Intelligent scheduling method and system for electricity utilization of intelligent building

Abstract

The invention discloses an intelligent scheduling method and system for power utilization of an intelligent building, and relates to the technical field of power utilization scheduling, and the main points of the technical scheme comprise the following steps: collecting a power utilization loss value of a target intelligent building under a standard working condition to obtain a first power utilization loss value; acquiring historical power consumption loss, historical environment characteristics and historical power consumption load of the intelligent building, and if the historical environment characteristics of different function partitions are dynamic change conditions, extracting a correlation coefficient between the dynamic change of the environment and the historical power consumption loss to obtain a first correlation influence coefficient; if the historical environment characteristics of different function partitions are static stable conditions, extracting a correlation coefficient between function partition conversion and historical power consumption loss to obtain a second correlation influence coefficient; extracting a correlation coefficient between historical power consumption load conversion and historical power consumption loss to obtain a third correlation influence coefficient; the method has the effects of realizing reasonable resource allocation, reducing the overall power utilization cost and improving the power utilization efficiency of the building.

Description

Technical Field

[0001] This invention relates to the field of power dispatching technology, and more specifically, to a smart building power dispatching method and system. Background Technology

[0002] With the diversification of functions in smart buildings, office, commercial, and leisure functional zones coexist. These zones exhibit significant differences in environmental characteristics, and frequent dynamic changes in the environment and functional zone transitions lead to drastic fluctuations in electricity load. Traditional management methods rely on manual experience to allocate electricity, which struggles to cope with changes in losses under complex scenarios. For example, sudden changes in ambient temperature can cause a sharp increase in air conditioning system power consumption, making timely manual adjustments difficult and resulting in energy waste or power shortages. Traditional smart building power dispatching is often based on fixed quotas or simple load forecasting, failing to fully consider the profound impact of environmental and scenario transitions. Fixed quotas cannot adapt to dynamic electricity demand, easily leading to resource misallocation; simple load forecasting only focuses on total electricity consumption, ignoring the complex effects of environmental and functional transition factors on losses. This results in difficulty in accurately controlling electricity losses, low energy utilization efficiency, and an inability to meet the energy-saving, efficiency-enhancing, and management needs of smart buildings. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of this invention is to provide a smart building power consumption intelligent scheduling method and system.

[0004] To achieve the above objectives, the present invention provides the following technical solution: A smart building power dispatching method, comprising the following steps: The first power loss value is obtained by collecting the power loss value of the target smart building under standard operating conditions; The historical power consumption loss, historical environmental characteristics, and historical power load of the smart building are obtained. If the historical environmental characteristics of different functional zones are dynamically changing, the correlation coefficient between the dynamic environmental changes and the historical power consumption loss is extracted to obtain the first correlation influence coefficient. If the historical environmental characteristics of different functional zones are static and stable, then the correlation coefficient between functional zone conversion and historical power consumption loss is extracted to obtain the second correlation influence coefficient. The third correlation influence coefficient is obtained by extracting the correlation coefficient between historical electricity load conversion and historical electricity loss; The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient, and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss. The actual electricity demand allocation is obtained by scheduling the electricity allocation based on either the first or second actual electricity loss judgment value.

[0005] Preferably, the first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient, and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss, specifically including the following steps: Based on the first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient, the degree of power loss during the operation of the target smart building affected by the transformation of the environment and power consumption scenarios is determined to obtain the second power loss judgment value. The comprehensive comparison verification conditions for building combinations in smart buildings with mismatched functional zoning and floor distribution are statistically analyzed; matching comparison verification conditions for power consumption loss prediction verification with the target smart building are selected from the comprehensive comparison verification conditions. The error of the second power loss judgment value is adjusted according to the matching verification conditions, and the actual power loss judgment value one and the actual power loss judgment value two are obtained according to the first power loss value.

[0006] Preferably, the first power loss value is obtained by collecting the power loss value of the target smart building under standard operating conditions, specifically including the following steps: Collect the current power consumption parameter values ​​and the original power consumption allocation preset in the target smart building, and collect the operating status of the power equipment in the target smart building to obtain the equipment operating characteristics; Collect standard power consumption data of smart buildings operating under standard conditions; Establish an electricity consumption forecasting model based on standard electricity consumption data; The target smart building, the original power allocation, the equipment operating characteristics, and the current power consumption parameter values ​​are input into the power consumption prediction model to obtain the first power loss value of the target smart building under standard operating conditions.

[0007] Preferably, if the historical environmental characteristics of different functional zones are dynamically changing, then the first correlation influence coefficient is obtained by extracting the correlation coefficient between the dynamic environmental changes and historical power consumption losses, specifically including the following steps: If the historical environmental characteristics of different functional zones are dynamically changing, they are marked as electrical environment characteristic one. Based on the characteristics of the power consumption environment, the power loss value of adjacent locations in the smart building belongs to the functional zone. The first correlation influence coefficient is obtained by extracting the correlation coefficient between dynamic environmental changes and power consumption based on the power consumption loss value and the corresponding environmental change value of the power consumption environment characteristics.

[0008] Preferably, if the historical environmental characteristics of different functional zones are static and stable, then the correlation coefficient between functional zone conversion and historical power consumption loss is extracted to obtain the second correlation influence coefficient, which specifically includes the following steps: If the historical environmental characteristics of different functional zones are static and stable, then they are marked as electrical environment characteristic two; Based on the second characteristic of the power consumption environment, the power loss value of the smart building connection location is obtained, with the front part being the functional zone and the back part being the non-adjacent floor. Based on the corresponding environmental stability values ​​in power consumption loss value two and power consumption environment characteristic two, the correlation coefficient between functional zoning conversion and power consumption loss is extracted to obtain the second correlation influence coefficient.

[0009] Preferably, the third correlation influence coefficient is obtained by extracting the correlation coefficient between historical electricity load conversion and historical electricity loss, specifically including the following steps: The power consumption value of the smart building connection location is obtained by considering the non-adjacent floors in the front section and the functional zones in the back section. Based on the corresponding environmental stability values ​​in the third power loss value and the second power environment characteristic, the correlation coefficient between the floor power load conversion and power loss is extracted to obtain the third correlation influence coefficient.

[0010] Preferably, the second power loss judgment value is obtained by judging the degree of power loss caused by environmental and power consumption scenario changes during the operation of the target smart building based on the first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient. This specifically includes the following steps: The first power consumption environment feature and the second power consumption environment feature are combined to form the first power consumption feature set to be trained; The first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient are combined to form the second set of electricity consumption features to be trained. Obtain the historical electricity consumption allocation for all historical buildings; A power loss prediction model is established based on historical power consumption parameter values, historical power consumption allocation, and power consumption feature set 1 and power consumption feature set 2 to be trained. Collect the current environmental characteristics of the target smart building; The current power consumption parameter values, current environmental characteristics, original power consumption allocation, and target smart building are input into the power consumption loss prediction model to obtain the second power consumption loss judgment value of the target smart building's operation process affected by environmental and power consumption scenario changes.

[0011] Preferably, the second power loss judgment value is adjusted for error according to the matching verification conditions, and the actual power loss judgment value one and the actual power loss judgment value two are obtained based on the first power loss value. Specifically, this includes the following steps: The matching verification conditions, current electricity consumption parameter values, current environmental characteristics, and original electricity consumption allocation are input into the electricity loss prediction model to obtain the judgment value of the electricity loss to be compared. If the difference between the second power loss judgment value and the power loss judgment value to be compared is within the preset power loss difference range, then the first power loss value and the second power loss judgment value are integrated to obtain the actual power loss judgment value one. If the difference between the second power loss judgment value and the power loss judgment value to be compared is outside the power loss difference range, then the second power loss judgment value is adjusted according to the power loss judgment value to be compared to obtain the third power loss judgment value. The first power loss value and the third power loss judgment value are integrated to obtain the second actual power loss judgment value.

[0012] A smart building power dispatching system includes: Data Acquisition Module: Acquires the first power loss value by collecting the power consumption value of the target smart building under standard operating conditions; The acquisition and extraction module acquires the historical power consumption loss, historical environmental characteristics, and historical power load of the smart building. If the historical environmental characteristics of different functional zones are dynamically changing, the correlation coefficient between the dynamic environmental changes and historical power consumption loss is extracted to obtain the first correlation influence coefficient. First extraction module: If the historical environmental characteristics of different functional zones are static and stable, then extract the correlation coefficient between functional zone conversion and historical power consumption loss to obtain the second correlation influence coefficient; The second extraction module extracts the correlation coefficient between historical electricity load conversion and historical electricity loss to obtain the third correlation influence coefficient; Processing module: The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss; The scheduling module: Based on the actual power loss judgment value one or the actual power loss judgment value two, the power allocation is scheduled to obtain the actual power demand allocation.

[0013] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent power scheduling method for smart buildings.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention quantifies the impact of different factors on power consumption loss by extracting a first, second, and third correlation coefficient. The first correlation coefficient represents the correlation between temperature and humidity fluctuations and power consumption loss; the second correlation coefficient represents the correlation between functional zoning conversion and historical power consumption loss; and the third correlation coefficient represents the correlation between historical power load conversion and historical power consumption loss. Power scheduling is performed based on actual power consumption loss assessment values ​​to dynamically optimize power allocation. The relationship between power demand and loss in each region and time period is determined, and power allocation is dynamically increased to ensure operation or equipment operation strategies are adjusted to reduce losses. This achieves rational resource allocation, reduces overall power costs, and improves building power efficiency. Attached Figure Description

[0015] Figure 1 This is a schematic diagram illustrating the steps of an intelligent power dispatching method for smart buildings proposed in this invention; Figure 2 This invention presents a schematic diagram of a smart building power dispatching system. Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0016] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] 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 those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0020] Reference Figures 1-3 .

[0021] The embodiments further illustrate the intelligent power dispatching method and system for smart buildings proposed in this invention.

[0022] A smart building power dispatching method, comprising the following steps: The first power loss value is obtained by collecting the power loss value of the target smart building under standard operating conditions; The historical power consumption loss, historical environmental characteristics, and historical power load of the smart building are obtained. If the historical environmental characteristics of different functional zones are dynamically changing, the correlation coefficient between the dynamic environmental changes and the historical power consumption loss is extracted to obtain the first correlation influence coefficient. If the historical environmental characteristics of different functional zones are static and stable, then the correlation coefficient between functional zone conversion and historical power consumption loss is extracted to obtain the second correlation influence coefficient. The third correlation influence coefficient is obtained by extracting the correlation coefficient between historical electricity load conversion and historical electricity loss; The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient, and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss. The actual electricity demand allocation is obtained by scheduling the electricity allocation based on either the first or second actual electricity loss judgment value.

[0023] The primary data collection target is the power consumption value of the smart building under standard operating conditions, which is the first power consumption value. The standard operating conditions are pre-set scenarios that represent the normal operation of building equipment, stable environment, and relatively balanced power load.

[0024] Acquire historical power consumption loss, historical environmental characteristics, and historical power load data for smart buildings. When the historical environmental characteristics of different functional areas exhibit dynamic changes—for example, frequent changes in office areas due to personnel movement, weather variations, and temperature and humidity, or fluctuations in lighting and ventilation demands in public areas due to different usage times—the correlation coefficient between dynamic environmental changes and historical power consumption loss is extracted to obtain the first correlation influence coefficient. By determining how dynamic environmental changes lead to changes in power consumption, the degree of impact of environmental dynamics on power consumption is quantified.

[0025] If the historical environmental characteristics of different functional zones are static and stable, such as the environmental parameters of the equipment room remaining within a specific range for a long time, then the stable operation of the functional zone's purpose and environmental control equipment results in minimal fluctuations in environmental parameters. Therefore, the correlation coefficient between functional zone conversion and historical power consumption losses is extracted to obtain the second correlation impact coefficient. This coefficient is derived from the changes in equipment power consumption patterns caused by the daytime switch from office to meeting room in a certain area, and the redistribution of power load due to temporary adjustments to floor functions. Focusing on the changes in power consumption losses caused by the start-up and shutdown of electrical equipment and load redistribution during the functional zone conversion process, a corresponding correlation is established to clarify the impact weight of functional conversion on power consumption losses.

[0026] The third correlation coefficient is obtained by extracting the correlation coefficient between historical electricity load conversion and historical electricity loss. Historical electricity load conversion is the rapid rise and fall of the overall building electricity load during morning and evening peak hours, as well as the multiple switching of load in different functional areas within a day due to usage demand.

[0027] Electricity consumption loss is predicted using the first, second, and third correlation influence coefficients, as well as the first electricity loss value. An electricity consumption prediction model is constructed based on these coefficients, the basic loss value, and the actual operating scenario of the smart building. The electricity consumption prediction model considers the impact of multiple factors such as environmental dynamics, functional transitions, and load variations on electricity consumption loss, deriving two judgment values ​​for actual electricity consumption loss.

[0028] Power dispatch is conducted based on either Actual Power Loss Judgment Value 1 or Actual Power Loss Judgment Value 2. The initial power allocation is adjusted based on the actual power demand of each area and device within the building, as well as the predicted power loss. If a significant increase in power loss is predicted for a certain area due to environmental dynamics or functional changes, unnecessary power allocation for that area is reduced or power usage periods are adjusted. If the predicted loss is within a controllable range, the allocation is optimized to improve power efficiency while ensuring the normal operation of equipment. This achieves efficient and rational allocation of power resources in smart buildings.

[0029] The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient, and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss. The specific steps include: Based on the first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient, the degree of power loss during the operation of the target smart building affected by the transformation of the environment and power consumption scenarios is determined to obtain the second power loss judgment value. The comprehensive comparison verification conditions for building combinations in smart buildings with mismatched functional zoning and floor distribution are statistically analyzed; matching comparison verification conditions for power consumption loss prediction verification with the target smart building are selected from the comprehensive comparison verification conditions. The error of the second power loss judgment value is adjusted according to the matching verification conditions, and the actual power loss judgment value one and the actual power loss judgment value two are obtained according to the first power loss value.

[0030] Based on the first, second, and third correlation influence coefficients, the degree of power consumption loss in the target smart building under the influence of environmental and power consumption scenario changes is determined to derive a second power consumption loss judgment value. These three coefficients quantify the impact of different factors on power consumption loss from the dimensions of dynamic environmental changes, functional zoning changes in static environments, and power load changes, respectively. For example, the first correlation influence coefficient reflects the degree of interference to building power consumption when the environment is unstable, based on the correlation between dynamic environmental changes and power consumption loss in historical data; the second correlation influence coefficient focuses on the loss changes caused by functional zoning changes; and the third correlation influence coefficient reflects the loss impact brought about by power load changes. By transforming complex factors such as environment and scenario changes into quantifiable power consumption loss values, a preliminary judgment can be made on the power consumption loss of the target building under the combined effects of these factors during actual operation.

[0031] This involves statistical analysis and screening of comprehensive comparative verification conditions for situations where there is a mismatch between functional zoning and floor distribution in smart buildings. A mismatch between functional zoning and floor distribution refers to a situation where the distribution of functional areas (such as offices, leisure areas, and equipment areas) on different floors does not align with typical electricity load patterns and environmental control requirements. For example, high-power-consuming equipment areas may be located at the top of a floor, increasing power transmission losses; densely populated office areas on floors lacking good ventilation and optimized power supply design may experience abnormal losses due to environmental control and concentrated electricity loads. The statistical analysis of the electricity consumption characteristics and loss patterns of building combinations in these mismatch scenarios forms comprehensive comparative verification conditions, including multiple dimensions such as the range of electricity load fluctuations, the correlation between environmental parameters and losses, and the impact of equipment operating efficiency. From these comprehensive conditions, matching comparative verification conditions suitable for predicting and verifying electricity losses in the target smart building are selected. The selection is based on the functional zoning layout, actual floor distribution, and equipment configuration characteristics of the target building, identifying historical case conditions where similar electricity consumption scenarios and building structures resulted from mismatched functional and floor distribution leading to similar electricity loss patterns.

[0032] Based on the matching verification conditions, the second power consumption loss judgment value is adjusted for error. Combined with the first power consumption loss value, two actual power consumption loss judgment values ​​are obtained. Based on the loss impact logic of the comparison conditions, the second judgment value is adjusted for error to obtain a corrected value that better reflects the actual scenario. Simultaneously, by integrating the first power consumption loss value with different weights and correlation logic, two actual power consumption loss judgment values ​​are finally generated. These two values ​​reflect the power consumption of the target smart building under the combined influence of environmental, scenario transition, and structural mismatch factors during actual operation from different dimensions.

[0033] The first power loss value is obtained by collecting the power loss value of the target smart building under standard operating conditions, which specifically includes the following steps: Collect the current power consumption parameter values ​​and the original power consumption allocation preset in the target smart building, and collect the operating status of the power equipment in the target smart building to obtain the equipment operating characteristics; Collect standard power consumption data of smart buildings operating under standard conditions; Establish an electricity consumption forecasting model based on standard electricity consumption data; The target smart building, the original power allocation, the equipment operating characteristics, and the current power consumption parameter values ​​are input into the power consumption prediction model to obtain the first power loss value of the target smart building under standard operating conditions.

[0034] This application collects current power consumption parameters for target smart buildings, including real-time voltage, current, and power signal data. It also collects the pre-planned initial power allocation for the target smart building and obtains equipment operating characteristics, such as start-up and shutdown durations, operating efficiency, and the presence of abnormal operating conditions, by monitoring the operational status of equipment like air conditioners, elevators, and lighting. Different operating states of the equipment are directly related to power consumption. Furthermore, it collects standard power consumption data for the smart building under standard operating conditions. Standard operating conditions refer to an ideal scenario where equipment operates normally and stably, environmental parameters are suitable, the power load is balanced, and there is no abnormal interference.

[0035] Based on the collected standard electricity consumption data, machine learning algorithms are used to build electricity consumption prediction models. For example, by using neural networks to simulate the interaction of multiple factors under complex operating conditions, the inherent logic between electricity distribution, equipment operating status, environmental conditions and other factors and electricity consumption loss in standard operating conditions is explored, transforming scattered standard electricity consumption data into a quantifiable mathematical model.

[0036] The target smart building's own attributes, original power allocation, equipment operating characteristics, and current power consumption parameter values ​​are input into the power consumption prediction model. The power consumption prediction model processes the input data based on pre-learned standard operating condition power loss patterns. It substitutes factors such as the original power allocation, real-time equipment status, and current power consumption parameters into a pre-constructed loss correlation logic to simulate the losses incurred by the target building under standard operating conditions due to equipment operation, power transmission, and environmental adaptation. Finally, it outputs the first power loss value of the target smart building under standard operating conditions.

[0037] If the historical environmental characteristics of different functional zones are dynamically changing, then the first correlation influence coefficient is obtained by extracting the correlation coefficient between the dynamic environmental changes and historical power consumption losses. This specifically includes the following steps: If the historical environmental characteristics of different functional zones are dynamically changing, they are marked as electrical environment characteristic one. Based on the characteristics of the power consumption environment, the power loss value of adjacent locations in the smart building belongs to the functional zone. The first correlation influence coefficient is obtained by extracting the correlation coefficient between dynamic environmental changes and power consumption based on the power consumption loss value and the corresponding environmental change value of the power consumption environment characteristics.

[0038] This application assesses the historical environmental characteristics of different functional zones in smart buildings. When the environment of these functional zones exhibits dynamic changes, such as the continuous adjustment of lighting and ventilation requirements in office areas due to personnel movement, weather changes, and frequent fluctuations in temperature and humidity, it is marked as electrical environment characteristic one.

[0039] This study aims to obtain power consumption loss values ​​for adjacent locations within a smart building that belong to the same functional zone. Adjacent locations within functional zones indicate a greater correlation in power consumption scenarios, with more significant mutual impacts on the coordinated operation and load distribution of electrical equipment during dynamic environmental changes. For example, dynamic environmental changes in adjacent office and meeting areas can trigger a chain reaction in power consumption. Collecting power consumption loss data from these areas captures the power consumption characteristics of adjacent scenarios within functional zones under dynamic environmental changes.

[0040] Based on the collected power consumption loss value and the corresponding environmental change value of the power consumption environment characteristics, a data analysis model is used, such as using a neural network to simulate the loss change pattern under complex environmental changes, and the correlation coefficient between environmental dynamic changes and power consumption loss is extracted to obtain the first correlation influence coefficient.

[0041] If the historical environmental characteristics of different functional zones are static and stable, then the second correlation influence coefficient is obtained by extracting the correlation coefficient between functional zone conversion and historical power consumption loss. The specific steps include: If the historical environmental characteristics of different functional zones are static and stable, then they are marked as electrical environment characteristic two; Based on the second characteristic of the power consumption environment, the power loss value of the smart building connection location is obtained, with the front part being the functional zone and the back part being the non-adjacent floor. Based on the corresponding environmental stability values ​​in power consumption loss value two and power consumption environment characteristic two, the correlation coefficient between functional zoning conversion and power consumption loss is extracted to obtain the second correlation influence coefficient.

[0042] This application first identifies the historical environmental characteristics of different functional zones in a smart building. When the environment of a functional zone exhibits a static and stable state, this scenario is marked as power consumption environment characteristic two. Based on the marked power consumption environment characteristic two, power loss data is collected at specific locations. Power loss values ​​are obtained for the functional zone at the connection point of the smart building and for the non-adjacent floors at the connection point. Due to differences in spatial layout and power consumption scenarios, the functional zone and non-adjacent floors at the connection point experience a redistribution of power load and changes in equipment collaborative operation modes during functional zone transitions. For example, a functional zone transitioning from low-power storage to high-power office space, and the collaboration of power transmission and environmental control equipment on non-adjacent floors, will trigger a chain reaction of changes in power loss.

[0043] By combining the collected power loss value 2 and the corresponding environmental stability value in power environment feature 2, data analysis algorithms (such as mining the nonlinear relationship between functional zoning conversion and power loss through grey relational analysis) are used to extract the correlation coefficient between functional zoning conversion and power loss, thereby obtaining the second correlation influence coefficient.

[0044] The third correlation influence coefficient is obtained by extracting the correlation coefficient between historical electricity load conversion and historical electricity loss, which specifically includes the following steps: The power consumption value of the smart building connection location is obtained by considering the non-adjacent floors in the front section and the functional zones in the back section. Based on the corresponding environmental stability values ​​in the third power loss value and the second power environment characteristic, the correlation coefficient between the floor power load conversion and power loss is extracted to obtain the third correlation influence coefficient.

[0045] This application first collects targeted power loss data from specific locations within smart buildings. It obtains power loss values ​​for locations where the preceding section is a non-adjacent floor and the following section belongs to a functional zone. For example, when high-power-consuming equipment areas on non-adjacent floors supply power to lower-level functional zones, voltage loss and reactive power loss caused by equipment start-up and shutdown coordination vary significantly with load transitions. Collecting loss data from these areas captures the real-time dynamics of cross-floor and cross-scenario power loss during floor load transitions.

[0046] In a static and stable environment, environmental parameters and equipment operating modes are relatively fixed. For example, when the environmental stability value is fixed, the increase in losses when the load shifts from low demand to high demand can be clearly attributed to load transition.

[0047] Based on the power loss value and environmental stability value, a data analysis model (such as a decision tree algorithm to break down the contribution of equipment type and power changes to losses during load switching) is used to extract the correlation coefficient between floor power load switching and power loss, thus obtaining the third correlation influence coefficient. This is to transform the complex impact of floor power load switching into a quantifiable coefficient indicator.

[0048] The second power consumption judgment value is obtained by determining the degree of power loss caused by environmental and power consumption scenario changes during the operation of the target smart building based on the first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient. The specific steps include: Electricity environment feature one and electricity environment feature two are combined to form the first set of electricity features to be trained; The first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient are combined to form the second set of electricity consumption features to be trained. Obtain the historical electricity consumption allocation for all historical buildings; A power loss prediction model is established based on historical power consumption parameter values, historical power consumption allocation, and power consumption feature set 1 and power consumption feature set 2 to be trained. Collect the current environmental characteristics of the target smart building; The current power consumption parameter values, current environmental characteristics, original power consumption allocation, and target smart building are input into the power consumption loss prediction model to obtain the second power consumption loss judgment value of the target smart building's operation process affected by environmental and power consumption scenario changes.

[0049] This application first integrates the features of factors affecting electricity consumption in smart buildings to construct two sets of electricity consumption feature sets to be trained. The first set of electricity consumption feature set is formed by combining the first and second sets of electricity consumption environment feature set. The second set of electricity consumption feature set is formed by combining the first, second and third correlation influence coefficients. The impact of environmental and scenario changes on electricity consumption loss is quantified from different dimensions.

[0050] Historical electricity consumption allocation and parameter values ​​for all historical buildings are obtained. This historical data, along with two sets of electricity consumption features to be trained, are then integrated. Machine learning algorithms (such as neural networks simulating the interaction of multiple features) are used to establish an electricity loss prediction model. By learning from environmental characteristics, correlation coefficients, and the intrinsic relationship between electricity allocation and loss in historical data, the model uncovers the changing patterns of electricity loss under different scenarios.

[0051] The system collects current environmental characteristics of the target building to determine whether the environment is dynamically changing, statically stable, or a mixture of both. Current power consumption parameters, environmental characteristics, original power allocation, and basic information about the target smart building are input into a pre-trained power loss prediction model. The model processes the input data based on pre-learned historical patterns, simulating the power loss of the target building under the combined influence of environmental and power consumption scenario changes during actual operation. Finally, it outputs a second power loss judgment value indicating the impact of environmental and power consumption scenario changes on the target smart building's operation.

[0052] The second power loss judgment value is adjusted for error based on the matching verification conditions. The actual power loss judgment value one and the actual power loss judgment value two are obtained based on the first power loss value. The specific steps include: The matching verification conditions, current electricity consumption parameter values, current environmental characteristics, and original electricity consumption allocation are input into the electricity loss prediction model to obtain the judgment value of the electricity loss to be compared. If the difference between the second power loss judgment value and the power loss judgment value to be compared is within the preset power loss difference range, then the first power loss value and the second power loss judgment value are integrated to obtain the actual power loss judgment value one. If the difference between the second power loss judgment value and the power loss judgment value to be compared is outside the power loss difference range, then the second power loss judgment value is adjusted according to the power loss judgment value to be compared to obtain the third power loss judgment value. The first power loss value and the third power loss judgment value are integrated to obtain the second actual power loss judgment value.

[0053] This application first inputs the matching verification conditions, current power consumption parameter values, current environmental characteristics, and original power consumption allocation into the power consumption loss prediction model to generate a comparison power consumption loss judgment value. Based on the difference analysis between the second power consumption loss judgment value and the comparison power consumption loss judgment value, if the difference between the second power consumption loss judgment value and the comparison power consumption loss judgment value is within a preset power consumption difference range, it indicates that the initially predicted second power consumption loss judgment value has a high degree of consistency with the comparison judgment value under similar scenarios. At this point, the first power consumption loss value and the second power consumption loss judgment value are integrated to obtain the first actual power consumption loss judgment value.

[0054] If the difference between the second power loss judgment value and the power loss judgment value to be compared is outside the power loss difference range, it indicates that there is a deviation in the preliminary prediction, and the second power loss judgment value needs to be adjusted for error. Using the power loss judgment value to be compared as the basis for correction, the second power loss judgment value is corrected to obtain the third power loss judgment value, making the loss prediction more consistent with the actual power consumption scenario of the target building.

[0055] Based on different strategies, the system outputs actual power loss judgment values. For cases within the difference range, the first power loss value and the second power loss judgment value are integrated to obtain actual power loss judgment value one; for cases outside the difference range, the first power loss value and the corrected third power loss judgment value are integrated to obtain actual power loss judgment value two. The two judgment value generation paths cover different scenarios with both accurate predictions and deviations. By integrating standard values ​​and predicted values, the system outputs loss judgment results that reference standard operating conditions, fit actual operation, and have undergone error verification or correction, providing a more adaptive basis for subsequent power dispatching.

[0056] A smart building power dispatching system includes: Data Acquisition Module: Acquires the first power loss value by collecting the power consumption value of the target smart building under standard operating conditions; The acquisition and extraction module acquires the historical power consumption loss, historical environmental characteristics, and historical power load of the smart building. If the historical environmental characteristics of different functional zones are dynamically changing, the correlation coefficient between the dynamic environmental changes and historical power consumption loss is extracted to obtain the first correlation influence coefficient. First extraction module: If the historical environmental characteristics of different functional zones are static and stable, then extract the correlation coefficient between functional zone conversion and historical power consumption loss to obtain the second correlation influence coefficient; The second extraction module extracts the correlation coefficient between historical electricity load conversion and historical electricity loss to obtain the third correlation influence coefficient; Processing module: The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss; The scheduling module: Based on the actual power loss judgment value one or the actual power loss judgment value two, the power allocation is scheduled to obtain the actual power demand allocation.

[0057] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a smart building power consumption intelligent scheduling method.

[0058] like Figure 3 As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions from the memory 630 to execute a smart building power scheduling method.

[0059] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0060] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute a smart building power consumption intelligent scheduling method.

[0061] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform a smart building power consumption intelligent scheduling method.

[0062] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0063] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart building power consumption intelligent scheduling method, characterized in that, The method includes the following steps: The first power loss value is obtained by collecting the power loss value of the target smart building under standard operating conditions; The historical power consumption loss, historical environmental characteristics, and historical power load of the smart building are obtained. If the historical environmental characteristics of different functional zones are dynamically changing, the correlation coefficient between the dynamic environmental changes and the historical power consumption loss is extracted to obtain the first correlation influence coefficient. If the historical environmental characteristics of different functional zones are static and stable, then the correlation coefficient between functional zone conversion and historical power consumption loss is extracted to obtain the second correlation influence coefficient. The third correlation influence coefficient is obtained by extracting the correlation coefficient between historical electricity load conversion and historical electricity loss; The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient, and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss. The actual electricity demand allocation is obtained by scheduling the electricity allocation based on either the first or second actual electricity loss judgment value.

2. The intelligent power dispatching method for smart buildings according to claim 1, characterized in that, The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient, and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss. The specific steps include: Based on the first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient, the degree of power loss during the operation of the target smart building affected by the transformation of the environment and power consumption scenarios is determined to obtain the second power loss judgment value. The comprehensive comparison verification conditions for building combinations with mismatched functional zoning and floor distribution of smart buildings are statistically analyzed; matching comparison verification conditions for power consumption loss prediction verification of the target smart building are selected from the comprehensive comparison verification conditions. The error of the second power loss judgment value is adjusted according to the matching verification conditions, and the actual power loss judgment value one and the actual power loss judgment value two are obtained according to the first power loss value.

3. The intelligent power dispatching method for smart buildings according to claim 2, characterized in that, The first power loss value is obtained by collecting the power loss value of the target smart building under standard operating conditions, which specifically includes the following steps: Collect the current power consumption parameter values ​​and the original power consumption allocation preset in the target smart building, and collect the operating status of the power equipment in the target smart building to obtain the equipment operating characteristics; Collect standard power consumption data of smart buildings operating under standard conditions; Establish an electricity consumption forecasting model based on standard electricity consumption data; The target smart building, the original power allocation, the equipment operating characteristics, and the current power consumption parameter values ​​are input into the power consumption prediction model to obtain the first power loss value of the target smart building under standard operating conditions.

4. The intelligent power dispatching method for smart buildings according to claim 3, characterized in that, If the historical environmental characteristics of different functional zones are dynamically changing, then the first correlation influence coefficient is obtained by extracting the correlation coefficient between the dynamic environmental changes and historical power consumption losses. This specifically includes the following steps: If the historical environmental characteristics of different functional zones are dynamically changing, they are marked as electrical environment characteristic one. Based on the characteristics of the power consumption environment, the power loss value of adjacent locations in the smart building belongs to the functional zone. The first correlation influence coefficient is obtained by extracting the correlation coefficient between dynamic environmental changes and power consumption based on the power consumption loss value and the corresponding environmental change value of the power consumption environment characteristics.

5. The intelligent power dispatching method for smart buildings according to claim 4, characterized in that, If the historical environmental characteristics of different functional zones are static and stable, then the second correlation influence coefficient is obtained by extracting the correlation coefficient between functional zone conversion and historical power consumption loss. The specific steps include: If the historical environmental characteristics of different functional zones are static and stable, then they are marked as electrical environment characteristic two; Based on the second characteristic of the power consumption environment, the power loss value of the smart building connection location is obtained, with the front part being the functional zone and the back part being the non-adjacent floor. Based on the corresponding environmental stability values ​​in power consumption loss value two and power consumption environment characteristic two, the correlation coefficient between functional zoning conversion and power consumption loss is extracted to obtain the second correlation influence coefficient.

6. The intelligent power dispatching method for smart buildings according to claim 5, characterized in that, The third correlation influence coefficient is obtained by extracting the correlation coefficient between historical electricity load conversion and historical electricity loss, which specifically includes the following steps: The power consumption value of the smart building connection location is obtained by considering the non-adjacent floors in the front section and the functional zones in the back section. Based on the corresponding environmental stability values ​​in the third power loss value and the second power environment characteristic, the correlation coefficient between the floor power load conversion and power loss is extracted to obtain the third correlation influence coefficient.

7. The intelligent power dispatching method for smart buildings according to claim 6, characterized in that, The second power consumption judgment value is obtained by determining the degree of power loss caused by environmental and power consumption scenario changes during the operation of the target smart building based on the first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient. The specific steps include: The first power consumption environment feature and the second power consumption environment feature are combined to form the first power consumption feature set to be trained; The first correlation influence coefficient, the second correlation influence coefficient, and the third correlation influence coefficient are combined to form the second set of electricity consumption features to be trained. Obtain the historical electricity consumption allocation for all historical buildings; A power loss prediction model is established based on historical power consumption parameter values, historical power consumption allocation, and power consumption feature set 1 and power consumption feature set 2 to be trained. Collect the current environmental characteristics of the target smart building; The current power consumption parameter values, current environmental characteristics, original power consumption allocation, and target smart building are input into the power consumption loss prediction model to obtain the second power consumption loss judgment value of the target smart building's operation process affected by environmental and power consumption scenario changes.

8. The intelligent power dispatching method for smart buildings according to claim 7, characterized in that, The second power loss judgment value is adjusted for error based on the matching verification conditions. The actual power loss judgment value one and the actual power loss judgment value two are obtained based on the first power loss value. The specific steps include: The matching verification conditions, current electricity consumption parameter values, current environmental characteristics, and original electricity consumption allocation are input into the electricity loss prediction model to obtain the judgment value of the electricity loss to be compared. If the difference between the second power loss judgment value and the power loss judgment value to be compared is within the preset power loss difference range, then the first power loss value and the second power loss judgment value are integrated to obtain the actual power loss judgment value one. If the difference between the second power loss judgment value and the power loss judgment value to be compared is outside the power loss difference range, then the second power loss judgment value is adjusted according to the power loss judgment value to be compared to obtain the third power loss judgment value. The first power loss value and the third power loss judgment value are integrated to obtain the second actual power loss judgment value.

9. A smart building power consumption intelligent dispatching system, applied to the smart building power consumption intelligent dispatching method according to any one of claims 1 to 8, characterized in that, include: Data Acquisition Module: Acquires the first power loss value by collecting the power consumption value of the target smart building under standard operating conditions; The acquisition and extraction module acquires the historical power consumption loss, historical environmental characteristics, and historical power load of the smart building. If the historical environmental characteristics of different functional zones are dynamically changing, the correlation coefficient between the dynamic environmental changes and historical power consumption loss is extracted to obtain the first correlation influence coefficient. First extraction module: If the historical environmental characteristics of different functional zones are static and stable, then extract the correlation coefficient between functional zone conversion and historical power consumption loss to obtain the second correlation influence coefficient; The second extraction module extracts the correlation coefficient between historical electricity load conversion and historical electricity loss to obtain the third correlation influence coefficient; Processing module: The first correlation influence coefficient, the second correlation influence coefficient, the third correlation influence coefficient and the first power loss value are processed and analyzed to obtain the first judgment value of actual power loss and the second judgment value of actual power loss; The scheduling module: Based on the actual power loss judgment value one or the actual power loss judgment value two, the power allocation is scheduled to obtain the actual power demand allocation.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the intelligent power scheduling method for smart buildings as described in any one of claims 1 to 8.

Images