and the partial derivative of the target control signal generated in the previous cycle by the preset second mapping model; wherein the second mapping model is used to indicate a mapping relationship between the target control signal and the actual total power consumption information;

[0079] Step S1315, determining a target partial derivative of a system error function with respect to a gain matrix according to the first partial derivative, the second partial derivative, the third partial derivative, and the fourth partial derivative;

[0080] Step S1316, based on the target partial derivative and the preset learning rate, the gain matrix of the previous cycle is updated to obtain the gain matrix of the current cycle.

[0081] The system error function can be used to measure the gap between the system state and the target state, and is mainly composed of two parts: state error and power consumption error. The state error represents the gap between the actual environmental state information currently measured by the sensor and the target environmental state information, and the power consumption error represents the gap between the actual total power consumption information of the n controlled devices and the target total power consumption information. Specifically, the system error function can represent the weighted sum of the state error and the power consumption error, that is, the system error function E can be expressed as formula (2):

[0082]

[0083] Among them, T i represents the actual environmental status information collected by the i-th sensor, T target Represents the target environment status information of the i-th point; P total Represents the actual total power consumption information, Ptarget Represents the target total power consumption information, λ i represents the weighting coefficient corresponding to the i-th sensor, and γ represents the weighting coefficient corresponding to the power consumption error.

[0084] In practical applications, the gain matrix of the previous cycle can be updated by calculating the target partial derivative of the above system error function with respect to the gain matrix to obtain the gain matrix of the current cycle; wherein the target partial derivative of the system error function with respect to the gain matrix can be expressed as According to the chain method, That is, the target partial derivative of the system error function with respect to the gain matrix is ​​expressed as formula (3):

[0085]

[0086] Therefore, if the target partial derivative is to be calculated, the first partial derivative of the system error function for each of the m actual environmental state information can be calculated separately. The second partial derivative of each actual environmental state information to the gain matrix The third partial derivative of the system error function with respect to the actual total power consumption information And the fourth partial derivative of the actual total power consumption information to the gain matrix

[0087] Wherein, based on the system error function shown in the above formula (2), the first partial derivative of the system error function with respect to the actual environmental state information collected by the i-th sensor can be expressed as formula (4):

[0088]

[0089] That is, formula (4) can be used to determine the first partial derivative of the preset system error function with respect to each of the m actual environmental state information based on the state error between the m actual environmental state information and the target environmental state information respectively specified by the m points.

[0090] Among them, the second partial derivative of the actual environmental state information collected by the i-th sensor with respect to the gain matrix K[i,j] can be expressed as formula (5):

[0091]

[0092] Where f(·) represents the first mapping model, that is, T = f(u, t), u r-1 represents the target control signal of the previous cycle, t represents time (i.e., the control time corresponding to the target control signal), W r-1 Represents the weight matrix of the previous cycle, du r-1Represents the column vector of the m initial control signals generated in the previous cycle, j represents the matrix W r-1 ·du r-1 The jth element in (1≤j≤n). That is, formula (5) can be used to determine the second partial derivative of each actual environmental state information with respect to the gain matrix according to the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle, and the partial derivative of the target control signal generated in the previous cycle by the preset first mapping model.

[0093] It should be understood that, depending on the type of controlled device in actual situations, the signal form of the target control signal used to control the controlled device to perform environmental state adjustment work may be different, and thus the mapping from the actual environmental state information T to the target control signal may have different physical models. A technician in this field may construct a first mapping model based on the physical model in actual situations to indicate the mapping relationship between the target control signal and the actual environmental state information through the first mapping model, and the embodiments of the present disclosure are not limited to this.

[0094] Wherein, based on the system error function shown in the above formula (2), the third partial derivative of the system error function with respect to the actual total power consumption information can be expressed as formula (6):

[0095]

[0096] That is, the third partial derivative of the system error function with respect to the actual total power consumption information can be determined according to the power consumption error between the actual total power consumption information and the specified target total power consumption information through formula (6).

[0097] The fourth partial derivative of the actual total power consumption information to the gain matrix is ​​expressed as formula (7):

[0098]

[0099] Wherein, g(·) represents the second mapping model, that is, P=g(u,t); as described above, according to different device types of the controlled device in actual situations, the signal form of the target control signal used to control the controlled device to perform the environmental state adjustment work may be different, so the mapping from the actual total power consumption information P to the target control signal may have different physical models. Those skilled in the art can construct a second mapping model based on the physical model in actual situations to indicate the mapping relationship between the target control signal and the actual total power consumption information through the second mapping model, and the embodiments of the present disclosure are not limited to this.

[0100] It should be understood that based on the above formulas (4) to (7), the first deviation number, the second partial derivative, the third partial derivative and the fourth partial derivative can be calculated respectively, and then the first deviation number, the second partial derivative, the third partial derivative and the fourth partial derivative can be substituted into the above formula (3) to obtain the target partial derivative of the system error function with respect to the gain matrix. Based on the above target partial derivative, the gain matrix K[i,j] of the current cycle is s It can be expressed as formula (8):

[0101]

[0102] Among them, K[i,j] r-1 represents the gain matrix of the previous cycle, and η represents the preset learning rate. That is, the gain matrix of the previous cycle can be updated based on the target partial derivative and the preset learning rate using formula (8) to obtain the gain matrix of the current cycle.

[0103] In practical applications, the update target of the weight matrix is ​​to make the environmental state change speed of each point the same, or to make each point reach its target environmental state as much as possible at the same time, so that the weight matrix can be adjusted by presetting the rate threshold θ. Specifically, in a possible implementation, in step S132, according to the m actual environmental state information currently collected by the m sensors and the m actual environmental state information collected by the m sensors in the previous period, and the weight matrix of the previous period, the weight matrix of the current period is determined, which may include:

[0104] Step S1321, for the i-th sensor among the m sensors, determining the rate of change from the actual environmental state information collected by the i-th sensor in the previous cycle to the actual environmental state information currently collected by the i-th sensor;

[0105] Step S1322, when the rate of change is greater than the preset rate threshold, multiply the i-th weight value in the weight matrix of the previous cycle by the first coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the first coefficient is less than 1, and the i-th weight value is the weight value corresponding to the i-th point;

[0106] Step S1323, when the change rate is less than or equal to the preset rate threshold, multiply the i-th weight value in the weight matrix of the previous cycle by the second coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the second coefficient is greater than 1.

[0107] Among them, the change rate of the actual environmental state information collected by the i-th sensor in the previous period to the actual environmental state information currently collected by the i-th sensor is determined. For example, the ratio between the difference between the actual environmental state information collected by the i-th sensor in the previous period and the actual environmental state information currently collected and the change time is calculated to obtain the change rate of the actual environmental state information collected in the previous period to the actual environmental state information currently collected; wherein the change time can be the time between the collection time of the actual environmental state information collected by the i-th sensor in the previous period to the actual environmental state information collected in the current period, or it can be the periodic interval of the sampling period (such as 30 seconds).

[0108] Among them, the preset rate threshold can be used to control the change rate of each point to be neither too fast nor too slow, so as to make the environmental state of each point change at the same speed, that is, each point can reach its respective target environmental state as simultaneously and smoothly as possible. Among them, the specific values ​​of the first coefficient and the second coefficient can be customized. For example, the first coefficient can be set to 0.9 and the second coefficient can be set to 1.1, which is not limited in the embodiment of the present disclosure. Based on this, the update process of the above weight matrix can be expressed as formula (9):

[0109]

[0110] Among them, w i,r represents the i-th weight value in the weight matrix of the current cycle (that is, the weight value corresponding to the i-th point), w i,r-1 Represents the i-th weight value in the weight matrix of the previous cycle, T i,r represents the actual environmental status information currently collected by the i-th sensor, T i,r-1 represents the actual environmental status information collected by the i-th sensor in the previous cycle, Δt represents the duration of the change, represents the rate of change, and θ represents the preset rate threshold.

[0111] In step S14, according to the gain matrix and weight matrix of the current cycle, the m initial control signals are converted into n target control signals. The n target control signals are used to respectively control the n controlled devices to perform corresponding environmental state adjustment tasks in the current cycle so that the environmental state of each point reaches the target environmental state.

[0112] In practical applications, the m initial control signals can be expressed as m×1 column vectors, the above gain matrix can be expressed as an n×m matrix, and the above weight matrix can be expressed as an m×m diagonal matrix; based on this, the conversion of the m initial control signals into n target control signals according to the gain matrix and weight matrix of the current cycle can include: matrix multiplication of the column vectors of the m initial control signals with the weight matrix of the current cycle and the gain matrix of the current cycle to obtain n target control signals. That is, the above target control signals can be calculated using formula (10):

[0113] u r =K r ·(W r ·du r ) (10)

[0114] Among them, r Represents the column vector of m initial control signals generated in the current cycle, W r Represents the weight matrix of the current cycle, K r Represents the gain matrix of the current cycle, u r Represents the column vector of n target control signals generated in the current cycle, where u r It can be expressed as formula (11):

[0115]

[0116] Among them, k ni Represents the element in the nth row and ith column of the gain matrix of the current cycle, w i Represents the i-th diagonal element in the weight matrix of the current cycle, du i The i-th initial control signal in the column vector representing m initial control signals.

[0117] Through the above matrix calculation, the target control signal for each controlled device can be obtained. The target control signal can be used, for example, to control the temperature change value, humidity change value, cleanliness change value, wind speed setting value, power setting value, etc. of the controlled device, so as to control the controlled device to perform corresponding environmental state adjustment work, for example, lowering the refrigeration temperature, increasing the refrigeration wind speed, etc.

[0118] In practical applications, the wind speed adjustment range, temperature adjustment range, humidity adjustment range, and cleanliness adjustment range of the controlled device may be limited. For example, the wind speed may be divided into three gears (low, medium, and high), and the temperature may be limited to between 18°C ​​and 30°C, etc. Therefore, the value of the target control signal can be limited to a certain range (such as the wind speed can be limited to between 0-2). If the change indicated by the calculated target control signal exceeds the set maximum range limit, the target control signal can be limited to a certain range by truncation to ensure that each environmental state adjustment is smooth, avoiding instability caused by excessive changes in the degree of environmental state adjustment. Among them, the embodiments of the present disclosure do not limit the specific implementation method of using the target control signal to control the controlled device to perform the corresponding adjustment work. For example, those skilled in the art can refer to the implementation method of using the PID control signal to control the controlled device in the prior art, and the embodiments of the present disclosure do not limit this.

[0119] According to the environmental state control method of the embodiment of the present disclosure, by acquiring the actual environmental state information and target environmental state information of multiple points and the actual total power consumption information and target total power consumption information of multiple controlled devices, the initial control signals generated by multiple controllers are converted into multiple target control signals to control multiple controlled devices to perform corresponding environmental state adjustment tasks. The initial control signals output by the controllers can be automatically and dynamically adaptively adjusted according to real-time data to achieve joint and precise control of the environmental states of multiple points, and the power consumption of the controlled devices can be managed more effectively so that each point can reach its respective target environmental state as simultaneously as possible, and the power consumption of the controlled devices can be reduced, reducing operating costs and maintenance costs, thereby achieving precise, multi-point joint, adaptive and low-energy environmental state control as a whole.

[0120] Based on the above-mentioned environmental state control method of the embodiment of the present disclosure, the embodiment of the present disclosure also provides Figure 3 The schematic diagram of the environmental state control system is shown in FIG. Figure 3As shown, the actual environmental state information collected by m sensors (i.e., sensor 1, sensor 2, ..., sensor m) are respectively output by m BP-PID controllers and error analysis modules, and the m BP-PID controllers respectively output m initial control signals (i.e., du1, du2, ..., dum). The error analysis module can execute the above steps S1311 to S1315 to obtain the target partial derivatives and execute the above step S1321 to obtain the change rate of the actual environmental state information collected by each sensor, and then use the target partial derivatives and the change rate to update the gain matrix and the weight matrix respectively, and then generate n target control signals (signal1, signal2, ..., signaln) based on the gain matrix and the weight matrix and send them to the corresponding n air-conditioning devices (i.e., air-conditioning 1, air-conditioning 2, ..., air-conditioning n) respectively; the above control system can be used to update the initial control signal output by the PID controller according to the current error value and the change rate, and continuously optimize the control effect. Figure 3 The feedback path of this process is also shown, in which each point to be controlled is equipped with a BP-PID controller, and the initial control signal output by each BP-PID controller will participate in the update of the weight matrix and the gain matrix, and the target control signal after the update of the gain matrix and the weight matrix can be output to the control unit of the air-conditioning equipment, and finally realize the adaptive adjustment in the process of environmental state regulation. The core of the above control system lies in its hierarchical architecture, which includes the integration of data acquisition and processing, energy consumption optimization and control algorithms, and realizes precise control of environmental state by jointly optimizing the control strategy at multiple points and dynamically updating the weight matrix and the gain matrix according to the actual environmental state information collected by multiple sensors and the actual total power consumption information of multiple controlled devices.

[0121] According to the environmental state control method and system of the disclosed embodiment, the control signal can be dynamically adjusted according to real-time data, and the precise joint control of multi-point environmental states can be achieved, thereby improving the adaptability and robustness of the system, effectively maintaining the stability of the environmental state of designated spaces such as data centers and computer rooms, reducing equipment failure rates, and improving the overall stability of the system. By optimizing the control strategy, the system can more effectively manage energy consumption, achieve the same target environmental state, reduce the power consumption of the controlled equipment, and reduce operating costs; it can reduce the need for manual intervention through self-learning and adaptive control algorithms, simplify system maintenance, and reduce maintenance costs.

[0122] According to the environmental state control method and system of the embodiments of the present disclosure, it is possible to realize multi-point environmental state control based on self-learning gain adjustment, realize precise joint control of multi-point environmental state control, and ensure that the environmental state of each monitoring point reaches the expected control accuracy. According to the environmental state change rate and proportion of each monitoring point, the weight matrix and gain matrix are dynamically adjusted to ensure the environmental state control accuracy of each point. In addition, through the joint feedback adjustment mechanism of environmental state control and power consumption optimization, the control signal output by the control system can be dynamically adjusted according to the feedback signal of environmental state error and power consumption, and precise environmental state adjustment can be provided according to the specific needs of different points, thereby ensuring the optimal working state of each area or equipment, while reducing energy consumption.

[0123] Figure 4 A block diagram of an environmental state control system according to an embodiment of the present disclosure is shown. Figure 3 As shown, the system includes:

[0124] The first acquisition module 401 is used to periodically acquire m actual environmental state information currently collected by m sensors set at m points in the specified space and the current actual total power consumption information of n controlled devices set in the specified space, wherein the controlled devices are used to adjust the environmental state, and m and n are positive integers;

[0125] The second acquisition module 402 is used to acquire m initial control signals generated by m controllers connected to the m sensors, wherein the i-th initial control signal is generated by the i-th controller based on the actual environmental state information currently collected by the i-th sensor and the target environmental state information specified by the i-th point, 1≤i≤m;

[0126] A matrix updating module 403 is used to determine a gain matrix and a weight matrix of the current cycle according to the m actual environmental state information and the target environmental state information respectively specified by the m points, as well as the actual total power consumption information and the specified target total power consumption information, wherein the gain matrix is ​​used to indicate the mapping relationship between the m controllers and the n controlled devices, and the weight matrix is ​​used to indicate the environmental state change rate of the m points;

[0127] The signal conversion module 404 is used to convert the m initial control signals into n target control signals according to the gain matrix and the weight matrix of the current cycle. The n target control signals are used to respectively control the n controlled devices to perform corresponding environmental state adjustment tasks in the current cycle so that the environmental state of each point reaches the target environmental state.

[0128] In a possible implementation, the gain matrix and weight matrix of the current cycle are determined based on the m actual environmental state information and the target environmental state information specified by each of the m points, as well as the actual total power consumption information and the specified target total power consumption information, including: determining the gain matrix of the current cycle based on the state error between the m actual environmental state information and the target environmental state information specified by each of the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signals generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle; determining the weight matrix of the current cycle based on the m actual environmental state information currently collected by the m sensors and the m actual environmental state information collected by the m sensors in the previous cycle, and the weight matrix of the previous cycle.

[0129] In a possible implementation, the gain matrix of the current cycle is determined based on the state error between the m actual environmental state information and the target environmental state information specified by each of the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signal generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle, including: determining the first partial derivative of a preset system error function for each of the m actual environmental state information according to the state error between the m actual environmental state information and the target environmental state information specified by each of the m points; wherein the system error function represents the weighted sum between the state error and the power consumption error; determining each actual environmental state according to the partial derivative of the target control signal generated in the previous cycle, the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle, and the preset first mapping model. The invention relates to a method for determining a target environment state information of a first embodiment of the present invention, wherein the first mapping model is used to indicate the mapping relationship between the target control signal and the actual environment state information; the third partial derivative of the system error function to the actual total power consumption information is determined according to the power consumption error between the actual total power consumption information and the specified target total power consumption information; the fourth partial derivative of the actual total power consumption information to the gain matrix is ​​determined according to the partial derivative of the target control signal generated in the previous cycle by the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle and the preset second mapping model; the second mapping model is used to indicate the mapping relationship between the target control signal and the actual total power consumption information; the target partial derivative of the system error function to the gain matrix is ​​determined according to the first partial derivative, the second partial derivative, the third partial derivative and the fourth partial derivative; the gain matrix of the previous cycle is updated based on the target partial derivative and the preset learning rate to obtain the gain matrix of the current cycle.

[0130] In a possible implementation, the weight matrix of the current cycle is determined based on the m actual environmental status information currently collected by the m sensors, the m actual environmental status information collected by the m sensors in the previous cycle, and the weight matrix of the previous cycle, including: for the i-th sensor among the m sensors, determining the change rate from the actual environmental status information collected by the i-th sensor in the previous cycle to the actual environmental status information currently collected by the i-th sensor; when the change rate is greater than a preset rate threshold, multiplying the i-th weight value in the weight matrix of the previous cycle by a first coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the first coefficient is less than 1; when the change rate is less than or equal to the preset rate threshold, multiplying the i-th weight value in the weight matrix of the previous cycle by a second coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the second coefficient is greater than 1.

[0131] In one possible implementation, the m initial control signals are represented as m×1 column vectors, the gain matrix is ​​represented as an n×m matrix, and the weight matrix is ​​represented as an m×m diagonal matrix; wherein, converting the m initial control signals into n target control signals based on the gain matrix and weight matrix of the current cycle includes: matrix multiplying the column vectors of the m initial control signals with the weight matrix of the current cycle and the gain matrix of the current cycle to obtain the n target control signals.

[0132] In a possible implementation, the environmental status information includes at least one of temperature, humidity, and cleanliness; the controlled device includes an air-conditioning device, and the air-conditioning device is used to adjust at least one of temperature, humidity, and cleanliness.

[0133] According to the environmental state control system of the embodiment of the present disclosure, by acquiring the actual environmental state information and target environmental state information of multiple points and the actual total power consumption information and target total power consumption information of multiple controlled devices, the initial control signals generated by multiple controllers are converted into multiple target control signals to control multiple controlled devices to perform corresponding environmental state adjustment tasks. The initial control signals output by the controllers can be automatically and dynamically adaptively adjusted according to real-time data to achieve joint and precise control of the environmental states of multiple points, and the power consumption of the controlled devices can be managed more effectively so that each point can reach its respective target environmental state at the same time as much as possible, and the power consumption of the controlled devices can be reduced, reducing operating costs and maintenance costs, thereby achieving precise, multi-point joint, adaptive and low-energy environmental state control as a whole.

[0134] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0135] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0136] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0137] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0138] Figure 5 1 is a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or a terminal device. Figure 5 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0139] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0140] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0141] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0142] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0143] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0144] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0145] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0146] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0147] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0148] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0149] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for controlling an environmental state, characterized in that: include: Periodically obtain m actual environmental status information currently collected by m sensors set at m points in a specified space and current actual total power consumption information of n controlled devices set in the specified space, wherein the controlled devices are used to adjust the environmental status, and m and n are positive integers; Obtain m initial control signals generated by m controllers connected to the m sensors, wherein the i-th initial control signal is generated by the i-th controller based on the actual environmental state information currently collected by the i-th sensor and the target environmental state information specified by the i-th point, 1≤i≤m; Determine a gain matrix and a weight matrix of the current cycle according to the m actual environmental state information and the target environmental state information respectively specified by the m points, as well as the actual total power consumption information and the specified target total power consumption information, wherein the gain matrix is ​​used to indicate a mapping relationship between the m controllers and the n controlled devices, and the weight matrix is ​​used to indicate a rate of change of the environmental state of the m points; According to the gain matrix and weight matrix of the current cycle, the m initial control signals are converted into n target control signals, and the n target control signals are used to respectively control the n controlled devices to perform corresponding environmental state adjustment work in the current cycle, so that the environmental state of each point reaches the target environmental state.

2. The method according to claim 1, characterized in that The step of determining a gain matrix and a weight matrix of a current cycle according to the m actual environmental state information and the target environmental state information respectively specified by the m points, and the actual total power consumption information and the specified target total power consumption information comprises: Determine a gain matrix for the current cycle according to the state errors between the m actual environmental state information and the target environmental state information respectively specified by the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signal generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle; The weight matrix of the current cycle is determined according to the m pieces of actual environmental status information currently collected by the m sensors, the m pieces of actual environmental status information collected by the m sensors in the previous cycle, and the weight matrix of the previous cycle.

3. The method according to claim 2, characterized in that The step of determining the gain matrix of the current cycle according to the state errors between the m actual environmental state information and the target environmental state information respectively specified by the m points, the power consumption error between the actual total power consumption information and the specified target total power consumption information, the m initial control signals generated in the previous cycle, the target control signal generated in the previous cycle, the weight matrix of the previous cycle, and the gain matrix of the previous cycle includes: Determine, according to the state errors between the m actual environmental state information and the target environmental state information respectively specified by the m points, a first partial derivative of a preset system error function with respect to each of the m actual environmental state information; wherein the system error function represents a weighted sum between the state error and the power consumption error; Determine the second partial derivative of each actual environment state information with respect to the gain matrix according to the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle, and the partial derivative of the target control signal generated in the previous cycle by the preset first mapping model; wherein the first mapping model is used to indicate the mapping relationship between the target control signal and the actual environment state information; Determining a third partial derivative of the system error function with respect to the actual total power consumption information according to a power consumption error between the actual total power consumption information and the specified target total power consumption information; Determine the fourth partial derivative of the actual total power consumption information to the gain matrix according to the m initial control signals generated in the previous cycle, the weight matrix of the previous cycle, and the partial derivative of the target control signal generated in the previous cycle by the preset second mapping model; wherein the second mapping model is used to indicate the mapping relationship between the target control signal and the actual total power consumption information; Determine a target partial derivative of the system error function with respect to a gain matrix according to the first partial derivative, the second partial derivative, the third partial derivative, and the fourth partial derivative; Based on the target partial derivative and a preset learning rate, the gain matrix of the previous cycle is updated to obtain the gain matrix of the current cycle.

4. The method according to claim 3, characterized in that The system error function E is expressed as: Among them, T i represents the actual environmental status information collected by the i-th sensor, T target Represents the target environment status information of the i-th point; P total Represents the actual total power consumption information, P target Represents the target total power consumption information, λ i represents the weighting coefficient corresponding to the i-th sensor, and γ represents the weighting coefficient corresponding to the power consumption error; The first partial derivative of the system error function with respect to the actual environmental state information collected by the i-th sensor is expressed as: The second partial derivative of the actual environmental state information collected by the i-th sensor to the gain matrix K[i,j] is expressed as: Where f(·) represents the first mapping model, u r-1 represents the target control signal of the previous cycle, t represents time, and W r-1 Represents the weight matrix of the previous cycle, du r-1 represents the column vector of the m initial control signals generated in the previous cycle, and j represents the jth element in the matrix; The third partial derivative of the system error function with respect to the actual total power consumption information is expressed as: The fourth partial derivative of the actual total power consumption information to the gain matrix is ​​expressed as: Wherein, g(·) represents the second mapping model; The target partial derivative of the system error function with respect to the gain matrix is ​​expressed as: The gain matrix K[i,j] of the current cycle r It is expressed as: Among them, K[i,j] r-1 represents the gain matrix of the previous cycle, and η represents the preset learning rate.

5. The method according to claim 2, characterized in that: Determining the weight matrix of the current cycle according to the m actual environment state information currently collected by the m sensors, the m actual environment state information collected by the m sensors in the previous cycle, and the weight matrix of the previous cycle includes: For an i-th sensor among the m sensors, determining a rate of change from actual environmental state information collected by the i-th sensor in a previous period to actual environmental state information currently collected by the i-th sensor; When the change rate is greater than the preset rate threshold, the i-th weight value in the weight matrix of the previous cycle is multiplied by the first coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the first coefficient is less than 1, and the i-th weight value is the weight value corresponding to the i-th point; When the change rate is less than or equal to the preset rate threshold, the i-th weight value in the weight matrix of the previous cycle is multiplied by the second coefficient to obtain the i-th weight value in the weight matrix of the current cycle; wherein the second coefficient is greater than 1.

6. The method according to claim 1, characterized in that The m initial control signals are represented as m×1 column vectors, the gain matrix is ​​represented as an n×m matrix, and the weight matrix is ​​represented as an m×m diagonal matrix; wherein, converting the m initial control signals into n target control signals according to the gain matrix and the weight matrix of the current cycle includes: The column vectors of the m initial control signals are matrix-multiplied with the weight matrix of the current cycle and the gain matrix of the current cycle to obtain the n target control signals.

7. The method according to any one of claims 1 to 6, characterized in that: The environmental status information includes at least: at least one of temperature, humidity, and cleanliness; The controlled device includes an air-conditioning device, and the air-conditioning device is used to adjust at least one of temperature, humidity and cleanliness.

8. An environmental state control system, characterized in that: include: A first acquisition module is used to periodically acquire m actual environmental status information currently collected by m sensors set at m points in a specified space and current actual total power consumption information of n controlled devices set in the specified space, wherein the controlled devices are used to adjust the environmental status, and m and n are positive integers; A second acquisition module is used to acquire m initial control signals generated by m controllers connected to the m sensors, wherein the i-th initial control signal is generated by the i-th controller based on the actual environmental state information currently collected by the i-th sensor and the target environmental state information specified by the i-th point, 1≤i≤m; A matrix update module, used to determine a gain matrix and a weight matrix of the current cycle according to the m actual environmental state information and the target environmental state information respectively specified by the m points, as well as the actual total power consumption information and the specified target total power consumption information, wherein the gain matrix is ​​used to indicate a mapping relationship between the m controllers and the n controlled devices, and the weight matrix is ​​used to indicate a rate of change of the environmental state of the m points; A signal conversion module is used to convert the m initial control signals into n target control signals according to the gain matrix and weight matrix of the current cycle. The n target control signals are used to respectively control the n controlled devices to perform corresponding environmental state adjustment work in the current cycle so that the environmental state of each point reaches the target environmental state.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method described in any one of claims 1 to 7 when executing the instructions stored in the memory.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images