Building energy consumption optimization method and system based on multi-objective optimization

Abstract

The application discloses a kind of building energy consumption optimization method and system based on multi-objective optimization, and the method comprises the following steps: collecting the environmental data of building in real time;According to environmental data, dynamically calculate environmental comprehensive influence factor, and correct current energy consumption control threshold based on the comprehensive influence factor;With energy consumption, thermal comfort and equipment operation cost as optimization target, the corrected energy consumption control threshold is used as dynamic boundary constraint, and a multi-objective energy consumption optimization model containing building envelope thermal inertia constraint and equipment boundary constraint is constructed;Solve the model and output the non-dominated control parameter solution set;Finally, based on the preference weight, dynamically screen target control strategy from the solution set and issue in real time.The application eliminates the lagging adjustment defects of traditional static threshold, has strong external disturbance feedforward adaptive defense capability, realizes the heat flow management of building energy consumption, and reduces the operation cost while ensuring thermal comfort.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and more specifically, to a building energy consumption optimization method and system based on multi-objective optimization. Background Technology

[0002] With the increasing demand for refined building energy conservation, traditional building energy consumption control methods are no longer able to meet the dynamic balance between low-carbon operation and human living comfort in modern smart buildings. Existing technologies usually rely on fixed energy consumption control thresholds or static timetables based on historical data to regulate high-efficiency equipment such as HVAC.

[0003] However, these methods have revealed three significant and critical flaws in practical applications:

[0004] 1. Poor adjustment lag and timeliness: Traditional building energy consumption control schemes cannot detect the instantaneous and drastic fluctuations in the outdoor weather environment. They are often only passively triggered to adjust after the indoor thermal environment has deteriorated or energy consumption has surged, resulting in a serious lag in the adjustment process.

[0005] 2. Multi-objective optimization is not possible. Existing single-objective or simple weighted control algorithms cannot find the optimal solution among reducing building energy consumption, ensuring human thermal comfort, and controlling equipment operating costs. This often results in energy saving at the expense of significant comfort or over-operation during peak electricity price periods.

[0006] 3. Lack of physical thermal inertia boundary: Traditional control models simplify the building envelope as a quasi-static process, ignoring the dynamic time delay effect and thermal saturation physical limitations of the envelope structure such as walls and glass. When the heat storage saturation of the envelope structure fails, the model cannot correct the allowable energy consumption boundary in time, which can easily lead to equipment overload operation. Summary of the Invention

[0007] The purpose of this invention is to provide a building energy consumption optimization method and system based on multi-objective optimization, which can solve the problems of excessive energy consumption and deterioration of comfort caused by the use of static thresholds leading to adjustment lag, inability to take into account multi-objective dynamic collaborative optimization, and lack of thermal inertia constraints of building envelope in the prior art.

[0008] The first aspect of this invention provides a building energy consumption optimization method based on multi-objective optimization, comprising the following steps:

[0009] Collect environmental data about the building;

[0010] The comprehensive environmental impact factor is dynamically calculated based on the environmental data, and the current energy consumption control threshold is corrected based on the comprehensive environmental impact factor.

[0011] A multi-objective energy consumption optimization model is constructed based on a preset optimization objective, wherein the energy consumption control threshold serves as the dynamic boundary constraint of the multi-objective energy consumption optimization model;

[0012] Solve the multi-objective energy consumption optimization model with the aforementioned dynamic boundary constraints to output a set of mutually independent control parameters;

[0013] Based on preference weights, target control strategies are dynamically selected from the solution set of control parameters, and control commands generated based on the target control strategies are sent to the preset control system.

[0014] In this scheme, the dynamic calculation of the comprehensive environmental impact factor based on the environmental data specifically includes:

[0015] The comprehensive environmental impact factor is calculated based on a multivariate meteorological property coupling formula, as follows:

[0016] ;

[0017] in, The aforementioned comprehensive environmental impact factors, This is the real-time outdoor temperature at the current sampling time. The baseline temperature set for the indoor environment. The comprehensive equivalent thermal resistance constant of the building's external structural walls. This represents the total solar radiation intensity at the current sampling time. The effective lighting area of ​​the glass on the sun-facing side of the building. The solar thermal gain coefficient of the glass material. The outdoor relative humidity at the current sampling time. The indoor relative humidity at the current sampling time. The air enthalpy-humidity convective heat transfer adjustment coefficient. , and These are the adaptive decoupling coefficients.

[0018] In this scheme, the step of correcting the current energy consumption control threshold based on the comprehensive environmental impact factor specifically includes:

[0019] The outdoor temperature change rate in the environmental data is monitored. When the outdoor temperature change rate is greater than the preset change rate threshold, a dynamic condition update is triggered, and the preset first-level environmental threshold is dynamically corrected down to the target environmental threshold.

[0020] The comprehensive environmental impact factor is compared with the target environmental threshold.

[0021] When the comprehensive environmental impact factor does not exceed the target environmental threshold, the current energy consumption control threshold remains unchanged;

[0022] When the comprehensive environmental impact factor exceeds the target environmental threshold, a secondary dynamic condition judgment is triggered to obtain the current load rate of the control system and to perform a nested comparison with a preset tiered power consumption threshold.

[0023] If the current load rate is lower than the stepped power consumption threshold, then the current energy consumption control threshold remains unchanged;

[0024] If the current load rate is higher than or equal to the stepped power consumption threshold, the energy consumption control threshold is reduced according to a preset step value.

[0025] In this scheme, the construction of a multi-objective energy consumption optimization model based on a preset optimization objective specifically includes:

[0026] With energy consumption, thermal comfort, and equipment operating costs as optimization objectives, a multi-objective energy consumption optimization model is constructed, incorporating thermal inertia constraints of the building envelope and equipment boundary constraints.

[0027] The building envelope is abstracted into a pre-defined dynamic thermal response network model, and the dynamic time delay effect of the envelope is calculated, transforming the instantaneous outdoor thermal disturbance into a dynamic delayed load term indoors.

[0028] The actual cumulative heat storage of the internal cross section of the enclosure structure is obtained, and the actual cumulative heat storage is compared with the preset physical heat saturation critical value;

[0029] When the actual accumulated heat storage reaches or exceeds the physical heat saturation critical value, the physical boundary failure condition is triggered, and a correction penalty coefficient is introduced into the dynamic delayed load term to compress the allowable energy consumption boundary of the multi-objective energy consumption optimization model.

[0030] In this scheme, solving the multi-objective energy consumption optimization model with the dynamic boundary constraints specifically includes:

[0031] A multi-objective optimization population with dynamic boundary constraints is initialized, and the composite constraint consisting of the energy consumption control threshold and the allowable energy consumption boundary after introducing the correction penalty coefficient is used as the feasibility search space limit for individual populations.

[0032] The multi-objective energy consumption optimization model is iteratively solved using a pre-defined non-dominated sorting genetic algorithm, wherein...

[0033] During each iteration, the changes in the dynamic boundary constraints are monitored. If the constraint boundary shrinks or expands, the fitness function value of the current generation individual is dynamically adjusted through an adaptive penalty function to eliminate invalid solutions that violate the dynamic boundary.

[0034] After the preset iteration termination condition is met, the final evolved population is divided into non-dominated hierarchical levels and crowding distance is calculated, and the solution set of control parameters that are not dominated is output.

[0035] In this scheme, the step of dynamically selecting a target control strategy from the control parameter solution set based on preference weights and issuing control commands generated based on the target control strategy to a preset control system specifically includes:

[0036] Obtain the building's current operating mode label, which includes energy-saving priority mode, comfort priority mode, and economical operating mode;

[0037] Based on the operating mode label, initial preference weights corresponding to energy consumption, thermal comfort, and equipment operating costs are matched from a preset weight matrix, and the initial preference weights are corrected in real time in conjunction with the current electricity price period signal to obtain the final target preference weights.

[0038] Using a multi-attribute decision-making algorithm, combined with the target preference weights, a comprehensive utility score is given to each solution in the control parameter solution set, and the solution with the highest score is determined as the target control strategy.

[0039] Based on the target control strategy, physical control commands are generated and sent to each execution terminal in the preset control system to optimize and adjust building energy consumption.

[0040] A second aspect of the present invention also provides a building energy consumption optimization system based on multi-objective optimization, comprising a memory and a processor. The memory includes a building energy consumption optimization method program based on multi-objective optimization, which, when executed by the processor, performs the following steps:

[0041] Collect environmental data about the building;

[0042] The comprehensive environmental impact factor is dynamically calculated based on the environmental data, and the current energy consumption control threshold is corrected based on the comprehensive environmental impact factor.

[0043] A multi-objective energy consumption optimization model is constructed based on a preset optimization objective, wherein the energy consumption control threshold serves as the dynamic boundary constraint of the multi-objective energy consumption optimization model;

[0044] Solve the multi-objective energy consumption optimization model with the aforementioned dynamic boundary constraints to output a set of mutually independent control parameters;

[0045] Based on preference weights, target control strategies are dynamically selected from the solution set of control parameters, and control commands generated based on the target control strategies are sent to the preset control system.

[0046] A third aspect of the present invention provides a computer-readable storage medium comprising a machine program for a multi-objective optimization-based building energy consumption optimization method, wherein when executed by a processor, the multi-objective optimization-based building energy consumption optimization method program implements the steps of the multi-objective optimization-based building energy consumption optimization method as described in any of the preceding claims.

[0047] The fourth aspect of the present invention provides a computer program product, the computer program product including computer program code, which, when run on a computer, causes the computer to implement the steps of a building energy consumption optimization method based on multi-objective optimization as described in any of the preceding claims.

[0048] The fifth aspect of the present invention provides an electronic device, the electronic device comprising: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the steps of a building energy consumption optimization method based on multi-objective optimization as described in any of the preceding claims.

[0049] The present invention discloses a building energy consumption optimization method and system based on multi-objective optimization, which has the following beneficial effects:

[0050] 1. It has active feedforward adjustment capability. Traditional control usually adjusts passively only after the indoor environment deteriorates, which has obvious lag. This invention senses the drastic fluctuations in outdoor weather through feedforward and can dynamically and stepwise correct the energy consumption control threshold before external interference damages the indoor environment, thus realizing the function of active adjustment.

[0051] 2. This invention changes the previous situation of single-objective control which was unbalanced. Specifically, it uses a multi-objective optimization algorithm to calculate a set of solutions that do not dominate each other, and combines time-of-use electricity price signals to correct operating preferences in real time. This ensures that the system can adaptively avoid peak electricity prices while ensuring the best thermal comfort for the human body, thus significantly reducing operating costs.

[0052] 3. To further ensure the safe operation of the equipment, this invention fully considers the physical thermal inertia of building walls, glass and other enclosure structures. By monitoring the actual cumulative heat storage of the walls in real time, the allowable energy consumption boundary is forcibly compressed when the heat storage reaches the physical critical value of saturation, which effectively prevents the equipment from overloaded operation caused by blind adjustment. Attached Figure Description

[0053] Figure 1 This diagram illustrates the steps of a building energy consumption optimization method based on multi-objective optimization according to the present invention.

[0054] Figure 2A flowchart illustrating the generation of control instructions for a building energy consumption optimization method based on multi-objective optimization according to the present invention is shown.

[0055] Figure 3 A block diagram of a building energy consumption optimization system based on multi-objective optimization according to the present invention is shown. Detailed Implementation

[0056] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments of the present invention and the features thereof can be combined with each other.

[0057] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0058] Specifically, Figure 1 The diagram illustrates the steps of a building energy consumption optimization method based on multi-objective optimization according to the present invention.

[0059] like Figure 1 As shown, this invention discloses a building energy consumption optimization method based on multi-objective optimization, comprising the following steps:

[0060] S102, Collect environmental data of the building;

[0061] S104, dynamically calculate the comprehensive environmental impact factor based on the environmental data, and correct the current energy consumption control threshold based on the comprehensive environmental impact factor;

[0062] S106, Construct a multi-objective energy consumption optimization model based on a preset optimization objective, wherein the energy consumption control threshold serves as the dynamic boundary constraint of the multi-objective energy consumption optimization model;

[0063] S108, Solve the multi-objective energy consumption optimization model with the dynamic boundary constraints to output a set of control parameters that are not mutually dominant;

[0064] S110, dynamically select target control strategies from the control parameter solution set based on preference weights, and send control commands generated based on the target control strategies to the preset control system.

[0065] It should be noted that, in this embodiment, the technical point of the present invention lies in using environmental impact factors coupled with multiple meteorological properties as dynamic boundary constraints, and combining the thermal inertia penalty mechanism of the building envelope with real-time operation mode labels to adaptively decouple and iteratively solve the multi-objective energy consumption model. Furthermore, the present invention is specifically applied to fields such as intelligent building energy management, and refined energy-saving control of central air conditioning and heating systems in smart parks. In these scenarios, the present invention can achieve the following beneficial effects: through the original environmental factor property coupling formula and the thermal saturation penalty mechanism of the building envelope, the accurate mapping of meteorological disturbances to indoor loads and the physical elimination of thermal inertia dead zones are realized; at the same time, combined with the adaptive penalty function and electricity price correction weight, the control strategy is driven to achieve a second-level dynamic balance between energy saving, comfort and economy, significantly reducing the overall energy consumption of buildings and greatly improving the flexible interactive response capability of the power grid.

[0066] Specifically, in this embodiment, the environmental data collected for the building includes at least four core dimensions: outdoor macro-meteorology, indoor comfort perception, building physical state, and external power grid market signals. Among them, the outdoor macro-meteorology dimension mainly collects real-time outdoor temperature, total solar radiation intensity, and outdoor relative humidity to accurately capture the instantaneous thermal disturbance sources of the external environment on the building; the indoor comfort perception dimension monitors indoor temperature and humidity in real time, sets a baseline temperature, and air quality indicators as core constraints for evaluating thermal comfort and feedback control; the building physical state dimension focuses on the surface temperature of the inner and outer surfaces of the exterior walls and the cumulative heat storage of the internal cross-sections to quantitatively calculate the thermal inertia and dynamic time delay effects of the building envelope; and the external power grid market signal dimension dynamically acquires time-of-use electricity prices, peak electricity prices, and the current load rate and operating mode label of the system to adjust the preference weights of multi-objective optimization in real time.

[0067] According to an embodiment of the present invention, the step of dynamically calculating the comprehensive environmental impact factor based on the environmental data specifically includes:

[0068] The comprehensive environmental impact factor is calculated based on a multivariate meteorological property coupling formula, as follows:

[0069] ;

[0070] in, The aforementioned comprehensive environmental impact factors, This is the real-time outdoor temperature at the current sampling time. The baseline temperature set for the indoor environment. The comprehensive equivalent thermal resistance constant of the building's external structural walls. This represents the total solar radiation intensity at the current sampling time. The effective lighting area of ​​the glass on the sun-facing side of the building. The solar thermal gain coefficient of the glass material. The outdoor relative humidity at the current sampling time. The indoor relative humidity at the current sampling time. The air enthalpy-humidity convective heat transfer adjustment coefficient. , and These are the adaptive decoupling coefficients.

[0071] It should be noted that, in this embodiment, by introducing a multi-dimensional meteorological property coupling formula, outdoor temperature and humidity, indoor baseline, solar radiation, and the physical characteristics of the building itself (equivalent thermal resistance of the exterior walls, glass daylighting and heat gain coefficient) are creatively integrated into a single indicator, the comprehensive environmental impact factor. This indicator breaks through the limitations of traditional energy control based solely on outdoor temperature, and essentially reveals the joint mechanism of the multi-dimensional environmental energy input on indoor thermal balance. By using an adaptive decoupling coefficient, the dimensional influence and coupling interference between different physical quantities are dynamically eliminated, enabling the comprehensive environmental impact factor to accurately and quantitatively reflect the actual heat load impact of the building's external environment.

[0072] Specifically, in this embodiment, the current outdoor temperature is collected in real time through a sensor network. Total solar radiation intensity Outdoor relative humidity and indoor relative humidity This real-time data, along with inherent building parameters (equivalent thermal resistance of the walls), Effective lighting area Heat gain coefficient of glass Substituting (etc.) into the coupling formula together, the adaptive decoupling coefficients... , and It will automatically adjust according to the current season and climate type, and finally quickly calculate the scalar value of the comprehensive environmental impact factor, providing a highly sensitive dynamic benchmark input for subsequent energy consumption control threshold correction.

[0073] According to an embodiment of the present invention, the step of correcting the current energy consumption control threshold based on the comprehensive environmental impact factor specifically includes:

[0074] The outdoor temperature change rate in the environmental data is monitored. When the outdoor temperature change rate is greater than the preset change rate threshold, a dynamic condition update is triggered, and the preset first-level environmental threshold is dynamically corrected down to the target environmental threshold.

[0075] The comprehensive environmental impact factor is compared with the target environmental threshold.

[0076] When the comprehensive environmental impact factor does not exceed the target environmental threshold, the current energy consumption control threshold remains unchanged;

[0077] When the comprehensive environmental impact factor exceeds the target environmental threshold, a secondary dynamic condition judgment is triggered to obtain the current load rate of the control system and to perform a nested comparison with a preset tiered power consumption threshold.

[0078] If the current load rate is lower than the stepped power consumption threshold, then the current energy consumption control threshold remains unchanged;

[0079] If the current load rate is higher than or equal to the stepped power consumption threshold, the energy consumption control threshold is reduced according to a preset step value.

[0080] It should be noted that, in this embodiment, a two-level dynamic threshold correction mechanism based on meteorological change rate triggering and nested load rate comparison is specifically constructed. The innovation lies in abandoning the rigid control of traditional fixed energy consumption thresholds and introducing outdoor temperature change rate as a feedforward early warning indicator. Specifically, when the external environment deteriorates drastically, the control sensitivity is improved by pre-adjusting the target environmental threshold. In the secondary judgment, the external impact of environmental factors is compared with the current load rate inside the control system in a stepped power consumption nested comparison. Through this dual logic, it is ensured that the step-by-step threshold compression is only initiated when the external environmental load is high and the device's own power consumption is high, thus avoiding equipment oscillation caused by frequent adjustments.

[0081] Specifically, in this embodiment, in actual operation, the outdoor temperature difference between adjacent sampling periods is continuously calculated. Once the rate of change is found to exceed the preset threshold, the first-level environmental threshold is immediately lowered. Then, the currently calculated comprehensive environmental impact factor is compared with the target environmental threshold. If it does not exceed the standard, the original state is maintained; if it exceeds the standard, the current real-time load rate of the control system (e.g., central air conditioning or heating system) is retrieved and compared with the tiered power consumption threshold. If it is found that the system is already operating in the high load area (i.e., higher than or equal to the power consumption threshold), the step command will be automatically executed to tighten the energy consumption control threshold according to the preset incremental step value (e.g., 5% reduction each time), forcibly raising the energy consumption red line.

[0082] According to an embodiment of the present invention, the construction of a multi-objective energy consumption optimization model based on a preset optimization objective specifically includes:

[0083] With energy consumption, thermal comfort, and equipment operating costs as optimization objectives, a multi-objective energy consumption optimization model is constructed, incorporating thermal inertia constraints of the building envelope and equipment boundary constraints.

[0084] The building envelope is abstracted into a pre-defined dynamic thermal response network model, and the dynamic time delay effect of the envelope is calculated, transforming the instantaneous outdoor thermal disturbance into a dynamic delayed load term indoors.

[0085] The actual cumulative heat storage of the internal cross section of the enclosure structure is obtained, and the actual cumulative heat storage is compared with the preset physical heat saturation critical value;

[0086] When the actual accumulated heat storage reaches or exceeds the physical heat saturation critical value, the physical boundary failure condition is triggered, and a correction penalty coefficient is introduced into the dynamic delayed load term to compress the allowable energy consumption boundary of the multi-objective energy consumption optimization model.

[0087] It should be noted that in this embodiment, the building envelope is abstracted as a dynamic thermal response network model. Its innovation lies in the introduction of a physical thermal saturation critical value and a correction penalty coefficient. Traditional models often ignore the limit of heat storage in walls. This invention accurately captures the evolution law of outdoor instantaneous thermal disturbances transforming into indoor delayed loads by calculating the dynamic time delay effect of the building envelope. When the actual cumulative heat storage of the internal cross-section of the wall reaches physical saturation, it means that the wall has lost its buffering capacity to continue to block or absorb heat (i.e., physical boundary failure). At this time, the correction penalty coefficient is introduced to actively shrink the allowable energy consumption boundary of the model, thus preventing the risk of energy consumption exceeding the limit from the physical mechanism level.

[0088] Specifically, in this embodiment, a multi-objective optimization algorithm is run, with total energy consumption, thermal comfort index and equipment operating cost as the joint optimization objective function. The instantaneously changing outdoor thermal disturbance is transformed into an indoor load term with a time delay. At the same time, the cumulative heat storage of the internal cross section of the building envelope is estimated in real time through sensors or state observers embedded in the wall. Once this value exceeds the physical thermal saturation critical value, the boundary failure procedure is immediately triggered, and the penalty coefficient is multiplied by the dynamic delay load term, thereby automatically tightening the solution space boundary of the multi-objective model and preventing the model from giving an invalid solution that exceeds the energy control limit.

[0089] According to an embodiment of the present invention, solving the multi-objective energy consumption optimization model with the dynamic boundary constraints specifically includes:

[0090] A multi-objective optimization population with dynamic boundary constraints is initialized, and the composite constraint consisting of the energy consumption control threshold and the allowable energy consumption boundary after introducing the correction penalty coefficient is used as the feasibility search space limit for individual populations.

[0091] The multi-objective energy consumption optimization model is iteratively solved using a pre-defined non-dominated sorting genetic algorithm, wherein...

[0092] During each iteration, the changes in the dynamic boundary constraints are monitored. If the constraint boundary shrinks or expands, the fitness function value of the current generation individual is dynamically adjusted through an adaptive penalty function to eliminate invalid solutions that violate the dynamic boundary.

[0093] After the preset iteration termination condition is met, the final evolved population is divided into non-dominated hierarchical levels and crowding distance is calculated, and the solution set of control parameters that are not dominated is output.

[0094] It should be noted that the inventive aspect of this embodiment lies in combining the dynamic energy consumption control threshold with the allowable energy consumption boundary after thermal inertia correction into a composite constraint condition, and directly mapping it to the feasibility search space constraint of the genetic algorithm population. Specifically, considering the characteristic that the dynamic boundary may shrink or expand at any time due to weather and heat storage conditions, this invention creatively adopts an adaptive penalty function technique. In each iteration of evolution, the adaptive penalty function dynamically adjusts the fitness function value of the current generation individuals according to the real-time displacement of the boundary, assigning extremely low fitness to those individuals that cross the boundary due to boundary shrinkage, thereby gently and accurately eliminating invalid solutions during the evolution process, ensuring that the final output Pareto solution set fully satisfies the real-time dual constraints of physics and environment.

[0095] Specifically, in this embodiment, in practical application, a multi-objective optimization population containing several individuals with control parameters is initialized. An improved NSGA-II (non-dominated sorting genetic algorithm) is used for multiple generations of iteration. During each generation of evolution, the algorithm monitors the boundary position of the composite constraint in real time. If boundary shrinkage is detected, the adaptive penalty function module immediately calculates the distance between the individual and the new boundary and deducts the fitness score of the violating individual. After hundreds of generations of iteration until the termination error is met, the algorithm performs non-dominated hierarchical division and crowding distance calculation on the final population, eliminates inferior solutions, and finally outputs a set of control parameter solutions that are non-dominated, evenly distributed, and satisfy the dynamic boundary to the policy layer.

[0096] According to embodiments of the present invention, such as Figure 2 The diagram shows a flowchart for generating control commands. Specifically, the step of dynamically selecting a target control strategy from the control parameter solution set based on preference weights and issuing control commands generated based on the target control strategy to a preset control system includes:

[0097] Obtain the building's current operating mode label, which includes energy-saving priority mode, comfort priority mode, and economical operating mode;

[0098] Based on the operating mode label, initial preference weights corresponding to energy consumption, thermal comfort, and equipment operating costs are matched from a preset weight matrix.

[0099] The initial preference weights are adjusted in real time based on the current electricity price time signal to obtain the final target preference weights;

[0100] Using a multi-attribute decision-making algorithm, combined with the target preference weights, a comprehensive utility score is given to each solution in the control parameter solution set, and the solution with the highest score is determined as the target control strategy.

[0101] Based on the target control strategy, physical control commands are generated and sent to each execution terminal in the preset control system to optimize and adjust building energy consumption.

[0102] It should be noted that, in this embodiment, a multi-level intelligent decision-making mechanism is specifically constructed, including an intelligent decision-making mechanism with operation tag guidance, real-time correction of electricity price periods, and multi-attribute decision scoring. Compared with traditional technologies, this embodiment no longer uses unchanging weights to select control strategies. Instead, it uses the macro-operation mode tags of the building complex (energy saving, comfort, economy) as the basis and introduces external market signals such as time-of-use electricity prices and peak electricity prices as dynamic correction factors. This achieves flexible interaction between control strategies and the electricity market. By using a multi-attribute decision-making algorithm to score the utility of the solution set, it can perfectly take into account the multi-dimensional interests and thus accurately select the optimal target control strategy under the current spatiotemporal conditions.

[0103] Specifically, in this embodiment, during execution, the current building's operating mode label is first obtained. For example, late night is identified as the economic operating mode, and daytime is identified as the comfort-first mode. Initial weights (energy consumption, thermal comfort, and cost) are extracted from the built-in weight matrix. At this time, the time-of-use electricity price signal issued by the power grid is obtained. If the current period is a peak period of high electricity price, the cost weight is increased and the comfort weight is reduced in real time to obtain the target preference weight. Subsequently, a multi-attribute decision algorithm (such as the TOPSIS method) combines the weight to comprehensively score the Pareto solution set, selects the control parameter solution with the highest score, and finally converts it into physical control commands such as frequency and valve opening. These commands are dynamically sent to the field control system via, for example, a Modbus bus. Correspondingly, the control system includes various execution terminals such as air conditioners, fans, and water pumps.

[0104] Figure 3 A block diagram of a building energy consumption optimization system based on multi-objective optimization according to the present invention is shown.

[0105] like Figure 3 As shown, this invention discloses a building energy consumption optimization system based on multi-objective optimization, including a memory and a processor. The memory includes a building energy consumption optimization method program based on multi-objective optimization. When the processor executes the building energy consumption optimization method program based on multi-objective optimization, it performs the following steps:

[0106] Collect environmental data about the building;

[0107] The comprehensive environmental impact factor is dynamically calculated based on the environmental data, and the current energy consumption control threshold is corrected based on the comprehensive environmental impact factor.

[0108] A multi-objective energy consumption optimization model is constructed based on a preset optimization objective, wherein the energy consumption control threshold serves as the dynamic boundary constraint of the multi-objective energy consumption optimization model;

[0109] Solve the multi-objective energy consumption optimization model with the aforementioned dynamic boundary constraints to output a set of mutually independent control parameters;

[0110] Based on preference weights, target control strategies are dynamically selected from the solution set of control parameters, and control commands generated based on the target control strategies are sent to the preset control system.

[0111] It should be noted that when the building energy consumption optimization system based on multi-objective optimization disclosed in this invention is applied, the specific process corresponds to the building energy consumption optimization method based on multi-objective optimization described in the above embodiments. Since the specific implementation details of the system application are consistent with the content of the above-mentioned building energy consumption optimization method based on multi-objective optimization, no further details will be provided in this embodiment.

[0112] A third aspect of the present invention provides a computer-readable storage medium comprising a building energy consumption optimization method program based on multi-objective optimization, wherein when the building energy consumption optimization method program based on multi-objective optimization is executed by a processor, it implements the steps of the building energy consumption optimization method based on multi-objective optimization as described in any of the preceding claims.

[0113] The fourth aspect of the present invention provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to execute any of the methods described in the embodiments of the building energy consumption optimization method based on multi-objective optimization.

[0114] The fifth aspect of the present invention provides an electronic device, the electronic device comprising: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the steps of a building energy consumption optimization method based on multi-objective optimization as described in any of the preceding claims.

[0115] The terms “component,” “module,” “system,” etc., used in this specification are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0116] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0117] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0118] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0121] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0122] This invention discloses a building energy consumption optimization method and system based on multi-objective optimization. Through an original environmental factor property coupling formula, it achieves accurate mapping between meteorological disturbances and indoor loads. It also introduces a physical heat saturation correction penalty for the building envelope, which effectively prevents the dead zone of the energy consumption boundary caused by insufficient thermal inertia estimation in traditional control. At the same time, by eliminating iterative invalid solutions through an adaptive penalty function and combining it with the preference weight of electricity price time period correction, a dynamic balance is achieved between energy saving, comfort and economy, which significantly reduces the overall building energy consumption.

[0123] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A building energy consumption optimization method based on multi-objective optimization, characterized in that, Includes the following steps: Collect environmental data about the building; The comprehensive environmental impact factor is dynamically calculated based on the environmental data, and the current energy consumption control threshold is corrected based on the comprehensive environmental impact factor. A multi-objective energy consumption optimization model is constructed based on a preset optimization objective, wherein the energy consumption control threshold serves as the dynamic boundary constraint of the multi-objective energy consumption optimization model; Solve the multi-objective energy consumption optimization model with the aforementioned dynamic boundary constraints to output a set of mutually independent control parameters; Based on preference weights, target control strategies are dynamically selected from the solution set of control parameters, and control commands generated based on the target control strategies are sent to the preset control system.

2. The building energy consumption optimization method based on multi-objective optimization according to claim 1, characterized in that, The dynamic calculation of the comprehensive environmental impact factor based on the environmental data specifically includes: The comprehensive environmental impact factor is calculated based on a multivariate meteorological property coupling formula, as follows: ； in, The aforementioned comprehensive environmental impact factors, This represents the real-time outdoor temperature at the current sampling time. The baseline temperature set for the indoor environment. The comprehensive equivalent thermal resistance constant of the building's external structural walls. This represents the total solar radiation intensity at the current sampling time. The effective lighting area of ​​the glass on the sun-facing side of the building. The solar thermal gain coefficient of the glass material. The outdoor relative humidity at the current sampling time. The indoor relative humidity at the current sampling time. The air enthalpy-humidity convective heat transfer adjustment coefficient. , and These are the adaptive decoupling coefficients.

3. The building energy consumption optimization method based on multi-objective optimization according to claim 1, characterized in that, The process of correcting the current energy consumption control threshold based on the comprehensive environmental impact factors specifically includes: The outdoor temperature change rate in the environmental data is monitored. When the outdoor temperature change rate is greater than the preset change rate threshold, a dynamic condition update is triggered, and the preset first-level environmental threshold is dynamically corrected down to the target environmental threshold. The comprehensive environmental impact factor is compared with the target environmental threshold. When the comprehensive environmental impact factor does not exceed the target environmental threshold, the current energy consumption control threshold remains unchanged; When the comprehensive environmental impact factor exceeds the target environmental threshold, a secondary dynamic condition judgment is triggered to obtain the current load rate of the control system and to perform a nested comparison with a preset tiered power consumption threshold. If the current load rate is lower than the stepped power consumption threshold, then the current energy consumption control threshold remains unchanged; If the current load rate is higher than or equal to the stepped power consumption threshold, the energy consumption control threshold is reduced according to a preset step value.

4. The building energy consumption optimization method based on multi-objective optimization according to claim 1, characterized in that, The construction of a multi-objective energy consumption optimization model based on preset optimization objectives specifically includes: With energy consumption, thermal comfort, and equipment operating costs as optimization objectives, a multi-objective energy consumption optimization model is constructed, incorporating thermal inertia constraints of the building envelope and equipment boundary constraints. The building envelope is abstracted into a pre-defined dynamic thermal response network model, and the dynamic time delay effect of the envelope is calculated, transforming the instantaneous outdoor thermal disturbance into a dynamic delayed load term indoors. The actual cumulative heat storage of the internal cross section of the enclosure structure is obtained, and the actual cumulative heat storage is compared with the preset physical heat saturation critical value; When the actual accumulated heat storage reaches or exceeds the physical heat saturation critical value, the physical boundary failure condition is triggered, and a correction penalty coefficient is introduced into the dynamic delayed load term to compress the allowable energy consumption boundary of the multi-objective energy consumption optimization model.

5. The building energy consumption optimization method based on multi-objective optimization according to claim 4, characterized in that, The solution of the multi-objective energy consumption optimization model with the aforementioned dynamic boundary constraints specifically includes: A multi-objective optimization population with dynamic boundary constraints is initialized, and the composite constraint consisting of the energy consumption control threshold and the allowable energy consumption boundary after introducing the correction penalty coefficient is used as the feasibility search space limit for individual populations. The multi-objective energy consumption optimization model is iteratively solved using a pre-defined non-dominated sorting genetic algorithm, wherein... During each iteration, the changes in the dynamic boundary constraints are monitored. If the constraint boundary shrinks or expands, the fitness function value of the current generation individual is dynamically adjusted through an adaptive penalty function to eliminate invalid solutions that violate the dynamic boundary. After the preset iteration termination condition is met, the final evolved population is divided into non-dominated hierarchical levels and crowding distance is calculated, and the solution set of control parameters that are not dominated is output.

6. The building energy consumption optimization method based on multi-objective optimization according to claim 5, characterized in that, The step of dynamically selecting a target control strategy from the control parameter solution set based on preference weights and issuing control commands generated based on the target control strategy to the preset control system specifically includes: Obtain the building's current operating mode label, which includes energy-saving priority mode, comfort priority mode, and economical operating mode; Based on the operating mode label, initial preference weights corresponding to energy consumption, thermal comfort, and equipment operating costs are matched from a preset weight matrix, and the initial preference weights are corrected in real time in conjunction with the current electricity price period signal to obtain the final target preference weights. Using a multi-attribute decision-making algorithm, combined with the target preference weights, a comprehensive utility score is given to each solution in the control parameter solution set, and the solution with the highest score is determined as the target control strategy. Based on the target control strategy, physical control commands are generated and sent to each execution terminal in the preset control system to optimize and adjust building energy consumption.

7. A building energy consumption optimization system based on multi-objective optimization, characterized in that, The system includes a memory and a processor. The memory contains a program for a building energy consumption optimization method based on multi-objective optimization. When executed by the processor, the program for the building energy consumption optimization method based on multi-objective optimization performs the following steps: Collect environmental data about the building; The comprehensive environmental impact factor is dynamically calculated based on the environmental data, and the current energy consumption control threshold is corrected based on the comprehensive environmental impact factor. A multi-objective energy consumption optimization model is constructed based on a preset optimization objective, wherein the energy consumption control threshold serves as the dynamic boundary constraint of the multi-objective energy consumption optimization model; Solve the multi-objective energy consumption optimization model with the aforementioned dynamic boundary constraints to output a set of mutually independent control parameters; Based on preference weights, target control strategies are dynamically selected from the solution set of control parameters, and control commands generated based on the target control strategies are sent to the preset control system.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a building energy consumption optimization method program based on multi-objective optimization, which, when executed by a processor, implements the steps of a building energy consumption optimization method based on multi-objective optimization as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes computer program code, which, when run on a computer, causes the computer to implement the steps of a building energy consumption optimization method based on multi-objective optimization as described in any one of claims 1 to 6.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to cause the electronic device to perform the steps of a building energy consumption optimization method based on multi-objective optimization as described in any one of claims 1 to 6.

Images