Building energy consumption management system and method based on big data

Abstract

The invention discloses a building energy consumption management system and method based on big data, and relates to the technical field of energy consumption management, and the system comprises an intelligent energy consumption analysis module, an equipment health monitoring module, a dynamic energy consumption scheduling module, a renewable energy integration module, a user behavior analysis module, and a collaborative energy management module. The method comprises the steps of data acquisition and input, data analysis and decision, and resource sharing and collaborative management. According to the big data-based building energy consumption management system and method, through implementation of the big data-based building energy consumption management system, a building manager can realize comprehensive monitoring and intelligent optimization of energy consumption, energy consumption and operation cost are significantly reduced, and comfort and satisfaction of a user are improved at the same time; through integration of real-time data and an advanced analysis technology, environment setting in a building can be effectively adjusted, sharing of renewable energy sources and collaborative management of communities can be promoted, the goal of sustainable development is promoted, and the win-win situation of economy and environmental protection is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management, and in particular to a building energy consumption management system and method based on big data. Background Art

[0002] In today's building management field, with the acceleration of urbanization and the continuous rise in energy costs, traditional building energy management methods can no longer meet the complex needs of modern buildings. Existing technologies usually rely on static monitoring and simple data analysis, and cannot respond to energy consumption changes and user needs in real time, resulting in energy waste and reduced user comfort.

[0003] In addition, the lack of effective integration of renewable energy and collaborative management among communities has greatly reduced energy utilization efficiency.

[0004] Therefore, by introducing big data technology, this system builds a comprehensive energy consumption management system through multiple modules such as intelligent energy consumption analysis, equipment health monitoring, and user behavior analysis, which can monitor, predict and optimize building energy consumption in real time and improve the efficiency and sustainability of resource utilization. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a building energy consumption management system and method based on big data to solve the problems raised in the above background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a building energy consumption management system based on big data, comprising an intelligent energy consumption analysis module, an equipment health monitoring module, a dynamic energy consumption scheduling module, a renewable energy integration module, a user behavior analysis module and a collaborative energy management module;

[0007] The intelligent energy consumption analysis module uses a machine learning algorithm to perform in-depth analysis on the energy consumption data in the building, define the energy consumption characteristics in the building, and group the various areas in the building according to the energy consumption characteristics;

[0008] The equipment health monitoring module monitors the operating status of equipment in the building, such as air conditioners, heating systems, and lighting equipment, in real time, and identifies whether the equipment has malfunctions, reduced efficiency, or excessive energy consumption by collecting equipment operating data and energy consumption data;

[0009] The dynamic energy consumption scheduling module dynamically schedules the energy consumption in the building based on real-time big data information, and intelligently adjusts the working status of each device by analyzing factors such as external weather and internal activity arrangements;

[0010] The renewable energy integration module manages the use of renewable energy such as solar energy and wind energy in the building, and automatically adjusts the energy consumption strategy in the building by real-time monitoring the generation and consumption of renewable energy, giving priority to the use of renewable energy;

[0011] The user behavior analysis module analyzes the behavior habits of users in the building based on big data, and constructs user portraits through data mining technology, and automatically adjusts environmental settings, such as temperature and lighting, according to the needs and behavior patterns of users;

[0012] The collaborative energy management module performs collaborative energy management of the building and the surrounding community. By integrating the energy consumption data of multiple buildings, it identifies the overall energy consumption situation in the community and formulates corresponding scheduling strategies to achieve resource sharing.

[0013] To further optimize the technical solution, the intelligent energy consumption analysis module, when defining the energy consumption characteristics in the building, includes:

[0014] First, define the regional characteristics, which include energy consumption of different floors and functional areas, such as office areas, meeting rooms, and public areas;

[0015] Redefine time characteristics, equipment characteristics, and environmental characteristics;

[0016] in,

[0017] Temporal features, including date, time, working day / non-working day, and season;

[0018] Equipment characteristics, including the type, power, and frequency of use of different equipment;

[0019] Environmental characteristics, including outdoor temperature, humidity, and weather conditions.

[0020] To further optimize the technical solution, the intelligent energy consumption analysis module groups the energy consumption characteristics of the areas in the building according to time characteristics, equipment characteristics and environmental characteristics based on regional characteristics, and uses a cluster analysis algorithm to minimize the distance from each point to its cluster center. The algorithm is as follows:

[0021]

[0022] in,

[0023] J is the objective function, which is the sum of the distances from all points in the cluster to the center of the cluster;

[0024] k is the number of clusters;

[0025] n i is the number of samples in the i-th cluster;

[0026] is the jth sample in the i-th cluster;

[0027] μ i is the center point of the i-th cluster;

[0028] The ARIMA model is used to predict energy consumption trends. The model is as follows:

[0029] Y t =μ+φ1Y t-1 +φ2Y t-2 +...+θ1∈ t-1 +θ2∈ t-2 +∈ t ;

[0030] in,

[0031] Y t is the energy consumption value at time t;

[0032] μ is a constant term;

[0033] φ is the coefficient of the autoregressive term;

[0034] θ is the coefficient of the sliding average term;

[0035] ∈ is the white noise error term;

[0036] After analyzing the energy consumption characteristics of energy consumption data in each area of ​​the building, the ARI MA model is used to predict future energy consumption.

[0037] To further optimize the technical solution, the equipment health monitoring module identifies the equipment operating status based on a recognition model, and the model is as follows:

[0038]

[0039] in,

[0040] E is the energy consumption of the equipment;

[0041] P is the equipment power;

[0042] T is the equipment working time;

[0043] A is the workload of the device;

[0044] C is the normal working coefficient of the equipment, ranging from 0 to 1;

[0045] R is the health monitoring index, which indicates the efficiency status of the equipment;

[0046] When R>0, it means that the energy consumption of the equipment is higher than the normal level, and there is a possibility of failure or reduced efficiency;

[0047] When R≈0, it means the device is within the normal operating range;

[0048] When R < 0, it means that the energy consumption of the equipment is lower than expected, and there is a possibility of insufficient load or equipment failure.

[0049] To further optimize the technical solution, the dynamic energy consumption scheduling module has a built-in dynamic scheduling model, which adjusts the working status of each device in the building according to real-time big data information and external environmental factors. Assuming that the devices to be scheduled are air conditioning AC, lighting L and heating H, the dynamic scheduling model is as follows:

[0050] D=(L·L adj )+(AC·AC adj )+(H·H adj );

[0051] in,

[0052] D is the total energy demand;

[0053] T is the current temperature in the building;

[0054] T set To set the temperature;

[0055] H is the flow of people in the building;

[0056] W is external weather factors, such as temperature and humidity;

[0057] L adj is the lighting adjustment factor, ranging from 0 to 1, indicating the adjustment of lighting intensity;

[0058] AC adj is the air conditioning adjustment factor, ranging from 0 to 1, indicating the adjustment of the air conditioning intensity;

[0059] H adj is the heating adjustment factor, ranging from 0 to 1, indicating the adjustment of heating intensity;

[0060] When the dynamic scheduling model is in use, the data of the equipment is collected in real time through the Internet of Things. At each time point, the adjustment factor L is calculated based on the collected data. adj , AC adj and H adj , calculate the current total energy demand D, and intelligently adjust the working status of the equipment based on the calculation results; for example, if the flow of people is large and the indoor temperature is high, increase the output of the air conditioner and increase the lighting appropriately; conversely, reduce the energy consumption of all equipment in unmanned areas.

[0061] To further optimize the technical solution, the renewable energy integration module automatically adjusts the energy consumption strategy in the building including:

[0062] Real-time monitoring and data collection;

[0063] This includes real-time monitoring of the energy output of solar panels and wind turbines; real-time tracking of energy consumption data within buildings, such as the use of lighting, air conditioning, and heating equipment; and monitoring the charge and discharge status of battery energy storage systems to facilitate replenishment when energy supply is insufficient.

[0064] Energy consumption priority strategy;

[0065] Including giving priority to the use of renewable energy; dynamically adjusting energy supply strategies;

[0066] Economic benefit analysis;

[0067] This includes collecting data on the generation cost, maintenance cost, and cost of traditional energy for renewable energy, and conducting dynamic economic analysis.

[0068] To further optimize the technical solution, the user behavior analysis module collects user data, including personal information, behavior data, and environmental data, analyzes user behavior habits based on the user data, and constructs user portraits to achieve automatic adjustment of the energy consumption of the device, including:

[0069] Personalized settings: Automatically adjust environmental settings based on user profiles when users enter the building, such as adjusting temperature and lighting to the user's preferred level;

[0070] Dynamic response: By monitoring user activities in real time, the device can be adjusted dynamically, such as automatically reducing lighting intensity and adjusting air conditioning temperature when a user leaves an area.

[0071] Feedback learning: Collect user feedback data on environment settings, continuously optimize user portraits and device adjustment strategies, and form a closed-loop system.

[0072] To further optimize the technical solution, the user data specifically includes the following contents:

[0073] Personal information is:

[0074] User basic information: age, gender, occupation;

[0075] User preferences: such as preferred temperature range, light intensity, silent or music environment;

[0076] The behavioral data are:

[0077] Entry and exit records: monitor the user's entry and exit time through the access control system;

[0078] Usage habits: record the user's usage of lighting and air-conditioning equipment in different time periods;

[0079] Feedback data: user feedback on the environment settings, such as satisfaction surveys;

[0080] The environmental data are:

[0081] Environmental parameters: real-time monitoring data of indoor temperature, humidity, and light intensity;

[0082] External environment: external weather changes, such as temperature and sunlight intensity.

[0083] To further optimize the technical solution, the collaborative energy management module dynamically adjusts the allocation of resources based on real-time data. For example, when a building has a high renewable energy output, the excess energy is automatically allocated to buildings with higher demand. Prediction algorithms are used, such as time series analysis to predict energy consumption demand in the future, to prepare for resource allocation in advance, and to set priority strategies when allocating resources to ensure the rational use of resources.

[0084] A building energy consumption management method based on big data is used based on the above-mentioned building energy consumption management system based on big data, and includes the following specific steps:

[0085] S1, data collection and input;

[0086] Through the Internet of Things technology, energy consumption data, environmental data, and equipment status information in the building are automatically collected.

[0087] Connect renewable energy equipment such as solar panels and wind turbines to monitor their power generation and usage in real time;

[0088] Collect user behavior and preference data through user feedback or regular surveys;

[0089] S2, data analysis and decision making;

[0090] Analyze the energy consumption trends of each area and each device, and identify high energy consumption areas;

[0091] Build user portraits and analyze user habits and needs;

[0092] Automatically adjust energy consumption strategies within the building, such as adjusting temperature and lighting intensity, based on real-time data and analysis results;

[0093] S3, resource sharing and collaborative management;

[0094] Share renewable energy with neighboring buildings to optimize resource use.

[0095] Compared with the prior art, the present invention provides a building energy consumption management system and method based on big data, which has the following beneficial effects:

[0096] This building energy consumption management system and method based on big data, by implementing a building energy consumption management system based on big data, can enable building managers to achieve comprehensive monitoring and intelligent optimization of energy consumption, significantly reduce energy consumption and operating costs, and improve user comfort and satisfaction; by integrating real-time data and advanced analysis technology, it can not only effectively adjust the environmental settings within the building, but also promote the sharing of renewable energy and collaborative management of the community, promote the goal of sustainable development, and achieve a win-win situation for the economy and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 This is a structural schematic diagram of a building energy consumption management system based on big data proposed by the present invention;

[0098] Figure 2 This is an interval diagram of the adjustment factor in a building energy consumption management system based on big data proposed by the present invention;

[0099] Figure 3 A decision model diagram of an energy consumption priority strategy in a building energy consumption management system based on big data proposed by the present invention;

[0100] Figure 4 Three strategy diagrams of energy consumption priority strategies in a building energy consumption management system based on big data proposed by the present invention;

[0101] Figure 5 This is a flow chart of a building energy consumption management method based on big data proposed in the present invention. DETAILED DESCRIPTION

[0102] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0103] Embodiment 1:

[0104] See also Figure 1 , a building energy consumption management system based on big data, including an intelligent energy consumption analysis module, an equipment health monitoring module, a dynamic energy consumption scheduling module, a renewable energy integration module, a user behavior analysis module and a collaborative energy management module.

[0105] The intelligent energy consumption analysis module uses a machine learning algorithm to perform in-depth analysis on the energy consumption data in the building, define the energy consumption characteristics in the building, and group the various areas in the building according to the energy consumption characteristics.

[0106] In this embodiment, the intelligent energy consumption analysis module, when defining the energy consumption characteristics in the building, includes:

[0107] First, define the regional characteristics, which include energy consumption of different floors and functional areas, such as office areas, meeting rooms, and public areas;

[0108] Redefine time characteristics, equipment characteristics, and environmental characteristics;

[0109] in,

[0110] Temporal features, including date, time, working day / non-working day, and season;

[0111] Equipment characteristics, including the type, power, and frequency of use of different equipment;

[0112] Environmental characteristics, including outdoor temperature, humidity, and weather conditions.

[0113] Furthermore, the intelligent energy consumption analysis module groups the energy consumption characteristics of the areas in the building according to time characteristics, equipment characteristics and environmental characteristics based on regional characteristics, and uses a cluster analysis algorithm to minimize the distance from each point to its cluster center. The algorithm is as follows:

[0114]

[0115] in,

[0116] J is the objective function, which is the sum of the distances from all points in the cluster to the center of the cluster;

[0117] k is the number of clusters;

[0118] n i is the number of samples in the i-th cluster;

[0119] is the jth sample in the i-th cluster;

[0120] μ i is the center point of the ith cluster.

[0121] When using the clustering analysis algorithm, we need to choose a suitable k value. We can use the Elbow Method to determine the optimal number of clusters.

[0122] The ARIMA model is used to predict energy consumption trends. The model is as follows:

[0123] Y t =μ+φ1Y t-1 +φ2Y t-2 +...+θ1∈ t-1 +θ2∈ t-2 +∈ t ;

[0124] in,

[0125] Y t is the energy consumption value at time t;

[0126] μ is a constant term;

[0127] φ is the coefficient of the autoregressive term;

[0128] θ is the coefficient of the sliding average term;

[0129] ∈ is a white noise error term.

[0130] After analyzing the energy consumption characteristics of energy consumption data in each area of ​​the building, the ARIMA model is used to predict future energy consumption.

[0131] This module will regularly collect energy consumption data in the building and use clustering to analyze the energy consumption characteristics of different areas. The clustering results will provide managers with a basis for energy-saving measures. Then, the ARIMA model is used to predict future energy consumption trends. Once a peak in energy consumption is predicted, an early warning will be automatically generated and corresponding adjustment measures will be recommended.

[0132] The equipment health monitoring module monitors the operating status of equipment in the building, such as air conditioners, heating systems, and lighting equipment, in real time. By collecting the operating data and energy consumption data of the equipment, it identifies whether the equipment has faults, reduced efficiency, or excessive energy consumption.

[0133] In this embodiment, the equipment health monitoring module identifies the equipment operating status based on a recognition model, and the model is as follows:

[0134]

[0135] in,

[0136] E is the energy consumption of the device, which can be obtained through real-time monitoring of IoT devices, recording the total energy consumption of the device in a specific time period;

[0137] P is the equipment power, the rated power of the equipment, usually provided by the equipment manufacturer;

[0138] T is the equipment working time, which is the running time of the equipment since the last maintenance, and can be automatically recorded by the system;

[0139] A is the workload of the equipment, which is measured based on the actual working conditions of the equipment. For example, the actual cooling load of an air conditioner can be obtained in real time through sensors.

[0140] C is the normal operating coefficient of the equipment, ranging from 0 to 1, a value set according to industry standards or historical data, used to represent the efficiency of the equipment under normal operating conditions;

[0141] R is a health monitoring indicator, which indicates the efficiency status of the equipment.

[0142] When R>0, it means that the energy consumption of the equipment is higher than the normal level, and there is a possibility of failure or reduced efficiency;

[0143] When R≈0, it means the device is within the normal operating range;

[0144] When R < 0, it means that the energy consumption of the equipment is lower than expected, and there is a possibility of insufficient load or equipment failure.

[0145] A number of factors that affect the health status of equipment are comprehensively considered to form a relatively comprehensive evaluation index. At the same time, through real-time monitoring and data-driven methods, more refined management and maintenance can be achieved, improving the overall operating efficiency and life cycle of the equipment.

[0146] Through the use of models, building managers can take timely measures to reduce energy consumption and improve equipment efficiency before equipment problems occur, thereby achieving more intelligent equipment health monitoring.

[0147] The dynamic energy consumption scheduling module dynamically schedules the energy consumption in the building based on real-time big data information, and intelligently adjusts the working status of each device by analyzing factors such as external weather and internal activity arrangements.

[0148] In this embodiment, the dynamic energy consumption scheduling module has a built-in dynamic scheduling model, which adjusts the working status of each device in the building according to real-time big data information and external environmental factors. Assuming that the devices to be scheduled are air conditioning AC, lighting L and heating H, the dynamic scheduling model is as follows:

[0149] D=(L·L adj )+(AC·AC adj )+(H·H adj );

[0150] in,

[0151] D is the total energy demand;

[0152] T is the current temperature in the building;

[0153] T set To set the temperature;

[0154] H is the flow of people in the building;

[0155] W is external weather factors, such as temperature and humidity;

[0156] L adj is the lighting adjustment factor, ranging from 0 to 1, indicating the adjustment of lighting intensity;

[0157] AC adj is the air conditioning adjustment factor, ranging from 0 to 1, indicating the adjustment of the air conditioning intensity;

[0158] H adj is the heating adjustment factor, ranging from 0 to 1, indicating the adjustment of heating intensity;

[0159] like Figure 2 As shown, when the dynamic scheduling model is used, the data of the equipment is collected in real time through the Internet of Things. At each time point, the adjustment factor L is calculated based on the collected data. adj , AC adj and H adj , calculate the current total energy demand D, and intelligently adjust the working status of the equipment based on the calculation results; for example, if the flow of people is large and the indoor temperature is high, increase the output of the air conditioner and increase the lighting appropriately; conversely, reduce the energy consumption of all equipment in unmanned areas.

[0160] By comprehensively considering the flow of people, temperature and external weather factors, dynamic intelligent scheduling of various equipment in the building is achieved. The model can make decisions quickly in a real-time environment, optimize energy consumption configuration and improve energy efficiency.

[0161] The renewable energy integration module manages the use of renewable energy such as solar energy and wind energy in the building, and automatically adjusts the energy consumption strategy in the building by real-time monitoring the generation and consumption of renewable energy, giving priority to the use of renewable energy.

[0162] In this embodiment, the renewable energy integration module automatically adjusts the energy consumption strategy in the building including:

[0163] Real-time monitoring and data collection;

[0164] It includes real-time monitoring of the energy output of solar panels and wind turbines; real-time tracking of energy consumption data within the building, such as the use of lighting, air conditioning, and heating equipment; and monitoring the charge and discharge status of the battery energy storage system to facilitate replenishment when energy supply is insufficient.

[0165] Energy consumption priority strategy;

[0166] Including giving priority to the use of renewable energy and dynamically adjusting energy supply strategies.

[0167] like Figure 3 and Figure 4 As shown, a decision model is built to determine the current energy usage strategy.

[0168] When renewable energy is in sufficient supply, the working status of non-core loads (such as lighting and air conditioning during off-peak hours) is automatically adjusted to ensure the priority use of renewable energy. When there is a surplus of renewable energy, the excess energy is stored in the battery energy storage system. When renewable energy is insufficient or when electricity is in peak demand, energy is extracted from the battery to reduce dependence on traditional energy.

[0169] Economic benefit analysis;

[0170] This includes collecting data on the generation cost, maintenance cost, and cost of traditional energy for renewable energy, and conducting dynamic economic analysis.

[0171] By optimizing the energy consumption strategy in the building in real time, we can maximize the use of renewable energy and achieve sustainable development goals. Through automated decision-making and feedback mechanisms, we can continuously learn and improve to cope with different environments and usage scenarios.

[0172] The user behavior analysis module analyzes the behavioral habits of users in the building based on big data, and constructs user portraits through data mining technology, and automatically adjusts environmental settings, such as temperature and lighting, according to user needs and behavior patterns.

[0173] Based on big data analysis, analyze users' usage habits in different time periods, identify peak and off-peak periods, and predict future usage patterns.

[0174] Through data mining technology, a detailed user profile is built for each user, including:

[0175] Basic characteristics: age, gender, occupation, work location, etc.

[0176] Behavioral characteristics: commonly used devices, frequency of use, preferred settings (such as temperature, brightness), peak usage time periods, etc.

[0177] Situational characteristics: Differences in user behavior in different situations, such as changes in behavior on weekdays and weekends, and on sunny and cloudy days.

[0178] In this embodiment, the user behavior analysis module collects user data, including personal information, behavior data, and environmental data, analyzes user behavior habits based on the user data, and constructs a user profile to achieve automatic adjustment of the energy consumption of the device, including:

[0179] Personalized settings: Automatically adjust environmental settings based on user profiles when users enter the building, such as adjusting temperature and lighting to the user's preferred level;

[0180] Dynamic response: By monitoring user activities in real time, the device can be adjusted dynamically, such as automatically reducing lighting intensity and adjusting air conditioning temperature when a user leaves an area.

[0181] Feedback learning: Collect user feedback data on environment settings, continuously optimize user portraits and device adjustment strategies, and form a closed-loop system.

[0182] Furthermore, the user data specifically includes the following:

[0183] Personal information is:

[0184] User basic information: age, gender, occupation;

[0185] User preferences: such as preferred temperature range, light intensity, silent or music environment;

[0186] The behavioral data are:

[0187] Entry and exit records: monitor the user's entry and exit time through the access control system;

[0188] Usage habits: record the user's usage of lighting and air-conditioning equipment in different time periods;

[0189] Feedback data: user feedback on the environment settings, such as satisfaction surveys;

[0190] The environmental data are:

[0191] Environmental parameters: real-time monitoring data of indoor temperature, humidity, and light intensity;

[0192] External environment: external weather changes, such as temperature and sunlight intensity.

[0193] The collaborative energy management module performs collaborative energy management of the building and the surrounding community. By integrating the energy consumption data of multiple buildings, it identifies the overall energy consumption situation in the community and formulates corresponding scheduling strategies to achieve resource sharing.

[0194] In this embodiment, the collaborative energy management module dynamically adjusts the allocation of resources based on real-time data. For example, when a building has a high renewable energy output, it automatically allocates excess energy to buildings with higher demand. It uses prediction algorithms, such as time series analysis to predict energy consumption demand in the future, prepares for resource allocation in advance, and sets priority strategies to ensure the rational use of resources when allocating resources.

[0195] When allocating resources, set a priority strategy to ensure the rational use of resources:

[0196] Priority for high-demand buildings: Priority is given to buildings that have high energy consumption and lack renewable energy.

[0197] Neighboring building priority: When sharing resources, the needs of neighboring buildings are given priority to reduce transmission losses.

[0198] Time priority: Prioritize resource allocation during peak power consumption periods.

[0199] Integrate the energy consumption management of buildings and communities, make full use of renewable energy, and realize resource sharing within the community. Through dynamic scheduling, it not only improves energy utilization efficiency, but also promotes the realization of sustainable development goals.

[0200] Embodiment 2:

[0201] See also Figure 5 A building energy consumption management method based on big data is used based on the building energy consumption management system based on big data described in Example 1, and includes the following specific steps:

[0202] S1, data collection and input;

[0203] Through the Internet of Things technology, energy consumption data, environmental data, and equipment status information in the building are automatically collected.

[0204] Connect renewable energy equipment such as solar panels and wind turbines to monitor their power generation and usage in real time;

[0205] Collect user behavior and preference data through user feedback or regular surveys;

[0206] S2, data analysis and decision making;

[0207] Analyze the energy consumption trends of each area and each device, and identify high energy consumption areas;

[0208] Build user portraits and analyze user habits and needs;

[0209] Automatically adjust energy consumption strategies within the building, such as adjusting temperature and lighting intensity, based on real-time data and analysis results;

[0210] S3, resource sharing and collaborative management;

[0211] Share renewable energy with neighboring buildings to optimize resource use.

[0212] The beneficial effects of the present invention are:

[0213] This building energy consumption management system and method based on big data, by implementing a building energy consumption management system based on big data, can enable building managers to achieve comprehensive monitoring and intelligent optimization of energy consumption, significantly reduce energy consumption and operating costs, and improve user comfort and satisfaction; by integrating real-time data and advanced analysis technology, it can not only effectively adjust the environmental settings within the building, but also promote the sharing of renewable energy and collaborative management of the community, promote the goal of sustainable development, and achieve a win-win situation for the economy and environmental protection.

[0214] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0215] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A building energy consumption management system based on big data, characterized in that: It includes intelligent energy consumption analysis module, equipment health monitoring module, dynamic energy consumption scheduling module, renewable energy integration module, user behavior analysis module and collaborative energy management module; The intelligent energy consumption analysis module uses a machine learning algorithm to perform in-depth analysis on the energy consumption data in the building, define the energy consumption characteristics in the building, and group the various areas in the building according to the energy consumption characteristics; The equipment health monitoring module monitors the operating status of equipment in the building, such as air conditioners, heating systems, and lighting equipment, in real time, and identifies whether the equipment has malfunctions, reduced efficiency, or excessive energy consumption by collecting equipment operating data and energy consumption data; The dynamic energy consumption scheduling module dynamically schedules the energy consumption in the building based on real-time big data information, and intelligently adjusts the working status of each device by analyzing factors such as external weather and internal activity arrangements; The renewable energy integration module manages the use of renewable energy such as solar energy and wind energy in the building, and automatically adjusts the energy consumption strategy in the building by real-time monitoring the generation and consumption of renewable energy, giving priority to the use of renewable energy; The user behavior analysis module analyzes the behavior habits of users in the building based on big data, and constructs user portraits through data mining technology, and automatically adjusts environmental settings, such as temperature and lighting, according to the needs and behavior patterns of users; The collaborative energy management module performs collaborative energy management of the building and the surrounding community. By integrating the energy consumption data of multiple buildings, it identifies the overall energy consumption situation in the community and formulates corresponding scheduling strategies to achieve resource sharing.

2. The building energy consumption management system based on big data according to claim 1 is characterized in that: The intelligent energy consumption analysis module, when defining the energy consumption characteristics in the building, includes: First, define the regional characteristics, which include energy consumption of different floors and functional areas, such as office areas, meeting rooms, and public areas; Redefine time characteristics, equipment characteristics, and environmental characteristics; in, Temporal features, including date, time, working day / non-working day, and season; Equipment characteristics, including the type, power, and frequency of use of different equipment; Environmental characteristics, including outdoor temperature, humidity, and weather conditions.

3. The building energy consumption management system based on big data according to claim 2 is characterized in that: The intelligent energy consumption analysis module groups the energy consumption characteristics of the areas in the building according to time characteristics, equipment characteristics and environmental characteristics based on regional characteristics, and uses a cluster analysis algorithm to minimize the distance from each point to its cluster center. The algorithm is as follows: in, J is the objective function, which is the sum of the distances from all points in the cluster to the center of the cluster; k is the number of clusters; n i is the number of samples in the i-th cluster; is the jth sample in the i-th cluster; μ i is the center point of the i-th cluster; The ARIMA model is used to predict energy consumption trends. The model is as follows: Y t =μ+φ1Y t-1 +φ2Y t-2 +...+θ1∈ t-1 +θ2∈ t-2 +∈ t ; in, Y t is the energy consumption value at time t; μ is a constant term; φ is the coefficient of the autoregressive term; θ is the coefficient of the sliding average term; ∈ is the white noise error term; After analyzing the energy consumption characteristics of energy consumption data in each area of ​​the building, the ARIMA model is used to predict future energy consumption.

4. The building energy consumption management system based on big data according to claim 1 is characterized in that: The equipment health monitoring module identifies the equipment operating status based on the recognition model, and the model is as follows: in, E is the energy consumption of the equipment; P is the equipment power; T is the equipment working time; A is the workload of the device; C is the normal working coefficient of the equipment, ranging from 0 to 1; R is the health monitoring index, which indicates the efficiency status of the equipment; When R>0, it means that the energy consumption of the equipment is higher than the normal level, and there is a possibility of failure or reduced efficiency; When R≈0, it means the device is within the normal operating range; When R < 0, it means that the energy consumption of the equipment is lower than expected, and there is a possibility of insufficient load or equipment failure.

5. The building energy consumption management system based on big data according to claim 1 is characterized in that: The dynamic energy consumption scheduling module has a built-in dynamic scheduling model, which adjusts the working status of each device in the building according to real-time big data information and external environmental factors. Assuming that the devices to be scheduled are air conditioning AC, lighting L and heating H, the dynamic scheduling model is as follows: D=(L·L adj )+(AC·AC adj )+(H·H adj ); in, D is the total energy demand; T is the current temperature in the building; T set To set the temperature; H is the flow of people in the building; W is external weather factors, such as temperature and humidity; L adj is the lighting adjustment factor, ranging from 0 to 1, indicating the adjustment of lighting intensity; AC adj is the air conditioning adjustment factor, ranging from 0 to 1, indicating the adjustment of the air conditioning intensity; H adj is the heating adjustment factor, ranging from 0 to 1, indicating the adjustment of heating intensity; When the dynamic scheduling model is in use, the data of the equipment is collected in real time through the Internet of Things. At each time point, the adjustment factor L is calculated based on the collected data. adj , AC adj and H adj , calculate the current total energy demand D, and intelligently adjust the working status of the equipment based on the calculation results; if the flow of people is large and the indoor temperature is high, increase the output of the air conditioner and increase the lighting appropriately; conversely, reduce the energy consumption of all equipment in unmanned areas.

6. The building energy consumption management system based on big data according to claim 1 is characterized in that: The renewable energy integration module automatically adjusts the energy consumption strategy in the building including: Real-time monitoring and data collection; This includes real-time monitoring of the energy output of solar panels and wind turbines; real-time tracking of energy consumption data within buildings, such as the use of lighting, air conditioning, and heating equipment; and monitoring the charge and discharge status of battery energy storage systems to facilitate replenishment when energy supply is insufficient. Energy consumption priority strategy; Including giving priority to the use of renewable energy; dynamically adjusting energy supply strategies; Economic benefit analysis; This includes collecting data on the generation cost, maintenance cost, and cost of traditional energy for renewable energy, and conducting dynamic economic analysis.

7. The building energy consumption management system based on big data according to claim 1 is characterized in that: The user behavior analysis module collects user data, including personal information, behavior data, and environmental data, analyzes user behavior habits based on the user data, and constructs user portraits to achieve automatic adjustment of the energy consumption of the device, including: Personalized settings: Automatically adjust environmental settings based on user profiles when users enter the building, such as adjusting temperature and lighting to the user's preferred level; Dynamic response: By monitoring user activities in real time, the device can be adjusted dynamically, such as automatically reducing lighting intensity and adjusting air conditioning temperature when a user leaves an area. Feedback learning: Collect user feedback data on environment settings, continuously optimize user portraits and device adjustment strategies, and form a closed-loop system.

8. The building energy consumption management system based on big data according to claim 7 is characterized in that: The user data specifically includes the following: Personal information is: User basic information: age, gender, occupation; User preferences: such as preferred temperature range, light intensity, silent or music environment; The behavioral data are: Entry and exit records: monitor the user's entry and exit time through the access control system; Usage habits: record the user's usage of lighting and air-conditioning equipment in different time periods; Feedback data: user feedback on the environment settings, such as satisfaction surveys; The environmental data are: Environmental parameters: real-time monitoring data of indoor temperature, humidity, and light intensity; External environment: external weather changes, such as temperature and sunlight intensity.

9. The building energy consumption management system based on big data according to claim 1 is characterized in that: The collaborative energy management module dynamically adjusts resource allocation based on real-time data. For example, when a building has a high renewable energy output, it automatically allocates excess energy to buildings with higher demand. It uses prediction algorithms, such as time series analysis, to predict energy consumption demand in the future, prepares for resource allocation in advance, and sets priority strategies to ensure the rational use of resources when allocating resources.

10. A building energy consumption management method based on big data, which is used based on the building energy consumption management system based on big data according to any one of claims 1 to 9, characterized in that: The specific steps include: S1, data collection and input; Through the Internet of Things technology, energy consumption data, environmental data, and equipment status information in the building are automatically collected. Connect renewable energy equipment such as solar panels and wind turbines to monitor their power generation and usage in real time; Collect user behavior and preference data through user feedback or regular surveys; S2, data analysis and decision making; Analyze the energy consumption trends of each area and each device, and identify high energy consumption areas; Build user portraits and analyze user habits and needs; Automatically adjust energy consumption strategies within the building, such as adjusting temperature and lighting intensity, based on real-time data and analysis results; S3, resource sharing and collaborative management; Share renewable energy with neighboring buildings to optimize resource use.

Images