Energy-saving data collaborative management system and method based on big data analysis

Abstract

The application discloses an energy-saving data collaborative management system and method based on big data analysis, relates to the technical field of energy-saving data collaborative management, and comprises the following steps: obtaining a target region by evaluating the temperature change abnormal condition of an evaluation region in a central air conditioner refrigeration process; analyzing the correlation degree of a monitoring index in a historical environment monitoring record and people flow in the target region, and predicting the people flow change condition in the target region in a current period; obtaining cold load demand data by analyzing the cold load demand condition of the target region in the current period; obtaining the cold load demand data of different regions in a building in the current period, obtaining equipment energy-saving data of the central air conditioner, combining the cold load demand data, generating a control strategy of the central air conditioner, and collaboratively managing refrigeration in different regions based on the control strategy, so that not only is the cold load demand of each region ensured to be met, but also the energy consumption of the central air conditioner during work is greatly reduced, and the energy consumption is significantly saved.

Description

Technical Field

[0001] This invention relates to the field of energy-saving data collaborative management technology, specifically to an energy-saving data collaborative management system and method based on big data analysis. Background Technology

[0002] Currently, large buildings rely on central air conditioning for cooling. Central air conditioning systems install corresponding air outlets in different areas of a large building, and the temperature and airflow at these outlets are preset. While this method can lower the temperature in different areas of a large building, the conditions in each area vary. Some areas have fixed environments with minimal personnel movement, resulting in relatively stable cooling needs. However, the cooling needs of other areas fluctuate significantly due to factors such as personnel movement. Therefore, this traditional method of controlling the temperature and airflow at the outlets based solely on preset values, and then having the central air conditioning system operate according to these preset parameters, fails to dynamically control the central air conditioning system according to the cooling needs of different areas. It cannot adapt to the varying cooling requirements of different areas within a large building, resulting in poor cooling performance and significantly increased energy consumption, thus failing to meet the energy-saving requirements of central air conditioning systems. Summary of the Invention

[0003] The purpose of this invention is to provide an energy-saving data collaborative management system and method based on big data analysis to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: an energy-saving data collaborative management method based on big data analysis, the method comprising:

[0005] Step S100: Obtain the area in the building where the central air conditioning is used for cooling, obtain historical temperature change records within the area, assess the abnormal temperature change situation in the area during the central air conditioning cooling process, and obtain the target area;

[0006] Step S200: Obtain historical records of pedestrian flow changes and historical environmental monitoring records for the target area; analyze the correlation between monitoring indicators in the historical environmental monitoring records and pedestrian flow in the target area to obtain relevant data; obtain environmental monitoring data for the target area in the current period; and combine the relevant data to predict pedestrian flow changes in the target area in the current period to obtain pedestrian flow prediction data.

[0007] Step S300: Obtain heat source data for the target area in the current period, and combine it with pedestrian flow prediction data to analyze the cooling load demand of the target area in the current period, and obtain cooling load demand data.

[0008] Step S400: Obtain cooling load demand data for different areas of the building during the current period, obtain energy-saving data of the central air conditioning equipment, and generate a control strategy for the central air conditioning system based on the cooling load demand data. Based on the control strategy, coordinate the cooling in different areas.

[0009] Furthermore, step S100 includes:

[0010] Step S101: Obtain historical temperature change records for each area in the building where the central air conditioning system is responsible for cooling, and set the unit time. The average temperature within a unit time interval is obtained from the historical temperature change records at regular intervals, and then aggregated to obtain a temperature dataset of historical temperature change records.

[0011] Step S102: Obtain the historical period to which the historical temperature change records belong, and calculate the temperature trend slope β of the region within the historical period based on the temperature dataset;

[0012] Step S103: Obtain the mean μ and variance δ of the temperature of each element in the temperature dataset, construct the temperature vector A = [β,μ,δ] of the region within the historical period, and obtain the mean μ of the temperature of each region in the building within the historical period. △ The mean of the variance δ △ and the mean β of the slope of the temperature trend △ Construct the temperature vector A of the building within the historical period. △ =[β △ μ △ δ △ ], Calculate the similarity of temperature changes between the region and the building over historical cycles (B):

[0013]

[0014] Step S104: Obtain the similarity of temperature changes between the region and the building in each historical period, and calculate the temperature change difference value C between the region and the building.

[0015]

[0016] Where j is the total number of historical cycles; B i The similarity of temperature changes between the region and the building during the i-th historical period;

[0017] Obtain the mean value C of the temperature variation differences between various regions and buildings. △ The temperature change difference C is compared with the mean C. △ The absolute value of the difference divided by the mean C △The value α is recorded as the degree of temperature change abnormality in the region. When α is greater than the preset threshold, it is determined that the temperature change in the region is abnormal during the central air conditioning cooling process, and the region is recorded as the target region.

[0018] Furthermore, step S200 includes:

[0019] Step S201: Obtain historical pedestrian flow records and historical environmental monitoring records for each historical period of the target area, preprocess the data in the historical pedestrian flow records and historical environmental monitoring records, obtain the total number of pedestrians in the target area from the historical pedestrian flow records every unit of time, and aggregate them to obtain a pedestrian flow dataset;

[0020] Step S202: Obtain historical environmental monitoring records for the target area, and extract the values ​​of various monitoring indicators from the historical environmental monitoring records at regular intervals to obtain the monitoring dataset;

[0021] Step S203: Based on the pedestrian flow dataset and the monitoring dataset, calculate the correlation coefficient between each monitoring indicator in the historical period to which the historical pedestrian flow records belong and the total number of pedestrians in the target area, obtain the average value of the correlation coefficient between the monitoring indicators in each historical period and the total number of pedestrians in the target area, and obtain the degree of correlation between the monitoring indicators and the total number of pedestrians in the target area.

[0022] Obtain the correlation between each monitoring indicator and the total number of people in the target area, and calculate the correlation ratio L between the monitoring indicators and the total number of people in the target area.

[0023]

[0024] Where, q x denoted as x, representing the correlation between the xth monitoring indicator and the total number of people in the target area; q represents the correlation ratio between the monitoring indicator and the total number of people in the target area; n represents the total number of monitoring indicators.

[0025] Set a value k, sort the monitoring indicators according to their proportion of the total number of people in the target area, select the top k monitoring indicators and mark them, determine that the top k monitoring indicators are related to the total number of people in the target area, and record them as relevant monitoring indicators. Collect and aggregate all relevant monitoring indicators that are related to the target area to obtain relevant data.

[0026] Step S204: Remove the values ​​of monitoring indicators that are marked as relevant monitoring indicators from the monitoring dataset of historical environmental monitoring records to obtain the relevant monitoring dataset;

[0027] Obtain historical pedestrian flow datasets for the target area over various historical periods, obtain relevant monitoring datasets from historical environmental monitoring records for the target area over various historical periods, and obtain data on the seasons and holidays for each historical period. Construct a pedestrian flow prediction model y(t) for the target area:

[0028] y(t)=g(t)+s(t)+h(t)+r(t)+ε t ,

[0029] Wherein, g(t) is the trend term of the traffic flow prediction model y(t); s(t) is the seasonal term of the traffic flow prediction model y(t); h(t) is the holiday term of the traffic flow prediction model y(t); r(t) is the regression term of the monitoring indicators of the traffic flow prediction model y(t), where r(t) is composed of various relevant monitoring indicators in the target area; ε t This is the error term of the human traffic prediction model y(t);

[0030] Step S205: Obtain the objective function of the pedestrian flow prediction model y(t), train the pedestrian flow prediction model y(t) to minimize the objective function, obtain the key parameters of the pedestrian flow prediction model y(t), and complete the construction of the pedestrian flow prediction model y(t).

[0031] The pedestrian flow prediction model y(t) is used to predict the pedestrian flow in each unit of time within the current period, and the pedestrian flow prediction data of the target area is obtained.

[0032] The above steps obtain relevant monitoring indicators for the target area because, in reality, pedestrian traffic in different regions and even different buildings will affect environmental factors to varying degrees. However, the environment contains various monitoring indicators. Therefore, selecting those related to pedestrian traffic changes in the target area from among numerous monitoring indicators can not only greatly save computing time and resources but also improve the accuracy of model predictions. Furthermore, when building the model, considering the influencing factors in time and space, holidays and seasons are also taken as relational factors in model construction, thereby greatly improving the accuracy of model predictions.

[0033] Furthermore, step S300 includes:

[0034] Step S301: Obtain heat source data for the target area within the current period. The heat source data includes the total heat P of the static heat source in the target area per unit time. sum ;

[0035] Step S302: Obtain the predicted pedestrian flow in the target area within each unit of time in the current period, and calculate the cooling demand Q of the target area in the z-th unit of time in the current period. zcool The specific calculation formula is as follows:

[0036] Obtain the predicted outdoor temperature T within the z-th unit of time. (z,out) Obtain the pedestrian flow forecast data for the target area within the current period, and extract the pedestrian flow forecast quantity M for the z-th unit of time from the pedestrian flow forecast data. z Calculate the heat load Q of the target region in the z-th unit of the current period. z total :

[0037]

[0038] Among them, w l and w e These are the sensible heat loss and latent heat loss of the human body, respectively; P (z,sum) The total heat generated by the static heat source in the target area during the z-th unit of time; Let be the initial temperature of the target region at the z-th position;

[0039] Step S303: When the central air conditioning system stops cooling the target area during the z-th unit of time, obtain the highest temperature reached by the target area during the z-th unit of time.

[0040] in, H represents the heat consumed per unit volume of air to raise its temperature by one unit, where H is the unit of time; and V is the volume of the target area.

[0041] Step S304: Calculate the cooling load demand Q of the target area in the z-th unit of time. z cool :

[0042]

[0043] Among them, T △ The target temperature for the target area within the current cycle;

[0044] The cold load demand of the target area in each unit of time within the current period is obtained and aggregated to obtain the cold load demand data of the target area in the current period.

[0045] The above steps analyze the heat load of the target area using a different method than conventional methods. Instead, the heat load of the target area is analyzed based on the predicted pedestrian flow and the heat status of static heat sources. This approach dynamically adjusts the heat load of the area based on the predicted pedestrian flow, making the acquisition of the cooling load demand of the target area in the current cycle more accurate. It also makes the subsequent control of the central air conditioning more accurate, greatly saving energy consumption during the operation of the central air conditioning system.

[0046] Furthermore, step S400 includes:

[0047] Step S401: Obtain cooling load demand data for different areas of the building, and obtain the cooling load demand for different areas of the building in each unit of time within the current period from the cooling load demand data.

[0048] Step S402: Obtain the energy-saving data of the central air conditioning system. The energy-saving data includes the range of the central air conditioning load rate ζ, the range of the difference between the outlet air temperature and the room temperature ψ, and the range of the air velocity at the outlet when the central air conditioning system has the highest energy efficiency ratio.

[0049] Based on the cooling load demand of different regions within each unit of time in the current cycle, the air velocity and air temperature of the air outlets of different regions are adjusted according to the order of cooling load demand to generate a central air conditioning control strategy. Based on the control strategy, the cooling in different regions is managed in a coordinated manner.

[0050] The specific adjustment strategy for the air outlet speed and air outlet temperature in different areas is as follows: the central air conditioning load rate is within the range ζ in the current cycle, the difference between the air outlet temperature and the room temperature in different areas is within the range ψ, and the air outlet speed in different areas is within the range τ.

[0051] To better implement the above methods, an energy-saving data collaborative management system based on big data analysis is also proposed. The system includes a temperature anomaly assessment module, a people flow prediction module, a cooling load demand analysis module, and an energy-saving collaborative management module.

[0052] The temperature anomaly assessment module is used to assess abnormal temperature changes in areas cooled by central air conditioning during the central air conditioning cooling process, and to identify the target area.

[0053] The pedestrian flow prediction module is used to predict the changes in pedestrian flow in the target area within the current period and obtain pedestrian flow prediction data.

[0054] The cold load demand analysis module is used to analyze the cold load demand status of the target area in the current period and obtain cold load demand data.

[0055] The energy-saving collaborative management module is used to acquire energy-saving data of central air conditioning equipment and, in combination with cooling load demand data, generate control strategies for central air conditioning to collaboratively manage cooling in different areas.

[0056] Furthermore, the temperature anomaly assessment module includes a temperature change similarity assessment unit and a temperature anomaly assessment unit;

[0057] The temperature change similarity assessment unit is used to assess the similarity of temperature changes between a region and a building over a historical period, and to calculate the similarity of temperature changes between a region and a building over a historical period.

[0058] The temperature anomaly assessment unit is used to calculate the temperature change difference between the area and the building based on the similarity of temperature changes, and to assess the abnormal temperature change situation of the area during the central air conditioning cooling process based on the temperature change difference value, thereby obtaining the target area.

[0059] Furthermore, the pedestrian flow prediction module includes a correlation analysis unit and a pedestrian flow prediction unit;

[0060] The correlation analysis unit is used to acquire historical environmental monitoring records in the target area, obtain the correlation between monitoring indicators in the historical environmental monitoring records and the flow of people in the target area, and obtain relevant data.

[0061] The pedestrian flow prediction unit is used to acquire historical pedestrian flow change records of the target area and combine them with relevant data to predict the pedestrian flow change in the target area within the current period, thus obtaining pedestrian flow prediction data.

[0062] Furthermore, the cold load demand analysis module includes a regional heat load acquisition unit and a cold load demand analysis unit;

[0063] The regional heat load acquisition unit is used to acquire heat source data of the target area in the current period, acquire the pedestrian flow prediction data of the target area in the current period, and calculate the heat load of the target area per unit time in the current period.

[0064] The cooling load demand analysis unit is used to analyze the cooling load demand of the target area within the current period based on the heat load of the target area per unit time in the current period, and obtain the cooling load demand data of the target area in the current period.

[0065] Furthermore, the energy-saving collaborative management module includes an energy-saving collaborative management unit;

[0066] The energy-saving collaborative management unit is used to acquire cooling load demand data for different areas of the building, obtain energy-saving data of the central air conditioning equipment, and generate control strategies for the central air conditioning system in combination with the cooling load demand data to collaboratively manage the cooling of different areas of the building.

[0067] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention achieves intelligent control of central air conditioning. By analyzing the areas where the central air conditioning is responsible for cooling and comparing the abnormal temperature changes in these areas, a target area is obtained. The correlation between different monitoring indicators and pedestrian traffic is analyzed, and combined with influencing factors such as holidays and seasons in historical periods, a pedestrian traffic prediction model for the target area is constructed. This model predicts the pedestrian traffic in the target area during the current period, thereby analyzing the cooling load demand of the target area during the current period. Based on the cooling load demand data of different areas in the building and the energy-saving data of the central air conditioning equipment, a control strategy for the central air conditioning is generated. Based on the control strategy, the central air conditioning is controlled, which not only ensures that the cooling load demand of each area is met, but also greatly reduces the energy consumption of the central air conditioning during operation, resulting in significant energy savings. Attached Figure Description

[0068] Figure 1 This is a flowchart of the energy-saving data collaborative management method based on big data analysis according to the present invention;

[0069] Figure 2 This is a schematic diagram of the modules of the energy-saving data collaborative management system based on big data analysis of the present invention. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] Example: Figures 1-2 As shown, the present invention provides a technical solution, an energy-saving data collaborative management method based on big data analysis, the method comprising:

[0072] Step S100: Obtain the area in the building where the central air conditioning is used for cooling, obtain historical temperature change records within the area, assess the abnormal temperature change situation in the area during the central air conditioning cooling process, and obtain the target area;

[0073] Step S100 includes:

[0074] Step S101: Obtain historical temperature change records for each area in the building where the central air conditioning system is responsible for cooling, and set the unit time. The average temperature within a unit time interval is obtained from the historical temperature change records at regular intervals, and then aggregated to obtain a temperature dataset of historical temperature change records.

[0075] Step S102: Obtain the historical period to which the historical temperature change records belong, and calculate the temperature trend slope β of the region within the historical period based on the temperature dataset;

[0076] For example, the specific formula for calculating the slope β of the temperature trend in the region over historical periods is:

[0077]

[0078] Among them, t i Let be the feature duration of the i-th element in the temperature dataset, where t △ T is the average of the feature durations of each element in the temperature dataset; i T represents the average temperature of the i-th element in the temperature dataset; △ This represents the average temperature of each element in the temperature dataset.

[0079] Step S103: Obtain the mean μ and variance δ of the temperature of each element in the temperature dataset, construct the temperature vector A = [β,μ,δ] of the region within the historical period, and obtain the mean μ of the temperature of each region in the building within the historical period. △ The mean of the variance δ △ and the mean β of the slope of the temperature trend △ Construct the temperature vector A of the building within the historical period. △ =[β △ μ △ δ △ ], Calculate the similarity of temperature changes between the region and the building over historical cycles (B):

[0080]

[0081] Step S104: Obtain the similarity of temperature changes between the region and the building in each historical period, and calculate the temperature change difference value C between the region and the building.

[0082]

[0083] Where j is the total number of historical cycles; B i The similarity of temperature changes between the region and the building during the i-th historical period;

[0084] Obtain the mean value C of the temperature variation differences between various regions and buildings. △ The temperature change difference C is compared with the mean C. △ The absolute value of the difference divided by the mean C△ The value of the abnormal temperature change in the region is recorded as α. When α is greater than the preset threshold, it is determined that the temperature change in the region is abnormal during the central air conditioning cooling process, and the region is recorded as the target region.

[0085] Step S200: Obtain historical records of pedestrian flow changes and historical environmental monitoring records for the target area; analyze the correlation between monitoring indicators in the historical environmental monitoring records and pedestrian flow in the target area to obtain relevant data; obtain environmental monitoring data for the target area in the current period; and combine the relevant data to predict pedestrian flow changes in the target area in the current period to obtain pedestrian flow prediction data.

[0086] Step S200 includes:

[0087] Step S201: Obtain historical pedestrian flow records and historical environmental monitoring records for each historical period of the target area, preprocess the data in the historical pedestrian flow records and historical environmental monitoring records, obtain the total number of pedestrians in the target area from the historical pedestrian flow records every unit of time, and aggregate them to obtain a pedestrian flow dataset;

[0088] For example, preprocessing includes outlier removal and normalization or standardization.

[0089] Step S202: Obtain historical environmental monitoring records for the target area, and extract the values ​​of various monitoring indicators from the historical environmental monitoring records at regular intervals to obtain the monitoring dataset;

[0090] For example, various monitoring indicators, including ambient temperature, humidity, and rainfall;

[0091] Step S203: Based on the pedestrian flow dataset and the monitoring dataset, calculate the correlation coefficient between each monitoring indicator in the historical period to which the historical pedestrian flow records belong and the total number of pedestrians in the target area, obtain the average value of the correlation coefficient between the monitoring indicators in each historical period and the total number of pedestrians in the target area, and obtain the degree of correlation between the monitoring indicators and the total number of pedestrians in the target area.

[0092] For example, the specific formula for calculating the correlation coefficient P between the monitoring indicators within the historical period to which the historical pedestrian flow records belong and the total number of pedestrians in the target area can be:

[0093]

[0094] Where, x i x is the value of the monitoring indicator in the i-th element of the historical environmental monitoring dataset; △ To measure the average value of the monitoring indicators in each element of the monitoring dataset; y iy represents the total number of people in the i-th element of the historical pedestrian flow dataset; △ is the total number of people in each element of the human flow dataset; n is the total number of each element in the human flow dataset;

[0095] Obtain the correlation between each monitoring indicator and the total number of people in the target area, and calculate the correlation ratio L between the monitoring indicators and the total number of people in the target area.

[0096]

[0097] Where, q x denoted as x, representing the correlation between the xth monitoring indicator and the total number of people in the target area; q represents the correlation ratio between the monitoring indicator and the total number of people in the target area; n represents the total number of monitoring indicators.

[0098] Set a value k, sort the monitoring indicators according to their proportion of the total number of people in the target area, select the top k monitoring indicators and mark them, determine that the top k monitoring indicators are related to the total number of people in the target area, and record them as relevant monitoring indicators. Collect and aggregate all relevant monitoring indicators that are related to the target area to obtain relevant data.

[0099] Step S204: Remove the values ​​of monitoring indicators that are marked as relevant monitoring indicators from the monitoring dataset of historical environmental monitoring records to obtain the relevant monitoring dataset;

[0100] Obtain historical pedestrian flow datasets for the target area over various historical periods, obtain relevant monitoring datasets from historical environmental monitoring records for the target area over various historical periods, and obtain data on the seasons and holidays for each historical period. Construct a pedestrian flow prediction model y(t) for the target area:

[0101] y(t)=g(t)+s(t)+h(t)+r(t)+ε t ,

[0102] Wherein, g(t) is the trend term of the traffic flow prediction model y(t); s(t) is the seasonal term of the traffic flow prediction model y(t); h(t) is the holiday term of the traffic flow prediction model y(t); r(t) is the regression term of the monitoring indicators of the traffic flow prediction model y(t), where r(t) is composed of various relevant monitoring indicators in the target area; ε t This is the error term of the human traffic prediction model y(t);

[0103] For example, g(t), h(t), r(t) and ε t The specific formula is as follows:

[0104] g(t) is specifically:

[0105]

[0106] Wherein, δ is the total number of elements in the pedestrian flow dataset in the target region n. i γ represents the change in the growth rate of the total number of people in the i-th element of the human flow dataset; i =-δ i ·t i k is the base growth rate of the total number of people; m is the initial value of the total number of people.

[0107] a i (t) is the variable point indicator function, and its specific formula is:

[0108]

[0109] The specific formula for s(t) is:

[0110]

[0111] Where P = {daily, weekly, yearly}, and for each term in P, a Fourier series is taken, s p (t):

[0112]

[0113] Among them, a p,n and b p,n These are the coefficients of the Fourier series, which together determine the specific form of seasonal fluctuations. When p is weekly, N weekly =3;

[0114] The specific formula for h(t) is:

[0115]

[0116] Among them, κ i For the impact intensity parameter of holidays; I Di is the preset indicator function; L is the total number of holiday events;

[0117] The specific formula for r(t) is:

[0118]

[0119] Where, β k x is the k-th relevant monitoring indicator for the target area; k (t) represents the standardized value of the k-th relevant monitoring indicator for the target area;

[0120] ε t :

[0121]

[0122] Step S205: Obtain the objective function of the pedestrian flow prediction model y(t), train the pedestrian flow prediction model y(t) to minimize the objective function, obtain the key parameters of the pedestrian flow prediction model y(t), and complete the construction of the pedestrian flow prediction model y(t).

[0123] For example, the specific formula for the objective function L of the pedestrian flow prediction model y(t) is:

[0124] L = [(y t -y′ t ) 2 ],

[0125] y t Let y′ be the true value at time t. t Let be the predicted value at time t;

[0126] Furthermore, the key parameters of the pedestrian flow prediction model y(t) converge, specifically:

[0127]

[0128] Θ = {k, δ, a} n b n ,β,κ},

[0129] Where, k, δ, a n b n β and κ are the key parameters of the human traffic prediction model y(t);

[0130] The pedestrian flow prediction model y(t) is used to predict the pedestrian flow in each unit of time within the current period, and the pedestrian flow prediction data of the target area is obtained.

[0131] Step S300: Obtain heat source data for the target area in the current period, and combine it with pedestrian flow prediction data to analyze the cooling load demand of the target area in the current period, and obtain cooling load demand data.

[0132] Step S300 includes:

[0133] Step S301: Obtain heat source data for the target area within the current period. The heat source data includes the total heat P of the static heat source in the target area per unit time. sum ;

[0134] Among them, static heat sources include fixed heat generated by lighting and equipment operation;

[0135] Step S302: Obtain the predicted pedestrian flow in the target area within each unit of time in the current period, and calculate the cooling demand Q of the target area in the z-th unit of time in the current period. z cool The specific calculation formula is as follows:

[0136] Obtain the predicted outdoor temperature T within the z-th unit of time. (z,out) Obtain the pedestrian flow forecast data for the target area within the current period, and extract the pedestrian flow forecast quantity M for the z-th unit of time from the pedestrian flow forecast data. z Calculate the heat load Q of the target region in the z-th unit of the current period. z total :

[0137]

[0138] Among them, w l and w e These are the sensible heat loss and latent heat loss of the human body, respectively; P (z,sum) The total heat generated by the static heat source in the target area during the z-th unit of time; Let be the initial temperature of the target region at the z-th position;

[0139] For example, w l and w e All can be queried through the preset tables in the platform;

[0140] For example, the initial temperature is usually the target temperature set by the central air conditioning system for the target area;

[0141] Step S303: When the central air conditioning system stops cooling the target area during the z-th unit of time, obtain the highest temperature reached by the target area during the z-th unit of time.

[0142] in, H represents the heat consumed per unit volume of air to raise its temperature by one unit, where H is the unit of time; and V is the volume of the target area.

[0143] Step S304: Calculate the cooling load demand Q of the target area in the z-th unit of time. z cool :

[0144]

[0145] Among them, T △ The target temperature for the target area within the current cycle;

[0146] The cold load demand of the target area in each unit of time within the current period is obtained and aggregated to obtain the cold load demand data of the target area in the current period.

[0147] Step S400: Obtain cooling load demand data for different areas of the building in the current period, obtain energy-saving data of the central air conditioning equipment, and combine the cooling load demand data to generate a control strategy for the central air conditioning. Based on the control strategy, coordinate the cooling in different areas.

[0148] Step S400 includes:

[0149] Step S401: Obtain cooling load demand data for different areas of the building, and obtain the cooling load demand for different areas of the building in each unit of time within the current period from the cooling load demand data.

[0150] For example, when a certain area is not the target area, the impact of human heat does not need to be calculated. This refers to the heat load Q of a certain area in the f-th unit of the current cycle. z total :

[0151]

[0152] P (f,sum) The total heat generated by a static heat source in a certain region during the f-th unit of time; T represents the initial temperature of the target region at the f-th position. (f,out) The expected outdoor temperature of a certain area during the f-th unit of time;

[0153] Step S402: Obtain the energy-saving data of the central air conditioning system. The energy-saving data includes the range of the central air conditioning load rate ζ, the range of the difference between the outlet air temperature and the room temperature ψ, and the range of the air velocity at the outlet when the central air conditioning system has the highest energy efficiency ratio.

[0154] Based on the cooling load demand of different regions within each unit of time in the current cycle, the air velocity and air temperature of the air outlets of different regions are adjusted according to the order of cooling load demand to generate a central air conditioning control strategy. Based on the control strategy, the cooling in different regions is managed in a coordinated manner.

[0155] The specific adjustment strategy for the air outlet speed and air outlet temperature in different areas is as follows: the central air conditioning load rate is within the range ζ in the current cycle, the difference between the air outlet temperature and the room temperature in different areas is within the range ψ, and the air outlet speed in different areas is within the range τ.

[0156] To better implement the above methods, an energy-saving data collaborative management system based on big data analysis is also proposed. The system includes a temperature anomaly assessment module, a people flow prediction module, a cooling load demand analysis module, and an energy-saving collaborative management module.

[0157] The temperature anomaly assessment module is used to assess abnormal temperature changes in areas cooled by central air conditioning during the central air conditioning cooling process, and to identify the target area.

[0158] The pedestrian flow prediction module is used to predict the changes in pedestrian flow in the target area within the current period and obtain pedestrian flow prediction data.

[0159] The cold load demand analysis module is used to analyze the cold load demand status of the target area in the current period and obtain cold load demand data.

[0160] The energy-saving collaborative management module is used to acquire energy-saving data of central air conditioning equipment and, in combination with cooling load demand data, generate control strategies for central air conditioning to collaboratively manage cooling in different areas.

[0161] The temperature anomaly assessment module includes a temperature change similarity assessment unit and a temperature anomaly assessment unit.

[0162] The temperature change similarity assessment unit is used to assess the similarity of temperature changes between a region and a building over a historical period, and to calculate the similarity of temperature changes between a region and a building over a historical period.

[0163] The temperature anomaly assessment unit is used to calculate the temperature change difference between the area and the building based on the similarity of temperature changes, and to assess the abnormal temperature change situation of the area during the central air conditioning cooling process based on the temperature change difference value, so as to obtain the target area.

[0164] The pedestrian flow prediction module includes a relevant analysis unit and a pedestrian flow prediction unit.

[0165] The correlation analysis unit is used to acquire historical environmental monitoring records in the target area, obtain the correlation between monitoring indicators in the historical environmental monitoring records and the flow of people in the target area, and obtain relevant data.

[0166] The pedestrian flow prediction unit is used to acquire historical pedestrian flow change records of the target area and combine them with relevant data to predict the pedestrian flow change in the target area within the current period, thereby obtaining pedestrian flow prediction data.

[0167] The cold load demand analysis module includes a regional heat load acquisition unit and a cold load demand analysis unit.

[0168] The regional heat load acquisition unit is used to acquire heat source data of the target area in the current period, acquire the pedestrian flow prediction data of the target area in the current period, and calculate the heat load of the target area per unit time in the current period.

[0169] The cooling load demand analysis unit is used to analyze the cooling load demand of the target area in the current period based on the heat load of the target area per unit time in the current period, and obtain the cooling load demand data of the target area in the current period.

[0170] The energy-saving collaborative management module includes an energy-saving collaborative management unit;

[0171] The energy-saving collaborative management unit is used to acquire cooling load demand data for different areas of the building, obtain energy-saving data of the central air conditioning equipment, and generate control strategies for the central air conditioning system in combination with the cooling load demand data to collaboratively manage the cooling of different areas of the building.

[0172] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A collaborative management method for energy-saving data based on big data analytics, characterized in that: The method includes: Step S100: Obtain the area in the building where the central air conditioning is used for cooling, obtain historical temperature change records in the area, assess the abnormal temperature change in the area during the central air conditioning cooling process, and obtain the target area; Step S200: Obtain historical records of pedestrian flow changes and historical environmental monitoring records of the target area, analyze the correlation between the monitoring indicators in the historical environmental monitoring records and pedestrian flow in the target area, obtain relevant data, obtain environmental monitoring data of the target area in the current period, and combine the relevant data to predict the pedestrian flow changes in the target area in the current period, and obtain pedestrian flow prediction data. Step S300: Obtain the heat source data of the target area in the current period, and combine it with the pedestrian flow prediction data to analyze the cooling load demand of the target area in the current period, and obtain the cooling load demand data. Step S400: Obtain cooling load demand data for different areas of the building within the current period. The cooling load demand for other non-target areas does not take into account the impact of pedestrian traffic. Obtain the energy-saving data of the central air conditioning system and, in combination with the cooling load demand data, generate a control strategy for the central air conditioning system. Based on the control strategy, coordinate the cooling in the different areas.

2. The energy-saving data collaborative management method based on big data analysis according to claim 1, characterized in that, Step S100 includes: Step S101: Obtain historical temperature change records for each area in the building that is cooled by the central air conditioning system, and set a unit time t. ▽ Every unit of time, the average temperature of the region within the unit of time is obtained from the historical temperature change records and aggregated to obtain the temperature dataset of the historical temperature change records. Step S102: Obtain the historical period to which the historical temperature change record belongs, and calculate the temperature trend slope β of the region within the historical period based on the temperature dataset; Step S103: Obtain the mean μ and variance δ of the temperature of each element in the temperature dataset, construct the temperature vector A=[β,μ,δ] of the region within the historical period, and obtain the mean μ of the temperature of each region in the building within the historical period. △ The mean of the variance δ △ and the mean β of the temperature trend slope △ Construct the temperature vector A of the building within the historical period. △ =[β △ μ △ δ △ ] Calculate the similarity B between the temperature changes of the region and the building during the historical period: ， Step S104: Obtain the similarity of temperature changes between the region and the building in various historical periods, and calculate the temperature change difference value C between the region and the building. ， Where j is the total number of the various historical cycles; B i The similarity of temperature changes between the region and the building during the i-th historical period; Obtain the mean value C of the temperature change difference between each region and the building. △ The temperature change difference value C is compared with the mean value C. △ The absolute value of the difference divided by the mean C △ The value α is recorded as the degree of temperature change abnormality in the region. When α is greater than a preset threshold, it is determined that the temperature change in the region is abnormal during the central air conditioning cooling process, and the region is recorded as the target region.

3. The energy-saving data collaborative management method based on big data analysis according to claim 1, characterized in that, Step S200 includes: Step S201: Obtain historical pedestrian flow records and historical environmental monitoring records for each historical period of the target area; preprocess the data in the historical pedestrian flow records and historical environmental monitoring records; obtain the total number of pedestrians in the target area from the historical pedestrian flow records every unit of time; and aggregate them to obtain a pedestrian flow dataset. Step S202: Obtain historical environmental monitoring records in the target area, and extract the values ​​of various monitoring indicators from the historical environmental monitoring records at regular intervals to obtain a monitoring dataset; Step S203: Based on the pedestrian flow dataset and the monitoring dataset, calculate the correlation coefficient between each monitoring indicator within the historical period to which the historical pedestrian flow record belongs and the total number of pedestrians in the target area, obtain the average value of the correlation coefficient between the monitoring indicators within each historical period and the total number of pedestrians in the target area, and obtain the degree of correlation between the monitoring indicators and the total number of pedestrians in the target area; Obtain the correlation between each monitoring indicator and the total number of people in the target area, and calculate the correlation ratio L between the monitoring indicator and the total number of people in the target area. ， Where, q x q represents the correlation between the x-th monitoring indicator and the total number of people in the target area; n represents the correlation ratio between the monitoring indicator and the total number of people in the target area; and n represents the total number of monitoring indicators. Set a value k, and sort the monitoring indicators according to their correlation with the total number of people in the target area. Select the top k monitoring indicators and mark them. Determine that the top k monitoring indicators are related to the total number of people in the target area and record them as relevant monitoring indicators. Acquire and collect all relevant monitoring indicators that are related to the target area to obtain relevant data. Step S204: Remove the values ​​of monitoring indicators that are marked as relevant monitoring indicators from the monitoring dataset of the historical environmental monitoring records to obtain the relevant monitoring dataset; Obtain historical pedestrian flow datasets for each historical period in the target area, obtain relevant monitoring datasets of historical environmental monitoring records for each historical period in the target area, obtain data on the seasons and holidays for each historical period, and construct a pedestrian flow prediction model y(t) for the target area: ， Wherein, g(t) is the trend term of the traffic flow prediction model y(t); s(t) is the seasonal term of the traffic flow prediction model y(t); h(t) is the holiday term of the traffic flow prediction model y(t); r(t) is the regression term of the monitoring indicators of the traffic flow prediction model y(t), wherein r(t) is composed of various relevant monitoring indicators in the target area; ε t Let be the error term of the pedestrian flow prediction model y(t); Step S205: Obtain the objective function of the pedestrian flow prediction model y(t), train the pedestrian flow prediction model y(t) to minimize the objective function, obtain the key parameters of the pedestrian flow prediction model y(t), and complete the construction of the pedestrian flow prediction model y(t); The pedestrian flow prediction model y(t) is used to predict the pedestrian flow in each unit of time within the current period, thereby obtaining the pedestrian flow prediction data for the target area.

4. The energy-saving data collaborative management method based on big data analysis according to claim 3, characterized in that, Step S300 includes: Step S301: Obtain the heat source data of the target area in the current period, the heat source data including the total heat P of the static heat source of the target area in a unit time period. sum ; Step S302: Obtain the predicted pedestrian flow in the target area within each unit of time in the current period, and calculate the cooling demand Q of the target area in the z-th unit of time in the current period. z cool The specific calculation formula is as follows: Obtain the predicted outdoor temperature T within the z-th unit time period. (z,out) Obtain the pedestrian flow prediction data for the target area within the current period, and obtain the pedestrian flow prediction quantity M for the z-th unit of time from the pedestrian flow prediction data. z Calculate the heat load Q of the target region in the z-th unit time of the current period. z total : ， Among them, w l and w e These are the sensible heat loss and latent heat loss of the human body, respectively; P （z,sum） T represents the total static heat generated by the heat source in the target area during the z-th unit of time. Z ▽ The initial temperature of the target region at the z-th position; Step S303: When the central air conditioning system suspends cooling of the target area during the z-th unit of time, the highest temperature T' reached by the target area during the z-th unit of time is obtained. Z =T Z ▽ +t ▽ / (H·V)·Q z total ; Among them, t ▽ H is the heat consumed per unit time to raise the temperature per unit volume of air; V is the volume of the target area. Step S304: Calculate the cooling load demand Q of the target area during the z-th unit time period. z cool : ， Among them, T △ The target temperature of the target area within the current cycle; The cold load demand of the target area in each unit of time within the current period is obtained and aggregated to obtain the cold load demand data of the target area in the current period.

5. The energy-saving data collaborative management method based on big data analysis according to claim 4, characterized in that, Step S400 includes: Step S401: Obtain cooling load demand data for different areas of the building, and obtain the cooling load demand for different areas of the building in each unit of time within the current period from the cooling load demand data; Step S402: Obtain the energy-saving data of the central air conditioning system. The energy-saving data includes the range of the load rate ζ of the central air conditioning system when the energy efficiency ratio is at its highest, the range of the difference between the outlet air temperature and the room temperature ψ, and the range of the air velocity at the outlet air τ. Based on the cooling load demand of different regions within each unit of time in the current cycle, the air velocity and air temperature of the air outlets of different regions are adjusted according to the order of cooling load demand to generate the control strategy of the central air conditioning. Based on the control strategy, the cooling in different regions is managed in a coordinated manner. The specific adjustment strategy for the air velocity and air temperature of the air outlets in the different areas is as follows: the central air conditioner is kept within the load rate range ζ in the current cycle, the difference between the air temperature and the room temperature of the air outlets in the different areas is kept within the range ψ, and the air velocity of the air outlets in the different areas is kept within the range τ.

6. An energy-saving data collaborative management system based on big data analytics, used to execute the energy-saving data collaborative management method based on big data analytics as described in any one of claims 1-5, characterized in that, The system includes a temperature anomaly assessment module, a pedestrian flow prediction module, a cooling load demand analysis module, and an energy-saving collaborative management module. The temperature anomaly assessment module is used to assess the abnormal temperature changes in the area cooled by the central air conditioning system during the cooling process, and to obtain the target area. The pedestrian flow prediction module is used to predict the changes in pedestrian flow within the target area during the current period, and obtain pedestrian flow prediction data. The cold load demand analysis module is used to analyze the cold load demand status of the target area in the current period and obtain cold load demand data. The energy-saving collaborative management module is used to acquire energy-saving data of the central air conditioning equipment, and combine it with the cooling load demand data to generate a control strategy for the central air conditioning, and to collaboratively manage the cooling in different areas.

7. The energy-saving data collaborative management system based on big data analysis according to claim 6, characterized in that, The temperature anomaly assessment module includes a temperature change similarity assessment unit and a temperature anomaly assessment unit; The temperature change similarity assessment unit is used to assess the similarity of temperature changes between the region and the building during the historical period, and to calculate the similarity of temperature changes between the region and the building during the historical period. The temperature anomaly assessment unit is used to calculate the temperature change difference value between the area and the building based on the temperature change similarity, and to assess the temperature change anomaly status of the area during the central air conditioning cooling process based on the temperature change difference value, thereby obtaining the target area.

8. The energy-saving data collaborative management system based on big data analysis according to claim 6, characterized in that, The pedestrian flow prediction module includes a correlation analysis unit and a pedestrian flow prediction unit; The correlation analysis unit is used to acquire historical environmental monitoring records in the target area, obtain the correlation between monitoring indicators in the historical environmental monitoring records and the flow of people in the target area, and obtain relevant data. The pedestrian flow prediction unit is used to acquire historical pedestrian flow change records of the target area, and combine the relevant data to predict the pedestrian flow change in the target area within the current period, thereby obtaining pedestrian flow prediction data.

9. The energy-saving data collaborative management system based on big data analysis according to claim 6, characterized in that, The cold load demand analysis module includes a regional heat load acquisition unit and a cold load demand analysis unit. The regional heat load acquisition unit is used to acquire heat source data of the target area in the current period, acquire pedestrian flow prediction data of the target area in the current period, and calculate the heat load of the target area per unit time in the current period. The cooling load demand analysis unit is used to analyze the cooling load demand of the target area in the current period based on the heat load of the target area within a unit of time in the current period, and obtain the cooling load demand data of the target area in the current period.

10. The energy-saving data collaborative management system based on big data analysis according to claim 6, characterized in that, The energy-saving collaborative management module includes an energy-saving collaborative management unit; The energy-saving collaborative management unit is used to acquire cooling load demand data for different areas of the building, acquire energy-saving data of the central air conditioning equipment, and generate a control strategy for the central air conditioning system in combination with the cooling load demand data to collaboratively manage the cooling of different areas of the building.

Images