A data analytics based energy efficiency assessment optimization system and method

Abstract

The application discloses an energy efficiency evaluation optimization system and method based on data analysis, and relates to the technical field of data analysis, and the method comprises the following steps: obtaining various equipment information and energy consumption and resource data of a catering service place; determining energy efficiency evaluation quantitative indexes and differentiated conditions, comparing equipment resource requests and actual allocation, and calculating evaluation total satisfaction; calculating the load balancing degree of various equipment of the catering service place; obtaining request data of resources required by various equipment of the catering service place in future operation; setting optimization targets for the total satisfaction and total load balancing degree of various equipment of the catering service place, and defining resource allocation and equipment load balancing constraint conditions, so that energy efficiency evaluation optimization is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, and particularly relates to an energy efficiency evaluation optimization system and method based on data analysis. BACKGROUND

[0002] With the increasingly fierce competition in the catering industry and the increasing emphasis on energy saving and emission reduction, the demand for energy efficiency management and operation optimization of equipment in catering service places is becoming more and more urgent.

[0003] However, the traditional catering equipment management mode often faces the following problems when dealing with complex equipment energy consumption analysis, resource rational allocation and load balancing optimization. First, the energy efficiency evaluation efficiency is low and the accuracy is poor. There are various types of equipment in the catering service place, the running state is complex, and the energy consumption data is huge. Second, the resource allocation lacks scientific basis. The traditional resource allocation is mainly based on experience, which cannot match the actual demand of the equipment and the change of business volume. In addition, the equipment load balancing management means is backward, and lacks global optimization capability. The traditional method cannot monitor and analyze the load of the equipment in real time, cannot find the problem of load imbalance in time, and increases energy consumption. And the load of some equipment is too low, which leads to resource idling. SUMMARY

[0004] The purpose of the present application is to provide an energy efficiency evaluation optimization system and method based on data analysis to solve the problems in the prior art.

[0005] To achieve the above purpose, the present application provides the following technical scheme: an energy efficiency evaluation optimization method based on data analysis, the method comprising the following steps:

[0006] Obtain the information of various types of equipment and the energy consumption and resource data of the catering service place;

[0007] Determine the energy efficiency evaluation quantitative indicators and differentiated conditions, compare the equipment resource requests and actual allocation, calculate the single satisfaction degree, calculate the weight and total satisfaction degree of the equipment by using the weighted average method, and obtain the evaluation total satisfaction degree. The single satisfaction degree represents the satisfaction degree calculated according to the comparison between each quantitative indicator or resource request and actual allocation;

[0008] Calculate the load balancing degree of various types of equipment included in the catering service place;

[0009] Obtain the request data of resources required for future operation of various types of equipment included in the catering service place;

[0010] Set optimization goals for the total satisfaction degree and total load balancing degree of various types of equipment included in the catering service place, and define resource allocation and equipment load balancing constraint conditions.

[0011] Acquire the device types in the site and set the priority, collect the device energy consumption data through sensors, collect the resource request data, record the actual resource allocation, the specific steps are as follows:

[0012] Acquire the device types contained in the catering service site, wherein the coffee shop devices include but are not limited to coffee machines, refrigerators;

[0013] According to the importance of the device type to the operation of the catering service site, the energy consumption proportion and the influence degree on the user experience, set the priority for each device type;

[0014] Among them, the specific method of setting the priority according to the importance of the device type to the operation of the catering service site is as follows:

[0015] Core business devices have priority: for devices directly involved in core catering production, high priority is given, for example, in a coffee shop, a coffee machine determines the production of coffee, and is a key device for providing core products, and is set to high priority;

[0016] Indispensable support devices: some devices are necessary for operation, and such devices are set to medium priority, for example, refrigerators are used to store food raw materials to ensure the freshness and safety of food;

[0017] Priority determination of auxiliary devices: some devices are used to ensure the operation environment of the catering service site, and such auxiliary devices are set to low priority, for example, the lighting devices in the store,

[0018] Collect the energy consumption data of each type of device contained in the catering service site through sensors, including real-time power, daily power consumption and cumulative running time;

[0019] Collect the request data of resources required for the operation of each type of device contained in the catering service site, wherein the request data of resources required for the operation of the device includes but is not limited to the power required for the coffee machine, the water flow, the refrigeration capacity required for the refrigerator, and the storage space required for the refrigerator;

[0020] Record the actual allocation of resources to each type of device contained in the catering service site, wherein the resource allocation to each type of device contained in the catering service site includes but is not limited to the actual access of the device to the power, the actual water supply, and the actual allocation of the refrigeration resource to the refrigerator.

[0021] Determine the energy efficiency evaluation quantitative index and the differentiated condition, compare the device resource request and the actual allocation, calculate the single item satisfaction degree, calculate the weight and the total satisfaction degree of the device by the weighted average method, and obtain the evaluation total satisfaction degree, the specific steps include:

[0022] determining quantitative indicators of energy efficiency evaluation of various types of equipment contained in the catering service site, including but not limited to energy utilization rate of equipment, unit product energy consumption and equipment load rate, wherein the energy utilization rate of equipment represents the ratio of actual effective utilization of electric energy to total consumed electric energy, the unit product energy consumption represents energy consumption for making a unit of product, such as electric energy consumption for making a cup of coffee or refrigerating a unit of product, and the equipment load rate represents the ratio of actual load to rated load;

[0023] formulating differentiated quantitative indicator conditions according to the types of equipment contained in the catering service site and their priorities, wherein for a coffee machine with high priority, the energy utilization rate is required to reach 80%, and the unit product energy consumption is required to be lower than a set product energy consumption threshold;

[0024] comparing resource request data and actual allocation for each type of equipment contained in the catering service site, and calculating single item satisfaction degree in combination with quantitative indicators, wherein when the actually allocated resource amount meets the equipment request, the satisfaction degree is set to 1, wherein the single item satisfaction degree represents the calculated satisfaction degree value for each quantitative indicator or comparison between resource request and actual allocation;

[0025] when the actually allocated resource amount R does not meet the equipment request threshold D, the satisfaction degree is set to 1- |R-D| / |R+D|; wherein R represents the actually allocated resource amount, D represents the resource amount requested by the equipment during operation, the request threshold D is obtained according to the statistical historical request resource amount of the equipment when completing work, the lowest request resource amount aa of the historical equipment when completing work is obtained, and 1.2aa is taken as the request threshold;

[0026] for the quantitative indicator S meeting the indicator threshold, the satisfaction degree is 1, and when the quantitative indicator S does not meet the indicator threshold I, the satisfaction degree is set to 1- |S-I| / |S+I|; wherein S represents the obtained quantitative indicators of energy efficiency evaluation of various types of equipment contained in the catering service site, I represents the corresponding threshold set for the quantitative indicators of energy efficiency evaluation of various types of equipment contained in the catering service site, the indicator threshold I is obtained according to the statistical historical quantitative indicators of the equipment when completing work, the lowest quantitative indicator ee of the historical equipment when completing work is obtained, and 1.2ee is taken as the indicator threshold;

[0027] the single item satisfaction degree set of each equipment is represented as S' = {s1', s2',..., si',...}; wherein s1', s2',..., si' represent the satisfaction degrees of the 1st, 2nd,..., i-th quantitative indicators, respectively, and si' represents the satisfaction degree of the i-th quantitative indicator. i i+1 n i i+1 n ​​​​​' represents the satisfaction level of the requested resource for the (i+1), ..., nth item, respectively, s1', s2', ..., s i ',s i+1 ',...,s n '∈[0,1];

[0028] The weighted average method is used to determine the weights of each quantitative indicator and resource request: The weight set W' = {w1', w2', ..., w...} is determined. i ',w i+1 ',...,w n '}; where n represents the quantitative indicator and the number of requested resources, n is a positive integer, w1', w2', ..., w i 'represent the weights of the 1st, 2nd, ..., ith quantitative indicators, respectively, w i+1 ',...,w n ' represents the weight of the requested resource for the (i+1), ..., nth item respectively, and w1'+w2'+...+w i '+w i+1 '+...+w n =1, where the weights of each quantitative indicator and resource request can be determined based on expert experience;

[0029] The overall satisfaction level S of the t-th device t '=w1'*s1'+w2'*s2'+...+w i '*s i '+w i+1 '*s 1+1 '+...+w n '*s n ';

[0030] Calculate the satisfaction level of each device, sum the satisfaction levels of all devices, and then divide by the total number of devices to obtain the total satisfaction level S of this evaluation. total .

[0031] The specific steps for calculating the load balancing of various equipment in the aforementioned catering service venue include:

[0032] According to the real-time acquired load data of various equipment included in the catering service venue, the load data of various equipment included in the catering service venue includes the real-time power of coffee machine equipment, the operating frequency of refrigerator compressor, and the working load of refrigerator refrigeration system.

[0033] Based on the design specifications, performance parameters, and long-term operating experience of the various equipment included in the catering service venue, the optimal load value is set for the load data of the various equipment included in the catering service venue.

[0034] For the load data of each type of equipment contained in the catering service site, according to the optimal load value and the mean and variance of the load data in a period of time, the probability density function f(x, a, b) of Beta distribution is constructed, wherein x represents the actual value of the load data of each type of equipment contained in the catering service site, a and b represent the parameters of the probability density function of Beta distribution, a>1 and b>1;

[0035] The probability density function f(x, a, b) of Beta distribution is defined as follows:

[0036]

[0037] Wherein, B(a, b) represents the Beta function;

[0038]

[0039] Wherein, G(m) represents the gamma function with m as the parameter;

[0040]

[0041] Wherein, m represents the independent variable of the gamma function, t represents the integral variable, which takes values in the integral interval [0, ∞), and e represents the natural constant;

[0042] Substitute the actually collected load data of the equipment contained in the catering service site into the constructed probability density function, and the function value obtained is the load balancing degree of the equipment contained in the catering service site. For a device, there are different types of load data, and the average value of the load balancing degree of different types of load data is calculated as the load balancing degree of the device.

[0043] The load balancing degrees of all the equipment in the catering service site are summarized, and the load balancing degrees of all the equipment are added and divided by the total number of equipment to obtain the average value, which is the total load balancing degree of each type of equipment in the catering service site.

[0044] Obtain the request data of resources required for future operation of each type of equipment contained in the catering service site, and the specific steps include:

[0045] Collect the request data of resources required for operation of each type of equipment contained in the catering service site in the past; record the time stamp corresponding to each data;

[0046] Divide the data into training set and test set; construct LSTM model; add input layer and output layer; input the training set data into the constructed LSTM model, and use optimization algorithm Adam for training;

[0047] Use the trained model for prediction;

[0048] The test set data is input into the trained LSTM model, and the model outputs a predicted value of request data for future operation of each type of equipment included in the catering service place.

[0049] An optimization target is set for the total satisfaction of each type of equipment included in the catering service place and the total load balancing degree of each type of equipment included in the catering service place, and a resource allocation and equipment load balancing constraint condition is defined, and the specific steps include:

[0050] The total satisfaction of each type of equipment included in the catering service place and the total load balancing degree of each type of equipment included in the catering service place are summed up to form an optimization target;

[0051] The constraint condition is defined, wherein the constraint condition includes a resource allocation constraint and a device load balancing constraint included in the catering service place;

[0052] The energy resource allocation constraint: the total amount of energy actually allocated to all devices included in the catering service place does not exceed the total amount of available energy of the energy;

[0053] The device load balancing constraint included in the catering service place: when the load of a device is greater than the optimal load value, the allocated task is reduced and part of the task is migrated to other devices; when the load of a device is less than the optimal load value, the allocated task is increased.

[0054] An energy efficiency evaluation optimization system based on data analysis, the system includes a data acquisition module, an energy efficiency evaluation module, a load balancing analysis module, a resource request prediction module and an optimization decision module, the data acquisition module is used for acquiring each type of equipment information and energy consumption and resource data included in the catering service place; the energy efficiency evaluation module is used for determining energy efficiency evaluation quantitative indicators and differentiated conditions, comparing device resource requests and actual allocation, calculating single satisfaction, calculating weight and total satisfaction of equipment by weighted average method, and obtaining evaluation total satisfaction; the load balancing analysis module is used for calculating the load balancing degree of each type of equipment included in the catering service place; the resource request prediction module is used for obtaining the request data of resources required for future operation of each type of equipment included in the catering service place; the optimization decision module is used for setting an optimization target for the total satisfaction of each type of equipment included in the catering service place and the total load balancing degree, and defining a resource allocation and equipment load balancing constraint condition.

[0055] The data acquisition module includes a device information acquisition unit, an energy consumption data acquisition unit, and a resource request and allocation recording unit. The device information acquisition unit is configured to acquire the types of various devices in the catering service site. The energy consumption data acquisition unit is configured to collect energy consumption data of various devices through sensors. The resource request and allocation recording unit is configured to collect request data for resources required by device operation and record the actual allocation of resources to devices. The energy efficiency evaluation module includes a quantitative index determination unit, an index condition formulation unit, and a satisfaction calculation unit. The quantitative index determination unit is configured to determine quantitative indexes for evaluating the energy efficiency of devices. The index condition formulation unit is configured to formulate differentiated quantitative index conditions according to the types of devices and their priorities. The satisfaction calculation unit is configured to compare device resource requests with actual allocation, calculate individual satisfaction degrees based on quantitative indexes, calculate weights and total satisfaction degrees of devices using a weighted average method, and obtain an evaluation total satisfaction degree.

[0056] The load balancing analysis module includes an optimal load value setting unit, a probability model construction unit, and a load balancing degree calculation unit. The optimal load value setting unit is configured to set optimal load values for load data of various devices based on design specifications, performance parameters, and long-term operation experience of devices. The probability model construction unit is configured to construct a probability density function of Beta distribution based on the optimal load values of device load data, the mean, and the variance of load data within a period of time. The load balancing degree calculation unit is configured to substitute the actually collected device load data into the constructed probability density function to obtain load balancing degree values of different types of load data of each device, calculate the average value as the load balancing degree of the device, and calculate the total load balancing degree of various devices in the entire catering service site by aggregating the load balancing degrees of all devices.

[0057] The resource request prediction module includes a historical data collection unit, a model construction and training unit, and a prediction unit. The historical data collection unit is configured to collect request data for resources required by operation of various devices in the past and record the time stamps corresponding to each data. The model construction and training unit is configured to divide the collected data into a training set and a test set, construct an LSTM model and add an input layer and an output layer, and use an optimization algorithm Adam to train the training set data. The prediction unit is configured to input the test set data into the trained LSTM model, and the model outputs predicted values of request data for resources required by future operation of various devices. The optimization decision module includes a target setting unit, a constraint condition definition unit, and a strategy generation unit. The target setting unit is configured to sum the total satisfaction degree of devices and the total load balancing degree to form an optimization target. The constraint condition definition unit is configured to define resource allocation and device load balancing constraint conditions. The strategy generation unit is configured to generate an optimization strategy based on the optimization target and the constraint conditions.

[0058] Compared with the prior art, the present application has the beneficial effects of:

[0059] 1. By dynamically analyzing the energy consumption and resource data trends of the equipment, combining the energy utilization rate, unit product energy consumption, and equipment load rate multiple energy efficiency evaluation dimensions, and calculating the load balancing degree by constructing a Beta distribution probability density function, the present application captures the complex correlation between various parameters during equipment operation, realizes multi-dimensional comprehensive energy efficiency evaluation, and improves the evaluation ability of the equipment energy efficiency status, which is different from the single-dimensional equipment evaluation in the prior art.

[0060] 2. The present application introduces a resource allocation module, combines the equipment priority, future resource request prediction data, and load balancing degree, and allocates energy resources and work tasks. BRIEF DESCRIPTION OF DRAWINGS

[0061] Fig. 1 The flowchart of the energy efficiency evaluation optimization method based on data analysis of the present application;

[0062] Fig. 2 The structural diagram of the energy efficiency evaluation optimization system based on data analysis of the present application. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0064] In the embodiments: as shown in the drawings, Figs. 1-2 The present application provides a technical solution, an energy efficiency evaluation optimization method based on data analysis, which comprises the following steps:

[0065] Obtaining various types of equipment information and energy consumption and resource data contained in the catering service place;

[0066] Determining the energy efficiency evaluation quantitative indicators and differentiated conditions, comparing the equipment resource requests and actual allocations, calculating the single-item satisfaction degree, calculating the weight and total satisfaction degree of the equipment by the weighted average method, and obtaining the evaluation total satisfaction degree, wherein the single-item satisfaction degree represents the satisfaction degree calculated according to the comparison between each quantitative indicator or resource request and actual allocation;

[0067] Calculating the load balancing degree of various types of equipment contained in the catering service place;

[0068] Obtaining the request data of resources required for future operation of various types of equipment contained in the catering service place;

[0069] An optimization goal is set for the total satisfaction and total load balancing of each type of equipment included in the catering service site, and resource allocation and equipment load balancing constraints are defined.

[0070] The types of equipment in the site are obtained and prioritized, energy consumption data of the equipment is collected by sensors, resource request data is collected, and actual resource allocation is recorded. The specific steps are as follows:

[0071] The types of equipment included in the catering service site are obtained, wherein the coffee shop equipment includes but is not limited to coffee machines, refrigerators;

[0072] According to the importance of equipment type to the operation of the catering service site, the energy consumption proportion and the influence degree on user experience, the priority of each equipment type is set;

[0073] The specific method of setting priority according to the importance of equipment type to the operation of the catering service site is as follows:

[0074] Core business equipment priority: for equipment directly involved in core catering production, high priority is given, for example, in a coffee shop, the coffee machine determines the production of coffee, and is a key equipment for providing core products, and is set to high priority;

[0075] Essential support equipment: some equipment is essential for operation, and such equipment is set to medium priority, for example, a refrigerator is used to store food raw materials to ensure food freshness and safety;

[0076] Priority determination of auxiliary equipment: some equipment is used to ensure the operation environment of the catering service site, and such auxiliary equipment is set to low priority, for example, the lighting equipment in the store,

[0077] The energy consumption data of each type of equipment included in the catering service site is collected by sensors, including real-time power, daily power consumption and cumulative running time;

[0078] The request data for resources required by the operation of each type of equipment included in the catering service site is collected, wherein the request data for resources required by the operation of the equipment includes but is not limited to the power required by the coffee machine, the water flow, the refrigeration capacity required by the refrigerator, and the storage space required by the refrigerator;

[0079] The actual allocation of resources to each type of equipment included in the catering service site is recorded, wherein the allocation of resources to each type of equipment included in the catering service site includes but is not limited to the actual access of the equipment to the power, the actual water supply, and the actual allocation of refrigeration resources to the refrigerator.

[0080] Specifically, the in-store equipment types are determined to be coffee machines, refrigerators, and ice machines, and priorities are set according to the importance of the equipment to the operation, the proportion of energy consumption, and the degree of influence on user experience. The coffee machine, as a core business equipment, is set to high priority; the refrigerator, used for storing food materials, is set to medium priority; and the ice machine, with a relatively low usage frequency, is set to low priority.

[0081] The energy consumption data of the equipment within a week is collected by sensors. The average real-time power of coffee machine A is 2kW per day, the daily power consumption is 16 degrees, and the cumulative running time is 8 hours. The real-time power of refrigerator B is 0.5kW, the daily power consumption is 12 degrees, and the cumulative running time is 24 hours. The real-time power of the ice machine is 1kW, the daily power consumption is 10 degrees, and the cumulative running time is 10 hours.

[0082] The request data and actual allocation of resources required for equipment operation are collected. The coffee machine requests 3kW of power and 0.5 liters of water flow for each cup of coffee. The refrigerator requests a refrigeration capacity to maintain an internal temperature of 2-8℃. The ice machine requests an ice making capacity of 100 kilograms per day. In terms of actual allocation, the coffee machine actually accesses 2.5kW of power and actually supplies 0.4 liters of water per cup. The refrigerator actually allocates refrigeration resources to maintain a temperature of 5℃.

[0083] Quantitative indicators and differentiated conditions for energy efficiency evaluation are determined. The single-item satisfaction is calculated by comparing the resource request and the actual allocation. The weight and the total satisfaction of the equipment are calculated by the weighted average method, and the total satisfaction of the evaluation is obtained. The specific steps include:

[0084] Quantitative indicators for energy efficiency evaluation of various types of equipment included in the catering service site are determined, including but not limited to energy utilization rate of equipment, unit product energy consumption, and equipment load rate. The energy utilization rate of equipment represents the ratio of actual effective utilization of electric energy to total consumption of electric energy. The unit product energy consumption represents the energy consumption for making a unit of product, such as making a cup of coffee or refrigerating a unit of product. The equipment load rate represents the proportion of actual load to rated load.

[0085] According to the types of equipment included in the catering service site and their priorities, differentiated quantitative indicator conditions are developed. For high-priority coffee machines, the energy utilization rate is required to reach 80%, and the unit product energy consumption is required to be lower than the set product energy consumption threshold.

[0086] For various types of equipment included in the catering service site, the resource request data and the actual allocation are compared, and the single-item satisfaction is calculated in combination with the quantitative indicators. When the actual allocation of resources meets the equipment request, the satisfaction is set to 1. The single-item satisfaction represents the satisfaction degree value calculated for each quantitative indicator or the comparison between resource request and actual allocation.

[0087] When the actual allocated resource amount R does not satisfy the device request threshold D, the satisfaction degree is set as 1- |R-D| / |R+D|; wherein, R represents the actual allocated resource amount, D represents the resource amount requested by the device during operation, the request threshold D is obtained according to the statistical historical request resource amount of the device during completion of work, the lowest request resource amount aa of the historical device during completion of work is obtained, and 1.2aa is taken as the request threshold;

[0088] When the quantification index S satisfies the index threshold, the satisfaction degree is 1, and when the quantification index S does not satisfy the index threshold I, the satisfaction degree is set as 1- |S-I| / |S+I|; wherein, S represents the obtained quantification index of the energy efficiency evaluation of each type of device contained in the catering service place, I represents the corresponding threshold set for the quantification index of the energy efficiency evaluation of each type of device contained in the catering service place, the index threshold I is obtained according to the statistical historical quantification index of the device during completion of work, the lowest quantification index ee of the historical device during completion of work is obtained, and 1.2ee is taken as the index threshold;

[0089] The single-item satisfaction degree set of each device is represented as S' = {s1', s2',..., si',..., sn'}; wherein, s1', s2',..., si' represent the satisfaction degrees of the 1st, 2nd,..., i-th quantification index, sn' represents the satisfaction degree of the i+1-th,..., n-th requested resource, and s1', s2',..., sn' ∈ [0, 1]. i i+1 n i i+1 n i i+1 n

[0090] The weights of each quantification index and resource request are determined by using the weighted average method: the weight set W' = {w1', w2',..., wi',..., wn'} is determined; wherein, n represents the number of quantification indexes and requested resources, n is a positive integer, w1', w2',..., wi' represent the weights of the 1st, 2nd,..., i-th quantification index, wn' represents the weight of the i+1-th,..., n-th requested resource, and w1'+w2'+...+wi'+...+wn' = 1, wherein, the weights of each quantification index and resource request can be known according to expert experience; i i+1 n i i+1 n i i+1 n ​​​​​​​​​​​​​​​​​​

[0091] Total satisfaction S of the tth device t ' = w1's1 + w2's2 +... + w i ' * s i ' + w i+1 ' * s 1+1 ' +... + w n ' * s n ' ;

[0092] Calculate the satisfaction of each device, add the satisfaction of all devices, and divide by the total number of devices to get the total satisfaction S of this evaluation total .

[0093] Specifically, determine the energy efficiency evaluation quantitative indicators, energy utilization rate, unit product energy consumption and device load rate. Take the coffee machine as an example. The actual effective utilization of electric energy is 12 degrees in a certain period, and the total consumption of electric energy is 16 degrees. Therefore, the energy utilization rate is 12÷16=75%. The consumption of electric energy for making a cup of coffee is 0.2 degrees, and the unit product energy consumption is 0.2 degrees / cup. If the rated load is 3kW and the actual load is 2.5kW, the device load rate is 2.5÷3≈83.3%.

[0094] Compare the resource request and the actual allocation, calculate the single satisfaction degree combined with the quantitative indicators. For the power request of the coffee machine, the actual allocation is 2.5kW, the request threshold is assumed to be 3kW, and the satisfaction degree is calculated according to the formula as 1-|2.5-3|÷|2.5+3|≈0.91. The energy utilization rate indicator threshold is set to 80%, and the actual energy utilization rate is 75%. Therefore, the indicator satisfaction degree is 1-|75%-80%|÷|75%+80%|≈0.97.

[0095] Given that the unit product energy consumption threshold for making a cup of coffee for the coffee machine is 0.15 degrees / cup, and the actual unit product energy consumption is 0.2 degrees / cup, the unit product energy consumption satisfaction degree is 0.857 according to the satisfaction degree calculation formula.

[0096] Determine the weight by using the weighted average method. Given that the rated load of the coffee machine is 3kW, the optimal load value is 2.8kW, and the actual load is 2.5kW.

[0097] Define the device load rate satisfaction degree as the closeness of the actual load to the optimal load value. The satisfaction degree is calculated as follows: when the actual load is within a certain range (10%) of the optimal load value, the satisfaction degree is 1. If it exceeds the range, it is calculated according to the deviation from the optimal load value. Here, 2.8*(1-10%) = 2.52kW, (2.5<2.52), which means that the actual load is lower than the reasonable range of the optimal load value, and the device load rate satisfaction degree is 0.893.

[0098] The quantitative indicators and resource request weights are determined according to expert experience, for the coffee machine, the energy utilization rate weight is 0.4, the unit product energy consumption weight is 0.3, the equipment load rate weight is 0.2, and the power request weight is 0.1, and then the total satisfaction of the coffee machine can be calculated as 0.9147, and the total satisfaction of other equipment is calculated in the same way, and then the evaluation total satisfaction is obtained.

[0099] The load balancing degree of each type of equipment included in the catering service place is calculated, and the specific steps include:

[0100] According to the real-time obtained load data of each type of equipment included in the catering service place, wherein the load data of each type of equipment included in the catering service place includes the real-time power of the coffee machine, the operating frequency of the compressor of the refrigerated cabinet, and the working load of the refrigeration system of the refrigerated cabinet.

[0101] According to the design specifications, performance parameters and long-term operation experience of each type of equipment included in the catering service place, the best load value of the load data of each type of equipment included in the catering service place is set;

[0102] For the load data of each type of equipment included in the catering service place, according to the best load value and the mean and variance of the load data in a period of time, a Beta distribution probability density function f(x, a, b) is constructed, wherein x represents the actual value of the load data of each type of equipment included in the catering service place, a and b represent the parameters of the Beta distribution probability density function, and a>1 and b>1;

[0103] The Beta distribution probability density function f(x, a, b) is defined as follows:

[0104]

[0105] Wherein, B(a, b) represents the Beta function;

[0106]

[0107] Wherein, G(m) represents the gamma function with m as the parameter;

[0108]

[0109] Wherein, m represents the independent variable of the gamma function, t represents the integral variable, e represents the natural constant, and the integral interval is [0, ∞);

[0110] The load data of the equipment contained in the actual collected catering service place is substituted into the constructed probability density function, and the function value obtained is the load balancing degree of the equipment contained in the catering service place. For a device, there are different types of load data, and the average value of the load balancing degree of different types of load data is calculated as the load balancing degree of the device.

[0111] The load balancing degrees of all the devices in the catering service place are calculated and summed up, and the average value obtained by dividing the total load balancing degree of all the devices by the total number of devices is the total load balancing degree of all the devices in the catering service place.

[0112] Specifically, the device load data, coffee machine real-time power, and refrigerator compressor operating frequency are obtained. According to the design specifications and operation experience of the equipment, the best power load value of the coffee machine is set to 2.8kW, and the best operating frequency of the refrigerator compressor is set to 50Hz.

[0113] Constructing the probability density function and calculating the load balancing degree: according to the best load value, mean and variance of the load data, the Beta distribution probability density function is constructed, the mean of the coffee machine load data is 2.6kW, and the variance is 0.04. After determining the parameters α and β, the function is constructed, the actual load data is substituted into the function to calculate the load balancing degree value, and the load balancing degree value of the coffee machine at a certain moment is calculated as 0.85. For a device, the average value of the load balancing degree values of different types of load data is calculated as the load balancing degree of the device, and the total load balancing degree of all the devices is calculated.

[0114] Obtaining the request data of the resources required for the future operation of each type of equipment contained in the catering service place, the specific steps include:

[0115] Collecting the request data of the resources required for the operation of each type of equipment contained in the past catering service place; recording the time stamp corresponding to each data;

[0116] Divide the data into training set and test set; construct LSTM model; add input layer and output layer; input the training set data into the constructed LSTM model, and use the optimization algorithm Adam for training;

[0117] Using the trained model for prediction;

[0118] Input the test set data into the trained LSTM model, and the model outputs the predicted value of the request data of the resources required for the future operation of each type of equipment contained in the catering service place.

[0119] Setting the optimization goal for the total satisfaction and total load balancing degree of each type of equipment contained in the catering service place, and defining the resource allocation and device load balancing constraint conditions, the specific steps include:

[0120] The total satisfaction of each type of equipment contained in the catering service place and the total load balance degree of each type of equipment contained in the catering service place are summed up to form an optimization target;

[0121] Constraints are defined, wherein the constraints include resource allocation constraints and equipment load balance constraints of the catering service place;

[0122] Energy resource allocation constraints: the total amount of energy actually allocated to all equipment contained in the catering service place does not exceed the total amount of available energy of the energy;

[0123] Equipment load balance constraints of the catering service place: when the load of a certain equipment is greater than the optimal load value, the allocated tasks are reduced and part of the tasks are migrated to other equipment; when the load of a certain equipment is less than the optimal load value, the allocated tasks are increased.

[0124] Specifically, the total satisfaction of equipment and the total load balance degree are summed up as the optimization target, the total satisfaction of the current coffee machine is 0.8, the load balance degree is 0.82, the total satisfaction of the refrigerator is 0.75, the load balance degree is 0.78, the total satisfaction of the ice maker is 0.7, and the load balance degree is 0.75, then the optimization target value is calculated.

[0125] An energy efficiency evaluation optimization system based on data analysis, the system comprises a data acquisition module, an energy efficiency evaluation module, a load balance analysis module, a resource request prediction module and an optimization decision module, the data acquisition module is used to acquire information of each type of equipment contained in the catering service place and energy consumption and resource data; the energy efficiency evaluation module is used to determine energy efficiency evaluation quantitative indicators and differentiated conditions, compare equipment resource requests and actual allocation, calculate single satisfaction, calculate weight and total satisfaction of equipment by weighted average method, and obtain evaluation total satisfaction; the load balance analysis module is used to calculate the load balance degree of each type of equipment contained in the catering service place; the resource request prediction module is used to acquire request data of resources required for future operation of each type of equipment contained in the catering service place; the optimization decision module is used to set optimization targets for the total satisfaction of each type of equipment contained in the catering service place and the total load balance degree, and define resource allocation and equipment load balance constraints.

[0126] The data acquisition module includes a device information acquisition unit, an energy consumption data acquisition unit, and a resource request and allocation recording unit. The device information acquisition unit is configured to acquire the types of various devices in the catering service site. The energy consumption data acquisition unit is configured to collect energy consumption data of various devices through sensors. The resource request and allocation recording unit is configured to collect request data for resources required by device operation and record the actual allocation of resources to devices. The energy efficiency evaluation module includes a quantitative index determination unit, an index condition formulation unit, and a satisfaction calculation unit. The quantitative index determination unit is configured to determine quantitative indexes for evaluating the energy efficiency of devices. The index condition formulation unit is configured to formulate differentiated quantitative index conditions according to the types of devices and their priorities. The satisfaction calculation unit is configured to compare device resource requests with actual allocation, calculate individual satisfaction degrees based on quantitative indexes, calculate weights and total satisfaction degrees of devices using a weighted average method, and obtain an evaluation total satisfaction degree.

[0127] The load balancing analysis module includes an optimal load value setting unit, a probability model construction unit, and a load balancing degree calculation unit. The optimal load value setting unit is configured to set optimal load values for load data of various devices based on design specifications, performance parameters, and long-term operation experience of devices. The probability model construction unit is configured to construct a probability density function of Beta distribution based on the optimal load values of device load data, the mean, and the variance of load data within a period of time. The load balancing degree calculation unit is configured to substitute the actually collected device load data into the constructed probability density function to obtain load balancing degree values of different types of load data of each device, calculate the average value as the load balancing degree of the device, and calculate the total load balancing degree of various devices in the entire catering service site by aggregating the load balancing degrees of all devices.

[0128] The resource request prediction module includes a historical data collection unit, a model construction and training unit, and a prediction unit. The historical data collection unit is configured to collect request data for resources required by operation of various devices in the past and record the time stamps corresponding to each data. The model construction and training unit is configured to divide the collected data into a training set and a test set, construct an LSTM model and add an input layer and an output layer, and use an optimization algorithm Adam to train the training set data. The prediction unit is configured to input the test set data into the trained LSTM model, and the model outputs predicted values of request data for resources required by future operation of various devices. The optimization decision module includes a target setting unit, a constraint condition definition unit, and a strategy generation unit. The target setting unit is configured to sum the total satisfaction degree of devices and the total load balancing degree to form an optimization target. The constraint condition definition unit is configured to define resource allocation and device load balancing constraint conditions. The strategy generation unit is configured to generate an optimization strategy based on the optimization target and the constraint conditions.

[0129] It will be apparent to those skilled in the art that the application is not limited to the details of the above-exemplified embodiments and that the present application can be implemented in other particular forms without departing from the spirit or essential characteristics of the present application. The embodiments should therefore be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the above description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference signs in the claims should be considered as limiting the scope of the claims with respect to the figures of the patent document.

Claims

1. A data-driven energy efficiency assessment and optimization method, characterized in that: The method includes the following steps: Obtain information on various equipment and energy consumption and resource data contained in catering service venues; Determine the quantitative indicators and differentiated conditions for energy efficiency assessment, compare the equipment resource requests with the actual allocation, and calculate and assess the overall satisfaction of various types of equipment; Quantitative indicators for energy efficiency assessment of various equipment included in the aforementioned catering service venues; Based on the types and priorities of the various equipment included in the catering service venues, differentiated quantitative indicator conditions are formulated; For the various types of equipment included in the catering service venue, the resource request data and the actual allocation are compared, and the individual satisfaction is calculated in combination with quantitative indicators. When the actual allocated resources meet the equipment request, the satisfaction of that item is set to 1. The individual satisfaction represents the satisfaction level calculated for each quantitative indicator or resource request compared with the actual allocation. When the actual allocated resource amount R does not meet the device request threshold D, the satisfaction level is set to 1-|RD| / |R+D|; where R represents the actual allocated resource amount, D represents the resource amount requested by the device during operation, and the request threshold D is based on the historical resource request amount when the device completes its work. When the quantitative indicator S meets the indicator threshold, the satisfaction level is 1. When the quantitative indicator S does not meet the indicator threshold I, the satisfaction level is set to 1-|SI| / |S+I|. Wherein, S represents the quantitative indicator of energy efficiency assessment of various equipment included in the catering service venue, and I represents the corresponding threshold set for the quantitative indicator of energy efficiency assessment of various equipment included in the catering service venue. The set of individual satisfaction levels for each device is represented as S'={s1',s2',...,s...} i ',s i+1 ',...,s n '}; where s1', s2', ..., s i ' represents the satisfaction level of the 1st, 2nd, ..., ith quantitative indicators, respectively, s i+1 ',...,s n ' represents the satisfaction level of the requested resource for the (i+1), ..., nth item, respectively, s1', s2', ..., s i ',s i+1 ',...,s n '∈[0,1]; The weighted average method is used to determine the weights of each quantitative indicator and resource request: The weight set W'={w1',w2',...,w...} is determined. i ',w i+1 ',...,w n '}; where n represents the quantitative indicator and the number of requested resources, n is a positive integer, w1', w2', ..., w i 'represent the weights of the 1st, 2nd, ..., ith quantitative indicators, respectively, w i+1 ',...,w n ' represents the weight of the requested resource for the (i+1), ..., nth item respectively, and w1'+w2'+...+w i '+w i+1 '+...+w n =1; The overall satisfaction level S of the t-th device t =w1'*s1'+w2'*s2'+...+w i '*s i '+w i+1 '*s 1+1 '+...+w n '*s n '; Calculate the satisfaction level of each device, sum the satisfaction levels of all devices, and then divide by the total number of devices to obtain the total satisfaction level S of this evaluation. total ; Calculate the overall load balancing degree of all types of equipment included in the catering service venue; Based on the real-time acquisition of load data for various equipment in the aforementioned catering service venues; Set optimal load values ​​for the load data of various equipment included in the catering service venue; For the load data of various equipment included in the catering service venue, based on their optimal load values ​​and the mean and variance of the load data over a period of time, a probability density function f(x,α,β) of the Beta distribution is constructed, where x represents the actual value of the load data of various equipment included in the catering service venue, and α and β represent the probability density function parameters of the Beta distribution, α>1 and β>1. Substituting the actual collected load data of the equipment in the catering service venue into the constructed probability density function, the obtained function value is the load balancing degree of the equipment in the catering service venue. For a single device, there are different types of load data. The average load balancing degree of different types of load data is calculated as the load balancing degree of the device. The calculated load balancing degree of all equipment in the catering service venue is summarized, the load balancing degree of all equipment is added together, and the average value is divided by the total number of equipment. The average value is the total load balancing degree of all types of equipment in the catering service venue. Obtain request data for the resources required for the future operation of various equipment included in the catering service venue; Optimization targets are set for the overall satisfaction and overall load balance of various equipment in the catering service venue, and resource allocation and equipment load balance constraints are defined.

2. The energy efficiency assessment and optimization method based on data analysis according to claim 1, characterized in that: The specific steps are as follows: Identify the types of equipment within the site and assign priorities; collect equipment energy consumption data through sensors; gather resource request data; and record actual resource allocation. Obtain the types of equipment included in food service establishments; Prioritize each equipment type based on its importance to the operation of catering service venues, its energy consumption ratio, and its impact on user experience. The energy consumption data of various equipment in the catering service venue are collected by sensors, including real-time power, daily power consumption and cumulative running time. Collect request data for resources required for the operation of various equipment in the catering service venue; Record the resources actually allocated to the various types of equipment included in the catering service venue.

3. The energy efficiency assessment and optimization method based on data analysis according to claim 2, characterized in that: The specific steps for obtaining request data on the resources required for the future operation of various equipment included in the catering service venue are as follows: Collect past request data for resources required for the operation of various equipment in the aforementioned catering service venues; record the timestamp corresponding to each data entry; The data is divided into training and testing sets; an LSTM model is built; an input layer and an output layer are added; the training set data is input into the built LSTM model and trained using the Adam optimization algorithm; Use a trained model to make predictions; The test set data is input into the trained LSTM model, and the model outputs predicted values ​​of the resource requests required for the future operation of various equipment in the catering service venue.

4. The energy efficiency assessment and optimization method based on data analysis according to claim 3, characterized in that: To set optimization objectives for the overall satisfaction and overall load balance of various equipment in the aforementioned catering service venue, and to define resource allocation and equipment load balancing constraints, the specific steps include: The optimization objective is formed by summing the overall satisfaction of all types of equipment in the catering service venue and the overall load balance of all types of equipment in the catering service venue. Define constraints, including resource allocation constraints and equipment load balancing constraints within the catering service venue; Energy resource allocation constraint: The total amount of energy actually allocated to all equipment included in the catering service venue shall not exceed the total available energy. The equipment load balancing constraints in the catering service venue are as follows: when the load of a certain equipment is greater than the optimal load value, the tasks assigned to it are reduced and some tasks are migrated to other equipment; when the load of a certain equipment is less than the optimal load value, the tasks assigned to it are increased.

5. A data-based energy efficiency assessment and optimization system, applied to the data-based energy efficiency assessment and optimization method described in any one of claims 1-4, characterized in that: The system includes a data acquisition module, an energy efficiency assessment module, a load balancing analysis module, a resource request prediction module, and an optimization decision module. The data acquisition module acquires information on various equipment and energy consumption and resource data within the catering service venue. The energy efficiency assessment module determines quantitative indicators and differentiated conditions for energy efficiency assessment, compares equipment resource requests with actual allocations, calculates individual satisfaction levels, calculates weights and overall equipment satisfaction using a weighted average method, and derives the overall satisfaction assessment. The load balancing analysis module calculates the load balancing degree of various equipment within the catering service venue. The resource request prediction module acquires request data for resources required for the future operation of various equipment within the catering service venue. The optimization decision module sets optimization targets for the overall satisfaction and overall load balancing degree of various equipment within the catering service venue and defines resource allocation and equipment load balancing constraints.

6. The energy efficiency assessment and optimization system based on data analysis according to claim 5, characterized in that: The data acquisition module includes an equipment information acquisition unit, an energy consumption data acquisition unit, and a resource request and allocation recording unit. The equipment information acquisition unit is used to acquire the types of various equipment in the catering service venue; the energy consumption data acquisition unit is used to collect energy consumption data of various equipment through sensors; the resource request and allocation recording unit is used to collect request data of resources required for equipment operation and record the actual resource allocation to the equipment. The energy efficiency assessment module includes a quantitative indicator determination unit, an indicator condition formulation unit, and a satisfaction calculation unit. The quantitative indicator determination unit is used to determine the quantitative indicators used to assess equipment energy efficiency; the indicator condition formulation unit is used to formulate differentiated quantitative indicator conditions according to equipment type and priority; the satisfaction calculation unit is used to compare the equipment resource requests with the actual allocation, calculate the individual satisfaction level in combination with the quantitative indicators, calculate the weight and the total equipment satisfaction level using a weighted average method, and obtain the overall assessment satisfaction level.

7. The energy efficiency assessment and optimization system based on data analysis according to claim 6, characterized in that: The load balancing analysis module includes an optimal load value setting unit, a probability model construction unit, and a load balancing degree calculation unit. The optimal load value setting unit is used to set the optimal load value for the load data of various types of equipment based on the equipment's design specifications, performance parameters, and long-term operating experience. The probability model construction unit is used to construct a probability density function of Beta distribution based on the optimal load value of the equipment load data and the mean and variance of the load data over a period of time. The load balancing degree calculation unit is used to substitute the actual collected equipment load data into the constructed probability density function to obtain the load balancing degree value of different types of load data of each equipment, calculate the average value as the load balancing degree of the equipment, summarize the load balancing degree of all equipment, and calculate the total load balancing degree of all types of equipment in the entire catering service venue.

8. The energy efficiency assessment and optimization system based on data analysis according to claim 7, characterized in that: The resource request prediction module includes a historical data collection unit, a model building and training unit, and a prediction unit. The historical data collection unit collects resource request data for various types of equipment in the past and records the timestamp of each data point. The model building and training unit divides the collected data into training and testing sets, builds an LSTM model, adds input and output layers, and trains the training set data using the Adam optimization algorithm. The prediction unit inputs the testing set data into the trained LSTM model, and the model outputs predicted values ​​for the resource request data required for the future operation of various types of equipment. The optimization decision module includes a target setting unit, a constraint definition unit, and a strategy generation unit. The target setting unit sums the overall equipment satisfaction and the overall load balancing to form an optimization target. The constraint definition unit is used to define resource allocation and device load balancing constraints; the strategy generation unit is used to generate optimization strategies based on the optimization objectives and constraints.

Images