Stadium electricity consumption operation processing method and system

Abstract

The invention provides a stadium power consumption operation processing method and system, and the method comprises the steps: obtaining internal sensor data and external meteorological station data of a stadium, fusing a personnel activity intensity monitoring value and an illumination change record, and removing noise through data preprocessing, thereby obtaining a clean real-time input data set; according to the clean real-time input data set, a support vector machine algorithm is adopted to classify personnel activity intensity levels and illumination change modes, and the thermal disturbance contribution proportion of each area is determined; according to the dynamically updated cooling and heating load demand matrix, a multi-equipment operation scene is simulated, a genetic algorithm is adopted to optimize collaborative parameters of air conditioner ventilation equipment, and an adjusting scheme matched with actual demands is obtained; and extracting a key control signal from the obtained adjustment scheme, transmitting the key control signal to a central control system, and adjusting the output power of the equipment in real time to obtain optimized electric energy consumption configuration.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to a method and system for handling the operation and processing of electrical energy consumption in venues. Background Technology

[0002] Large public venues such as stadiums, exhibition centers, and theaters rely heavily on the coordinated operation of multiple systems, including air conditioning and ventilation, for their interior comfort. The electricity consumption of these systems often accounts for a significant portion of the venue's total energy consumption. With the diversification of usage demands and the continuous rise in energy costs, effectively controlling electricity consumption while ensuring personnel comfort and air quality has become a crucial issue that venue managers must address.

[0003] Many venues still rely on pre-set, fixed operating modes or extensive adjustments based on historical experience. While simple to implement, this approach struggles to adapt to the frequent changes in the use of the venue's internal spaces. Areas where people congregate can shift from vacant to high-density activity at any time; lighting intensity fluctuates significantly depending on the type of activity at different times; and outdoor weather conditions change rapidly. These factors combined result in highly dynamic and unevenly distributed heating and cooling requirements for the venue. Traditional methods struggle to capture these real-time changes, often leading to equipment operating at excessively high capacity or experiencing both overheating and underheating in certain areas, wasting energy and negatively impacting the user experience.

[0004] Looking deeper, the heating and cooling load of a venue is not simply the sum of a single source, but rather determined by multiple coupled thermal disturbances. The instantaneous heat exchange between the building envelope and the outdoor environment, the heat released by personnel activities, the load from the introduction of fresh air, and the heat transfer between different areas—inner and outer zones—are all tightly intertwined in time and space. Especially during transitional seasons, the availability of natural cooling sources outdoors directly alters whether the fresh air system can still handle some of the cooling load. Current technology struggles to accurately separate and identify the respective contributions of the fresh air load and the inherent indoor load during operation. This mixed and dynamically coupled state of load sources makes it difficult to precisely quantify the overall heating and cooling demand, resulting in a lack of coordinated regulation between multiple air conditioning and ventilation systems to truly match actual needs.

[0005] For example, during a large-scale sporting event, the spectator area may experience intense instantaneous thermal disturbances due to the simultaneous entry of tens of thousands of people in a short period of time. Meanwhile, the heat generated by the lighting and athletes' activities in the competition venue remains relatively stable. If the true contribution ratio of each area and source to the total load cannot be determined in a timely manner, the central control system may misjudge the peak demand, causing multiple main units to start up at full load at the same time or the fresh air system to operate ineffectively and excessively, directly increasing energy consumption.

[0006] The key issue in achieving efficient collaboration among multiple devices and refined power operation is how to calculate the dynamic and clearly zoned heating and cooling load requirements of the entire venue in real time based on the venue's current actual usage status, the intensity of personnel activities, lighting changes, and external weather conditions. Summary of the Invention

[0007] This invention provides a method and system for handling the operation and management of electrical energy consumption in venues, mainly including:

[0008] Data from internal sensors and external weather stations were acquired, and monitoring values ​​of human activity intensity and lighting changes were integrated. Noise was removed through data preprocessing to obtain a clean real-time input dataset. Based on this clean real-time input dataset, a support vector machine algorithm was used to classify human activity intensity levels and lighting change patterns, determining the proportion of thermal disturbance contribution in each area. From the determined proportions, the heat exchange portion of the building envelope and the fresh air intake portion were extracted. If the heat exchange of the building envelope exceeded a preset threshold, the impact of external weather conditions on the total load was separated, yielding an independent fresh air load value. This independent fresh air load value was then combined with indoor inherent heat release data... The indoor load components are calculated, and the impact of heat transfer between different areas is quantified using a linear regression algorithm to determine the zonal indoor load distribution. The influence of lighting variation patterns is integrated from the determined zonal indoor load distribution. If the lighting intensity fluctuation exceeds a preset threshold, the contribution ratio of thermal disturbance is adjusted to obtain a dynamically updated cooling and heating load demand matrix. Based on the dynamically updated cooling and heating load demand matrix, a multi-device operation scenario is simulated, and a genetic algorithm is used to optimize the coordination parameters of air conditioning and ventilation equipment to obtain an adjustment scheme that matches actual needs. Key control signals are extracted from the obtained adjustment scheme and transmitted to the central control system to adjust the equipment output power in real time, resulting in an optimized power consumption configuration.

[0009] Preferably, as one possible implementation; the acquisition of sensor data inside the venue and data from an external weather station, fusion of personnel activity intensity monitoring values ​​and lighting change records, and noise removal through data preprocessing to obtain a clean real-time input dataset, includes:

[0010] The venue collects internal sensor data and personnel activity intensity monitoring values ​​through internal sensors, obtains external meteorological data and lighting change records from external meteorological stations, and merges the personnel activity intensity monitoring values ​​and lighting change records to obtain a preliminary fused dataset.

[0011] For the aforementioned preliminary fused dataset, the Kalman filter algorithm is used to remove noise through state estimation and prediction updates to obtain a denoised fused dataset;

[0012] If the denoised fusion dataset contains outliers, the outliers are replaced by the median value of the neighborhood using a median filtering algorithm to obtain the adjusted dataset.

[0013] Based on the adjusted dataset, venue energy consumption records are integrated to determine the clean real-time input dataset.

[0014] Preferably, as one possible implementation; the step of classifying the intensity level of human activity and lighting change patterns using a support vector machine algorithm based on a clean real-time input dataset, and determining the proportion of thermal disturbance contribution in each area, includes:

[0015] Based on the clean real-time input dataset, the support vector machine algorithm is used to classify the intensity level of the personnel activities and the lighting change pattern, and a classification result set is obtained;

[0016] Based on the classification result set, the meteorological influencing factors and energy consumption records are integrated, and the preliminary distribution of thermal disturbances is determined by comparing the meteorological conditions and energy use in different regions.

[0017] By adjusting the outlier adjustment and noise removal effects based on the initial thermal disturbance distribution, and correcting the data deviation by combining the regional activity intensity differences, an optimized thermal disturbance model is obtained.

[0018] The optimized thermal disturbance model is obtained, and the matching between the regional classification level and the contribution ratio is determined to obtain the thermal disturbance contribution ratio of each region.

[0019] Preferably, as one possible implementation; the step of extracting the heat exchange portion and the fresh air introduction portion of the building envelope from the determined thermal disturbance contribution ratio, and determining whether the heat exchange of the building envelope exceeds a preset threshold, then separating the impact of external meteorological conditions on the total load to obtain an independent fresh air load value, includes:

[0020] From the thermal disturbance ratio data, the specific values ​​of heat exchange and fresh air introduction of the building envelope are obtained. The two are separated by the sub-item extraction technology to obtain independent data of heat exchange of the building envelope and independent data of fresh air introduction.

[0021] For independent data on heat exchange of the building envelope, if the value exceeds the preset threshold, the analysis process of external meteorological conditions is triggered. The corresponding external meteorological parameters are obtained by calling the meteorological data interface to determine the degree of influence of external meteorology on heat exchange of the building envelope.

[0022] Based on the degree of influence of external meteorological parameters, the portion of the total load value caused by external meteorological factors is separated, and the total load value is decomposed using a regression analysis algorithm to obtain the remaining load data after removing the effects of external meteorological factors;

[0023] From the remaining load data, the load portion related to fresh air introduction is extracted. Through data matching technology, the independent data of fresh air introduction is correlated with the remaining load data to determine the specific value of the fresh air load.

[0024] Based on the specific values ​​of the fresh air load and the distribution of its contribution ratio, we analyze the actual proportion of fresh air introduced into the total load and obtain independent calculation results for the fresh air load.

[0025] Based on the independent calculation results of the fresh air load, the accuracy of the load separation is verified. By comparing the contribution ratio with the data after separation, the final fresh air load value is determined.

[0026] Starting from the final fresh air load value, a corresponding load distribution record is generated. Data storage technology is used to archive the heat exchange volume of the building envelope, the fresh air load value, and external meteorological parameters to obtain a complete load analysis dataset.

[0027] Preferably, as one possible implementation; the step of combining the obtained independent fresh air load value with indoor inherent heat release data to calculate indoor load components, using a linear regression algorithm to quantify the impact of heat transfer between different areas, and determining the zoned indoor load distribution includes:

[0028] Obtain independent fresh air load values ​​and indoor inherent heat release data for each area;

[0029] By matching data, the independent fresh air load values ​​are allocated to the corresponding areas to obtain the initial load components of each area;

[0030] For the initial load component of each region, a linear regression algorithm is used to calculate the heat transfer coefficient between adjacent regions;

[0031] Adjust the load components of each region according to the heat transfer coefficient to obtain the corrected load value after taking into account the heat exchange between regions.

[0032] If the load difference between adjacent areas exceeds the preset range, the indoor inherent heat release data of the corresponding area will be re-extracted for matching and correction.

[0033] By adjusting load values ​​and summarizing data from all regions, the complete distribution of indoor load in each zone can be determined.

[0034] By linking the indoor load distribution of each zone with the building's spatial layout information, a record of the load percentage for each zone is generated.

[0035] Preferably, as one feasible implementation; the influence of lighting variation patterns is integrated from the determined indoor load distribution of different zones, and if the lighting intensity fluctuation exceeds a preset threshold, the proportion of thermal disturbance contribution is adjusted to obtain a dynamically updated cooling and heating load demand matrix, including:

[0036] Obtain the hourly sequence of lighting power in each area from the zonal indoor load distribution data;

[0037] By performing time-series differential calculations on the lighting power of each region, a sequence of changes in lighting intensity amplitude is obtained.

[0038] Determine whether the maximum value in the sequence of changes in lighting intensity is greater than a preset threshold. If it is, mark the region as a high fluctuation region.

[0039] Obtain the proportion of lighting thermal disturbance at the corresponding moment from the high fluctuation region;

[0040] The adjusted regional load component is obtained by multiplying the proportion of lighting thermal disturbance by the original regional heating and cooling load components.

[0041] The load components of all area lighting after adjustment are organized in matrix form to obtain the area load correction matrix;

[0042] By performing row vector summation and column vector summation operations on the regional load correction matrix, the total distribution of cooling and heating loads for the entire floor and the cooling and heating load demand matrix for each zone are determined.

[0043] Preferably, as one feasible implementation; based on the dynamically updated cooling and heating load demand matrix, simulating multi-device operation scenarios, and using a genetic algorithm to optimize the coordination parameters of air conditioning and ventilation equipment, an adjustment scheme matching actual needs is obtained, including:

[0044] By extracting load data for each region from the dynamically updated heating and cooling load demand matrix, an initial model of multi-device operation scenarios is constructed to obtain the load distribution of each region at different times.

[0045] Based on the load distribution, analyze the operating status of air conditioning and ventilation equipment in the multi-equipment group, and determine the preliminary parameter configuration of each equipment in the current scenario.

[0046] A genetic algorithm is used to iteratively optimize the initial parameter configuration, adjust the collaborative parameters, and obtain the optimized combination of equipment operating parameters.

[0047] For the optimized combination of equipment operating parameters, the performance of multiple equipment groups in the operating scenario is simulated. If the operating parameters of a certain equipment exceed the preset threshold range, the parameters of that equipment are fine-tuned to obtain the adjusted parameter set.

[0048] By adjusting the parameter set, specific adjustment schemes are generated for air conditioning and ventilation equipment, and the operating modes of each device at different times are determined.

[0049] Based on the generated adjustment scheme, the operating status of the equipment in the actual scenario is mapped to obtain the final equipment collaborative control command.

[0050] Preferably, as one feasible implementation, key control signals are extracted from the obtained adjustment scheme and transmitted to the central control system to adjust the equipment output power in real time, thereby obtaining an optimized power consumption configuration, including:

[0051] By extracting control signals from the adjustment scheme and transmitting them to the central system, preliminary equipment adjustment instructions are obtained;

[0052] Based on the initial equipment adjustment instructions, analyze the matching between the equipment operating status and output power to determine the priority order of power adjustment;

[0053] By adopting a priority order, the output power of the equipment is controlled in layers to obtain a layered power allocation scheme;

[0054] For the tiered power allocation scheme, the data is transmitted to the central system in real time for comparison. If the comparison result shows that the power allocation exceeds the preset threshold range, the relevant devices are adjusted for secondary allocation to obtain the adjusted power configuration.

[0055] By adjusting the power configuration, specific control signals are generated for each device, and the final instruction set for device operation is determined.

[0056] Based on the final instruction set, the control logic of the central system is updated to obtain an optimized mapping between equipment operation and power consumption;

[0057] For optimized mapping, the system continuously monitors changes in equipment operating status. If an abnormal power distribution is detected, the control signal is regenerated through the central system to determine the next steps for equipment adjustment.

[0058] This invention provides a venue power consumption operation and processing system, including a preprocessing module, an input module, a separation module, a heat transfer calculation module, an adjustment module, and an output module:

[0059] The preprocessing module is used to acquire sensor data inside the venue and data from external weather stations, integrate monitoring values ​​of personnel activity intensity with lighting change records, remove noise through data preprocessing, and obtain a clean real-time input dataset;

[0060] The system comprises the following modules: an input module, which uses a support vector machine algorithm to classify the intensity level of human activity and lighting change patterns based on a clean, real-time input dataset, determining the proportion of thermal disturbance contribution in each area; a separation module, which extracts the heat exchange portion of the building envelope and the fresh air introduction portion from the determined thermal disturbance contribution proportions, and determines the impact of external meteorological conditions on the total load if the heat exchange of the building envelope exceeds a preset threshold, thus obtaining an independent fresh air load value; a heat transfer calculation module, which combines the obtained independent fresh air load value with indoor inherent heat release data to calculate indoor load components, uses a linear regression algorithm to quantify the impact of heat transfer between different areas, and determines the zonal indoor load distribution; an adjustment module, which integrates the impact of lighting change patterns from the determined zonal indoor load distribution, and adjusts the thermal disturbance contribution proportion if the lighting intensity fluctuation exceeds a preset threshold, thus obtaining a dynamically updated cooling and heating load demand matrix; and an output module, which simulates multi-equipment operation scenarios based on the dynamically updated cooling and heating load demand matrix, uses a genetic algorithm to optimize the collaborative parameters of air conditioning and ventilation equipment, obtaining an adjustment scheme that matches actual needs, extracts key control signals from the obtained adjustment scheme, transmits them to the central control system, and adjusts the equipment output power in real time to obtain an optimized power consumption configuration.

[0061] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0062] This invention discloses a dynamic control method for building air conditioning load based on multi-source data fusion and intelligent optimization. It acquires real-time data from internal sensors, external weather stations, and records of human activity intensity and lighting changes. After noise reduction preprocessing, a clean dataset is formed. A support vector machine algorithm is used to classify the intensity levels of human activity and lighting change patterns, thereby accurately determining the contribution ratio of thermal disturbance in each area. Based on this, the load is separated into two parts: heat exchange in the building envelope and fresh air introduction. When the heat exchange in the building envelope exceeds a threshold, the fresh air load value is extracted independently. Combined with the release of inherent indoor heat, the influence of heat transfer between areas is quantified through linear regression, resulting in a refined zonal indoor load distribution. Furthermore, the dynamic impact of lighting fluctuations on thermal disturbance is integrated. When the lighting intensity change exceeds a threshold, the thermal disturbance ratio is adjusted in real time, forming a dynamically updated cooling and heating load demand matrix. Finally, based on this matrix, a genetic algorithm is used to simulate a multi-device collaborative operation scenario, optimize the operating parameters of the air conditioning and ventilation equipment, generate a control scheme matching actual needs, and output key control signals to the central control system. This enables precise real-time adjustment of equipment output power, significantly reducing energy consumption and improving indoor environmental comfort and energy efficiency. Attached Figure Description

[0063] Figure 1 This is a flowchart of a method for handling the operation of electrical energy consumption in a venue according to the present invention;

[0064] Figure 2 This is a schematic diagram of a venue power consumption operation and management method according to the present invention;

[0065] Figure 3 This is another schematic diagram of a venue power consumption operation and processing method according to the present invention;

[0066] Figure 4 This is a schematic diagram of a venue power consumption operation and processing system according to the present invention. Detailed Implementation

[0067] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0068] Example 1

[0069] like Figures 1-3 This embodiment provides a method and system for handling the operation of venue electricity consumption, which may specifically include:

[0070] S101. Acquire data from internal sensors and external weather stations, integrate monitoring values ​​of personnel activity intensity with lighting change records, and remove noise through data preprocessing to obtain a clean real-time input dataset.

[0071] S102. Based on the clean real-time input dataset, use the support vector machine algorithm to classify the intensity level of human activity and lighting change patterns, and determine the proportion of thermal disturbance contribution in each area.

[0072] Thermal perturbation value of region i at time t: ;in: Normalized intensity of human activity (0-1); Normalized lighting heat load (0-1); Normalized equipment heat load (0-1); α+β+γ=1 (default α=0.5, β=0.3, γ=0.2); Thermal disturbance contribution ratio: N: is the total number of regions.

[0073] S103. Extract the heat exchange portion and fresh air introduction portion of the building envelope from the determined heat disturbance contribution ratio. If the heat exchange of the building envelope exceeds the preset threshold, separate the influence of external meteorological conditions on the total load and obtain an independent fresh air load value.

[0074] The heat exchange of the building envelope is

[0075] ;

[0076] S104. By combining the obtained independent fresh air load values ​​with the indoor inherent heat release data, calculate the indoor load components, use a linear regression algorithm to quantify the impact of heat transfer between different areas, and determine the indoor load distribution of the zones.

[0077] The fresh air load value is : ; ;

[0078] Fresh air load separation conditions: If This triggers the use of multiple linear regression in meteorological impact analysis;

[0079] Multiple linear regression is calculated as follows ;

[0080] Represents total load: the building's total heating and cooling load (kW) at time t; Represents the heat exchange load of the building envelope, which means: the load generated by heat exchange between the building envelope (exterior walls, roof, windows, etc.) and the outdoor environment; Represents the fresh air load, which means: the formula for calculating the amount of cooling and heating required to process outdoor fresh air to achieve indoor conditions; The meaning of the internal heat source load is: the heat generated by building lighting, etc., which can be simply calculated by mathematical formulas based on the number and power of the lights, and will not be elaborated further; the meaning of the regression coefficients a, b, c is: the contribution coefficient of each load component to the total load. The range is: 0 ≤ a,b,c ≤ 1. The constraint condition is: under ideal conditions, a + b +c ≈ 1; in addition, ε represents the error term.

[0081] S105. Integrate the influence of lighting change patterns from the determined indoor load distribution of the zones, and determine if the lighting intensity fluctuation is greater than the preset threshold. Then adjust the contribution ratio of thermal disturbance to obtain a dynamically updated cooling and heating load demand matrix.

[0082] S106. Based on the dynamically updated cooling and heating load demand matrix, simulate multi-device operation scenarios, and use a genetic algorithm to optimize the coordination parameters of air conditioning and ventilation equipment to obtain an adjustment scheme that matches the actual needs.

[0083] S107. Extract key control signals from the obtained adjustment scheme, transmit them to the central control system, adjust the equipment output power in real time, and obtain an optimized power consumption configuration.

[0084] Control signals are extracted from the adjustment scheme and transmitted to the central system to obtain preliminary equipment adjustment instructions. Based on these instructions, the matching between equipment operating status and output power is analyzed to determine the priority order of power adjustments. Using this priority order, the output power of the equipment is stratified for control, resulting in a stratified power allocation scheme. This scheme is then transmitted to the central system in real time for data comparison. If the comparison shows that the power allocation exceeds a preset threshold, secondary allocation adjustments are made to the relevant equipment to obtain the adjusted power configuration. Based on the adjusted power configuration, specific control signals are generated for each device to determine the final instruction set for equipment operation. According to the final instruction set, the control logic of the central system is updated to obtain an optimized mapping between equipment operation and energy consumption. For this optimized mapping, changes in equipment operating status are continuously monitored. If an abnormal power distribution is detected, the central system regenerates control signals to determine the subsequent equipment adjustment scheme.

[0085] In a specific embodiment, the acquisition of sensor data from inside the venue and data from an external weather station, the fusion of personnel activity intensity monitoring values ​​and lighting change records, and the removal of noise through data preprocessing to obtain a clean real-time input dataset specifically include:

[0086] S11. Collect the internal sensor data and personnel activity intensity monitoring values ​​through the internal sensors of the venue, obtain the external meteorological data and lighting change records from the external meteorological station, and fuse the personnel activity intensity monitoring values ​​and lighting change records to obtain a preliminary fused dataset.

[0087] S12. For the preliminary fused dataset, the Kalman filter algorithm is used to remove noise through state estimation and prediction update to obtain a denoised fused dataset.

[0088] S13. If outliers exist in the denoised fusion dataset, the outliers are replaced by the median value in the neighborhood using a median filtering algorithm to obtain the adjusted dataset. Based on the adjusted dataset, the venue's energy consumption records are integrated to determine the clean real-time input dataset.

[0089] Analysis of steps S11-S13 above shows that they are mainly used to improve data quality and reliability. In their specific implementation, they use sensor fusion, Kalman filtering to remove noise, and median filtering to process outliers, ensuring the accuracy and stability of the input data and providing a reliable foundation for subsequent analysis.

[0090] In a specific embodiment, step S102, based on a clean real-time input dataset, uses a support vector machine algorithm to classify the intensity level of human activity and lighting change patterns, and determines the proportion of thermal disturbance contribution in each area, specifically includes:

[0091] It should be noted that the above technical solution specifically involves the following operation, namely S21, using a support vector machine algorithm to classify the intensity level of the personnel activity and the lighting change pattern based on the clean real-time input dataset, and obtaining a classification result set.

[0092] S22. For the classification result set, integrate the meteorological influencing factors and energy consumption records, and determine the preliminary thermal disturbance distribution by comparing the meteorological conditions and energy use in different regions.

[0093] S23. Based on the preliminary thermal disturbance distribution, adjust the outlier adjustment and noise removal effects, and correct the data deviation by combining the regional activity intensity differences to obtain an optimized thermal disturbance model.

[0094] S24. Obtain the optimized thermal disturbance model, determine the matching between the regional classification level and the contribution ratio, and obtain the thermal disturbance contribution ratio of each region.

[0095] Analysis of steps S21-S24 above shows that support vector machines are used to classify activity intensity and lighting patterns, meteorological influencing factors (such as ambient temperature and light intensity) and energy consumption records, establish a thermal disturbance distribution model, and quantify the contribution ratio of each region.

[0096] In a specific embodiment, the step of extracting the heat exchange portion and the fresh air introduction portion of the building envelope from the determined thermal disturbance contribution ratio, and determining whether the heat exchange of the building envelope exceeds a preset threshold, then separating the impact of external meteorological conditions on the total load to obtain an independent fresh air load value, specifically includes:

[0097] Step 1: Obtain the specific values ​​of heat exchange and fresh air introduction of the building envelope from the thermal disturbance ratio data, and use the sub-item extraction technology to separate the two to obtain independent data of heat exchange of the building envelope and independent data of fresh air introduction.

[0098] Step 2: For independent data on heat exchange of the building envelope, if the value exceeds the preset threshold, the analysis process of external meteorological conditions is triggered. By calling the meteorological data interface, the corresponding external meteorological parameters are obtained to determine the degree of influence of external meteorology on the heat exchange of the building envelope.

[0099] Step 3: Based on the degree of influence of external meteorological parameters, separate the portion of the total load value caused by external meteorological factors, and use regression analysis algorithm to decompose the total load value to obtain the remaining load data after removing the influence of external meteorological factors.

[0100] Step 4: Extract the load portion related to fresh air introduction from the remaining load data. Using data matching technology, correlate the independent data of fresh air introduction with the remaining load data to determine the specific value of the fresh air load.

[0101] Step 5: Based on the specific value of the fresh air load and the distribution of its contribution ratio, analyze the actual proportion of fresh air introduced into the total load and obtain the independent calculation results of the fresh air load.

[0102] Step Six: Based on the independent calculation results of the fresh air load, verify the accuracy of the load separation. By comparing the contribution ratio with the data after separation, determine the final fresh air load value.

[0103] Step 7: Starting from the final fresh air load value, generate the corresponding load distribution record, and use data storage technology to archive the heat exchange of the building envelope, fresh air load value and external meteorological parameters to obtain a complete load analysis dataset.

[0104] It should be noted that the above technical solution mainly uses threshold judgment to trigger meteorological analysis, regress and decompose the total load, extract the fresh air portion, and achieve accurate separation of the building envelope load and the fresh air load.

[0105] In a specific embodiment, the process of combining the obtained independent fresh air load values ​​with indoor inherent heat release data to calculate indoor load components, using a linear regression algorithm to quantify the impact of heat transfer between different areas, and determining the zonal indoor load distribution specifically includes:

[0106] S41. Obtain independent fresh air load values ​​and indoor inherent heat release data for each area.

[0107] S42. By matching data, the independent fresh air load values ​​are allocated to the corresponding areas to obtain the initial load components of each area.

[0108] S43. For the initial load component of each area, a linear regression algorithm is used to calculate the heat transfer coefficient between adjacent areas. The load component of each area is adjusted according to the heat transfer coefficient to obtain the corrected load value considering heat exchange between areas. If the load difference between adjacent areas exceeds a preset range, the indoor inherent heat release data of the corresponding area is re-extracted for matching and correction.

[0109] It should be noted that a linear regression algorithm is used to calculate the heat transfer coefficient between adjacent areas (i.e., the heat transfer coefficient between areas), and then the area load is corrected using the heat transfer coefficient to obtain the corrected load value considering heat exchange between areas. The linear regression model is as follows: ;

[0110] in: Represents the set of neighboring regions of region i; The heat transfer coefficient from region j to region i is represented; the solution is obtained using the least squares method.

[0111] Corrected area load: ;

[0112] S44. By summarizing all regional data through corrected load values, the complete distribution of indoor load in each zone is determined. The indoor load distribution in each zone is then linked with the building space layout information to generate a record of the load percentage for each zone.

[0113] Analysis of steps S41-S44 above shows that this process is used to achieve refined zonal load calculation. In the specific implementation process, it quantifies the heat transfer between regions through linear regression, and combines the inherent heat and fresh air load to obtain a more accurate zonal load distribution. Finally, it associates the zonal indoor load distribution with the building space layout information to generate a record of the load ratio of each region, and then provides a technical basis for subsequent regional power consumption control.

[0114] In a specific embodiment, the step of integrating the influence of lighting variation patterns from the determined indoor load distribution of zones, determining whether the lighting intensity fluctuation exceeds a preset threshold, and then adjusting the thermal disturbance contribution ratio to obtain a dynamically updated cooling and heating load demand matrix specifically includes:

[0115] S51. Obtain the hourly sequence of lighting power for each area in the indoor load distribution data of the zones. Perform differential calculation on the hourly sequence of lighting power for each area to obtain the sequence of lighting intensity variation. Determine whether the maximum value in the sequence of lighting intensity variation is greater than a preset threshold. If it is, mark the area as a high-fluctuation area.

[0116] S52. Obtain the proportion of lighting thermal disturbance at the corresponding time from the high-fluctuation area. Multiply the proportion of lighting thermal disturbance by the original heating and cooling load components of the area to obtain the area load component after lighting adjustment.

[0117] S53. Organize the adjusted load components of all area lighting in matrix form to obtain the area load correction matrix. By performing row vector summation and column vector summation operations on the area load correction matrix, determine the total distribution of cooling and heating loads for the entire floor and the cooling and heating load demand matrix for each zone.

[0118] In a specific embodiment, the step of simulating multi-device operation scenarios based on a dynamically updated cooling and heating load demand matrix, and using a genetic algorithm to optimize the coordination parameters of air conditioning and ventilation equipment to obtain an adjustment scheme that matches actual needs, specifically includes:

[0119] S61. By extracting load data for each region from the dynamically updated cooling and heating load demand matrix, an initial model of a multi-equipment operation scenario is constructed to obtain the load distribution of each region at different times. Based on the load distribution, the operating status of air conditioning and ventilation equipment in the multi-equipment group is analyzed to determine the preliminary parameter configuration of each equipment in the current scenario.

[0120] S62. A genetic algorithm is used to iteratively optimize the initial parameter configuration, adjust the collaborative parameters, and obtain an optimized combination of equipment operating parameters. For the optimized combination of equipment operating parameters, the performance of multiple equipment groups in the operating scenario is simulated. If the operating parameters of a certain equipment exceed the preset threshold range, the parameters of that equipment are fine-tuned to obtain the adjusted parameter set.

[0121] S63. Using the adjusted parameter set, generate specific adjustment schemes for air conditioning and ventilation equipment, and determine the operating modes of each device at different times. Based on the generated adjustment schemes, map the operating states of the equipment in the actual scenario to obtain the final equipment coordinated control commands.

[0122] A genetic algorithm is used to iteratively optimize the initial parameter configuration and finally determine the fitness.

[0123] ;

[0124] in:

[0125] Device parameter vector;

[0126] ;

[0127] For equipment status penalties (frequent start-stop penalties);

[0128] Genetic operations: Selection: Roulette wheel selection, probability Cross-operation: machine-arithmetic cross-operation, Then perform the mutation operation: namely, Gaussian mutation. (0, σ²) The above S51-S53 is to monitor lighting fluctuations and adjust the thermal disturbance ratio to achieve dynamic updates of load demand and improve system response sensitivity. Finally, the S61-S63 steps are coordinated to optimize the coordinated operation of equipment. In specific execution, the genetic algorithm optimizes the parameters of multiple equipment, simulates the operation scenario, and finds the equipment coordination scheme with the best energy efficiency.

[0129] In a specific embodiment, the step of extracting key control signals from the obtained adjustment scheme, transmitting them to the central control system, and adjusting the equipment output power in real time to obtain an optimized power consumption configuration specifically includes:

[0130] S71. By extracting control signals from the adjustment scheme and transmitting them to the central system, preliminary equipment adjustment instructions are obtained.

[0131] S72. Based on the preliminary equipment adjustment instructions, analyze the matching between the equipment operating status and output power, and determine the priority order of power adjustment.

[0132] S73. Using a priority order, the output power of the equipment is controlled in layers to obtain a layered power allocation scheme. The layered power allocation scheme is transmitted to the central system in real time for data comparison. If the comparison result shows that the power allocation exceeds the preset threshold range, the relevant equipment is adjusted again to obtain the adjusted power configuration.

[0133] S74. Based on the adjusted power configuration, specific control signals are generated for each device to determine the final instruction set for device operation. According to the final instruction set, the control logic of the central system is updated to obtain an optimized mapping between device operation and power consumption. For this optimized mapping, changes in device operating status are continuously monitored. If an abnormal power distribution is detected, the central system regenerates the control signals to determine the next steps for device adjustment.

[0134] It should be noted that the above technical solution extracts key control signals at any time, adjusts equipment power in layers, and optimizes power consumption through real-time adjustments via a central system.

[0135] Example 2

[0136] See Figure 4 Embodiment 2 of the present invention provides a venue power consumption operation and processing system, including a preprocessing module 10, an input module 20, a separation module 30, a heat transfer calculation module 40, an adjustment module 50, and an output module 60.

[0137] Preprocessing module 10 is used to acquire sensor data inside the venue and data from external weather stations, integrate monitoring values ​​of personnel activity intensity with lighting change records, remove noise through data preprocessing, and obtain a clean real-time input dataset;

[0138] Input module 20 is used to classify the intensity level of human activity and lighting change patterns based on a clean real-time input dataset using a support vector machine algorithm, and to determine the proportion of thermal disturbance contribution in each area;

[0139] The separation module 30 is used to extract the heat exchange part of the building envelope and the fresh air introduction part from the determined heat disturbance contribution ratio. If the heat exchange of the building envelope exceeds the preset threshold, the influence of external meteorological conditions on the total load is separated to obtain an independent fresh air load value.

[0140] The heat transfer calculation module 40 is used to calculate the indoor load components by combining the obtained independent fresh air load values ​​with the indoor inherent heat release data, and to quantify the impact of heat transfer between different areas using a linear regression algorithm to determine the zonal indoor load distribution.

[0141] The adjustment module 50 is used to integrate the influence of lighting change patterns from the determined indoor load distribution of the zones, and if the lighting intensity fluctuation is greater than a preset threshold, adjust the thermal disturbance contribution ratio to obtain a dynamically updated cooling and heating load demand matrix.

[0142] The output module 60 is used to simulate the operation scenario of multiple devices based on the dynamically updated cooling and heating load demand matrix, and to optimize the coordination parameters of the air conditioning and ventilation equipment using a genetic algorithm to obtain an adjustment scheme that matches the actual needs. The key control signals are extracted from the obtained adjustment scheme and transmitted to the central control system to adjust the output power of the equipment in real time to obtain an optimized power consumption configuration.

[0143] In summary, the overall technical solution provided by this invention constructs a complete intelligent closed-loop system from perception and analysis to precise control. Its core lies in achieving refined dynamic management of building thermal environment and energy consumption through deep fusion and intelligent processing of multi-source heterogeneous data. The system first integrates sensor data from inside the venue and information from external weather stations, and merges records of personnel activity intensity and lighting changes. Data preprocessing is performed using Kalman filtering and median filtering algorithms to effectively filter out noise and outliers, providing a high-quality data foundation for subsequent analysis.

[0144] Based on a clean, real-time dataset, the solution employs a support vector machine algorithm to intelligently classify the intensity of human activity and lighting variation patterns, and quantifies the contribution ratio of thermal disturbance in each area. Through innovative load decomposition technology, the total load is accurately separated into three parts: heat exchange within the building envelope, fresh air intake, and internal heat sources. Specifically, when the building envelope load exceeds a preset threshold of 30%, the system automatically triggers a meteorological impact analysis process, using a multiple linear regression model to separate the influence of external meteorological conditions, thereby obtaining an independent and accurate fresh air load value.

[0145] Based on precise load decomposition, the system further integrates indoor inherent heat release data and employs a linear regression algorithm to quantify the heat transfer effect between areas, ultimately determining a refined indoor load distribution by region. The system dynamically responds to changes in key parameters such as lighting intensity; when fluctuations exceed thresholds, it adjusts the contribution ratio of thermal disturbances in real time, forming a dynamically updated cooling and heating load demand matrix. For this demand matrix, the solution uses a genetic algorithm to optimize the collaborative parameters of multiple devices, including air conditioning and ventilation, to balance energy saving and comfort objectives, obtaining the optimal adjustment scheme. Finally, the system translates the optimized scheme into key control commands, enabling hierarchical real-time control of equipment power through a central control system. This achieves end-to-end automation and intelligence from data perception to energy-saving execution, ultimately resulting in a significant energy efficiency improvement while ensuring environmental comfort.

[0146] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for managing the operation and management of electrical energy consumption in a venue, characterized in that, The method includes: Data from internal sensors and external weather stations were acquired, and monitoring values ​​of human activity intensity and lighting changes were integrated. Noise was removed through data preprocessing to obtain a clean real-time input dataset. Based on this clean real-time input dataset, a support vector machine algorithm was used to classify human activity intensity levels and lighting change patterns, determining the proportion of thermal disturbance contribution in each area. From the determined proportions, the heat exchange portion of the building envelope and the fresh air intake portion were extracted. If the heat exchange of the building envelope exceeded a preset threshold, the impact of external weather conditions on the total load was separated, yielding an independent fresh air load value. This independent fresh air load value was then combined with indoor inherent heat release data... The indoor load components are calculated, and the impact of heat transfer between different areas is quantified using a linear regression algorithm to determine the zonal indoor load distribution. The influence of lighting variation patterns is integrated from the determined zonal indoor load distribution. If the lighting intensity fluctuation exceeds a preset threshold, the contribution ratio of thermal disturbance is adjusted to obtain a dynamically updated cooling and heating load demand matrix. Based on the dynamically updated cooling and heating load demand matrix, a multi-device operation scenario is simulated, and a genetic algorithm is used to optimize the coordination parameters of air conditioning and ventilation equipment to obtain an adjustment scheme that matches actual needs. Key control signals are extracted from the obtained adjustment scheme and transmitted to the central control system to adjust the equipment output power in real time, resulting in an optimized power consumption configuration.

2. The method for handling the operation and management of venue power consumption according to claim 1, characterized in that, The process involves acquiring data from internal sensor sensors and external weather stations, fusing monitoring values ​​of personnel activity intensity with lighting change records, and removing noise through data preprocessing to obtain a clean, real-time input dataset, including: The venue collects internal sensor data and personnel activity intensity monitoring values ​​through internal sensors, obtains external meteorological data and lighting change records from external meteorological stations, and merges the personnel activity intensity monitoring values ​​and lighting change records to obtain a preliminary fused dataset. For the aforementioned preliminary fused dataset, the Kalman filter algorithm is used to remove noise through state estimation and prediction updates to obtain a denoised fused dataset; If the denoised fusion dataset contains outliers, the outliers are replaced by the median value of the neighborhood using a median filtering algorithm to obtain the adjusted dataset. Based on the adjusted dataset, venue energy consumption records are integrated to determine the clean real-time input dataset.

3. The method for handling the operation and management of venue power consumption according to claim 1, characterized in that, Based on a clean, real-time input dataset, a support vector machine algorithm is used to classify the intensity levels of human activity and lighting change patterns to determine the proportion of thermal disturbance contribution in each area, including: Based on the clean real-time input dataset, the support vector machine algorithm is used to classify the intensity level of the personnel activities and the lighting change pattern, and a classification result set is obtained; Based on the classification result set, the meteorological influencing factors and energy consumption records are integrated, and the preliminary distribution of thermal disturbances is determined by comparing the meteorological conditions and energy use in different regions. By adjusting the outlier adjustment and noise removal effects based on the initial thermal disturbance distribution, and correcting the data deviation by combining the regional activity intensity differences, an optimized thermal disturbance model is obtained. The optimized thermal disturbance model is obtained, and the matching between the regional classification level and the contribution ratio is determined to obtain the thermal disturbance contribution ratio of each region.

4. The method for handling the operation and management of venue power consumption according to claim 1, characterized in that, The process involves extracting the heat exchange portion and fresh air introduction portion of the building envelope from a determined thermal disturbance contribution ratio, determining if the heat exchange of the building envelope exceeds a preset threshold, and then separating the impact of external meteorological conditions on the total load to obtain an independent fresh air load value, including: From the thermal disturbance ratio data, the specific values ​​of heat exchange and fresh air introduction of the building envelope are obtained. The two are separated by the sub-item extraction technology to obtain independent data of heat exchange of the building envelope and independent data of fresh air introduction. For independent data on heat exchange of the building envelope, if the value exceeds the preset threshold, the analysis process of external meteorological conditions is triggered. The corresponding external meteorological parameters are obtained by calling the meteorological data interface to determine the degree of influence of external meteorology on heat exchange of the building envelope. Based on the degree of influence of external meteorological parameters, the portion of the total load value caused by external meteorological factors is separated, and the total load value is decomposed using a regression analysis algorithm to obtain the remaining load data after removing the effects of external meteorological factors; From the remaining load data, the load portion related to fresh air introduction is extracted. Through data matching technology, the independent data of fresh air introduction is correlated with the remaining load data to determine the specific value of the fresh air load. Based on the specific values ​​of the fresh air load and the distribution of its contribution ratio, we analyze the actual proportion of fresh air introduced into the total load and obtain independent calculation results for the fresh air load. Based on the independent calculation results of the fresh air load, the accuracy of the load separation is verified. By comparing the contribution ratio with the data after separation, the final fresh air load value is determined. Starting from the final fresh air load value, a corresponding load distribution record is generated. Data storage technology is used to archive the heat exchange volume of the building envelope, the fresh air load value, and external meteorological parameters to obtain a complete load analysis dataset.

5. The method for handling the operation and management of venue power consumption according to claim 1, characterized in that, The process involves combining the obtained independent fresh air load values ​​with indoor inherent heat release data to calculate indoor load components. A linear regression algorithm is then used to quantify the impact of heat transfer between different areas, determining the zonal indoor load distribution, including: Obtain independent fresh air load values ​​and indoor inherent heat release data for each area; By matching data, the independent fresh air load values ​​are allocated to the corresponding areas to obtain the initial load components of each area; For the initial load component of each region, a linear regression algorithm is used to calculate the heat transfer coefficient between adjacent regions; Adjust the load components of each region according to the heat transfer coefficient to obtain the corrected load value after taking into account the heat exchange between regions. If the load difference between adjacent areas exceeds the preset range, the indoor inherent heat release data of the corresponding area will be re-extracted for matching and correction. By adjusting load values ​​and summarizing data from all regions, the complete distribution of indoor load in each zone can be determined. By linking the indoor load distribution of each zone with the building's spatial layout information, a record of the load percentage for each zone is generated.

6. The method for handling the operation and management of venue power consumption according to claim 1, characterized in that, The process of integrating the influence of lighting variation patterns from the determined indoor load distribution of different zones, and determining whether the lighting intensity fluctuation exceeds a preset threshold, adjusts the thermal disturbance contribution ratio to obtain a dynamically updated cooling and heating load demand matrix, includes: Obtain the hourly sequence of lighting power in each area from the zonal indoor load distribution data; By performing time-series differential calculations on the lighting power of each region, a sequence of changes in lighting intensity amplitude is obtained. Determine whether the maximum value in the sequence of changes in lighting intensity is greater than a preset threshold. If it is, mark the region as a high fluctuation region. Obtain the proportion of lighting thermal disturbance at the corresponding moment from the high fluctuation region; The adjusted regional load component is obtained by multiplying the proportion of lighting thermal disturbance by the original regional heating and cooling load components. The load components of all area lighting after adjustment are organized in matrix form to obtain the area load correction matrix; By performing row vector summation and column vector summation operations on the regional load correction matrix, the total distribution of cooling and heating loads for the entire floor and the cooling and heating load demand matrix for each zone are determined.

7. The method for handling the operation and management of venue power consumption according to claim 1, characterized in that, The process involves simulating multi-device operation scenarios based on a dynamically updated cooling and heating load demand matrix, and using a genetic algorithm to optimize the coordination parameters of air conditioning and ventilation equipment to obtain an adjustment scheme that matches actual needs. This includes: By extracting load data for each region from the dynamically updated heating and cooling load demand matrix, an initial model of multi-device operation scenarios is constructed to obtain the load distribution of each region at different times. Based on the load distribution, analyze the operating status of air conditioning and ventilation equipment in the multi-equipment group, and determine the preliminary parameter configuration of each equipment in the current scenario. A genetic algorithm is used to iteratively optimize the initial parameter configuration, adjust the collaborative parameters, and obtain the optimized combination of equipment operating parameters. For the optimized combination of equipment operating parameters, the performance of multiple equipment groups in the operating scenario is simulated. If the operating parameters of a certain equipment exceed the preset threshold range, the parameters of that equipment are fine-tuned to obtain the adjusted parameter set. By adjusting the parameter set, specific adjustment schemes are generated for air conditioning and ventilation equipment, and the operating modes of each device at different times are determined. Based on the generated adjustment scheme, the operating status of the equipment in the actual scenario is mapped to obtain the final equipment collaborative control command.

8. The method for handling the operation and management of electrical energy consumption in venues according to claim 1, characterized in that, The process of extracting key control signals from the obtained adjustment scheme, transmitting them to the central control system, and adjusting the equipment output power in real time to obtain an optimized power consumption configuration includes: By extracting control signals from the adjustment scheme and transmitting them to the central system, preliminary equipment adjustment instructions are obtained; Based on the initial equipment adjustment instructions, analyze the matching between the equipment operating status and output power to determine the priority order of power adjustment; By adopting a priority order, the output power of the equipment is controlled in layers to obtain a layered power allocation scheme; For the tiered power allocation scheme, the data is transmitted to the central system in real time for comparison. If the comparison result shows that the power allocation exceeds the preset threshold range, the relevant devices are adjusted for secondary allocation to obtain the adjusted power configuration. By adjusting the power configuration, specific control signals are generated for each device, and the final instruction set for device operation is determined. Based on the final instruction set, the control logic of the central system is updated to obtain an optimized mapping between equipment operation and power consumption; For optimized mapping, the system continuously monitors changes in equipment operating status. If an abnormal power distribution is detected, the control signal is regenerated through the central system to determine the next steps for equipment adjustment.

9. A venue power consumption operation and processing system, characterized in that, It includes a preprocessing module, an input module, a separation module, a heat transfer calculation module, an adjustment module, and an output module. The preprocessing module is used to acquire sensor data inside the venue and data from external weather stations, integrate monitoring values ​​of personnel activity intensity with lighting change records, remove noise through data preprocessing, and obtain a clean real-time input dataset; The input module is used to classify the intensity level of human activity and lighting change patterns based on a clean real-time input dataset using a support vector machine algorithm, and determine the proportion of thermal disturbance contribution in each area; the separation module is used to extract the heat exchange part of the building envelope and the fresh air introduction part from the determined proportion of thermal disturbance contribution, and if the heat exchange of the building envelope exceeds a preset threshold, the influence of external meteorological conditions on the total load is separated to obtain an independent fresh air load value. The heat transfer calculation module is used to calculate indoor load components by combining the obtained independent fresh air load values ​​with indoor inherent heat release data, and uses a linear regression algorithm to quantify the impact of heat transfer between different areas to determine the zonal indoor load distribution; the adjustment module is used to integrate the impact of lighting change patterns from the determined zonal indoor load distribution, and if the lighting intensity fluctuation is greater than a preset threshold, adjust the heat disturbance contribution ratio to obtain a dynamically updated cooling and heating load demand matrix. The output module is used to simulate the operation of multiple devices based on the dynamically updated cooling and heating load demand matrix, and to optimize the coordination parameters of air conditioning and ventilation equipment using a genetic algorithm to obtain an adjustment scheme that matches the actual demand. Key control signals are extracted from the obtained adjustment scheme and transmitted to the central control system to adjust the equipment output power in real time, thereby obtaining an optimized power consumption configuration.

Images