A method for monitoring water, electricity, gas, heating and cooling energy consumption and coordinating energy saving

Abstract

The present invention relates to the field of energy consumption monitoring technology, and specifically to a method for monitoring water, electricity, gas, heating and cooling energy consumption and collaborative energy saving, comprising the following steps: through multiple sensor nodes installed in a building, real-time energy consumption data of each energy system is collected, the energy system includes a water supply system, a power supply system, a gas supply system, a heating system, and a cooling system, and the energy consumption data includes usage data, fluctuation amplitude and energy consumption time period; the energy consumption data is transmitted to a central processing unit for pre-processing to form a complete energy consumption data set; a comprehensive analysis of the relationship between the energy systems is performed to generate an energy consumption interaction model between the energy systems; energy consumption peak periods and redundant usage are identified, collaborative energy saving strategies are automatically generated, and scheduling between the energy systems is optimized. The present invention can not only greatly improve the overall energy efficiency of each energy system, but also effectively balance the load between the systems, ensuring the rational use of energy and the long-term stable operation of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption monitoring, and in particular to a water, electricity, gas, heating and cooling energy consumption monitoring and coordinated energy saving method. Background Art

[0002] In modern buildings and industrial environments, multiple energy systems such as water, electricity, gas, heating, and cooling jointly support the normal operation of buildings. With the increase in energy demand, how to achieve coordinated management of multiple energy systems and efficient energy saving has become an important research direction in the field of energy-saving technology. However, traditional energy management systems usually only focus on the optimization of a single energy system and lack comprehensive analysis and scheduling control of the complex relationships between various energy systems. This isolated management method often makes it difficult to form synergistic effects between different energy systems, and even leads to problems such as low energy efficiency and waste of resources during peak or non-peak load periods.

[0003] Existing energy management methods mostly rely on fixed parameters or simple time series to save energy, ignoring the mutual influence and dynamic interaction between different energy systems. This approach is not only difficult to adapt to complex building energy consumption needs, but also unable to cope with the fluctuations in energy loads over time. For example, heating and cooling systems may conflict with each other during certain periods, resulting in a decrease in overall energy efficiency. At the same time, redundant use of water and gas supply systems is difficult to effectively identify, resulting in energy waste.

[0004] In order to achieve efficient energy management and energy saving effects, there is an urgent need for a collaborative management method that can monitor and analyze multiple energy systems such as water, electricity, gas, heating and cooling in real time. Summary of the Invention

[0005] The present invention provides a method for monitoring water, electricity, gas, heating and cooling energy consumption and for collaborative energy saving.

[0006] A method for monitoring water, electricity, gas, heating and cooling energy consumption and coordinating energy saving, comprising the following steps:

[0007] S1: Multiple sensor nodes installed in the building collect real-time energy consumption data from various energy systems, including water supply, electricity supply, gas supply, heating, and cooling systems. Energy consumption data includes usage data, fluctuation range, and energy consumption time period. The energy consumption data is transmitted to the central processing unit for pre-processing to form a complete energy consumption data set.

[0008] S2: Based on the acquired energy consumption data set and combined with historical energy consumption data, the interrelationships among energy systems are comprehensively analyzed to generate an energy consumption interaction model among energy systems;

[0009] S3: Based on the established energy consumption interaction model, calculate the energy utilization efficiency of the water supply system, power supply system, gas supply system, heating system, and cooling system in different time periods, identify peak energy consumption periods and redundant usage, automatically generate collaborative energy-saving strategies, and optimize the scheduling between various energy systems.

[0010] Optionally, the multi-sensor node includes multiple sensors installed in various energy systems within the building, specifically including:

[0011] Water flow sensor: used to collect water consumption data of the water supply system and record water flow rate and usage in real time;

[0012] Current and voltage sensors: used to collect power consumption data of the power supply system and calculate actual power consumption by monitoring current, voltage and power factor;

[0013] Gas flow sensor: used to collect gas consumption data of the gas supply system and calculate gas consumption by monitoring gas flow rate;

[0014] Temperature sensor and humidity sensor: used for energy consumption monitoring of heating and cooling systems. By collecting changes in ambient temperature and humidity and combining them with the operating conditions of heating and cooling equipment, energy consumption can be calculated.

[0015] The raw energy consumption data collected by each sensor is transmitted to the central processing unit. After receiving the raw energy consumption data from each sensor node, the central processing unit performs data preprocessing, specifically including:

[0016] S11: Usage data: Normalize the usage data of each energy system to a standard unit (unify the units of water, electricity, and gas to standard units) to ensure that data from different energy types can be directly compared;

[0017] S12: Fluctuation amplitude data: Calculate the amplitude or variance of energy consumption fluctuation based on the data changes within a predetermined time period. The fluctuation amplitude is expressed as standard deviation. To indicate, set the time period The energy consumption data in , then the fluctuation range, that is, the standard deviation is calculated as: ,in, is the mean of energy consumption data, is the number of samples, It is Energy consumption data at each sampling moment;

[0018] S13: Energy consumption time period data: Based on time series data, classify the consumption data of each energy system in different time periods, identify the peak energy consumption period and the valley energy consumption period of each energy system, determine the optimal use time of each energy, divide the total time period into several sub-time periods, and calculate the total energy consumption of each sub-time period ,mark the time periods in each sub-time period where the energy consumption exceeds the predetermined threshold (the threshold is set to 90% of the historical data) as peak energy consumption periods.,The usage data, fluctuation range and energy consumption time period are integrated into a complete energy consumption data set.

[0019] Optionally, S2 performs a comprehensive analysis based on the energy consumption dataset acquired in S1 and combined with historical energy consumption data to generate an energy consumption interaction model between various energy systems, revealing the relationship between various energy systems (including water supply system, power supply system, gas supply system, heating system and cooling system), and providing a decision-making basis for subsequent collaborative energy-saving strategies, specifically including:

[0020] S21, fusion of historical energy consumption data and real-time data: combining historical energy consumption data with real-time collected energy consumption data to construct a comprehensive energy consumption data set. The historical data includes the energy consumption data of each energy system obtained through the S1 method at different time periods.

[0021] S22, by calculating the correlation coefficient between each energy system , analyzing the linear correlation between consumption patterns in different time periods, including the water supply system and power supply system As an example, the correlation coefficient calculation is and In time The energy consumption is and , correlation coefficient The calculation formula is: , Indicates the moment, Indicates the Real-time water supply system The energy consumption value, Indicates the Constant power supply system The energy consumption value, For water supply system The average energy consumption, For power supply system The average energy consumption, is the number of samples, the value range of the Pearson correlation coefficient is [-1,1]. When it approaches 1 or 1, it means that the energy consumption data of the two systems are highly linearly correlated; When the value is close to 0, it means that there is no significant linear relationship between the energy consumption data of the two systems;

[0022] S23, clustering algorithms are used to perform cluster analysis on the energy consumption data of each energy system to identify similar patterns of energy consumption and patterns of coordinated consumption. For example, heating and cooling systems may exhibit similar load fluctuations under similar seasonal patterns, and clustering algorithms can help reveal such coordinated consumption patterns.

[0023] S24, Generate Energy Consumption Interaction Model: Based on correlation coefficients and cluster analysis, construct a multi-dimensional energy consumption interaction model to reflect the mutual influence and potential conflicts between various energy systems:

[0024] Usage data interaction sub-model: Analyzes the consumption of different energy systems over the same time period and identifies interdependencies or conflicts between systems;

[0025] Fluctuation amplitude synergy effect sub-model: Based on the energy consumption fluctuation amplitude of each energy system, that is, the standard deviation, it is determined whether there is a superposition or suppression effect between the fluctuations of certain energy systems;

[0026] Energy consumption time period interaction sub-model: By analyzing the data of energy consumption time periods, the energy efficiency interaction patterns of different energy systems in daily and seasonal changes are identified. The energy consumption data of a certain day or season is set, and the coordinated consumption trends of different systems in these time periods are analyzed by dividing them into time periods (peak, off-peak and low-peak periods).

[0027] Optionally, the clustering algorithm in S23 is used to analyze the energy consumption patterns of different energy systems to find the rules of collaborative consumption in the time period The energy consumption data of water supply system, power supply system, gas supply system, heating system and cooling system are ,in Representing different energy systems, we use K-means clustering to cluster similar consumption patterns into the same class. The goal of K-means clustering is to minimize the variance of energy consumption data within a class:

[0028] initialization Cluster centers ;

[0029] Each sample data Assign to the closest cluster center ,form clusters;

[0030] Calculate the center point of each cluster (new cluster centers), and update the cluster centers: ,in, Belongs to cluster The set of all samples of is a collection The number of samples in ;

[0031] The cluster centers are updated repeatedly until they converge or the maximum number of iterations is reached.

[0032] The clustering results will reveal the collaborative consumption patterns among energy systems. For example, some energy systems (such as heating and cooling) may show similar energy consumption fluctuations in certain seasons or time periods.

[0033] Optionally, the usage data interaction sub-model is implemented through a multi-dimensional interaction matrix Indicates that based on the Pearson correlation coefficient , which represents the interactive relationship between energy consumption data among energy systems.

[0034] Optionally, the multidimensional interaction matrix Elements It is expressed as follows:

[0035] ,in, is a The matrix, is the number of energy systems, each element Indicates the energy systems and The correlation between energy systems.

[0036] Optionally, the energy efficiency in S3 is calculated as:

[0037] ,in, Indicates the time period Internal energy system energy efficiency, Indicates the time period Internal energy system Output of services provided, Indicates the time period Internal energy system energy consumption, Represents the energy system and The correlation coefficient between : Indicates time period Internal energy system Energy efficiency change, used to correct The efficiency of this formula shows that by introducing the interaction effects of other systems (i.e. and ), which can more accurately calculate the actual utilization efficiency of each energy system and comprehensively consider the interactions between them.

[0038] Optionally, the identification of energy consumption peak periods and redundant usage in S3 specifically includes:

[0039] Peak energy consumption identification during peak hours: By analyzing the energy consumption data and correlation coefficients of each energy system, the peak energy consumption during peak hours is identified. The identification of peak energy consumption not only depends on the energy consumption changes of a single energy system, but also considers the impact of other energy systems on the peak period. For example, the load fluctuations of the heating and cooling systems may have a strong correlation with the peak load of the power supply system, affecting its utilization efficiency; Peak energy consumption during peak hours Calculated as:

[0040] .

[0041] Redundant usage identification: Combine the correlation coefficient and energy efficiency in the energy consumption interaction model to analyze redundant usage. If an energy system maintains a high energy consumption level without requiring additional energy input, it indicates redundant usage. The judgment is expressed as:

[0042] During low demand periods (e.g., at night), if High energy consumption and low efficiency of the system indicate redundant usage.

[0043] Optionally, the automatic generation of the collaborative energy-saving strategy in S3 specifically includes:

[0044] During peak hours for a particular energy system, collaborative energy-saving strategies adjust the loads of other energy systems to reduce overall energy consumption. For example, when the air conditioning system is under high load, unnecessary power consumption can be appropriately reduced, concentrating power supply to priority equipment. At the same time, cooling system operating parameters (such as compressor operating frequency) can be optimized to balance the load and avoid excessive system consumption.

[0045] Based on redundant usage identified during off-peak hours, collaborative energy-saving strategies adjust the operating status of corresponding energy systems to avoid inefficient consumption. For example, during low-usage periods at night, the output of gas, water, or cooling systems is reduced or energy consumption in standby mode is reduced to avoid excessive energy consumption during periods of low demand.

[0046] Based on the interactions between energy systems, collaborative energy-saving strategies disperse or shift energy consumption from high-load energy systems. For example, when the power supply system is highly loaded and correlation analysis indicates that demand from the cooling system will increase pressure on the power supply system, the cooling system's operating load can be appropriately reduced, or some power demand can be distributed through other systems (such as the water supply system) to achieve coordinated load shifting. This ensures balanced energy supply during peak hours and avoids overloading a single system.

[0047] Beneficial effects of the present invention:

[0048] The present invention establishes an energy consumption interaction model between various energy systems by real-time monitoring of multiple energy systems in a building. This model can not only reveal the mutual relationship and synergy between various systems, but also dynamically calculate the energy utilization efficiency of each system in different time periods. This analysis method based on interactive relationships enables the collaborative energy-saving strategy to automatically optimize the scheduling of various systems in different time periods, avoiding the problem of overload or low energy efficiency of a single system. Through this method, not only the overall energy efficiency of various energy systems can be greatly improved, but also the load between various systems can be effectively balanced, ensuring the rational use of energy and the long-term stable operation of the system.

[0049] This invention, through in-depth analysis of the energy efficiency of each energy system, can accurately identify load characteristics during peak hours and redundant energy consumption during off-peak hours. Based on this analysis, the system can generate collaborative energy-saving strategies, automatically optimize energy distribution, and reduce unnecessary energy waste. Especially during peak hours, the system prioritizes energy allocation to critical systems based on an energy consumption interaction model, deferring or reducing energy consumption in less important systems, thereby alleviating high loads and reducing energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 A schematic flow chart of a collaborative energy-saving method according to an embodiment of the present invention;

[0052] Figure 2 Schematic diagram of the energy consumption interaction model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0054] It should be noted that references in the specification to "one embodiment," "an embodiment," "exemplary embodiments," "some embodiments," etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment will include such specific features, structures, or characteristics. Furthermore, when specific features, structures, or characteristics are described in conjunction with an embodiment, it is within the knowledge of persons skilled in the relevant art to implement such features, structures, or characteristics in conjunction with other embodiments (whether or not explicitly described).

[0055] In general, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending at least in part on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0056] like Figure 1-Figure 2 As shown, a method for monitoring water, electricity, gas, heating and cooling energy consumption and collaborative energy saving includes the following steps:

[0057] S1: Multiple sensor nodes installed in the building collect real-time energy consumption data from various energy systems, including water supply, power supply, gas supply, heating, and cooling systems. Energy consumption data includes usage data, fluctuation range, and energy consumption time period. The energy consumption data is transmitted to the central processing unit for pre-processing to form a complete energy consumption data set.

[0058] S2: Based on the acquired energy consumption data set and combined with historical energy consumption data, the interrelationships among energy systems are comprehensively analyzed to generate an energy consumption interaction model among energy systems;

[0059] S3: Based on the established energy consumption interaction model, calculate the energy utilization efficiency of the water supply system, power supply system, gas supply system, heating system, and cooling system in different time periods, identify peak energy consumption periods and redundant usage, automatically generate collaborative energy-saving strategies, and optimize the scheduling between various energy systems.

[0060] A multi-sensor node involves installing a variety of sensors across various energy systems within a building, including:

[0061] Water flow sensor: used to collect water consumption data of the water supply system and record water flow rate and usage in real time;

[0062] Current and voltage sensors: used to collect power consumption data of the power supply system and calculate actual power consumption by monitoring current, voltage and power factor;

[0063] Gas flow sensor: used to collect gas consumption data of the gas supply system and calculate gas consumption by monitoring gas flow rate;

[0064] Temperature sensor and humidity sensor: used for energy consumption monitoring of heating and cooling systems. By collecting changes in ambient temperature and humidity and combining them with the operating conditions of heating and cooling equipment, energy consumption can be calculated.

[0065] The raw energy consumption data collected by each sensor is transmitted to the central processing unit. After receiving the raw energy consumption data from each sensor node, the central processing unit performs data preprocessing, specifically including:

[0066] S11: Usage data: Normalize the usage data of each energy system to a standard unit (unify the units of water, electricity, and gas to standard units) to ensure that data from different energy types can be directly compared;

[0067] S12: Fluctuation amplitude data: Calculate the amplitude or variance of energy consumption fluctuation based on the data changes within a predetermined time period. The fluctuation amplitude is expressed as standard deviation. To indicate, set the time period The energy consumption data in , then the fluctuation range, that is, the standard deviation is calculated as: ,in, is the mean of energy consumption data, is the number of samples, It is Energy consumption data at each sampling moment;

[0068] S13: Energy consumption time period data: Based on time series data, classify the consumption data of each energy system in different time periods, identify the peak energy consumption period and the valley energy consumption period of each energy system, determine the optimal use time of each energy, divide the total time period into several sub-time periods, and calculate the total energy consumption of each sub-time period ,mark the time periods in each sub-time period where the energy consumption exceeds the predetermined threshold (the threshold is set to 90% of the historical data) as peak energy consumption periods.,The usage data, fluctuation range and energy consumption time period are integrated into a complete energy consumption data set.

[0069] In S2, based on the energy consumption dataset obtained in S1 and combined with historical energy consumption data, a comprehensive analysis is performed to generate an energy consumption interaction model between various energy systems. This model reveals the interrelationships between various energy systems (including water supply systems, power supply systems, gas supply systems, heating systems, and cooling systems), and provides a decision-making basis for subsequent collaborative energy-saving strategies, including:

[0070] S21, fusion of historical energy consumption data and real-time data: combining historical energy consumption data with real-time collected energy consumption data to construct a comprehensive energy consumption data set. The historical data includes the energy consumption data of each energy system obtained through the S1 method at different time periods.

[0071] S22, by calculating the correlation coefficient between each energy system , analyzing the linear correlation between consumption patterns in different time periods, including the water supply system and power supply system As an example, the correlation coefficient calculation is and In time The energy consumption is and , correlation coefficient The calculation formula is: , Indicates the moment, Indicates the Real-time water supply system The energy consumption value, Indicates the Constant power supply system The energy consumption value, For water supply system The average energy consumption, For power supply system The average energy consumption, is the number of samples, the value range of the Pearson correlation coefficient is [-1,1]. When it approaches 1 or 1, it means that the energy consumption data of the two systems are highly linearly correlated; When the value is close to 0, it means that there is no significant linear relationship between the energy consumption data of the two systems;

[0072] S23, clustering algorithms are used to perform cluster analysis on the energy consumption data of each energy system to identify similar patterns of energy consumption and patterns of coordinated consumption. For example, heating and cooling systems may exhibit similar load fluctuations under similar seasonal patterns, and clustering algorithms can help reveal such coordinated consumption patterns.

[0073] S24, Generate Energy Consumption Interaction Model: Based on correlation coefficients and cluster analysis, construct a multi-dimensional energy consumption interaction model to reflect the mutual influence and potential conflicts between various energy systems:

[0074] Usage data interaction sub-model: Analyzes the consumption of different energy systems over the same time period and identifies interdependencies or conflicts between systems;

[0075] Fluctuation amplitude synergistic effect sub-model: According to the energy consumption fluctuation amplitude of each energy system, that is, the standard deviation, it is judged whether there is a superposition or suppression effect between certain energy systems. Suppose the energy consumption of the heating system and the cooling system in a certain time period are and , their fluctuation range (standard deviation) is calculated by the following formula:

[0076] ;

[0077] ;

[0078] if and The fluctuation amplitude of is large and their correlation is strong, which indicates that there may be a phenomenon of coordinated load fluctuation between the two systems;

[0079] Energy consumption time period interaction sub-model: By analyzing the data of energy consumption time periods, the energy efficiency interaction patterns of different energy systems in daily and seasonal changes are identified. The energy consumption data of a certain day or season is set, and the coordinated consumption trends of different systems in these time periods are analyzed by dividing them into time periods (peak, off-peak and low-peak periods).

[0080] The clustering algorithm in S23 is used to analyze the energy consumption patterns of different energy systems to find the rules of collaborative consumption in the time period The energy consumption data of water supply system, power supply system, gas supply system, heating system and cooling system are ,in Representing different energy systems, we use K-means clustering to cluster similar consumption patterns into the same class. The goal of K-means clustering is to minimize the variance of energy consumption data within a class:

[0081] initialization Cluster centers ;

[0082] Each sample data Assign to the closest cluster center ,form clusters;

[0083] Calculate the center point of each cluster (new cluster centers), and update the cluster centers: ,in, Belongs to cluster The set of all samples of is a collection The number of samples in ;

[0084] The cluster centers are updated repeatedly until they converge or the maximum number of iterations is reached.

[0085] The clustering results will reveal the collaborative consumption patterns among energy systems. For example, some energy systems (such as heating and cooling) may show similar energy consumption fluctuations in certain seasons or time periods.

[0086] The usage data interaction sub-model uses a multi-dimensional interaction matrix Indicates that based on the Pearson correlation coefficient , which represents the interactive relationship between energy consumption data among energy systems.

[0087] Multidimensional interaction matrix Elements It is expressed as follows:

[0088] ,in, is a The matrix, is the number of energy systems, each element Indicates the energy systems and The correlation between energy systems.

[0089] In the energy consumption interaction model generated above, the mutual influence between various energy systems has been revealed through correlation analysis and cluster analysis. Based on this model, the energy efficiency performance of each energy system in different time periods is identified, especially the impact of the relationship between each system on the overall energy utilization efficiency.

[0090] For example, assuming that there is a strong correlation between the water supply system and the power supply system, the energy efficiency changes of these two systems may be synchronized to a certain extent. To take into account the energy consumption interaction between them, the energy efficiency in S3 is calculated as:

[0091] ,in, Indicates the time period Internal energy system energy efficiency, Indicates the time period Internal energy system Output of services provided, Indicates the time period Internal energy system energy consumption, Represents the energy system and The correlation coefficient between : Indicates time period Internal energy system Energy efficiency change, used to correct The efficiency of this formula shows that by introducing the interaction effects of other systems (i.e. and ), which can more accurately calculate the actual utilization efficiency of each energy system and comprehensively consider the interactions between them.

[0092] Identifying peak energy consumption periods and redundant usage in S3 specifically includes:

[0093] Peak energy consumption identification during peak hours: By analyzing the energy consumption data and correlation coefficients of each energy system, the peak energy consumption during peak hours is identified. The identification of peak energy consumption not only depends on the energy consumption changes of a single energy system, but also considers the impact of other energy systems on the peak period. For example, the load fluctuations of the heating and cooling systems may have a strong correlation with the peak load of the power supply system, affecting its utilization efficiency; Peak energy consumption during peak hours Calculated as:

[0094] .

[0095] Redundant usage identification: Combine the correlation coefficient and energy efficiency in the energy consumption interaction model to analyze redundant usage. If an energy system maintains a high energy consumption level without requiring additional energy input, it indicates redundant usage. The judgment is expressed as:

[0096] During low demand periods (e.g., at night), if High energy consumption and low efficiency of the system indicate redundant usage.

[0097] The automatic generation of collaborative energy-saving strategies in S3 specifically includes:

[0098] Certain energy systems (such as cooling and heating systems) are heavily loaded, potentially leading to decreased energy efficiency and wasted resources. Therefore, during peak hours for a particular energy system, collaborative energy-saving strategies adjust the loads of other energy systems to reduce overall energy consumption. For example, during periods of high air conditioning system load, unnecessary power consumption can be appropriately reduced, concentrating power supply to priority equipment. Furthermore, cooling system operating parameters (such as compressor operating frequency) can be optimized to balance loads and avoid excessive system consumption.

[0099] Based on redundant usage identified during off-peak hours, collaborative energy-saving strategies adjust the operating status of corresponding energy systems to avoid inefficient consumption. For example, during low-usage periods at night, the output of gas, water, or cooling systems is reduced or energy consumption in standby mode is reduced to avoid excessive energy consumption during periods of low demand.

[0100] Based on the interactions between energy systems, collaborative energy-saving strategies disperse or shift energy consumption from high-load energy systems. For example, when the power supply system is highly loaded and correlation analysis indicates that demand from the cooling system will increase pressure on the power supply system, the cooling system's operating load can be appropriately reduced, or some power demand can be distributed through other systems (such as the water supply system) to achieve coordinated load shifting. This ensures balanced energy supply during peak hours and avoids overloading a single system.

[0101] Also includes intelligent priority scheduling:

[0102] Based on the urgency of energy consumption peak periods and the importance of the system, priorities can be assigned to different energy systems when automatically generating energy-saving strategies. During peak periods, priority is given to ensuring the energy needs of core energy systems, and energy consumption of non-critical energy systems is delayed or reduced. For example, during peak periods, priority is given to ensuring the load needs of power supply and heating systems, while reducing the load on non-core functions of cooling and gas supply systems. This ensures that important energy needs are met while optimizing overall energy utilization efficiency.

[0103] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0104] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for monitoring and collaborative energy saving of water, electricity, gas, heating and cooling energy consumption, characterized in that: The following steps are involved: S1: Multiple sensor nodes installed in the building collect real-time energy consumption data from various energy systems, including water supply, power supply, gas supply, heating, and cooling systems. Energy consumption data includes usage data, fluctuation range, and energy consumption time period. The energy consumption data is transmitted to the central processing unit for pre-processing to form a complete energy consumption data set. S2: Based on the acquired energy consumption dataset and combined with historical energy consumption data, we comprehensively analyze the relationships between energy systems and generate an energy consumption interaction model between energy systems. Specifically, we include: By calculating the Pearson correlation coefficient r between the energy consumption data of each energy system, the linear correlation of consumption patterns in different time periods is analyzed; Clustering algorithms are used to perform cluster analysis on the energy consumption data of each energy system to identify similar patterns of energy consumption and the rules of coordinated consumption; Generate an energy consumption interaction model: Based on the Pearson correlation coefficient r and cluster analysis, a multi-dimensional energy consumption interaction model is constructed. This model includes a usage data interaction sub-model, a fluctuation amplitude synergy effect sub-model, and an energy consumption time period interaction sub-model. This model reflects the mutual influence and potential conflicts between energy systems. The usage data interaction sub-model analyzes the consumption of different energy systems in the same time period and identifies the interdependence or opposition between the systems; The synergistic effect sub-model of fluctuation amplitude determines whether there is a superposition or suppression effect of fluctuations between certain energy systems based on the energy consumption fluctuation amplitude of each energy system, that is, the standard deviation; The energy consumption time period interaction sub-model analyzes the data of energy consumption time periods to identify the energy efficiency interaction patterns of different energy systems in daily and seasonal changes; S3: Based on the established energy consumption interaction model, calculate the energy utilization efficiency of the water supply system, power supply system, gas supply system, heating system, and cooling system in different time periods, identify peak energy consumption periods and redundant usage, automatically generate collaborative energy-saving strategies, and optimize the scheduling between various energy systems.

2. A method for monitoring and collaborative energy saving of water, electricity, gas, heating and cooling energy consumption according to claim 1, characterized in that: The multi-sensor node includes multiple sensors installed in various energy systems within the building, specifically including: Water flow sensor: used to collect water consumption data of the water supply system and record water flow rate and usage in real time; Current and voltage sensors: used to collect power consumption data of the power supply system and calculate actual power consumption by monitoring current, voltage and power factor; Gas flow sensor: used to collect gas consumption data of the gas supply system and calculate gas consumption by monitoring gas flow rate; Temperature sensor and humidity sensor: used for energy consumption monitoring of heating and cooling systems. By collecting changes in ambient temperature and humidity and combining them with the operating conditions of heating and cooling equipment, energy consumption can be calculated. The raw energy consumption data collected by each sensor is transmitted to the central processing unit. After receiving the raw energy consumption data from each sensor node, the central processing unit performs data preprocessing, specifically including: S11: Usage data: Normalize the unit of usage data of each energy system; S12: Fluctuation amplitude data: Calculate the amplitude or variance of energy consumption fluctuation according to the data changes within a predetermined time period. The fluctuation amplitude is represented by the standard deviation σ. Suppose the energy consumption data within the time period T are Q1, Q2, ..., Q n , then the fluctuation range, that is, the standard deviation is calculated as: Among them, μ is the mean of energy consumption data, n is the number of samples, Q n is the energy consumption data at the nth sampling moment; S13: Energy consumption time period data: Based on time series data, classify the consumption data of each energy system in different time periods, identify the peak energy consumption period and the valley energy consumption period of each energy system, determine the optimal use time of each energy, divide the total time period into several sub-time periods, and calculate the total energy consumption Q of each sub-time period. segment (t), marking the time period in each sub-time period when the energy consumption is greater than the predetermined threshold as the peak energy consumption period.

3. The method for monitoring and collaborative energy saving of water, electricity, gas, heating and cooling energy consumption according to claim 1, characterized in that: The clustering algorithm is used to analyze the energy consumption patterns of different energy systems to discover the rules of collaborative consumption. In the time period T, the energy consumption data of the water supply system, power supply system, gas supply system, heating system, and cooling system are where E1, E2, …, E m Representing different energy systems, we use K-means clustering to cluster similar consumption patterns into the same class. The goal of K-means clustering is to minimize the variance of energy consumption data within a class: Initialize k cluster centers C1, C2, ..., C k ; Each sample data Assigned to the nearest cluster center C j , forming k clusters; Calculate the center point C of each cluster j ′, and update the cluster center: Among them, S j is the set of all samples belonging to cluster j, |S j | is the set S j The number of samples in ; The cluster centers are updated repeatedly until they converge or the maximum number of iterations is reached.

4. The method for monitoring and collaborative energy saving of water, electricity, gas, heating and cooling energy consumption according to claim 3, characterized in that: The usage data interaction sub-model is represented by a multi-dimensional interaction matrix R, the elements of which are It is expressed as follows: Where R is an m×m matrix, m is the number of energy systems, and each element represents the Pearson correlation coefficient between the i-th energy system and the j-th energy system.

5. The method for monitoring and collaborative energy saving of water, electricity, gas, heating and cooling energy consumption according to claim 4, characterized in that: The energy efficiency in S3 is calculated as: in, Indicates that in time period t, the energy system E i energy efficiency, Indicates that during the time period T, the energy system E i Output of services provided, Indicates that during the time period T, the energy system E i energy consumption, Represents the energy system E i With E j The correlation coefficient between Indicates that during the time period T, the energy system E j The energy efficiency change is used to correct E i efficiency.

6. The method for monitoring and collaborative energy saving of water, electricity, gas, heating and cooling energy consumption according to claim 5, characterized in that: The identification of energy consumption peak periods and redundant usage in S3 specifically includes: Peak energy consumption identification during peak hours: By analyzing the energy consumption data and correlation coefficients of each energy system, the peak energy consumption during peak hours is identified. The identification of peak energy consumption not only depends on the energy consumption changes of a single energy system, but also considers the impact of other energy systems on the peak period. Calculated as: Identification of redundant usage: Combine the correlation coefficient and energy efficiency in the energy consumption interaction model to analyze redundant usage. If an energy system maintains a high energy consumption level without requiring additional energy input, it indicates redundant usage.

7. The method for monitoring water, electricity, gas, heating and cooling energy consumption and coordinating energy saving according to claim 6, characterized in that: The automatic generation of collaborative energy-saving strategies in S3 specifically includes: During the peak period of a certain energy system, the collaborative energy-saving strategy adjusts the load of other energy systems to reduce overall energy consumption; Based on the redundant usage identified during off-peak hours, the collaborative energy-saving strategy adjusts the operating status of the corresponding energy system to avoid ineffective consumption; Based on the interactive relationship between various energy systems, the collaborative energy-saving strategy disperses or transfers the energy consumption of high-load energy systems.

Images