Building power utilization energy-saving method and system based on big data

Abstract

The invention discloses a building power utilization energy saving method and system based on big data, and relates to the technical field of data analysis, and the method comprises the steps: determining the use intensity of each power utilization device according to operation data, setting an energy consumption baseline of each region through power utilization data and the use intensity, analyzing the power utilization data, and setting a dynamic energy consumption baseline of each region, a high-energy-consumption area is screened out, a reliable basis is provided for an energy-saving strategy of a subsequent high-energy-consumption area, multi-objective optimization is performed on general equipment and special equipment in combination with the people flow change condition, the influence of the people flow change condition on the comfort requirement of the high-energy-consumption area is considered, the energy-saving strategy of the general equipment is determined, and the performance life condition of the equipment is considered. And the energy-saving strategy of the special equipment is determined, so that the accuracy and adaptability of building power utilization and energy saving are improved. And the energy-saving strategy is adjusted based on the energy-saving effect index, so that the energy-saving strategy is fed back and adjusted, and the balance between the power utilization demand of the building and energy conservation is considered.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a building electricity energy-saving method and system based on big data. Background Art

[0002] Against the backdrop of the "dual carbon" goals, buildings, as a major source of urban energy consumption, face an increasingly prominent challenge in energy conservation. Traditional building energy management methods suffer from low efficiency, inaccurate monitoring, and a lack of intelligence, making them unable to meet the energy conservation needs of modern buildings. With the rapid development of technologies such as big data, the Internet of Things, and cloud computing, big data-based building energy conservation solutions have emerged. This solution utilizes smart sensors and smart meters within buildings to collect real-time data on energy consumption, environmental conditions, and user behavior. This data is then deeply analyzed using big data analytics. These technologies can accurately identify areas of energy waste, predict energy consumption trends, and develop targeted energy conservation strategies. Furthermore, intelligent control systems enable real-time regulation of building equipment, enabling efficient energy utilization and refined management, providing strong support for building energy conservation.

[0003] In the existing technology, building electricity energy-saving strategies are often set in advance and remain unchanged. However, fixed energy-saving strategies are difficult to meet the changing needs of building electricity consumption, resulting in poor accuracy and adaptability of building electricity energy-saving strategies, and unable to take into account the balance between building electricity demand and energy conservation.

[0004] Therefore, how to improve the accuracy and adaptability of building electricity energy saving is a technical problem that needs to be solved. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem of poor accuracy and adaptability of building electricity energy saving in the prior art, and to propose a building electricity energy saving method based on big data, which includes: Obtain a geographic map of the interior of the building, divide the geographic map into regions according to regional categories, mark the electrical equipment in each region, and determine the functional area of ​​each electrical equipment; Collect the power consumption and operation data of each electrical device over a period of time, determine the usage intensity of each electrical device based on the operation data, set the energy consumption baseline for each area based on the power consumption data and usage intensity, and filter out high energy consumption areas according to the energy consumption baseline; Electricity-consuming equipment is divided into two categories: general-purpose equipment and special-purpose equipment according to their areas of use. The flow of people in high-energy-consuming areas is analyzed, and multi-objective optimization is performed based on the flow of people. Energy-saving strategies for general-purpose and special-purpose equipment are formulated. Energy-saving strategies are used to save electricity for general and special equipment, energy-saving effect indicators are defined during the energy-saving process, and energy-saving strategies are adjusted based on the energy-saving effect indicators.

[0006] In some embodiments of the present application, determining the active area of ​​each electrical device includes: Confirm the installation location of each electrical device, analyze the coverage characteristics of the functions of each electrical device and the layout structure of the area where the installation location is located, so as to determine the effective area of ​​​​each electrical device, and mark the effective area of ​​​​each electrical device at the corresponding position on the internal geographical map of the building.

[0007] In some embodiments of the present application, the usage intensity of each electrical device is determined based on the operating data, including: Operation data includes the operating time, average load rate and usage frequency of electrical equipment; Counting the average running time in the first preset period, determining the second period based on the average running time, and counting the average load rate, load rate standard deviation, and average usage frequency in the second period; The usage intensity of each electric device is determined based on the second cycle length, the average load rate, the load rate standard deviation, and the average usage frequency.

[0008] In some embodiments of the present application, the energy consumption baseline of each area is set by using electricity usage data and usage intensity, including: Integrate the electrical equipment in each area according to the installation location and the area of ​​use of the electrical equipment to obtain a regional electrical equipment set; The usage intensity of all electrical equipment in each area is counted according to the regional electrical equipment set, and the usage intensity of all electrical equipment is integrated to obtain the comprehensive usage intensity. A comprehensive usage intensity curve that changes over time is constructed, and multiple time periods are divided according to the comprehensive usage intensity on the comprehensive usage intensity curve; Calculate the time period coefficient for each time period and assign a functional coefficient to the regional type; Construct a time-varying electricity consumption curve, split the curve by time period, and obtain the corresponding relationship between time period and electricity consumption curve segment; The electricity consumption curve segment is evenly split to obtain multiple electricity consumption curve segments. The slope change and average value of each electricity consumption curve segment are calculated. The proportion of the electricity consumption curve segment is assigned based on the slope change. The benchmark energy consumption of the electricity consumption curve segment is set based on the proportion and average value of each electricity consumption curve segment under the electricity consumption curve segment. Set the energy consumption baseline for each time period based on the baseline energy consumption, time period factor and function factor.

[0009] In some embodiments of the present application, high energy consumption areas are screened out according to the energy consumption baseline, including: Taking time periods as units, compare the actual energy consumption of each period in each area with the energy consumption deviation value of the energy consumption baseline, integrate the energy consumption deviation values ​​of all periods to obtain the comprehensive energy consumption deviation value, and use the comprehensive energy consumption deviation value to screen out high-energy consumption areas.

[0010] In some embodiments of the present application, analyzing the changes in the flow of people in high energy consumption areas includes: Identify the areas adjacent to high energy consumption areas and calculate the connectivity between high energy consumption areas and their adjacent areas; Collect real-time multi-source data of pedestrian flow in the area, establish a pedestrian flow prediction model based on the real-time multi-source data of pedestrian flow and the connectivity between high-energy consumption areas and their adjacent areas, and analyze the changes in pedestrian flow through the pedestrian flow prediction model.

[0011] In some embodiments of the present application, multi-objective optimization is performed on general equipment and special equipment in combination with changes in passenger flow, and energy-saving strategies for general equipment and special equipment are formulated, including: The multi-objectives of general equipment include energy saving and comfort, while the multi-objectives of special equipment include energy saving and equipment life; Set comfort constraints based on the crowd flow prediction model, use the comfort constraints to perform multi-objective optimization of general equipment, and use the optimized control parameters of general equipment as the energy-saving strategy for general equipment; The equipment life constraint conditions are set according to the performance life of the special equipment, and the multi-objective optimization of the special equipment is performed through the equipment life constraint conditions. The control parameters of the optimized special equipment are used as the energy-saving strategy of the special equipment.

[0012] In some embodiments of the present application, energy-saving effect indicators in the energy-saving process are defined, including: The direct energy-saving effect description parameters and indirect energy-saving effect description parameters of general equipment and special equipment are collected respectively, and the energy-saving effect indicators of general equipment and special equipment are defined respectively by combining the direct energy-saving effect description parameters and the indirect energy-saving effect description parameters.

[0013] Correspondingly, this application also provides a building electricity energy-saving system based on big data, including: The first module is used to obtain a geographical map of the interior of the building, divide the geographical map into regions according to regional categories, mark the electrical equipment in each region, and determine the functional area of ​​each electrical equipment; The second module is used to collect the power consumption and operation data of each electrical device over a period of time, determine the usage intensity of each electrical device based on the operation data, set the energy consumption baseline for each area based on the power consumption data and usage intensity, and filter out high-energy consumption areas according to the energy consumption baseline; The third module is used to classify electrical equipment into general-purpose equipment and special-purpose equipment based on their areas of use. It analyzes changes in passenger flow in high-energy-consuming areas, conducts multi-objective optimization based on passenger flow changes, and develops energy-saving strategies for general-purpose and special-purpose equipment. The fourth module is used to save electricity for general equipment and special equipment through energy-saving strategies, define energy-saving effect indicators during the energy-saving process, and adjust energy-saving strategies based on the energy-saving effect indicators.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. Determine the usage intensity of each electrical device based on operating data, set the energy consumption baseline for each area based on the power consumption data and usage intensity, divide the time period into time periods based on the usage intensity of the electrical devices, and analyze the power consumption data to set the dynamic energy consumption baseline for each area based on time periods. Ensure the rationality of the baseline setting, screen out high energy consumption areas, and provide a reliable foundation for subsequent energy-saving strategies in high energy consumption areas. 2. Multi-objective optimization of general and specialized equipment is conducted based on changes in passenger flow. Energy-saving strategies for general equipment are determined based on the impact of passenger flow changes on comfort requirements in high-energy-consuming areas. Energy-saving strategies for specialized equipment are determined based on equipment performance and lifespan, improving the accuracy and adaptability of building electricity conservation. Energy-saving strategies are adjusted based on energy-saving effect indicators, which are defined to reflect the pros and cons of energy-saving strategies. This feedback is then used to adjust energy-saving strategies, balancing building electricity demand and energy conservation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a building electricity energy-saving method based on big data proposed by the present invention; Figure 2 This is a structural diagram of a building electricity energy-saving system based on big data proposed by the present invention. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0017] Reference Figure 1 , a building electricity energy-saving method based on big data, comprising the following steps: Step S101 : obtaining a geographical map of the interior of the building, dividing the geographical map into regions according to region categories, marking the electrical equipment in each region, and determining the functional area of ​​each electrical equipment.

[0018] In this embodiment, a building internal geographic map is obtained using building design drawings, BIM models, or on-site surveying. The building is divided into functional areas such as office areas, conference rooms, computer rooms, and corridors. The installation location of each electrical device (such as air conditioners, lighting fixtures, computers, and medical equipment) is determined. The functional coverage characteristics (such as the cooling and heating range of air conditioners and the lighting range of lighting fixtures) and the layout structure of the area in which the installation location is located are analyzed. The functional areas are determined and marked on the corresponding locations on the geographic map.

[0019] In some embodiments of the present application, determining the active area of ​​each electrical device includes: Confirm the installation location of each electrical device, analyze the coverage characteristics of the functions of each electrical device and the layout structure of the area where the installation location is located, so as to determine the effective area of ​​​​each electrical device, and mark the effective area of ​​​​each electrical device at the corresponding position on the internal geographical map of the building.

[0020] In this embodiment, design drawings: Obtain the original building design drawings, including electrical design drawings and floor plans. These drawings will detail the preliminary planned installation locations of various electrical equipment, such as the distribution points of lighting fixtures on the ceiling and the fixed locations of distribution boxes on the walls. Establish a database of electrical equipment installation locations, recording each device's name, model, serial number, and its specific coordinates within the building (e.g., using a corner of the building as the origin and recording the device's position on the X, Y, and Z axes) or relative location descriptions (e.g., located in the northwest corner of a room on a certain floor). Consult the equipment's technical manuals and product specifications to understand its operating principles and functional scope. For example, for air conditioning equipment, understand its cooling and heating capacity (in BTU or kilowatts), air supply distance, and angle range. For lighting fixtures, understand its beam angle and illumination range. For equipment whose functions can be analyzed using simulation software, such as air conditioning systems, use professional HVAC simulation software (such as EnergyPlus or TRNSYS) to input device parameters and building space information to simulate the device's functional coverage under different operating conditions. For equipment whose performance cannot be accurately determined through simulation, conduct actual testing. For example, after installing a lighting fixture, use a illuminance meter to measure illuminance at different locations and plot an illuminance distribution diagram to determine its functional coverage area. Measure the length, width, and height of the installation area, and record the distribution of obstacles (such as pillars and partitions). For example, in an office area, record the location and dimensions of pillars, as they may affect the airflow of the air conditioner or the illuminance distribution of the lighting fixture. Analyze the shape and openness of the area, such as whether it is a regular rectangle or an irregular polygon, and whether it is an open space or a closed space with partitions. Areas of different shapes and openness have different impacts on the functional coverage of the equipment. Combine the functional coverage characteristics of the equipment with the layout structure of the installation area. For example, for air conditioners, determine the area where it can effectively cool or heat by combining its airflow distance and angle range with the area's spatial dimensions and obstacle distribution. For lighting fixtures, determine the area where it can provide adequate lighting by combining its beam angle and illuminance range with the area's human activity zone. Based on this comprehensive analysis, determine the boundaries of the electrical equipment's functional area. Boundaries can be described using clear geometric shapes (such as circles and rectangles), or irregular ones can be used depending on the actual situation. At the same time, the relationship between the boundary and surrounding reference objects should be recorded for subsequent marking and verification.

[0021] Step S102: Collect the power consumption data and operation data of each power-consuming device over a period of time, determine the usage intensity of each power-consuming device based on the operation data, set the energy consumption baseline of each area based on the power consumption data and usage intensity, and filter out high-energy consumption areas according to the energy consumption baseline.

[0022] In this embodiment, data collection involves installing sensors on each electrical device to collect electricity usage data (e.g., electricity consumption, power consumption, etc.) and operational data (e.g., operating hours, average load rate, and frequency of use) over a period of time (e.g., one month). Usage intensity describes the usage of each electrical device. This data is combined to establish a dynamic energy consumption baseline for each area, facilitating the identification of high-energy-consuming areas.

[0023] In some embodiments of the present application, the usage intensity of each electrical device is determined based on the operating data, including: Operation data includes the operating time, average load rate and usage frequency of electrical equipment; Counting the average running time in the first preset period, determining the second period based on the average running time, and counting the average load rate, load rate standard deviation, and average usage frequency in the second period; The usage intensity of each electric device is determined based on the second cycle length, the average load rate, the load rate standard deviation, and the average usage frequency.

[0024] In this embodiment, the average operating time within the first preset period describes the daily status of the device's operating time. The average operating time is used as the second period, and the average load rate, load rate standard deviation, and average usage frequency within the second period are calculated. The first preset period can be one week, and the second period can be five hours (the average operating time of the device within a week). The usage intensity of each electrical device is determined based on the length of the second period (time length), the average load rate (device operation status), the load rate standard deviation (device stability), and the average usage frequency (device usage). These factors jointly determine the device's usage intensity. The second period length and average usage frequency reflect the usage intensity from the time dimension, while the average load rate and load rate standard deviation reflect the usage intensity from the device operation dimension. The usage intensity of the electrical device is determined by combining these two dimensions.

[0025] In some embodiments of the present application, the energy consumption baseline of each area is set by using electricity usage data and usage intensity, including: Integrate the electrical equipment in each area according to the installation location and the area of ​​use of the electrical equipment to obtain a regional electrical equipment set; The usage intensity of all electrical equipment in each area is counted according to the regional electrical equipment set, and the usage intensity of all electrical equipment is integrated to obtain the comprehensive usage intensity. A comprehensive usage intensity curve that changes over time is constructed, and multiple time periods are divided according to the comprehensive usage intensity on the comprehensive usage intensity curve; Calculate the time period coefficient for each time period and assign a functional coefficient to the regional type; Construct a time-varying electricity consumption curve, split the curve by time period, and obtain the corresponding relationship between time period and electricity consumption curve segment; The electricity consumption curve segment is evenly split to obtain multiple electricity consumption curve segments. The slope change and average value of each electricity consumption curve segment are calculated. The proportion of the electricity consumption curve segment is assigned based on the slope change. The benchmark energy consumption of the electricity consumption curve segment is set based on the proportion and average value of each electricity consumption curve segment under the electricity consumption curve segment. Set the energy consumption baseline for each time period based on the baseline energy consumption, time period factor and function factor.

[0026] In this embodiment, equipment grouping: all electrical equipment in the same area are grouped according to the installation location and area of ​​use of the electrical equipment. For example, in an office building, the air conditioners, lighting fixtures, projectors and other equipment in the conference room are classified as the regional electrical equipment set in the conference room area. Data recording: A regional electrical equipment list is established to record the name, type, quantity, installation location and other information of the equipment in each area to ensure that the correspondence between the equipment and the area is accurate. The usage intensity of all electrical equipment in each area is weighted averaged or summed to obtain the comprehensive usage intensity of the area. For example, the comprehensive usage intensity of the conference room area = air conditioner usage intensity × weight + lighting fixture usage intensity × weight + projector usage intensity × weight. With time as the horizontal axis and comprehensive usage intensity as the vertical axis, a curve of comprehensive usage intensity changing over time is drawn. For example, the horizontal axis is the hour of the day, and the vertical axis is the comprehensive usage intensity value of the conference room area per hour.

[0027] Based on the changing trends of the comprehensive usage intensity curve, a day or week is divided into multiple time periods. For example, the comprehensive usage intensity curve for a conference room area can be divided into weekday daytime (9:00-18:00), weekday evening (18:00-22:00), and weekend (all day). For each time period, a time period coefficient is calculated, which reflects the ratio of the area's usage intensity relative to the average usage intensity during that period. For example, a weekday daytime coefficient of 1.2 indicates that the usage intensity during that period is 1.2 times the average. Different function coefficients are assigned to areas based on their functional type (such as office area, conference room area, computer room area, etc.). The function coefficient reflects the area's importance and energy consumption requirements. For example, the function coefficient for a conference room area is 1.1 because conference rooms require higher energy consumption to meet meeting needs; the function coefficient for a computer room area is 1.3 because the equipment in the computer room needs to run continuously to ensure server stability. Electricity usage data (such as power consumption and power consumption) is collected for each area. A time-varying electricity usage curve is constructed, with time as the horizontal axis and electricity usage data as the vertical axis. For example, the hourly electricity consumption of the conference room area forms an electricity consumption data curve. Based on the previously defined time periods, the electricity consumption data curve is split into multiple time period-segment relationships. For example, the electricity consumption data curve for the conference room area is split into weekday daytime, weekday evening, and weekend segments.

[0028] Evenly split each electricity consumption curve segment into multiple energy consumption curve segments. For example, split the weekday daytime electricity consumption curve segment into energy consumption curve segments every 30 minutes. Calculate the slope change and average value for each energy consumption curve segment. The slope change reflects the changing trend of electricity consumption, while the average value reflects the average level of electricity consumption. Assign a percentage to the energy consumption curve segment based on the slope change; for example, a higher percentage is assigned to an energy consumption curve segment with a steeper slope. Calculate the baseline energy consumption for each energy consumption curve segment based on its percentage and average value. For example, baseline energy consumption = Σ(energy consumption curve segment average value × percentage).

[0029] The energy consumption baseline for each time period is set based on the baseline energy consumption, time period coefficient, and function coefficient. The calculation formula is as follows: ; in, For the Region The energy consumption baseline value for each period of time, For the Region The baseline energy consumption in each period is For the Region The period coefficient under each period, For the Function coefficient of the area.

[0030] In some embodiments of the present application, high energy consumption areas are screened out according to the energy consumption baseline, including: Taking time periods as units, compare the actual energy consumption of each period in each area with the energy consumption deviation value of the energy consumption baseline, integrate the energy consumption deviation values ​​of all periods to obtain the comprehensive energy consumption deviation value, and use the comprehensive energy consumption deviation value to screen out high-energy consumption areas.

[0031] In this embodiment, actual energy consumption data: collects actual energy consumption data of each area in each time period. For example, the actual energy consumption of the conference room area during the period of 9:00-12:00 is 18 kWh.

[0032] Energy consumption baseline data: Obtain the pre-calculated energy consumption baseline for each area in each time period. For example, the energy consumption baseline of the conference room area from 9:00 to 12:00 is 9 kWh / hour. Assuming that this period is 3 hours, the total energy consumption baseline is 27 kWh. Deviation value formula: Energy consumption deviation value = actual energy consumption - energy consumption baseline. For example, the actual energy consumption of the conference room area from 9:00 to 12:00 is 18 kWh, and the energy consumption baseline is 27 kWh. The energy consumption deviation value is 18-27=-9 kWh. The energy consumption deviation value can be positive or negative to facilitate subsequent calculations. The calculation formula for the comprehensive energy consumption deviation value is as follows: ; in, For the The comprehensive energy consumption deviation value in each region is: For the The number of time periods under each region, For the The deviation weight of each period, For the Region The energy consumption deviation value in each period is: and They are The maximum and minimum values ​​in For the The first constant under the region, Represents the average of the maximum and minimum values ​​versus the class average ( , slightly larger than the average value), the first constant exists to balance the size of the correction function.

[0033] Step S103, classify the electrical equipment into two categories: general equipment and special equipment according to their functional areas, analyze the changes in passenger flow in high-energy consumption areas, perform multi-objective optimization on general equipment and special equipment based on the changes in passenger flow, and formulate energy-saving strategies for general equipment and special equipment.

[0034] In this embodiment, general-purpose equipment refers to equipment that can be used in multiple areas or scenarios, and its functionality is relatively universal (affected by traffic flow). For example, lighting fixtures in public areas within a building and ventilation equipment in corridors are not limited to specific functional areas and support the basic operation of the building. Specialized equipment refers to equipment designed specifically for a specific area or function, and its use is closely tied to that specific scenario (rarely affected by traffic flow). For example, projectors and audio equipment in conference rooms and server cooling equipment in computer rooms play a critical role only in specific areas. Sensor Installation: Install traffic sensors, such as infrared sensors and cameras, in high-energy consumption areas (such as the office areas and computer rooms identified above). Infrared sensors can detect the entry and exit of people in real time, while cameras can use image recognition technology to more accurately count the number of people and their movement direction. Data Recording Period: Set a reasonable data recording period, such as hourly, continuously recording traffic data for a week or a month to capture comprehensive patterns of traffic flow.

[0035] In some embodiments of the present application, analyzing the changes in the flow of people in high energy consumption areas includes: Identify the areas adjacent to high energy consumption areas and calculate the connectivity between high energy consumption areas and their adjacent areas; Collect real-time multi-source data of pedestrian flow in the area, establish a pedestrian flow prediction model based on the real-time multi-source data of pedestrian flow and the connectivity between high-energy consumption areas and their adjacent areas, and analyze the changes in pedestrian flow through the pedestrian flow prediction model.

[0036] In this embodiment, the adjacent area is determined as follows: Spatial proximity principle: Based on the physical layout of the building or area, areas adjacent to high-energy-consuming areas are identified as adjacent areas. For example, in a large office building, if the high-energy-consuming area is an office area on a certain floor, then corridors, rest areas, pantries, and other areas directly connected to the office area on the same floor can be considered adjacent areas.

[0037] Functional Relevance Principle: In addition to spatial proximity, functional relevance can also be considered. For example, a high-energy-consuming conference room might be adjacent to a preparation room, equipment storage room, or other functionally related areas. Even if these areas are not physically adjacent, they can be considered adjacent areas due to their close functional connection.

[0038] Connectivity statistics Channel count: Count the number of channels between high-energy consumption areas and each adjacent area. For example, there are two primary channels and one secondary channel between a high-energy consumption office area and an adjacent corridor.

[0039] Channel Type and Capacity: Record the channel type (e.g., stairs, elevators, escalators, swing door channels, etc.) and capacity. Different channel types have different capacities. Elevators generally have higher capacities than stairs, while escalators have higher efficiency in certain directions.

[0040] Hours and restrictions: Find out the opening hours of a lane and any restrictions. For example, some lanes may be open during the day on weekdays but may be closed or have restricted access at night or on weekends.

[0041] Sensor data: Infrared sensors: Installed in passageways, entrances, and exits, they detect people entering and exiting in real time, recording the number of people passing through and the time they passed. For example, infrared sensors can be installed in passageways between office areas and corridors, recording the number of people passing through every minute.

[0042] Cameras: Use image recognition technology to count the number of people in an area, their movement direction, and speed. Cameras can be installed on the ceiling or in corners of public areas to provide wide coverage.

[0043] Wi-Fi probe data: Leveraging the building's Wi-Fi network, Wi-Fi probe devices collect location information from connected mobile devices (such as phones and tablets) to indirectly infer personnel movements. Set a reasonable data collection frequency, for example, collecting sensor data every minute. Camera data can be analyzed and counted in real time or at regular intervals (such as every five minutes). Ensure that data collected from different data sources is synchronized to facilitate subsequent comprehensive analysis and modeling.

[0044] Machine learning-based models: You can choose regression models (such as linear regression and polynomial regression), time series models (such as ARIMA models), and neural network models (such as recurrent neural networks (RNNs) and long short-term memory (LSTMs). For example, LSTM models are suitable for processing pedestrian flow data with time series characteristics and can capture long-term dependencies in the data. Feature selection: Real-time multi-source data on pedestrian flow and connectivity information between high-energy consumption areas and adjacent areas are collected as input features for the model. For example, input features may include the number of people passing through each channel at each moment, the number of people in each area, and the channel's capacity.

[0045] It can be understood that the flow prediction model mainly predicts the flow of people or the inflow of people near high energy consumption areas.

[0046] In some embodiments of the present application, multi-objective optimization is performed on general equipment and special equipment in combination with changes in passenger flow, and energy-saving strategies for general equipment and special equipment are formulated, including: The multi-objectives of general equipment include energy saving and comfort, while the multi-objectives of special equipment include energy saving and equipment life; Set comfort constraints based on the crowd flow prediction model, use the comfort constraints to perform multi-objective optimization of general equipment, and use the optimized control parameters of general equipment as the energy-saving strategy for general equipment; The equipment life constraint conditions are set according to the performance life of the special equipment, and the multi-objective optimization of the special equipment is performed through the equipment life constraint conditions. The control parameters of the optimized special equipment are used as the energy-saving strategy of the special equipment.

[0047] In this embodiment, the scope of equipment includes general equipment such as lighting systems and ventilation and air conditioning systems in public areas of a building. Their scope of operation is not limited to specific functional areas. Multi-objective setting: Energy conservation and comfort are two key objectives for general equipment optimization. Energy conservation aims to reduce equipment energy consumption and operating costs; comfort is related to the user experience within the area, such as maintaining a suitable temperature and light intensity. Lighting comfort: Based on the pedestrian flow prediction model, the distribution of people in each area at different times is determined. For example, in an office building corridor, if heavy traffic is predicted between 9:00 and 11:00 a.m., sufficient light intensity must be ensured, generally no less than 200 lx, to meet normal pedestrian and safety needs. During lunch break (12:00-1:00 p.m.), when traffic decreases, the light intensity can be appropriately reduced to 100-150 lx, ensuring basic lighting while saving energy. Temperature comfort: For the air conditioning system in the office area, based on traffic forecasts, the temperature is set at 24-26°C during peak hours (such as 9:00-12:00 a.m. and 2:00-5:00 p.m. on weekdays) to ensure comfortable working conditions. During less-populated hours (such as after work or on weekends), the temperature can be appropriately raised to 28-30°C to reduce air conditioning energy consumption. Multi-objective optimization algorithms, such as genetic algorithms and particle swarm optimization, are employed. With energy conservation and comfort as optimization goals, comfort constraints are incorporated into the optimization model. For example, in a genetic algorithm, individuals that meet light and temperature comfort constraints are considered feasible solutions. Through continuous iteration, the algorithm searches for the control parameter combination that minimizes energy consumption while maintaining comfort.

[0048] Energy-saving strategies for general equipment: Lighting system: Based on optimized control parameters, an intelligent lighting control system is installed to automatically adjust light intensity. For example, dimmable LED lamps are installed in corridors, and sensors and controllers automatically adjust the lamp brightness based on traffic flow and light intensity.

[0049] Ventilation and air conditioning system: Utilizing variable frequency technology, the fan and pump speeds are dynamically adjusted based on crowd forecasts and temperature comfort requirements. For example, fan speeds are increased during busy hours to increase ventilation, while speeds are reduced during less busy hours to reduce energy consumption.

[0050] Energy-saving strategies for specialized equipment: Equipment range: Special equipment such as projectors and audio equipment in conference rooms, server cooling equipment in computer rooms, etc., with specific usage scenarios and functions.

[0051] Multi-objective setting: Energy conservation and equipment lifespan are key priorities for specialized equipment optimization. Energy conservation reduces equipment operating costs, while extending equipment lifespan reduces equipment replacement frequency and maintenance costs.

[0052] Device Runtime: For devices like projectors, set a maximum daily run time based on their performance and lifespan. For example, a projector bulb typically has a lifespan of 2,000-3,000 hours. Using it for more than four hours per day may accelerate bulb aging and shorten the device's lifespan. Therefore, set the projector run time to no more than three hours per day.

[0053] Equipment load: For server cooling equipment in the computer room, set a reasonable load range based on the server load and the equipment's design parameters. For example, if the server cooling equipment's rated load is 80%, when the server load is low, appropriately reduce the cooling equipment's operating power to avoid prolonged high loads and extend equipment life.

[0054] Optimization Method: A multi-objective optimization algorithm is also used, with energy conservation and equipment lifespan as optimization objectives. Equipment lifespan constraints are incorporated into the optimization model. For example, in a particle swarm optimization algorithm, equipment energy consumption and lifespan are used as fitness functions. By continuously updating the positions and velocities of particles, the algorithm seeks the control parameters that minimize energy consumption while satisfying equipment lifespan constraints.

[0055] Step S104: saving electric energy for general equipment and special equipment through energy-saving strategies, defining energy-saving effect indicators during the energy-saving process, and adjusting the energy-saving strategies based on the energy-saving effect indicators.

[0056] In some embodiments of the present application, energy-saving effect indicators in the energy-saving process are defined, including: The direct energy-saving effect description parameters and indirect energy-saving effect description parameters of general equipment and special equipment are collected respectively, and the energy-saving effect indicators of general equipment and special equipment are defined respectively by combining the direct energy-saving effect description parameters and the indirect energy-saving effect description parameters.

[0057] In this embodiment, the direct energy-saving effect description parameters of general equipment include energy consumption changes, power changes, etc., and the indirect energy-saving effect description parameters include personnel comfort feedback, environmental parameter compliance rate (the proportion of time that meets the set environmental parameter standards to the total monitoring time. For example, if the temperature of the air-conditioning service area is set between 22-26°C, and the compliance time is 90% of the total monitoring time, then the environmental parameter compliance rate is 90%), etc. The direct energy-saving effect description parameters of special equipment include business energy consumption, standby energy consumption, etc., and the indirect energy-saving effect description parameters include equipment performance, equipment life, equipment failure conditions, etc. The direct energy-saving effect description parameters and the indirect energy-saving effect description parameters are standardized, and the energy-saving effect index calculation formulas for general equipment and special equipment are as follows: ; in, For the Energy-saving effect indicators of general equipment or special equipment, 、 2 are the number of direct energy-saving effect description parameters and indirect energy-saving effect description parameters, 、 Respectively The direct energy saving effect description parameter and The combined weight of the indirect energy saving effect description parameters, 、 Respectively The first The direct energy saving effect description parameter and Indirect energy saving effect description parameter, For the The second constant of a general or special device, It represents the correction of the average value of the indirect energy-saving effect description parameter to the average value of the direct energy-saving effect description parameter. The second constant is used to balance the size of the correction function.

[0058] Correspondingly, this application also provides a building electricity energy-saving system based on big data, such as Figure 2 Shown, including, The first module is used to obtain a geographical map of the interior of the building, divide the geographical map into regions according to regional categories, mark the electrical equipment in each region, and determine the functional area of ​​each electrical equipment; The second module is used to collect the power consumption and operation data of each electrical device over a period of time, determine the usage intensity of each electrical device based on the operation data, set the energy consumption baseline for each area based on the power consumption data and usage intensity, and filter out high-energy consumption areas according to the energy consumption baseline; The third module is used to classify electrical equipment into general-purpose equipment and special-purpose equipment based on their areas of use. It analyzes changes in passenger flow in high-energy-consuming areas, conducts multi-objective optimization based on passenger flow changes, and develops energy-saving strategies for general-purpose and special-purpose equipment. The fourth module is used to save electricity for general equipment and special equipment through energy-saving strategies, define energy-saving effect indicators during the energy-saving process, and adjust energy-saving strategies based on the energy-saving effect indicators.

[0059] Compared with the prior art, the present invention has the following beneficial effects: 1. Determine the usage intensity of each electrical device based on operating data, set the energy consumption baseline for each area based on the power consumption data and usage intensity, divide the time period into time periods based on the usage intensity of the electrical devices, and analyze the power consumption data to set the dynamic energy consumption baseline for each area based on time periods. Ensure the rationality of the baseline setting, screen out high energy consumption areas, and provide a reliable foundation for subsequent energy-saving strategies in high energy consumption areas. 2. Multi-objective optimization of general and specialized equipment is conducted based on changes in passenger flow. Energy-saving strategies for general equipment are determined based on the impact of passenger flow changes on comfort requirements in high-energy-consuming areas. Energy-saving strategies for specialized equipment are determined based on equipment performance and lifespan, improving the accuracy and adaptability of building electricity conservation. Energy-saving strategies are adjusted based on energy-saving effect indicators, which are defined to reflect the pros and cons of energy-saving strategies. This feedback is then used to adjust energy-saving strategies, balancing building electricity demand and energy conservation.

[0060] Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented via hardware or via software combined with a necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product. This software product can be stored on a non-volatile storage medium (such as a CD-ROM, USB flash drive, or external hard drive) and includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various implementation scenarios of the present invention.

[0061] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0062] Those skilled in the art will appreciate that the modules in the system of the implementation scenario can be distributed in the system of the implementation scenario according to the implementation scenario description, or can be modified accordingly and located in one or more systems different from the implementation scenario. The modules of the above implementation scenario can be combined into one module or further divided into multiple submodules.

[0063] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A building electricity energy-saving method based on big data, characterized in that: include, Obtain a geographic map of the interior of the building, divide the geographic map into regions according to regional categories, mark the electrical equipment in each region, and determine the functional area of ​​each electrical equipment; Collect the power consumption and operation data of each electrical device over a period of time, determine the usage intensity of each electrical device based on the operation data, set the energy consumption baseline for each area based on the power consumption data and usage intensity, and filter out high energy consumption areas according to the energy consumption baseline; Electricity-consuming equipment is divided into two categories: general-purpose equipment and special-purpose equipment according to their areas of use. The flow of people in high-energy-consuming areas is analyzed, and multi-objective optimization is performed based on the flow of people. Energy-saving strategies for general-purpose and special-purpose equipment are formulated. Energy-saving strategies are used to save electricity for general and special equipment, energy-saving effect indicators are defined during the energy-saving process, and energy-saving strategies are adjusted based on the energy-saving effect indicators.

2. The building electricity energy saving method based on big data according to claim 1 is characterized in that: Determine the area of ​​operation of each electrical device, including: Confirm the installation location of each electrical device, analyze the coverage characteristics of the functions of each electrical device and the layout structure of the area where the installation location is located, so as to determine the effective area of ​​​​each electrical device, and mark the effective area of ​​​​each electrical device at the corresponding position on the internal geographical map of the building.

3. The building electricity energy saving method based on big data according to claim 1 is characterized in that: Determine the usage intensity of each electrical device based on operating data, including: Operation data includes the operating time, average load rate and usage frequency of electrical equipment; Counting the average running time in the first preset period, determining the second period based on the average running time, and counting the average load rate, load rate standard deviation, and average usage frequency in the second period; The usage intensity of each electric device is determined based on the second cycle length, the average load rate, the load rate standard deviation, and the average usage frequency.

4. The building electricity energy saving method based on big data according to claim 2 is characterized in that: Set energy consumption baselines for each area using electricity usage data and usage intensity. include, Integrate the electrical equipment in each area according to the installation location and the area of ​​use of the electrical equipment to obtain a regional electrical equipment set; The usage intensity of all electrical equipment in each area is counted according to the regional electrical equipment set, and the usage intensity of all electrical equipment is integrated to obtain the comprehensive usage intensity. A comprehensive usage intensity curve that changes over time is constructed, and multiple time periods are divided according to the comprehensive usage intensity on the comprehensive usage intensity curve; Calculate the time period coefficient for each time period and assign a functional coefficient to the regional type; Construct a time-varying electricity consumption curve, split the curve by time period, and obtain the corresponding relationship between time period and electricity consumption curve segment; The electricity consumption curve segment is evenly split to obtain multiple electricity consumption curve segments. The slope change and average value of each electricity consumption curve segment are calculated. The proportion of the electricity consumption curve segment is assigned based on the slope change. The benchmark energy consumption of the electricity consumption curve segment is set based on the proportion and average value of each electricity consumption curve segment under the electricity consumption curve segment. Set the energy consumption baseline for each time period based on the baseline energy consumption, time period factor and function factor.

5. The building electricity energy saving method based on big data according to claim 4 is characterized in that: Screen out high energy consumption areas according to the energy consumption baseline, include, Taking time periods as units, compare the actual energy consumption of each period in each area with the energy consumption deviation value of the energy consumption baseline, integrate the energy consumption deviation values ​​of all periods to obtain the comprehensive energy consumption deviation value, and use the comprehensive energy consumption deviation value to screen out high-energy consumption areas.

6. The building electricity energy saving method based on big data according to claim 1 is characterized in that: Analyze the changes in passenger flow in high energy consumption areas, including: Identify the areas adjacent to high energy consumption areas and calculate the connectivity between high energy consumption areas and their adjacent areas; Collect real-time multi-source data of pedestrian flow in the area, establish a pedestrian flow prediction model based on the real-time multi-source data of pedestrian flow and the connectivity between high-energy consumption areas and their adjacent areas, and analyze the changes in pedestrian flow through the pedestrian flow prediction model.

7. The building electricity energy saving method based on big data according to claim 6 is characterized in that: Combined with the changes in passenger flow, multi-objective optimization is carried out for general equipment and special equipment, and energy-saving strategies for general equipment and special equipment are formulated, including: The multi-objectives of general equipment include energy saving and comfort, while the multi-objectives of special equipment include energy saving and equipment life; Set comfort constraints based on the crowd flow prediction model, use the comfort constraints to perform multi-objective optimization of general equipment, and use the optimized control parameters of general equipment as the energy-saving strategy for general equipment; The equipment life constraint conditions are set according to the performance life of the special equipment, and the multi-objective optimization of the special equipment is performed through the equipment life constraint conditions. The control parameters of the optimized special equipment are used as the energy-saving strategy of the special equipment.

8. The building electricity energy saving method based on big data according to claim 1 is characterized in that: Define energy-saving effect indicators during the energy-saving process, including: The direct energy-saving effect description parameters and indirect energy-saving effect description parameters of general equipment and special equipment are collected respectively, and the energy-saving effect indicators of general equipment and special equipment are defined respectively by combining the direct energy-saving effect description parameters and the indirect energy-saving effect description parameters.

9. A building electricity energy-saving system based on big data, characterized in that: include, The first module is used to obtain a geographical map of the interior of the building, divide the geographical map into regions according to regional categories, mark the electrical equipment in each region, and determine the functional area of ​​each electrical equipment; The second module is used to collect the power consumption and operation data of each electrical device over a period of time, determine the usage intensity of each electrical device based on the operation data, set the energy consumption baseline for each area based on the power consumption data and usage intensity, and filter out high-energy consumption areas according to the energy consumption baseline; The third module is used to classify electrical equipment into general-purpose equipment and special-purpose equipment based on their areas of use. It analyzes changes in passenger flow in high-energy-consuming areas, conducts multi-objective optimization based on passenger flow changes, and develops energy-saving strategies for general-purpose and special-purpose equipment. The fourth module is used to save electricity for general equipment and special equipment through energy-saving strategies, define energy-saving effect indicators during the energy-saving process, and adjust energy-saving strategies based on the energy-saving effect indicators.

Images