A method and device for hydraulic balance control of the entire heating network based on user behavior.
By employing non-intrusive thermal disturbance identification and distributed game theory control, the problem of insufficient user behavior recognition in traditional heating scheduling is solved, achieving full-network hydraulic balance and energy saving, and improving the adaptive capability and privacy security of the heating system.
Patent Information
- Application Number
- CN202611455456.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-18
- Publication Date
- 2026-11-10
AI Technical Summary
Traditional heating dispatching cannot accurately identify and respond to sudden behaviors such as users opening windows for ventilation, resulting in hydraulic fluctuations and energy waste. Furthermore, centralized control modes suffer from computing power bottlenecks and privacy and security risks.
Non-intrusive thermal disturbance identification, game theory utility constraints, alternating direction multiplier method and pump frequency adaptive control are adopted. Combined with user behavior data, distributed solution is performed to construct the game utility function. The hydraulic balance of the whole network is achieved through distributed iteration and pump frequency adaptive adjustment.
It can accurately identify irrational heating behaviors, suppress hydraulic oscillations, reduce computing power requirements, protect privacy, improve heating quality and equipment lifespan, and achieve on-demand heating.
Smart Images

Figure CN123065031A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of hot water hydraulic control technology, specifically relating to a method and device for hydraulic balance control of the entire heating network based on user behavior. Background Technology
[0002] Traditional heating dispatching relies heavily on adjusting macroscopic heat sources based on meteorological data, but it cannot detect or respond to microscopic thermal disturbances caused by sudden behaviors such as residents opening windows for ventilation or holding indoor gatherings. This leads to user-end valves operating haphazardly due to blind opening and closing, resulting in disordered regulation. This control mode, which lacks global hydraulic coordination, not only causes severe hydraulic oscillations throughout the network, such as near-end overheating and far-end undercooling, resulting in enormous energy waste, but also presents unbearable computing power bottlenecks and privacy and security risks if all the massive amounts of individual data are transmitted back to the central cloud for centralized processing.
[0003] Chinese patent publication number CN116557949A, entitled "A Method for Temperature Balance Control and Regulation of Multi-User Centralized Heating Networks," discloses a method for predicting heat load using actual indoor and outdoor temperatures and historical operating data. This method controls valve opening to adjust the deviation between the actual circulating flow rate and the preset flow rate of the primary network, thus achieving hydraulic balance regulation of the primary network. Based on the determined circulating flow rate, the method calculates the return water temperature of the primary network to predict the heat load, and then performs thermal and hydraulic balance regulation of the primary network. Based on the initial thermal and hydraulic balance of the primary network, the method sequentially adjusts the secondary network and each user unit's thermal and hydraulic balance, repeating the above steps to achieve overall thermal and hydraulic balance of the heating network. However, this method cannot accurately identify and suppress sudden thermal disturbances caused by users opening windows. Summary of the Invention
[0004] To overcome the problems existing in the prior art, the present invention aims to provide a method and device for hydraulic balance control of the entire heating network based on user behavior. By combining principles such as non-intrusive thermal disturbance identification, game theory utility constraints, distributed solution using alternating direction multiplier method, and pump frequency adaptive unobstructed control, it can suppress hydraulic oscillations, accurately identify irrational heat consumption, protect privacy, reduce computing power requirements, improve hydraulic balance, achieve on-demand heating, and extend equipment life.
[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a method for hydraulic balance control of the entire heating network based on user behavior, comprising the following steps: Real-time collection of household heat meter data from each user; The transient thermal response imbalance of each user is calculated by the first-order dynamic equation of thermodynamics, and the transient thermal response imbalance is analyzed by time-series gradient analysis through a behavior identification sliding window to identify irrational heat use behavior of users and update the user's heat credit score. Construct a game utility function for each user valve agent. The game utility function includes an indoor temperature comfort deviation term, a valve mechanical wear penalty term, and an external hydraulic penalty term. The external hydraulic penalty term is determined based on the network-wide hydraulic imbalance vulnerability index and the user's thermal credit score. By using the alternating direction multiplier method, distributed iteration is performed between the user local controller and the building edge gateway to update the user valve opening variables, global hydraulic coordination variables and dual residual vectors until the convergence condition is met and Nash equilibrium is reached, and the optimal user valve opening matrix of the entire network is output. The total flow demand of the secondary network is calculated based on the optimal valve opening matrix of the entire network, and the optimal operating frequency for controlling the variable frequency circulating water pump of the secondary network is calculated based on the similarity law of fluid mechanics and the valve opening dispersion correction term.
[0006] Secondly, the present invention provides a user-behavior-oriented hydraulic balance control system for the entire heating network, comprising: The data acquisition module is used to collect real-time data from each user's household heat meter. The thermal disturbance identification module is used to calculate the transient thermal response imbalance of each user through the first-order dynamic equation of thermodynamics, and to perform time-series gradient analysis on the transient thermal response imbalance through a behavior identification sliding window to identify the user's irrational heat use behavior and update the user's heat credit score. The game utility construction module is used to construct the game utility function of each user valve agent. The game utility function includes an indoor temperature comfort deviation term, a valve mechanical wear penalty term, and an external hydraulic penalty term. The external hydraulic penalty term is determined based on the network-wide hydraulic imbalance vulnerability index and the user's thermal credit score. The distributed solution module is used to perform distributed iteration between the user local controller and the building edge gateway using the alternating direction multiplier method, updating the user valve opening variables, global hydraulic coordination variables and dual residual vectors until the convergence condition is met and Nash equilibrium is reached, and outputting the optimal user valve opening matrix of the entire network. The pump frequency control module is used to calculate the total flow demand of the secondary network based on the optimal valve opening matrix of the entire network, and to calculate the optimal operating frequency for controlling the variable frequency circulating water pump of the secondary network based on the similarity law of fluid mechanics and the valve opening dispersion correction term.
[0007] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the user-oriented heating network hydraulic balance control method.
[0008] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the user-oriented heating network hydraulic balance control method.
[0009] Fifthly, the present invention provides a computer program product including a computer-readable medium, wherein computer-readable program code is included on the computer-readable medium, and the program code executes the user-oriented heating network hydraulic balance control method.
[0010] Compared with the prior art, the present invention has the following beneficial effects: This invention internalizes the global hydraulic cost into the adjustment constraints of each household valve through a game-theoretic utility function. Specifically, the utility function includes an external hydraulic penalty term, which is related to the overall network hydraulic imbalance vulnerability index and the user's heat credit score. When a heat exchange station detects that the main network is hydraulically vulnerable, users with poor heat credit scores will experience a sharp drop in their utility function if they significantly adjust their valves, thus forcing the user agent to spontaneously choose a gentle adjustment action. Simultaneously, through the alternating direction multiplier method, distributed iteration is performed between the user's local controller and the building's edge gateway. Each household valve no longer blindly opens and closes, but gradually reaches Nash equilibrium through game-theoretic coordination with its neighbors. Therefore, the valve adjustment actions across the entire network tend to be gentle and coordinated, effectively suppressing the problems of near-end overheating, far-end overcooling, and severe hydraulic oscillations throughout the network under traditional control modes.
[0011] This invention eliminates the need for monitoring equipment in users' homes. Instead, it directly utilizes the inlet and outlet water temperature difference and instantaneous flow rate collected at high frequency by the user's ultrasonic heat meter. It calculates the transient thermal response imbalance for each user using a first-order thermodynamic dynamic equation, eliminating normal heat loss due to outdoor weather and building envelope. Furthermore, it performs time-series gradient analysis on the transient thermal response imbalance using a behavioral recognition sliding window. When the rate of change exceeds a preset positive disturbance threshold, it identifies malicious negative heat disturbance behaviors such as opening windows or prolonged use of powerful exhaust fans. The system further uses a dynamic heat credit score update formula to cumulatively penalize users who frequently and irrationally open windows, resulting in excessive and unnecessary heat dissipation. Thus, the system can accurately identify irrational heat use behaviors and limit disorderly heat extraction at that node in subsequent game theory, reducing ineffective heat loss and corresponding energy waste.
[0012] Traditional centralized control systems, which transmit massive amounts of individual data back to a central cloud for centralized solution, suffer from unbearable computational bottlenecks and privacy and security risks. This invention employs the alternating direction multiplier method, transforming the global hydraulic balance problem into a distributed collaborative game between individual user valve agents. Each user's local controller only needs to update the valve opening variable locally, and the building edge gateway only collects valve position data from adjacent users and updates the global hydraulic coordination variable and dual residual vector. The entire process is decoupled and completed directly at the edge, independent of a central server. Therefore, the cloud does not need to collect and process massive amounts of user privacy data, eliminating the computational bottleneck and high-concurrency communication risks of the central server, while improving the system's real-time performance, reliability, and privacy security.
[0013] The heat exchange station collects the optimal valve opening after the game equilibrium of valves for all users within its jurisdiction. This is converted into flow rate using a valve opening-flow mapping function and summed to obtain the total flow demand of the secondary network. Subsequently, the base pump frequency is calculated based on the cube root relationship of the similarity law in fluid mechanics, and a valve opening dispersion correction term is introduced. If the valve openings across the network are inconsistent and have large dispersion, it indicates a risk of local hydraulic imbalance. The formula will automatically fine-tune to increase the pump frequency, using transient pressure head to flush out resistance imbalance areas and ensure sufficient heating head for end users. Therefore, this invention not only adjusts the circulating water pumps according to actual flow demand but also actively corrects hydraulic imbalances, alleviating near-end overheating and far-end undercooling problems, improving the overall network hydraulic balance and end-user heating quality.
[0014] This invention feeds back the total flow demand to the main heat source one time lag period in advance, enabling coordination among the heat source, pipeline network, heat exchange station, and user end. Through distributed game theory on the user side, coordination of building gateways, and adaptive pump frequency control at the heat exchange station, the entire system can achieve self-organization and oscillation-free on-demand heating across the entire chain. This reduces heat and electricity waste and improves the heating system's adaptability to thermal disturbances caused by user behavior. A valve mechanical wear penalty term is included in the game utility function to limit frequent valve fine-tuning; simultaneously, external hydraulic penalties and distributed coordination prevent frequent valve actuation due to blind adjustments by users. Therefore, this invention reduces mechanical wear on electric regulating valves, extends valve lifespan, and reduces the additional burden and maintenance costs on pumps caused by hydraulic oscillations. Attached Figure Description
[0015] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the invention in any way.
[0016] In the attached diagram: Figure 1 This is a flowchart of the method steps in an embodiment of the present invention. Detailed Implementation
[0017] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.
[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.
[0019] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. This application can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.
[0020] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.
[0021] The present invention will now be described in detail with reference to the accompanying drawings.
[0022] The present invention provides a user-behavior-oriented hydraulic balance control method for the entire heating network, comprising the following steps: Real-time collection of household heat meter data from each user; The transient thermal response imbalance of each user is calculated by the first-order dynamic equation of thermodynamics, and the transient thermal response imbalance is analyzed by time-series gradient analysis through a behavior identification sliding window to identify irrational heat use behavior of users and update the user's heat credit score. Construct a game utility function for each user valve agent. The game utility function includes an indoor temperature comfort deviation term, a valve mechanical wear penalty term, and an external hydraulic penalty term. The external hydraulic penalty term is determined based on the network-wide hydraulic imbalance vulnerability index and the user's thermal credit score. By using the alternating direction multiplier method, distributed iteration is performed between the user local controller and the building edge gateway to update the user valve opening variables, global hydraulic coordination variables and dual residual vectors until the convergence condition is met and Nash equilibrium is reached, and the optimal user valve opening matrix of the entire network is output. The total flow demand of the secondary network is calculated based on the optimal valve opening matrix of the entire network, and the optimal operating frequency for controlling the variable frequency circulating water pump of the secondary network is calculated based on the similarity law of fluid mechanics and the valve opening dispersion correction term.
[0023] This invention collects real-time data from household heat meters and uses first-order thermodynamic dynamic equations and sliding window time-series gradient analysis to accurately identify irrational heat consumption behaviors of users and update their heat credit scores. It introduces an external hydraulic penalty based on the vulnerability index of the entire network's hydraulic imbalance and the heat credit score into the game utility function. Through the alternating direction multiplier method, it achieves Nash equilibrium through distributed iteration between the local controller and building gateways, outputting the optimal household valve opening matrix. Then, based on the fluid mechanics similarity law and the valve opening dispersion correction term, it calculates the optimal operating frequency of the variable frequency circulating water pump. Thus, without the need for centralized processing of massive amounts of privacy data, it effectively suppresses network-wide hydraulic oscillations, reduces irrational heat loss and valve mechanical wear, eliminates computing bottlenecks and privacy risks, and proactively improves hydraulic imbalance using dispersion correction, achieving end-to-end on-demand heating and energy conservation.
[0024] Example 1 like Figure 1 As shown, in this embodiment, it is not necessary to install monitoring equipment in the user's home. Instead, the inlet and outlet water temperature difference is directly collected at high frequency by the household meter (household ultrasonic heat meter). and instantaneous flow It accurately identifies transient irrational heat loss caused by user behaviors such as opening windows and gatherings: based on the first-order dynamic equation of thermodynamics, for any user During the scheduling cycle The transient thermal response imbalance is calculated through the local gateway. :
[0025] In the formula: This is the specific heat capacity of water; 、 Time of the first Indoor water supply and return temperatures for each user; The overall heat transfer coefficient of the user's house; Time of the first The actual indoor temperature of each user; The overall outdoor temperature at any given time.
[0026] Set up a behavior recognition sliding window to... Perform time-series gradient analysis: like ( (The preset positive disturbance threshold is 0.4kW / min): This determines whether the resident is currently engaging in malicious negative heat disturbance behaviors such as opening windows or running powerful exhaust fans for extended periods.
[0027] Hot Credit Score Dynamically updated formula:
[0028] In the formula, The cumulative penalty coefficient ranges from 0.05 to 0.8. The more frequently a user engages in irrational window opening behavior and the greater the unnecessary heat dissipation, the higher the thermal credit penalty coefficient. This will lead to an exponential increase, and in the next stage of the game, the player will have to pay a higher price and be constrained.
[0029] When an individual user is disturbed and tries to forcibly adjust the local valve opening... At that time, blind adjustment is no longer allowed; instead, its utility function must be maximized. :
[0030] In the formula: For the first The game utility function of an individual user agent; , The factors are comfort weighting factor and valve mechanical wear penalty factor. The value ranges from 0.6 to 1.5. ; Values range from 0.1 to 0.4; for Time of the first The opening degree of the electric regulating valve for each user; for The hydraulic imbalance vulnerability index of the entire network at all times.
[0031] The first term in the above formula The second term in the above formula represents the user's own temperature comfort requirements. The third term in the above formula represents the mechanical wear penalty of the valve itself (limiting frequent valve fine-tuning); This represents external hydraulic penalty when the heat exchange station detects that the main hydraulic network is in a vulnerable state. When the level is relatively high, behavioral credit is poor. (High) users who make significant adjustments to the valve Its utility function It will collapse rapidly, forcing individual intelligent agents to spontaneously choose gentle actions when adjusting.
[0032] In the above formula, the room temperature at the next moment... With the current valve opening The following explicit first-order thermodynamic response relationship exists:
[0033] In the formula: ; .
[0034] To avoid cloud computing crashes caused by massive data concurrency, the global hydraulic balance problem is transformed into a distributed cooperative game among the intelligent agents of each valve. The Alternating Direction Multiplier Method (ADMM) algorithm is introduced, and in the... In this iteration, each user local controller performs the following three-step closed-loop recursion: 1) User-local valve opening variable renew:
[0035] In the formula: , In distributed solutions, the first Neighbor slack variables and dual residual vectors in the next iteration; This is the step size penalty parameter for the ADMM algorithm, with a value ranging from 0.1 to 5.0.
[0036] The above equation is simplified using the first derivative, and the optimal threshold that satisfies the game between itself and its neighbors can be quickly solved locally.
[0037] 2) Global hydraulic coordination variables on the building / gateway side renew:
[0038] This step involves the building edge gateway collecting valve positions from neighboring users (such as those above, below, left, and right neighbors) and calculating the average hydraulic buffer space.
[0039] 3) Dual residual vector renew:
[0040] Convergence termination condition: and
[0041] In the formula: For extremely small convergence accuracy (e.g.) When this condition is met, the game reaches a Nash equilibrium, and the optimal valve opening matrix for the entire network is output. .
[0042] The super-intelligent agent of the heat exchange station collects the sum of the optimal flow demands after all valves in its jurisdiction have reached equilibrium through game theory. :
[0043] In the formula: This is a nonlinear function for mapping valve opening to flow rate, pre-calibrated at the factory.
[0044] Based on the total flow demand of the secondary network, the heat exchange station's production scheduling controller calculates the optimal operating frequency of the secondary network's variable frequency circulating water pumps. :
[0045] In the formula: , These are the rated frequency and rated flow rate of the secondary network variable frequency circulating water pump, respectively. This represents the current average valve opening across the entire network. This is the correction factor for hydraulic misalignment.
[0046] The last term in the above formula is the one in Formula 2. :
[0047] The above formula not only provides the basic variable frequency power based on the similarity law of fluid mechanics (cubic root relationship), but also introduces a valve opening dispersion correction term. If the valve openings of the entire network are inconsistent and the dispersion is large (meaning there is a risk of hydraulic imbalance in some areas), the formula will automatically fine-tune to increase the pump frequency, using transient pressure head to flush out the resistance imbalance area and ensure sufficient heating head for end users.
[0048] Example 2 Optionally, in this embodiment, the building edge gateway collects the inlet and outlet water temperature difference of each household's ultrasonic heat meter in real time. Instantaneous flow and user room temperature .
[0049] Using the first-order thermodynamic equations, and eliminating normal heat loss due to outdoor weather and building envelope, the transient thermal response imbalance for each household is calculated. .
[0050] Irrational heat-related behaviors of users (such as opening windows or using strong ventilation) are identified through time-series gradient analysis. If malicious heat dissipation is determined, the user's historical heat credit penalty coefficient is increased using a cumulative penalty formula. This introduces constraints into subsequent game theory.
[0051] In this embodiment, the local controller predicts the current valve opening based on a first-order response model. The indoor temperature at the next moment .
[0052] The heat exchange station disseminates current hydraulic imbalance vulnerability indicators to the entire network. .
[0053] A game-theoretic utility function is constructed by combining the user's own temperature comfort requirements, valve mechanical wear penalties, and external hydraulic shock penalties. This makes the heat credit score Less skilled users will face extremely high overall costs when attempting to adjust valves drastically and haphazardly, forcing them to spontaneously choose a gentle adjustment strategy.
[0054] In this embodiment, each household valve intelligent agent performs parallel computation locally, and in the first... In this iteration, the first derivative is used to quickly solve for the optimal threshold variable that satisfies the game between itself and its neighbors. .
[0055] The building edge gateway collects valve position data from neighboring users (up, down, left, and right neighbors), calculates and updates global hydraulic coordination variables. and dual residual vector .
[0056] When the opening changes and residuals of all valves in the entire network are less than a small threshold At this point, the game reaches a Nash equilibrium, and ultimately outputs the optimal valve opening matrix for the entire network. The entire process does not rely on a central server and is completed decoupled directly at the edge.
[0057] In this embodiment, the super-agent of the heat exchange station collects the optimal valve openings after game convergence within its jurisdiction, converts them into flow rates through a calibration function, and sums them to obtain the total flow demand value of the secondary network. .
[0058] The dispatch controller calculates the fundamental frequency based on the similarity law of fluid mechanics and introduces a valve opening dispersion correction term to calculate the optimal operating frequency of the secondary network variable frequency circulating water pump. .
[0059] If the valve opening dispersion across the entire network is large (posing a risk of local hydraulic imbalance), the system will automatically fine-tune and increase the pump frequency, using transient pressure head to flush out the resistance imbalance area; at the same time, the total flow demand will be fed back to the main heat source one time lag period in advance, realizing self-organized, oscillation-free, on-demand heating throughout the entire chain from source to network to station to household.
[0060] Example 3 Based on the user behavior-oriented hydraulic balance control method for the entire heating network in Embodiment 1, a user behavior-oriented hydraulic balance control system for the entire heating network is disclosed, comprising: The data acquisition module is used to collect real-time data from each user's household heat meter. The thermal disturbance identification module is used to calculate the transient thermal response imbalance of each user through the first-order dynamic equation of thermodynamics, and to perform time-series gradient analysis on the transient thermal response imbalance through a behavior identification sliding window to identify the user's irrational heat use behavior and update the user's heat credit score. The game utility construction module is used to construct the game utility function of each user valve agent. The game utility function includes an indoor temperature comfort deviation term, a valve mechanical wear penalty term, and an external hydraulic penalty term. The external hydraulic penalty term is determined based on the network-wide hydraulic imbalance vulnerability index and the user's thermal credit score. The distributed solution module is used to perform distributed iteration between the user local controller and the building edge gateway using the alternating direction multiplier method, updating the user valve opening variables, global hydraulic coordination variables and dual residual vectors until the convergence condition is met and Nash equilibrium is reached, and outputting the optimal user valve opening matrix of the entire network. The pump frequency control module is used to calculate the total flow demand of the secondary network based on the optimal valve opening matrix of the entire network, and to calculate the optimal operating frequency for controlling the variable frequency circulating water pump of the secondary network based on the similarity law of fluid mechanics and the valve opening dispersion correction term.
[0061] Example 4 The purpose of this embodiment is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the user-oriented heating network hydraulic balance control method.
[0062] Example 5 The purpose of this embodiment is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the user-oriented heating network hydraulic balance control method.
[0063] Example 6 The purpose of this embodiment is to provide a computer program product including a computer-readable medium, wherein the computer-readable medium contains computer-readable program code that executes the user-oriented heating network hydraulic balance control method.
[0064] The steps and methods involved in the apparatuses of the above embodiments 3, 4, 5 and 6 correspond to those in embodiment 1. For specific implementation details, please refer to the relevant description section of embodiment 1.
[0065] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0066] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0067] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0068] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0069] Unless otherwise specified, the working methods or control methods involved in the above embodiments are conventional working methods or control methods in the art.
[0070] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.
[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Any other modifications or equivalent substitutions made by those skilled in the art to the technical solutions of the present invention, as long as they do not depart from the spirit and scope of the technical solutions of the present invention, should be covered within the scope of the claims of the present invention.
Claims
1. A user-behavior-oriented hydraulic balance control method for the entire heating network, characterized in that, Includes the following steps: Real-time collection of household heat meter data from each user; The transient thermal response imbalance of each user is calculated by the first-order dynamic equation of thermodynamics, and the transient thermal response imbalance is analyzed by time-series gradient analysis through a behavior identification sliding window to identify irrational heat use behavior of users and update the user's heat credit score. Construct a game utility function for each user valve agent. The game utility function includes an indoor temperature comfort deviation term, a valve mechanical wear penalty term, and an external hydraulic penalty term. The external hydraulic penalty term is determined based on the network-wide hydraulic imbalance vulnerability index and the user's thermal credit score. By using the alternating direction multiplier method, distributed iteration is performed between the user local controller and the building edge gateway to update the user valve opening variables, global hydraulic coordination variables and dual residual vectors until the convergence condition is met and Nash equilibrium is reached, and the optimal user valve opening matrix of the entire network is output. The total flow demand of the secondary network is calculated based on the optimal valve opening matrix of the entire network, and the optimal operating frequency for controlling the variable frequency circulating water pump of the secondary network is calculated based on the similarity law of fluid mechanics and the valve opening dispersion correction term.
2. The user-behavior-oriented hydraulic balance control method for the entire heating network according to claim 1, characterized in that, For any user i, during scheduling period t, its transient thermal response imbalance is calculated through the local gateway: In the formula, is This is the specific heat capacity of water; 、 for Time of the first Indoor water supply and return temperatures for each user; The overall heat transfer coefficient of the user's house; for Time of the first The actual indoor temperature of each user; for Real-time outdoor temperature; A behavior recognition sliding window is set up to perform time-series gradient analysis on the transient thermal response imbalance. When the rate of change of the transient thermal response imbalance over time is greater than a preset positive disturbance threshold, it is determined that the user is currently exhibiting malicious negative thermal disturbance behavior. The portion of the transient thermal response imbalance that is greater than zero is multiplied by the cumulative penalty coefficient and then added to the user's current thermal credit score to obtain the updated thermal credit score.
3. The user-behavior-oriented hydraulic balance control method for the entire heating network according to claim 1, characterized in that, The game utility function for user i is: In the formula For the first The game utility function of an individual user agent; , These are respectively the comfort weighting factor and the valve mechanical wear penalty factor; for Time of the first The opening degree of the electric regulating valve for each user; for The hydraulic imbalance vulnerability index of the entire network at all times.
4. The user-behavior-oriented hydraulic balance control method for the entire heating network according to claim 1, characterized in that, Distributed cooperative game using the alternating direction multiplier method, the k-th iteration includes: Each user's local controller introduces a product term of the dual residual vector and the difference between the valve opening variable and the global hydraulic coordination variable, as well as a squared term of the step size penalty parameter and the difference between the valve opening variable and the global hydraulic coordination variable, into its own utility function to solve for the valve opening that maximizes the local objective and obtain the updated local valve opening. The building edge gateway collects the updated valve openings of neighboring users and combines them with the dual residual vector to calculate and update the global hydraulic coordination variables to characterize the average hydraulic buffer space between neighboring users. The updated dual residual vector is obtained by multiplying the difference between the updated local valve opening and the global hydraulic coordination variable by the step size penalty parameter and then accumulating it into the current dual residual vector. Repeat the above iterations. When the opening changes and residuals of all valves in the network are less than the preset convergence accuracy, it is determined that the game has reached a Nash equilibrium, and the optimal valve opening matrix of the entire network is output.
5. The user-behavior-oriented hydraulic balance control method for the entire heating network according to claim 1, characterized in that, The heat exchange station collects the optimal valve opening after the game equilibrium of valves for all users within its jurisdiction. This is then converted into the flow rate for each user using a pre-calibrated valve opening-flow mapping function and summed to obtain the total flow demand of the secondary network. Based on the pump's rated frequency, rated flow rate, the cube root of the ratio of the total secondary network flow demand to the rated flow rate, and a valve opening dispersion correction term, the optimal operating frequency of the variable frequency circulating water pump is calculated. The valve opening dispersion correction term is 1 plus the product of the hydraulic imbalance correction coefficient and the overall network hydraulic imbalance vulnerability index. The overall network hydraulic imbalance vulnerability index is the sum of the absolute values of the differences between the optimal valve opening for each user and the average valve opening for the entire network, divided by the product of the total number of users and the average valve opening for the entire network. When the overall network valve opening dispersion is large, the pump frequency is automatically fine-tuned to increase, utilizing transient pressure head to flush out resistance imbalance areas and ensure sufficient heating head for end users.
6. The user-behavior-oriented hydraulic balance control method for the entire heating network according to claim 1, characterized in that, The distributed iterative solution process based on the alternating direction multiplier method and the calculation and control execution process of the optimal operating frequency of the variable frequency water pump are completed in a distributed parallel manner between the user edge side and the building gateway, so as to feed back the total flow demand of the secondary network to the main heat source one time delay period in advance.
7. A user-behavior-oriented hydraulic balance control system for a whole heating network, characterized in that, include: The data acquisition module is used to collect real-time data from each user's household heat meter. The thermal disturbance identification module is used to calculate the transient thermal response imbalance of each user through the first-order dynamic equation of thermodynamics, and to perform time-series gradient analysis on the transient thermal response imbalance through a behavior identification sliding window to identify the user's irrational heat use behavior and update the user's heat credit score. The game utility construction module is used to construct the game utility function of each user valve agent. The game utility function includes an indoor temperature comfort deviation term, a valve mechanical wear penalty term, and an external hydraulic penalty term. The external hydraulic penalty term is determined based on the network-wide hydraulic imbalance vulnerability index and the user's thermal credit score. The distributed solution module is used to perform distributed iteration between the user local controller and the building edge gateway using the alternating direction multiplier method, updating the user valve opening variables, global hydraulic coordination variables and dual residual vectors until the convergence condition is met and Nash equilibrium is reached, and outputting the optimal user valve opening matrix of the entire network. The pump frequency control module is used to calculate the total flow demand of the secondary network based on the optimal valve opening matrix of the entire network, and to calculate the optimal operating frequency for controlling the variable frequency circulating water pump of the secondary network based on the similarity law of fluid mechanics and the valve opening dispersion correction term.
8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the user-behavior-oriented hydraulic balance control method for the entire heating network as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the user-behavior-oriented hydraulic balance control method for the entire heating network as described in any one of claims 1-6.
10. A computer program product comprising a computer-readable medium, characterized in that, The computer-readable medium contains computer-readable program code that performs the user-behavior-oriented hydraulic balance control method for the entire heating network as described in any one of claims 1-6.
Citation Information
Patent Citations
Temperature balance control and adjustment method for multi-user central heating pipe network
CN116557949A
