CN-121978942-A - Method and system for collaborative optimization of indoor environment and energy consumption of green building group based on digital twin model

CN121978942ACN 121978942 ACN121978942 ACN 121978942ACN-121978942-A

Abstract

The application relates to the technical field of intelligent control of green building groups, and discloses a method and a system for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model. The method comprises the steps of obtaining original environment data of a building group, constructing a digital twin simulation model and outputting predicted environment data, generating a multi-target cooperative control function, generating an HVAC (heating, ventilating and air conditioning) optimal control instruction based on MPC (MPC) predictive control, executing a power redistribution task, and carrying out regional mapping to generate a final control instruction. Compared with the prior art, the method has the advantages that the control strategy is single, the response dynamic characteristics of equipment are ignored, and especially the technical problem that the global optimization control of energy consumption and environment cannot be realized under the condition of cooperative control of a green building group. According to the application, by constructing a comprehensive digital twin model and combining a multi-target cooperative optimization and a distributed power modulation mechanism, dynamic balance control of environmental comfort and energy consumption cost in a complex building group is realized.

Inventors

FAN JUAN
WANG YITING
WANG LANYING
DUAN LIGUO
CHEN JINJUN
GAO RONGQING
WANG JINGYU
CUI CHUNMEI

Assignees

内蒙古首辉科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260203

Claims (10)

1. The method for optimizing the indoor environment and the energy consumption of the green building group based on the digital twin model is characterized by comprising the following steps: Step S10, obtaining an original environment number vector of the indoor time data t of the green building group Based on the original environmental data vector Building a digital twin simulation model by adopting a modeling mechanism based on building thermal inertia decoupling and equipment response nesting, and outputting a predicted environment data vector by the digital twin simulation model ; Step S20, based on the prediction environment data vector The weighted absolute value mapping mechanism driven based on the environment deviation measure is adopted to execute the multi-target cooperative benefit estimation task, and the multi-target demand control function is output ; Step S30, controlling the function based on the multi-objective demand Executing an HVAC control strategy solving task by adopting an MPC model predictive control mechanism based on a mixed building group area, and outputting an HVAC optimal control instruction; Step S40, executing a power redistribution task by adopting a multi-index weight feedback modulation mechanism based on the HVAC optimization control instruction, and outputting a device-level control vector sequence; step S50, generating a final HVAC control instruction by adopting a split-region mapping mode based on a distributed harmonic decoder based on the equipment-level control vector sequence.
2. The method for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model as set forth in claim 1, wherein in step S10, an original environment number vector of indoor environment of the green building group at time t is obtained Based on the original environmental data vector Building a digital twin simulation model by adopting a modeling mechanism based on building thermal inertia decoupling and equipment response nesting, and outputting a predicted environment data vector by the digital twin simulation model Specifically comprises the following steps: Step S101, obtaining an original environment number vector of indoor time data t of a green building group Original environmental data vector The method comprises a thermal parameter feature vector, a structural parameter feature vector, an HVAC architecture parameter feature vector and an environmental sensor feature vector; step S102, building thermal inertia block network model of ith block area in green building group room is built by adopting a heat transfer dynamic model modeling mode based on thermal parameter feature vector and structural parameter feature vector Building thermal inertia block network model The output of (2) is the temperature response function of the i-th block region at time t+1 Building thermal inertia block network model Is an HVAC control command; Step S103, constructing a sensing equipment response block network model of an ith block area in a green building group room by adopting a zonal linear weighted modeling mode based on the HVAC architecture parameter feature vector and the environment sensor feature vector, wherein the output of the sensing equipment response block network model is a carbon dioxide concentration response function of the ith block area at a time t+1 PM2.5 concentration response function And humidity response function The sensing equipment responds to the input of the block network model to be an HVAC control instruction; step S104, fusing temperature response function Carbon dioxide concentration response function PM2.5 concentration response function And humidity response function Constructing a digital twin simulation model, and outputting a predicted environment data vector by the digital twin simulation model 。
3. The method for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model as set forth in claim 2, wherein in step S102, the temperature response function is The formula of (c) is expressed as: Wherein, the method comprises the steps of, A temperature response function at time t for the i-th block region; area heat capacity of the i-th area; Inputting heat for the HVAC indicated in the HVAC control command for the i-th block region; The heat loss of the enclosure structure is realized; In time steps.
4. The method for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model according to claim 1, wherein in step S20, the method is based on a predicted environment data vector The weighted absolute value mapping mechanism driven based on the environment deviation measure is adopted to execute the multi-target cooperative benefit estimation task, and the multi-target demand control function is output Specifically comprises the following steps: step S201, based on the prediction environment data vector Construction of environmental bias vector ; Wherein, the method comprises the steps of, Is a temperature deviation vector; Is a humidity deviation vector; is a carbon dioxide deviation vector; is PM2.5 concentration deviation vector; step S202, acquiring a building use weight template, and setting temperature comfort preference weight based on the building use weight template Humidity comfort preference weighting Weight of air freshness And air cleanliness weights ; Step S203 of simultaneously acquiring and predicting environmental data vector Instantaneous power deviation of HVAC energy consumption corresponding to moment And set the energy consumption sensitivity weight Eventually based on HVAC energy consumption instantaneous power bias Environmental deviation vector Preference weighting for temperature comfort Humidity comfort preference weighting Weight of air freshness Weight of air cleanliness And energy consumption sensitivity weight Constructing a multi-objective demand control function , 。
5. The method for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model according to claim 4, wherein in step S20, ; ; ; ; A temperature reference value set for the target area based on the building use; a humidity reference value set for the target area based on the building use; A carbon dioxide concentration reference value set for the target area based on the building use; PM2.5 concentration reference value set for the target area based on the building use; a temperature response function at time t+1 of the target area; a humidity response function at time t+1 for the target area; a carbon dioxide concentration response function at time t+1 for the target region; is the PM2.5 concentration response function of the target region at time t+1.
6. The method for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model according to claim 4, wherein in step S30, the function is controlled based on multiple objective demands Executing an HVAC control strategy solving task by adopting an MPC model predictive control mechanism based on a mixed building group area, and outputting an HVAC optimal control instruction, wherein the method specifically comprises the following steps: Step 301, acquiring personnel behavior mode data and energy consumption historical data corresponding to an i-th block area in a green building group room, performing time sequence prediction by adopting a TCN-GRU mixed time sequence model according to the personnel behavior mode data and the energy consumption historical data, and outputting personnel behavior mode prediction data and energy consumption prediction data corresponding to a time t+1; Step S302, constructing target demand priority factors based on the mode prediction data and the energy consumption prediction data, and controlling functions for multiple target demands according to the target demand priority factors Weighting processing is carried out, and an optimized demand control function corresponding to the ith block area is output ; Step S303, performing linear weighting processing on the optimized demand control functions corresponding to all areas in the green building group room, and outputting a comprehensive demand control function ; Step S304, presetting a distributed energy consumption constraint condition, and controlling a function based on the distributed energy consumption constraint condition and the comprehensive demand And with HVAC energy consumption instantaneous power bias And (3) carrying out rolling time domain sliding window solving by adopting an MPC model predictive control algorithm for the control quantity, and outputting an HVAC (heating, ventilating and cooling) optimization control instruction.
7. The method for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model according to claim 1, wherein in step S40, a multi-index weight feedback modulation mechanism is adopted to perform a power redistribution task based on HVAC optimization control instructions, and the step of outputting a device-level control vector sequence specifically comprises: Step S401, after an HVAC optimization control instruction is applied, equipment actual state indexes are synchronously collected, wherein the equipment actual state indexes comprise supply power, return air temperature, indoor CO2 concentration, indoor humidity and equipment maximum rated power; Step S402, acquiring a desired feedback state vector group corresponding to the HVAC optimization control instruction Based on a set of desired feedback state vectors Constructing a deviation regulation and control objective function with the multi-index feedback state vector group S by adopting a nonlinear modulation mode based on multi-dimensional weighted distance measurement; And S403, constructing a final equipment-level control vector sequence by adopting a power response normalization adjustment mode based on the deviation regulation objective function.
8. A digital twin model-based collaborative optimization system for indoor environments and energy consumption of a green building group, which is applied to the method for collaborative optimization for indoor environments and energy consumption of a green building group based on a digital twin model as set forth in any one of claims 1 to 7, characterized in that the digital twin model-based collaborative optimization system for indoor environments and energy consumption of a green building group comprises: the environment modeling simulation module is used for acquiring an original environment number vector of indoor time data t of the green building group Based on the original environmental data vector Building a digital twin simulation model by adopting a modeling mechanism based on building thermal inertia decoupling and equipment response nesting, and outputting a predicted environment data vector by the digital twin simulation model ; A cooperative benefit estimation module for estimating a data vector based on the prediction environment The weighted absolute value mapping mechanism driven based on the environment deviation measure is adopted to execute the multi-target cooperative benefit estimation task, and the multi-target demand control function is output ; MPC strategy solving module for controlling functions based on multiple target demands Executing an HVAC control strategy solving task by adopting an MPC model predictive control mechanism based on a mixed building group area, and outputting an HVAC optimal control instruction; The power feedback modulation module is used for executing a power redistribution task by adopting a multi-index weight feedback modulation mechanism based on the HVAC optimization control instruction and outputting a device-level control vector sequence; The distributed control decoding module is used for generating a final HVAC control instruction by adopting a zoning mapping mode based on a distributed harmonic decoder based on the equipment-level control vector sequence.
9. The digital twin model-based green building group indoor environment and energy consumption collaborative optimization device is characterized by comprising a memory, a processor and a digital twin model-based green building group indoor environment and energy consumption collaborative optimization program which is stored on the memory and can run on the processor, wherein the digital twin model-based green building group indoor environment and energy consumption collaborative optimization program is executed by the processor to realize the digital twin model-based green building group indoor environment and energy consumption collaborative optimization method according to any one of claims 1 to 7.
10. A computer program product, characterized in that the computer program product comprises a digital twin model-based collaborative optimization procedure for the indoor environment of a green building group, which when executed by a processor implements a digital twin model-based collaborative optimization method for the indoor environment of a green building group, as claimed in any one of claims 1 to 7.

Description

Method and system for collaborative optimization of indoor environment and energy consumption of green building group based on digital twin model Technical Field The invention relates to the technical field of intelligent control of green building groups, in particular to a method and a system for collaborative optimization of indoor environment and energy consumption of a green building group based on a digital twin model. Background At present, building group environment regulation mainly depends on independent operation of intelligent building systems (such as BAS, BEMS and the like) at a single building level, and temperature, humidity, illumination, ventilation and the like are controlled through local sensor data and a rule base. Although the basic energy consumption control target can be realized under a single building or stable working condition, in a large green building group comprising a laboratory, a dormitory, an office building and other multi-type functional areas, the control targets of different areas on indoor environments have obvious differences and even conflict. For example, laboratories emphasize constant temperature and humidity and stable cleanliness, dormitory concerns comfort and noise control, and office areas focus on energy conservation, consumption reduction and automatic dimming. The cooperative control requirement of multiple targets, multiple areas and multiple working conditions ensures that the conventional system has the following defects in global optimization capability (1) the conventional building energy consumption management method mostly adopts local feedback control or static policy tables, and is difficult to cope with the cross-building influences such as dynamic energy utilization behaviors or thermal coupling between buildings, airflow interference and the like. (2) Because the number of users and the use mode are periodically fluctuated or suddenly changed in transient state with the external meteorological conditions, the traditional system usually only depends on the temperature and humidity overrun alarm to perform passive response, and the prediction and scheduling capability is lacking. (3) Physical coupling factors such as energy use, airflow circulation, illumination shielding and the like in the building group are not systematically modeled, so that excessive refrigeration and heating of partial areas are caused, and the energy consumption is seriously wasted. Therefore, a method for optimizing the indoor environment and the energy consumption of the green building group based on the digital twin model is needed, and the method can dynamically allocate central energy system resources, predict the influence of user behaviors on the environment and realize the minimization of the energy consumption while guaranteeing the personalized comfort constraint of an area, and fulfill the requirements of the energy consumption cooperation and the environment commonality constraint of the multifunctional building areas such as a laboratory, a dormitory, an office and the like, thereby realizing the unified improvement of the indoor environment control and the energy consumption optimization target of the green building group. Disclosure of Invention Aiming at the technical defects, the invention aims to provide a digital twin model-based collaborative optimization method for indoor environment and energy consumption of a green building group, and aims to solve the technical problems that in the prior art, the control strategy is single, the response dynamic characteristics of equipment are ignored, and especially under the collaborative control condition of the green building group, the global optimization control for energy consumption and environment cannot be realized. In order to solve the technical problems, the invention adopts the following technical scheme that the invention provides a digital twin model-based collaborative optimization method for indoor environment and energy consumption of a green building group. The method for optimizing the indoor environment and the energy consumption of the green building group based on the digital twin model comprises the following steps: Step S10, obtaining an original environment number vector of the indoor time data t of the green building group Based on the original environmental data vectorBuilding a digital twin simulation model by adopting a modeling mechanism based on building thermal inertia decoupling and equipment response nesting, and outputting a predicted environment data vector by the digital twin simulation model; Step S20, based on the prediction environment data vectorThe weighted absolute value mapping mechanism driven based on the environment deviation measure is adopted to execute the multi-target cooperative benefit estimation task, and the multi-target demand control function is output; Step S30, controlling the function based on the multi-objective demandExecuting an HVAC control strategy