Intelligent energy consumption analysis method and device applied to communication machine room

Abstract

The invention relates to the technical field of energy consumption management, and discloses an intelligent energy consumption analysis method and device applied to a communication machine room, and the method comprises the steps: collecting a working condition parameter and an equipment type parameter of each energy consumption equipment in the communication machine room, and at least one multi-dimensional energy consumption impact factor of the communication machine room; for each energy consumption device, matching a first energy consumption calculation algorithm of the energy consumption device according to the working condition parameter and the device type parameter of the energy consumption device, and dynamically screening all the multi-dimensional energy consumption influence factors; inputting the screened target energy consumption influence factors into a corresponding first energy consumption calculation algorithm, and gradually outputting a real-time energy consumption value of the energy consumption equipment and a total energy consumption track parameter of the communication machine room; generating an energy consumption optimization strategy of the communication machine room in combination with a preset machine room energy consumption use efficiency threshold value; and the operation parameters of the corresponding energy consumption equipment in the communication machine room are adjusted. Therefore, the energy consumption analysis flexibility and accuracy of the communication machine room can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management, and in particular to an intelligent energy consumption analysis method and device applied to a communication room. Background Art

[0002] With the rapid development of 5G communications, cloud computing and Internet of Things technologies, the scale and energy consumption of communication rooms, as the core hub for data storage and processing, are growing exponentially.

[0003] Currently, the energy consumption analysis method usually adopts a fixed working condition classification analysis method, and divides the equipment operation status based on manual experience or simple thresholds. However, in the actual operation of the communication room, since its operation process is dynamic and the fixed working condition classification standard, the energy consumption analysis method is relatively one-sided and cannot comprehensively analyze the energy consumption of the communication room, and thus cannot guarantee the stable operation of the communication room.

[0004] It can be seen that how to improve the flexibility of energy consumption analysis in communication rooms in order to improve the accuracy of energy consumption analysis in communication rooms is particularly important. Summary of the invention

[0005] The present invention provides an intelligent energy consumption analysis method and device applied to a communication room, which can improve the flexibility of energy consumption analysis in the communication room, so as to improve the accuracy of energy consumption analysis in the communication room.

[0006] In order to solve the above technical problems, the first aspect of the present invention discloses an intelligent energy consumption analysis method applied to a communication room, the method comprising:

[0007] Collecting operating parameters and equipment type parameters of each energy-consuming device in the communication room, and at least one multi-dimensional energy consumption influencing factor of the communication room, wherein the multi-dimensional energy consumption influencing factor is used to represent factors influencing the energy consumption level of the energy-consuming device in the communication room;

[0008] For each of the energy-consuming devices, according to the operating parameters and the device type parameters of the energy-consuming device, a first energy consumption calculation algorithm of the energy-consuming device is matched; according to the first energy consumption calculation algorithm, all the multi-dimensional energy consumption influencing factors are dynamically screened; the screened target energy consumption influencing factors are input into the corresponding first energy consumption calculation algorithm, and the real-time energy consumption value of the energy-consuming device is output;

[0009] Generate a total energy consumption trajectory parameter of the communication room according to the real-time energy consumption values ​​of all the energy consuming devices;

[0010] Based on the total energy consumption trajectory parameter and a preset energy consumption efficiency threshold of the communication room, an energy consumption optimization strategy of the communication room is generated;

[0011] Based on the energy consumption optimization strategy, at least one target energy consuming device in the communication room and a target controller of each target energy consuming device are determined to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room.

[0012] As an optional implementation, in the first aspect of the present invention, the energy consuming equipment includes power supply and distribution equipment, temperature control equipment, IT equipment and other equipment, and for each of the energy consuming equipment;

[0013] When the energy consumption device is the power supply and distribution device, the first energy consumption calculation algorithm is:

[0014]

[0015] Among them, P loss A is used to represent the real-time energy consumption value of the power supply and distribution equipment. 1 It is used to represent the weight corresponding to the target energy consumption influencing factor, k 1 and k 2 Used to indicate the device characteristic factor, I rms It is used to indicate the harmonic component of current, THD is used to indicate the harmonic distortion rate of current, and cosφ is used to indicate the power factor;

[0016] When the energy consumption device is the temperature control device, the first energy consumption calculation algorithm is:

[0017]

[0018] Among them, P cool A is used to represent the real-time energy consumption value of the temperature control device. 2 It is used to represent the weight corresponding to the target energy consumption influencing factor, ΔT is used to represent the indoor and outdoor temperature difference, f comp Used to indicate the compressor frequency, T set Used to indicate the set temperature, T return It is used to represent the return air temperature, and α and β are used to represent the preset weights of the temperature control device;

[0019] When the energy-consuming device is the IT device, the first energy consumption calculation algorithm is:

[0020] P IT =A 3 [a 1 *u CPU +b 1 *u GPU +c 1 *u RAM +d 1 ]

[0021] Among them, PIT A is used to represent the real-time energy consumption value of the IT equipment. 3 It is used to represent the weight corresponding to the target energy consumption influencing factor, u CPU Used to indicate CPU utilization, u GPU Used to indicate GPU utilization, u RAM It is used to indicate the RAM usage, and other characters are the corresponding weights and biases;

[0022] When the energy-consuming device is the other device, the first energy consumption calculation algorithm is the product method of the operating power and the operating time of the energy-consuming device;

[0023] Among them, different energy-consuming devices have different corresponding weights of the target energy consumption influencing factors.

[0024] As an optional implementation manner, in the first aspect of the present invention, dynamically screening all the multi-dimensional energy consumption influencing factors according to the first energy consumption calculation algorithm includes:

[0025] Obtain the historical energy consumption value trajectory parameters of the energy consuming device;

[0026] For each of the multi-dimensional energy consumption influencing factors, obtain the current attribute parameter of the multi-dimensional energy consumption influencing factor; calculate the first correlation value between the current attribute parameter and the historical energy consumption value trajectory parameter according to the Pearson correlation coefficient; calculate the second correlation value between the multi-dimensional energy consumption influencing factor and the energy consuming device according to the first correlation value and the historical reference distance value of the historical energy consumption value trajectory parameter, wherein the historical reference distance value is used to indicate the distance degree of the historical energy consumption value trajectory parameter compared to the current moment;

[0027] Based on the random forest feature importance ranking and all the second correlation values, all the multi-dimensional energy consumption influencing factors are dynamically screened.

[0028] As an optional implementation, in the first aspect of the present invention, the energy consumption optimization strategy of the communication room is generated based on the total energy consumption trajectory parameter and the preset room energy consumption efficiency threshold, including:

[0029] Determine a multi-dimensional target optimization function according to the total energy consumption trajectory parameter, wherein the multi-dimensional target optimization function includes an energy consumption efficiency optimization function, a device peak power consumption control function, and a device start-stop control function;

[0030] Calculate the preliminary optimization parameter combination of the multi-dimensional objective optimization function in the communication room according to the preset genetic algorithm;

[0031] According to the acquired historical operating parameters of the communication room, setting a priority value of each function in the multi-dimensional objective optimization function;

[0032] According to all the priority values, the preliminary optimization parameter combination is adjusted to generate an energy consumption optimization strategy for the communication room.

[0033] As an optional implementation manner, in the first aspect of the present invention, the step of determining at least one target energy consuming device and a target controller of each target energy consuming device in the communication room based on the energy consumption optimization strategy, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room, includes:

[0034] Based on the energy consumption optimization strategy, determining at least one target energy consuming device in the communication room and a target controller for each of the target energy consuming devices;

[0035] When the target energy consumption device includes a temperature control device, determining the energy consumption optimization target parameter of the temperature control device according to the energy consumption optimization strategy; calculating the parameter distance value between the real-time energy consumption value of the temperature control device and the energy consumption optimization target parameter; determining at least one target component in the temperature control device according to a preset control algorithm, the parameter distance value and the target controller of the temperature control device, so as to adjust the operating parameters of the target component;

[0036] When the target energy-consuming device includes an IT device, determining an associated IT device of the IT device, wherein a task processing confidence between the associated IT device and the IT device is greater than or equal to a preset threshold, and the task processing confidence is positively correlated with device attribute parameters between the IT device and the associated IT device, and the device attribute parameters include at least one of a device attribution parameter and an execution task type parameter; determining a transfer task parameter of the IT device according to the energy consumption optimization strategy and the target controller of the IT device; and migrating the corresponding task to the associated IT device according to the transfer task parameter;

[0037] When the target energy-consuming equipment includes power supply and distribution equipment, the active filter is triggered to be put into operation and the transformer operation group is switched according to the energy consumption optimization strategy and the harmonic content of the power supply and distribution equipment.

[0038] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0039] Collecting actual energy consumption values ​​of the communication room;

[0040] A residual analysis is performed on the actual energy consumption value and the real-time energy consumption value of the first energy consumption calculation algorithm. If the mean absolute percentage error is greater than a preset error threshold, based on the transfer learning technology, the parameters in the second energy consumption calculation algorithm of the associated room of the communication room are used as initial values ​​and fine-tuned in combination with the first energy consumption calculation algorithm of the communication room.

[0041] The second aspect of the present invention discloses an intelligent energy consumption analysis device applied to a communication room, the device comprising:

[0042] A collection module, used to collect operating parameters and equipment type parameters of each energy-consuming device in the communication room, and at least one multi-dimensional energy consumption influencing factor of the communication room, wherein the multi-dimensional energy consumption influencing factor is used to represent factors affecting the energy consumption level of the energy-consuming device in the communication room;

[0043] A matching module, configured to match a first energy consumption calculation algorithm of each energy consuming device according to the operating condition parameter and the device type parameter of the energy consuming device;

[0044] A screening module, used for dynamically screening all the multi-dimensional energy consumption influencing factors according to the first energy consumption calculation algorithm;

[0045] A calculation module, used for inputting the screened target energy consumption influencing factor into the corresponding first energy consumption calculation algorithm, and outputting the real-time energy consumption value of the energy consuming device;

[0046] A generating module, used for generating a total energy consumption trajectory parameter of the communication room according to the real-time energy consumption values ​​of all the energy consuming devices;

[0047] The generating module is further used to generate an energy consumption optimization strategy for the communication room based on the total energy consumption trajectory parameter and a preset room energy consumption efficiency threshold;

[0048] A control module is used to determine at least one target energy consuming device and a target controller of each target energy consuming device in the communication room based on the energy consumption optimization strategy, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room.

[0049] As an optional implementation, in the second aspect of the present invention, the energy consuming equipment includes power supply and distribution equipment, temperature control equipment, IT equipment and other equipment, and for each of the energy consuming equipment;

[0050] When the energy consumption device is the power supply and distribution device, the first energy consumption calculation algorithm is:

[0051]

[0052] Among them, P loss A is used to represent the real-time energy consumption value of the power supply and distribution equipment. 1 It is used to represent the weight corresponding to the target energy consumption influencing factor, k 1 and k 2 Used to indicate the device characteristic factor, I rms It is used to indicate the harmonic component of current, THD is used to indicate the harmonic distortion rate of current, and cosφ is used to indicate the power factor;

[0053] When the energy consumption device is the temperature control device, the first energy consumption calculation algorithm is:

[0054]

[0055] Among them, P cool A is used to represent the real-time energy consumption value of the temperature control device. 2 It is used to represent the weight corresponding to the target energy consumption influencing factor, ΔT is used to represent the indoor and outdoor temperature difference, f comp Used to indicate the compressor frequency, T set Used to indicate the set temperature, T return It is used to represent the return air temperature, and α and β are used to represent the preset weights of the temperature control device;

[0056] When the energy-consuming device is the IT device, the first energy consumption calculation algorithm is:

[0057] P IT =A 3 [a 1 *u CPU +b 1 *u GPU +c 1 *u RAM +d 1 ]

[0058] Among them, P IT A is used to represent the real-time energy consumption value of the IT equipment. 3 It is used to represent the weight corresponding to the target energy consumption influencing factor, u CPU Used to indicate CPU utilization, u GPU Used to indicate GPU utilization, u RAM It is used to indicate the RAM usage, and other characters are the corresponding weights and biases;

[0059] When the energy-consuming device is the other device, the first energy consumption calculation algorithm is the product method of the operating power and the operating time of the energy-consuming device;

[0060] Among them, different energy-consuming devices have different corresponding weights of the target energy consumption influencing factors.

[0061] As an optional implementation, in the second aspect of the present invention, the specific manner in which the screening module dynamically screens all the multi-dimensional energy consumption influencing factors according to the first energy consumption calculation algorithm includes:

[0062] Obtain the historical energy consumption value trajectory parameters of the energy consuming device;

[0063] For each of the multi-dimensional energy consumption influencing factors, obtain the current attribute parameter of the multi-dimensional energy consumption influencing factor; calculate the first correlation value between the current attribute parameter and the historical energy consumption value trajectory parameter according to the Pearson correlation coefficient; calculate the second correlation value between the multi-dimensional energy consumption influencing factor and the energy consuming device according to the first correlation value and the historical reference distance value of the historical energy consumption value trajectory parameter, wherein the historical reference distance value is used to indicate the distance degree of the historical energy consumption value trajectory parameter compared to the current moment;

[0064] Based on the random forest feature importance ranking and all the second correlation values, all the multi-dimensional energy consumption influencing factors are dynamically screened.

[0065] As an optional implementation, in the second aspect of the present invention, the specific manner in which the generation module generates the energy consumption optimization strategy of the communication room based on the total energy consumption trajectory parameter and the preset room energy consumption efficiency threshold includes:

[0066] Determine a multi-dimensional target optimization function according to the total energy consumption trajectory parameter, wherein the multi-dimensional target optimization function includes an energy consumption efficiency optimization function, a device peak power consumption control function, and a device start-stop control function;

[0067] Calculate the preliminary optimization parameter combination of the multi-dimensional objective optimization function in the communication room according to the preset genetic algorithm;

[0068] According to the acquired historical operating parameters of the communication room, setting a priority value of each function in the multi-dimensional objective optimization function;

[0069] According to all the priority values, the preliminary optimization parameter combination is adjusted to generate an energy consumption optimization strategy for the communication room.

[0070] As an optional implementation, in the second aspect of the present invention, the control module determines at least one target energy consuming device in the communication room and a target controller of each target energy consuming device based on the energy consumption optimization strategy to control each target controller, and the specific manner of dynamically adjusting the operating parameters of the corresponding energy consuming device in the communication room includes:

[0071] Based on the energy consumption optimization strategy, determining at least one target energy consuming device in the communication room and a target controller for each of the target energy consuming devices;

[0072] When the target energy consumption device includes a temperature control device, determining the energy consumption optimization target parameter of the temperature control device according to the energy consumption optimization strategy; calculating the parameter distance value between the real-time energy consumption value of the temperature control device and the energy consumption optimization target parameter; determining at least one target component in the temperature control device according to a preset control algorithm, the parameter distance value and the target controller of the temperature control device, so as to adjust the operating parameters of the target component;

[0073] When the target energy-consuming device includes an IT device, determining an associated IT device of the IT device, wherein a task processing confidence between the associated IT device and the IT device is greater than or equal to a preset threshold, and the task processing confidence is positively correlated with device attribute parameters between the IT device and the associated IT device, and the device attribute parameters include at least one of a device attribution parameter and an execution task type parameter; determining a transfer task parameter of the IT device according to the energy consumption optimization strategy and the target controller of the IT device; and migrating the corresponding task to the associated IT device according to the transfer task parameter;

[0074] When the target energy-consuming equipment includes power supply and distribution equipment, the active filter is triggered to be put into operation and the transformer operation group is switched according to the energy consumption optimization strategy and the harmonic content of the power supply and distribution equipment.

[0075] As an optional implementation, in the second aspect of the present invention, the acquisition module is further used to collect the actual energy consumption value of the communication room;

[0076] And, the device also includes:

[0077] An analysis module, used for performing residual analysis on the actual energy consumption value and the real-time energy consumption value of the first energy consumption calculation algorithm;

[0078] An adjustment module is used to, if the mean absolute percentage error is greater than a preset error threshold, use the parameters in the second energy consumption calculation algorithm of the associated room of the communication room as initial values ​​based on the transfer learning technology, and fine-tune the first energy consumption calculation algorithm of the communication room in combination.

[0079] The third aspect of the present invention discloses another intelligent energy consumption analysis device for a communication room, the device comprising:

[0080] A memory storing executable program code;

[0081] a processor coupled to the memory;

[0082] The processor calls the executable program code stored in the memory to execute the intelligent energy consumption analysis method applied to a communication room disclosed in the first aspect of the present invention.

[0083] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the intelligent energy consumption analysis method applied to a communication room disclosed in the first aspect of the present invention.

[0084] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0085] In an embodiment of the present invention, operating parameters and equipment type parameters of each energy consuming device in a communication room, as well as at least one multidimensional energy consumption influencing factor of the communication room are collected, and the multidimensional energy consumption influencing factor is used to represent the factors affecting the energy consumption level of the energy consuming devices in the communication room; for each energy consuming device, a first energy consumption calculation algorithm of the energy consuming device is matched according to the operating parameters and equipment type parameters of the energy consuming device; according to the first energy consumption calculation algorithm, all multidimensional energy consumption influencing factors are dynamically screened; the screened target energy consumption influencing factors are input into the corresponding first energy consumption calculation algorithm, and the real-time energy consumption value of the energy consuming device is output; according to the real-time energy consumption values ​​of all energy consuming devices, a total energy consumption trajectory parameter of the communication room is generated; based on the total energy consumption trajectory parameter and a preset room energy consumption efficiency threshold, an energy consumption optimization strategy of the communication room is generated; based on the energy consumption optimization strategy, at least one target energy consuming device in the communication room and a target controller of each target energy consuming device are determined to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room. It can be seen that the implementation of the present invention can match the first energy consumption calculation algorithm of each energy consuming device based on the collected operating parameters and equipment type parameters of the energy consuming device, realize the classification of energy consumption calculation algorithms of different energy consuming devices, that is, equipment type matching model and dynamic operating condition clustering, adaptively calculate energy consumption for different energy consuming devices, improve the accuracy of energy consumption calculation, and dynamically screen all multi-dimensional energy consumption influencing factors based on the matched first energy consumption calculation algorithm, and input the screened target energy consumption influencing factors into the corresponding first energy consumption calculation algorithm, output the real-time energy consumption value of the energy consuming device, and through dynamic screening of multi-dimensional energy consumption influencing factors, through multi-model hybrid calculation + feature dynamic screening, the energy consumption calculation of the communication room has the ability to adapt to the operating conditions. Improve the flexibility, timeliness and accuracy of energy consumption calculation, improve the environmental adaptability and scenario matching of energy consumption calculation, generate the total energy consumption trajectory parameters of the communication room according to the real-time energy consumption values ​​of all energy-consuming equipment; generate the energy consumption optimization strategy of the communication room based on the total energy consumption trajectory parameters and the preset room energy consumption efficiency threshold; based on the energy consumption optimization strategy, determine at least one target energy-consuming equipment in the communication room and the target controller of each target energy-consuming equipment to control each target controller, dynamically adjust the operating parameters of the corresponding energy-consuming equipment in the communication room, realize multi-objective collaborative optimization, and build a complete technical chain of "working condition division, equipment classification, factor screening, energy consumption calculation, strategy generation, and closed-loop control" to improve the flexibility and accuracy of energy consumption analysis in the communication room at the full link level. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0087] Figure 1 It is a flow chart of an intelligent energy consumption analysis method applied to a communication room disclosed in an embodiment of the present invention;

[0088] Figure 2 It is a flow chart of another intelligent energy consumption analysis method applied to a communication room disclosed in an embodiment of the present invention;

[0089] Figure 3 It is a structural schematic diagram of an intelligent energy consumption analysis device applied to a communication room disclosed in an embodiment of the present invention;

[0090] Figure 4 It is a structural schematic diagram of another intelligent energy consumption analysis device applied to a communication room disclosed in an embodiment of the present invention;

[0091] Figure 5 It is a structural schematic diagram of another intelligent energy consumption analysis device applied to a communication room disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0092] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0093] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0094] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0095] The present invention discloses an intelligent energy consumption analysis method and device for a communication room. The method and device can match a first energy consumption calculation algorithm of each energy consumption device based on the collected working condition parameters and device type parameters of the energy consumption device, realize the classification of energy consumption calculation algorithms of different energy consumption devices, that is, device type matching model and dynamic working condition clustering, adaptively calculate energy consumption for different energy consumption devices, improve the accuracy of energy consumption calculation, and dynamically screen all multi-dimensional energy consumption influencing factors based on the matched first energy consumption calculation algorithm, and input the screened target energy consumption influencing factors into the corresponding first energy consumption calculation algorithm, output the real-time energy consumption value of the energy consumption device, and make the energy consumption calculation of the communication room more accurate by dynamically screening the multi-dimensional energy consumption influencing factors and by multi-model hybrid calculation + feature dynamic screening. It has the ability to adapt to working conditions, improve the flexibility, timeliness and accuracy of energy consumption calculation, improve the environmental adaptability and scene matching of energy consumption calculation, and generate the total energy consumption trajectory parameters of the communication room based on the real-time energy consumption values ​​of all energy-consuming devices; based on the total energy consumption trajectory parameters and the preset room energy consumption efficiency threshold, generate the energy consumption optimization strategy of the communication room; based on the energy consumption optimization strategy, determine at least one target energy-consuming device in the communication room and the target controller of each target energy-consuming device to control each target controller, dynamically adjust the operating parameters of the corresponding energy-consuming device in the communication room, realize multi-objective collaborative optimization, and build a complete technical chain of "working condition division, equipment classification, factor screening, energy consumption calculation, strategy generation, closed-loop control" to achieve the full-link level to improve the flexibility and accuracy of energy consumption analysis in the communication room. The following are detailed explanations.

[0096] Embodiment 1

[0097] See also Figure 1 , Figure 1 The figure is a flow chart of an intelligent energy consumption analysis method for a communication room disclosed in an embodiment of the present invention. Figure 1 The energy consumption intelligent analysis method for communication rooms described above can be applied to communication rooms, and can also be applied to intelligent devices related to communication rooms, including but not limited to energy consumption devices, energy storage devices, cloud devices, edge computing devices, relay devices, base station devices, urban management devices, and intelligent network devices. The embodiments of the present invention do not limit this. Figure 1As shown, the intelligent energy consumption analysis method applied to the communication room may include the following operations:

[0098] 101. Collect operating parameters and equipment type parameters of each energy-consuming equipment in the communication room, and at least one multi-dimensional energy consumption influencing factor of the communication room, where the multi-dimensional energy consumption influencing factor is used to indicate factors that affect the energy consumption of energy-consuming equipment in the communication room;

[0099] 102. For each energy consuming device, matching a first energy consumption calculation algorithm of the energy consuming device according to the operating condition parameters and device type parameters of the energy consuming device;

[0100] In an embodiment of the present invention, optionally, during the above-mentioned step 101 or step 102, when operating condition parameters are involved, further operating condition division operations can be performed, namely: first define the basic operating condition based on the equipment start-stop combination, and then use the K-means clustering algorithm to perform secondary division on the historical load rate, ambient temperature and humidity, and timestamp data to generate detailed operating condition types; attach an operating condition label to each operating condition, including an equipment operation status code, an environmental parameter range, and a time period identifier; establish an operating condition switching rule base, and trigger the operating condition migration when a change in the equipment combination or an environmental parameter out of bounds is detected.

[0101] In the embodiment of the present invention, as an optional implementation mode, the above-mentioned energy consuming equipment includes power supply and distribution equipment, temperature control equipment, IT equipment and other equipment, for each energy consuming equipment;

[0102] When the energy consumption device is a power supply and distribution device, the first energy consumption calculation algorithm is:

[0103]

[0104] Among them, P loss Used to indicate the real-time energy consumption value of power supply and distribution equipment, A 1 Used to represent the weight corresponding to the target energy consumption influencing factor, k 1 and k 2 Used to indicate the device characteristic factor, I rms It is used to indicate the harmonic component of current, THD is used to indicate the harmonic distortion rate of current, and cosφ is used to indicate the power factor;

[0105] When the energy consumption device is a temperature control device, the first energy consumption calculation algorithm is:

[0106]

[0107] Among them, P cool Used to indicate the real-time energy consumption value of the temperature control equipment, A 2 It is used to indicate the weight of the target energy consumption influencing factor, ΔT is used to indicate the indoor and outdoor temperature difference, f compUsed to indicate the compressor frequency, T set Used to indicate the set temperature, T return It is used to indicate the return air temperature, and α and β are used to indicate the preset weights of the temperature control device;

[0108] When the energy consuming device is an IT device, the first energy consumption calculation algorithm is:

[0109] P IT =A 3 [a 1 *u CPU +b 1 *u GPU +c 1 *u RAM +d 1 ]

[0110] Among them, P IT Used to indicate the real-time energy consumption value of IT equipment, A 3 Used to represent the weight corresponding to the target energy consumption influencing factor, u CPU Used to indicate CPU utilization, u GPU Used to indicate GPU utilization, u RAM It is used to indicate the RAM usage, and other characters are the corresponding weights and biases;

[0111] When the energy-consuming device is other equipment, the first energy consumption calculation algorithm is the product method of the operating power and the operating time of the energy-consuming device;

[0112] Among them, different energy-consuming equipment has different corresponding weights of the target energy consumption influencing factors.

[0113] It can be seen that the implementation of this optional embodiment can match the first energy consumption calculation algorithm of the energy consuming equipment based on the collected operating parameters and equipment type parameters of the energy consuming equipment, and concretize the abstract "energy consumption calculation method" into specific formulas such as harmonic loss model, variable frequency equation, and segmented regression model, so as to realize the classification of energy consumption calculation algorithms for different energy consuming equipment, that is, equipment type matching model and dynamic operating condition clustering, and adaptively calculate energy consumption for different energy consuming equipment, thereby improving the accuracy and feasibility of energy consumption calculation.

[0114] 103. According to the first energy consumption calculation algorithm, all multi-dimensional energy consumption influencing factors are dynamically screened;

[0115] In the embodiment of the present invention, as another optional implementation, the above-mentioned first energy consumption calculation algorithm is used to dynamically screen all multi-dimensional energy consumption influencing factors, including:

[0116] Obtain the historical energy consumption value trajectory parameters of the energy consuming device;

[0117] For each multidimensional energy consumption influencing factor, obtain the current attribute parameter of the multidimensional energy consumption influencing factor; calculate the first correlation value between the current attribute parameter and the historical energy consumption value trajectory parameter according to the Pearson correlation coefficient; calculate the second correlation value between the multidimensional energy consumption influencing factor and the energy consuming device according to the first correlation value and the historical reference distance value of the historical energy consumption value trajectory parameter, and the historical reference distance value is used to indicate the degree of distance between the historical energy consumption value trajectory parameter and the current moment;

[0118] Based on the random forest feature importance ranking and all second correlation values, all multi-dimensional energy consumption influencing factors are dynamically screened.

[0119] In the embodiment of the present invention, further optionally, in the case where the energy-consuming device is a temperature control device, a decision tree model can be further introduced into the temperature control device to automatically activate / shield specific factors according to the current ambient temperature and humidity and the device status.

[0120] It can be seen that the implementation of this optional embodiment can dynamically screen all multi-dimensional energy consumption influencing factors after the first energy consumption calculation algorithm is matched. In this process, specifically, by obtaining the historical energy consumption value trajectory parameters of the energy consumption equipment, and for each multi-dimensional energy consumption influencing factor, obtaining the current attribute parameters of the multi-dimensional energy consumption influencing factor; according to the Pearson correlation coefficient, the first correlation value between the current attribute parameter and the historical energy consumption value trajectory parameter is calculated; in order to further improve the calculation accuracy of the second correlation value between the multi-dimensional energy consumption influencing factor and the energy consumption equipment, according to the first correlation value and the historical reference distance value of the historical energy consumption value trajectory parameter, the correlation between the multi-dimensional energy consumption influencing factor and the energy consumption equipment is calculated. The second correlation value and the historical reference distance value are used to indicate the degree of distance between the trajectory parameters of the historical energy consumption values ​​and the current moment. Finally, based on the random forest feature importance sorting, redundant factors with importance scores lower than the preset threshold are eliminated to improve the dynamic screening accuracy and environmental adaptability of multi-dimensional energy consumption influencing factors, which is beneficial for the subsequent input of the screened target energy consumption influencing factors into the corresponding first energy consumption calculation algorithm, and output of the real-time energy consumption value of the energy consuming equipment. By dynamically screening multi-dimensional energy consumption influencing factors and through multi-model hybrid calculation + feature dynamic screening, the energy consumption calculation of the communication room has the ability to adapt to working conditions, improves the flexibility, timeliness and accuracy of energy consumption calculation, and improves the environmental adaptability and scenario matching of energy consumption calculation.

[0121] 104. Input the screened target energy consumption influencing factor into the corresponding first energy consumption calculation algorithm, and output the real-time energy consumption value of the energy consuming device;

[0122] 105. Generate the total energy consumption trajectory parameters of the communication room based on the real-time energy consumption values ​​of all energy-consuming devices;

[0123] 106. Generate an energy consumption optimization strategy for the communication room based on the total energy consumption trajectory parameters and the preset room energy consumption efficiency threshold;

[0124] In an embodiment of the present invention, as another optional implementation, the energy consumption optimization strategy of the communication room is generated based on the total energy consumption trajectory parameter and the preset room energy consumption efficiency threshold, including:

[0125] According to the total energy consumption trajectory parameters, a multi-dimensional target optimization function is determined, and the multi-dimensional target optimization function includes an energy consumption efficiency optimization function, a device peak power consumption control function, and a device start-stop control function;

[0126] According to the preset genetic algorithm, calculate the preliminary optimization parameter combination of the multi-dimensional objective optimization function in the communication room;

[0127] According to the acquired historical operating parameters of the communication room, a priority value of each function in the multi-dimensional objective optimization function is set;

[0128] According to all priority values, the preliminary optimization parameter combination is adjusted to generate the energy consumption optimization strategy of the communication room.

[0129] In this optional embodiment, optionally, for the energy consumption optimization strategy generated above, the strategy can be encoded into a control instruction set and sent to the device controller via the Modbus / TCP protocol.

[0130] It can be seen that the implementation of this optional embodiment can determine the multi-dimensional objective optimization function according to the total energy consumption trajectory parameters in the process of generating the energy consumption optimization strategy of the communication room. The multi-dimensional objective optimization function includes the energy consumption efficiency optimization function, the equipment peak power consumption control function and the equipment start and stop control function, thereby defining the multi-objective optimization function, while minimizing the PUE value, the equipment peak power consumption, and the number of start and stop times of the temperature control equipment, thereby improving the comprehensiveness of the energy consumption analysis of the communication room and the accuracy of the energy consumption management from the multi-dimensional optimization level, and calculating the preliminary optimization parameter combination of the multi-dimensional objective optimization function in the communication room according to the preset genetic algorithm. ,Optional, ,Generated Strategies include: adjusting the set temperature of the air conditioner, limiting the load rate of non-critical IT equipment, switching ,power circuits, according to the historical operating parameters of the ,communication room, setting the priority value of the function ,for each function in the multi-dimensional objective optimization function, setting ,priority rules for the strategy: giving priority to the power supply of IT ,equipment in emergency conditions, giving priority to optimizing the energy ,efficiency of temperature control equipment in non-emergency conditions, adjusting the combination of ,prepared optimization parameters according to all priority values, generating the ,energy consumption optimization strategy for the communication room, improving the ,generation accuracy of the energy consumption optimization strategy for the communication ,room, the comprehensiveness of the energy consumption analysis and the ,accuracy of the energy consumption management.

[0131] 107. Based on the energy consumption optimization strategy, determine at least one target energy consuming device in the communication room and a target controller for each target energy consuming device, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room.

[0132] In this optional embodiment, as an optional implementation mode, the above-mentioned energy consumption optimization strategy is based on determining at least one target energy consuming device in the communication room and a target controller of each target energy consuming device to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room, including:

[0133] Based on the energy consumption optimization strategy, determining at least one target energy consuming device and a target controller for each target energy consuming device in the communication room;

[0134] When the target energy consumption device includes a temperature control device, determining the energy consumption optimization target parameter of the temperature control device according to the energy consumption optimization strategy; calculating the parameter distance value between the real-time energy consumption value of the temperature control device and the energy consumption optimization target parameter; determining at least one target component in the temperature control device according to the preset control algorithm, the parameter distance value and the target controller of the temperature control device to adjust the operating parameters of the target component;

[0135] When the target energy-consuming device includes an IT device, determining the associated IT device of the IT device, the task processing confidence between the associated IT device and the IT device is greater than or equal to a preset threshold, the task processing confidence is positively correlated with the device attribute parameters between the IT device and the associated IT device, and the device attribute parameters include at least one of a device attribution parameter and an execution task type parameter; determining the transfer task parameters of the IT device according to the energy consumption optimization strategy and the target controller of the IT device; and migrating the corresponding task to the associated IT device according to the transfer task parameters;

[0136] When the target energy-consuming equipment includes power supply and distribution equipment, the active filter is triggered to be put into operation and the transformer operation group is switched according to the energy consumption optimization strategy and the harmonic content of the power supply and distribution equipment.

[0137] In this optional embodiment, the operating parameters of the equipment are dynamically adjusted. Specifically, for temperature control equipment, the compressor frequency and fan speed can be dynamically adjusted using a PID control algorithm based on the deviation between the real-time PUE value and the set threshold. For IT equipment, low-priority tasks can be migrated to server nodes with lower energy consumption through a load balancer. For power supply and distribution equipment, active filters can be triggered based on harmonic content, and transformer operation groups can be switched to reduce no-load losses. For other equipment, power consumption can be adaptively adjusted in combination with the tasks they perform.

[0138] It can be seen that the implementation of this optional embodiment can determine at least one target energy-consuming device and a target controller for each target energy-consuming device in the communication room based on the energy consumption optimization strategy, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy-consuming equipment in the communication room, thereby realizing multi-objective collaborative optimization, and constructing a complete technical chain of "working condition division, equipment classification, factor screening, energy consumption calculation, strategy generation, and closed-loop control", so as to improve the flexibility and accuracy of energy consumption analysis in the communication room at the full-link level.

[0139] It can be seen that the implementation of the embodiment of the present invention can match the first energy consumption calculation algorithm of each energy consuming device based on the collected operating parameters and equipment type parameters of the energy consuming device, realize the classification of energy consumption calculation algorithms of different energy consuming devices, that is, equipment type matching model and dynamic operating condition clustering, adaptively calculate energy consumption for different energy consuming devices, improve the accuracy of energy consumption calculation, and dynamically screen all multi-dimensional energy consumption influencing factors based on the matched first energy consumption calculation algorithm, and input the screened target energy consumption influencing factors into the corresponding first energy consumption calculation algorithm, output the real-time energy consumption value of the energy consuming device, and through dynamic screening of multi-dimensional energy consumption influencing factors and multi-model hybrid calculation + feature dynamic screening, the energy consumption calculation of the communication room has the ability to adapt to the operating conditions. , improve the flexibility, timeliness and accuracy of energy consumption calculation, improve the environmental adaptability and scenario matching of energy consumption calculation, generate the total energy consumption trajectory parameters of the communication room according to the real-time energy consumption values ​​of all energy-consuming equipment; generate the energy consumption optimization strategy of the communication room based on the total energy consumption trajectory parameters and the preset room energy consumption efficiency threshold; based on the energy consumption optimization strategy, determine at least one target energy-consuming device in the communication room and the target controller of each target energy-consuming device to control each target controller, dynamically adjust the operating parameters of the corresponding energy-consuming equipment in the communication room, realize multi-objective collaborative optimization, and build a complete technical chain of "working condition division, equipment classification, factor screening, energy consumption calculation, strategy generation, and closed-loop control" to achieve full-link level Improve the flexibility and accuracy of energy consumption analysis in the communication room.

[0140] Embodiment 2

[0141] See also Figure 2 , Figure 2 1 is a flow chart of another intelligent energy consumption analysis method for a communication room disclosed in an embodiment of the present invention. Figure 2 The energy consumption intelligent analysis method for communication rooms described above can be applied to communication rooms, and can also be applied to intelligent devices related to communication rooms, including but not limited to energy consumption devices, energy storage devices, cloud devices, edge computing devices, relay devices, base station devices, urban management devices, and intelligent network devices. The embodiments of the present invention do not limit this. Figure 2As shown, the intelligent energy consumption analysis method applied to the communication room may include the following operations:

[0142] 201. Collect operating parameters and equipment type parameters of each energy-consuming equipment in the communication room, and at least one multi-dimensional energy consumption influencing factor of the communication room, where the multi-dimensional energy consumption influencing factor is used to indicate factors that affect the energy consumption of energy-consuming equipment in the communication room;

[0143] 202. For each energy consuming device, matching a first energy consumption calculation algorithm of the energy consuming device according to the operating condition parameters and device type parameters of the energy consuming device;

[0144] 203. Dynamically screen all multi-dimensional energy consumption influencing factors according to the first energy consumption calculation algorithm;

[0145] 204. Input the screened target energy consumption influencing factor into the corresponding first energy consumption calculation algorithm, and output the real-time energy consumption value of the energy consuming device;

[0146] 205. Generate total energy consumption trajectory parameters of the communication room based on the real-time energy consumption values ​​of all energy-consuming devices;

[0147] 206. Generate an energy consumption optimization strategy for the communication room based on the total energy consumption trajectory parameter and a preset energy consumption efficiency threshold of the room;

[0148] 207. Based on the energy consumption optimization strategy, determine at least one target energy consuming device in the communication room and a target controller of each target energy consuming device, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room;

[0149] In the embodiment of the present invention, for the supplementary explanation of step 201 to step 207, please refer to the supplementary explanation of step 101 to step 107 in the first embodiment, and the embodiment of the present invention will not elaborate on this.

[0150] 208. Collect the actual energy consumption value of the communication room;

[0151] In the embodiment of the present invention, optionally, step 208 may be performed periodically or randomly;

[0152] 209. Perform residual analysis on the actual energy consumption value and the real-time energy consumption value of the first energy consumption calculation algorithm;

[0153] 210. If the mean absolute percentage error is greater than a preset error threshold, based on the transfer learning technology, the parameters in the second energy consumption calculation algorithm of the associated room of the communication room are used as initial values, and fine-tuned in combination with the first energy consumption calculation algorithm of the communication room.

[0154] In an embodiment of the present invention, for steps 208 to 210, it is optional and specific to collect actual energy consumption data regularly and perform residual analysis with the model prediction value. If the mean absolute percentage error (MAPE) exceeds 5%, the model recalibration is triggered; transfer learning technology is used to use the energy consumption model parameters of other computer rooms as initial values, and fine-tune them in combination with local data; a strategy effect evaluation module is established to count the energy saving before and after the implementation of the strategy, and the effectiveness of the new strategy is verified through A / B testing.

[0155] It can be seen that the implementation of the embodiments of the present invention can further improve the robustness and stability of the energy consumption analysis of the communication room by adding model maintenance mechanisms such as residual analysis, transfer learning, and A / B testing. According to the unique needs of the communication room (such as PUE optimization and harmonic control), a dedicated computing model and control logic are designed, and the electrical characteristics analysis (harmonics) and IT resource scheduling are integrated, which is conducive to solving the problem of cross-domain energy consumption collaborative optimization.

[0156] Embodiment 3

[0157] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of an intelligent energy consumption analysis device applied to a communication room disclosed in an embodiment of the present invention. The intelligent energy consumption analysis device applied to a communication room can be applied to a communication room, and can also be applied to intelligent devices related to the communication room, and the intelligent devices include but are not limited to energy consumption devices, energy storage devices, cloud devices, edge computing devices, relay devices, base station devices, city management devices, and intelligent network devices. One or more of these devices are not limited in the embodiment of the present invention.

[0158] like Figure 3 As shown, the energy consumption intelligent analysis device applied to the communication room may include:

[0159] The collection module 301 is used to collect the working condition parameters and equipment type parameters of each energy-consuming equipment in the communication room, and at least one multi-dimensional energy consumption influencing factor of the communication room, where the multi-dimensional energy consumption influencing factor is used to represent the factors that affect the energy consumption of the energy-consuming equipment in the communication room;

[0160] A matching module 302 is used to match a first energy consumption calculation algorithm of each energy consuming device according to an operating condition parameter and a device type parameter of the energy consuming device;

[0161] A screening module 303 is used to dynamically screen all multi-dimensional energy consumption influencing factors according to a first energy consumption calculation algorithm;

[0162] The calculation module 304 is used to input the screened target energy consumption influencing factor into the corresponding first energy consumption calculation algorithm, and output the real-time energy consumption value of the energy consuming device;

[0163] A generating module 305, for generating a total energy consumption trajectory parameter of a communication room according to the real-time energy consumption values ​​of all energy consuming devices;

[0164] The generation module 305 is further used to generate an energy consumption optimization strategy for the communication room based on the total energy consumption trajectory parameter and the preset room energy consumption efficiency threshold;

[0165] The control module 306 is used to determine at least one target energy consuming device and a target controller of each target energy consuming device in the communication room based on the energy consumption optimization strategy, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room.

[0166] It can be seen that the implementation of the embodiment of the present invention can match the first energy consumption calculation algorithm of each energy consuming device based on the collected operating parameters and equipment type parameters of the energy consuming device, realize the classification of energy consumption calculation algorithms of different energy consuming devices, that is, equipment type matching model and dynamic operating condition clustering, adaptively calculate energy consumption for different energy consuming devices, improve the accuracy of energy consumption calculation, and dynamically screen all multi-dimensional energy consumption influencing factors based on the matched first energy consumption calculation algorithm, and input the screened target energy consumption influencing factors into the corresponding first energy consumption calculation algorithm, output the real-time energy consumption value of the energy consuming device, and through dynamic screening of multi-dimensional energy consumption influencing factors and multi-model hybrid calculation + feature dynamic screening, the energy consumption calculation of the communication room has the ability to adapt to the operating conditions. , improve the flexibility, timeliness and accuracy of energy consumption calculation, improve the environmental adaptability and scenario matching of energy consumption calculation, generate the total energy consumption trajectory parameters of the communication room according to the real-time energy consumption values ​​of all energy-consuming equipment; generate the energy consumption optimization strategy of the communication room based on the total energy consumption trajectory parameters and the preset room energy consumption efficiency threshold; based on the energy consumption optimization strategy, determine at least one target energy-consuming device in the communication room and the target controller of each target energy-consuming device to control each target controller, dynamically adjust the operating parameters of the corresponding energy-consuming equipment in the communication room, realize multi-objective collaborative optimization, and build a complete technical chain of "working condition division, equipment classification, factor screening, energy consumption calculation, strategy generation, and closed-loop control" to achieve full-link level Improve the flexibility and accuracy of energy consumption analysis in the communication room.

[0167] In the embodiment of the present invention, as an optional implementation mode, the above-mentioned energy consuming equipment includes power supply and distribution equipment, temperature control equipment, IT equipment and other equipment, for each energy consuming equipment;

[0168] When the energy consumption device is a power supply and distribution device, the first energy consumption calculation algorithm is:

[0169]

[0170] Among them, P lossUsed to indicate the real-time energy consumption value of power supply and distribution equipment, A 1 Used to represent the weight corresponding to the target energy consumption influencing factor, k 1 and k 2 Used to indicate the device characteristic factor, I rms It is used to indicate the harmonic component of current, THD is used to indicate the harmonic distortion rate of current, and cosφ is used to indicate the power factor;

[0171] When the energy consumption device is a temperature control device, the first energy consumption calculation algorithm is:

[0172]

[0173] Among them, P cool Used to indicate the real-time energy consumption value of the temperature control equipment, A 2 It is used to indicate the weight of the target energy consumption influencing factor, ΔT is used to indicate the indoor and outdoor temperature difference, f comp Used to indicate the compressor frequency, T set Used to indicate the set temperature, T return It is used to indicate the return air temperature, and α and β are used to indicate the preset weights of the temperature control device;

[0174] When the energy consuming device is an IT device, the first energy consumption calculation algorithm is:

[0175] P IT =A 3 [a 1 *u CPU +b 1 *u GPU +c 1 *u RAM +d 1 ]

[0176] Among them, P IT Used to indicate the real-time energy consumption value of IT equipment, A 3 Used to represent the weight corresponding to the target energy consumption influencing factor, u CPU Used to indicate CPU utilization, u GPU Used to indicate GPU utilization, u RAM It is used to indicate the RAM usage, and other characters are the corresponding weights and biases;

[0177] When the energy-consuming device is other equipment, the first energy consumption calculation algorithm is the product method of the operating power and the operating time of the energy-consuming device;

[0178] Among them, different energy-consuming equipment has different corresponding weights of the target energy consumption influencing factors.

[0179] It can be seen that the implementation of this optional embodiment can match the first energy consumption calculation algorithm of the energy consuming equipment based on the collected operating parameters and equipment type parameters of the energy consuming equipment, and concretize the abstract "energy consumption calculation method" into specific formulas such as harmonic loss model, variable frequency equation, and segmented regression model, so as to realize the classification of energy consumption calculation algorithms for different energy consuming equipment, that is, equipment type matching model and dynamic operating condition clustering, and adaptively calculate energy consumption for different energy consuming equipment, thereby improving the accuracy and feasibility of energy consumption calculation.

[0180] In the embodiment of the present invention, as another optional implementation, the specific manner in which the above-mentioned screening module 303 dynamically screens all multi-dimensional energy consumption influencing factors according to the first energy consumption calculation algorithm includes:

[0181] Obtain the historical energy consumption value trajectory parameters of the energy consuming device;

[0182] For each multidimensional energy consumption influencing factor, obtain the current attribute parameter of the multidimensional energy consumption influencing factor; calculate the first correlation value between the current attribute parameter and the historical energy consumption value trajectory parameter according to the Pearson correlation coefficient; calculate the second correlation value between the multidimensional energy consumption influencing factor and the energy consuming device according to the first correlation value and the historical reference distance value of the historical energy consumption value trajectory parameter, and the historical reference distance value is used to indicate the degree of distance between the historical energy consumption value trajectory parameter and the current moment;

[0183] Based on the random forest feature importance ranking and all second correlation values, all multi-dimensional energy consumption influencing factors are dynamically screened.

[0184] It can be seen that the implementation of this optional embodiment can dynamically screen all multi-dimensional energy consumption influencing factors after the first energy consumption calculation algorithm is matched. In this process, specifically, by obtaining the historical energy consumption value trajectory parameters of the energy consumption equipment, and for each multi-dimensional energy consumption influencing factor, obtaining the current attribute parameters of the multi-dimensional energy consumption influencing factor; according to the Pearson correlation coefficient, the first correlation value between the current attribute parameter and the historical energy consumption value trajectory parameter is calculated; in order to further improve the calculation accuracy of the second correlation value between the multi-dimensional energy consumption influencing factor and the energy consumption equipment, according to the first correlation value and the historical reference distance value of the historical energy consumption value trajectory parameter, the correlation between the multi-dimensional energy consumption influencing factor and the energy consumption equipment is calculated. The second correlation value and the historical reference distance value are used to indicate the degree of distance between the trajectory parameters of the historical energy consumption values ​​and the current moment. Finally, based on the random forest feature importance sorting, redundant factors with importance scores lower than the preset threshold are eliminated to improve the dynamic screening accuracy and environmental adaptability of multi-dimensional energy consumption influencing factors, which is beneficial for the subsequent input of the screened target energy consumption influencing factors into the corresponding first energy consumption calculation algorithm, and output of the real-time energy consumption value of the energy consuming equipment. By dynamically screening multi-dimensional energy consumption influencing factors and through multi-model hybrid calculation + feature dynamic screening, the energy consumption calculation of the communication room has the ability to adapt to working conditions, improves the flexibility, timeliness and accuracy of energy consumption calculation, and improves the environmental adaptability and scenario matching of energy consumption calculation.

[0185] In the embodiment of the present invention, as another optional implementation, the specific manner in which the generation module 305 generates the energy consumption optimization strategy of the communication room based on the total energy consumption trajectory parameter and the preset room energy consumption efficiency threshold includes:

[0186] According to the total energy consumption trajectory parameters, a multi-dimensional target optimization function is determined, and the multi-dimensional target optimization function includes an energy consumption efficiency optimization function, a device peak power consumption control function, and a device start-stop control function;

[0187] According to the preset genetic algorithm, calculate the preliminary optimization parameter combination of the multi-dimensional objective optimization function in the communication room;

[0188] According to the acquired historical operating parameters of the communication room, a priority value of each function in the multi-dimensional objective optimization function is set;

[0189] According to all priority values, the preliminary optimization parameter combination is adjusted to generate the energy consumption optimization strategy of the communication room.

[0190] It can be seen that the implementation of this optional embodiment can determine the multi-dimensional objective optimization function according to the total energy consumption trajectory parameters in the process of generating the energy consumption optimization strategy of the communication room. The multi-dimensional objective optimization function includes the energy consumption efficiency optimization function, the equipment peak power consumption control function and the equipment start and stop control function, thereby defining the multi-objective optimization function, while minimizing the PUE value, the equipment peak power consumption, and the number of start and stop times of the temperature control equipment, thereby improving the comprehensiveness of the energy consumption analysis of the communication room and the accuracy of the energy consumption management from the multi-dimensional optimization level, and calculating the preliminary optimization parameter combination of the multi-dimensional objective optimization function in the communication room according to the preset genetic algorithm. ,Optional, ,Generated Strategies include: adjusting the set temperature of the air conditioner, limiting the load rate of non-critical IT equipment, switching ,power circuits, according to the historical operating parameters of the ,communication room, setting the priority value of the function ,for each function in the multi-dimensional objective optimization function, setting ,priority rules for the strategy: giving priority to the power supply of IT ,equipment in emergency conditions, giving priority to optimizing the energy ,efficiency of temperature control equipment in non-emergency conditions, adjusting the combination of ,prepared optimization parameters according to all priority values, generating the ,energy consumption optimization strategy for the communication room, improving the ,generation accuracy of the energy consumption optimization strategy for the communication ,room, the comprehensiveness of the energy consumption analysis and the ,accuracy of the energy consumption management.

[0191] In this optional embodiment, as an optional implementation, the control module 306 determines at least one target energy consuming device and a target controller of each target energy consuming device in the communication room based on the energy consumption optimization strategy to control each target controller, and the specific manner of dynamically adjusting the operating parameters of the corresponding energy consuming device in the communication room includes:

[0192] Based on the energy consumption optimization strategy, determining at least one target energy consuming device and a target controller for each target energy consuming device in the communication room;

[0193] When the target energy consumption device includes a temperature control device, determining the energy consumption optimization target parameter of the temperature control device according to the energy consumption optimization strategy; calculating the parameter distance value between the real-time energy consumption value of the temperature control device and the energy consumption optimization target parameter; determining at least one target component in the temperature control device according to the preset control algorithm, the parameter distance value and the target controller of the temperature control device to adjust the operating parameters of the target component;

[0194] When the target energy-consuming device includes an IT device, determining the associated IT device of the IT device, the task processing confidence between the associated IT device and the IT device is greater than or equal to a preset threshold, the task processing confidence is positively correlated with the device attribute parameters between the IT device and the associated IT device, and the device attribute parameters include at least one of a device attribution parameter and an execution task type parameter; determining the transfer task parameters of the IT device according to the energy consumption optimization strategy and the target controller of the IT device; and migrating the corresponding task to the associated IT device according to the transfer task parameters;

[0195] When the target energy-consuming equipment includes power supply and distribution equipment, the active filter is triggered to be put into operation and the transformer operation group is switched according to the energy consumption optimization strategy and the harmonic content of the power supply and distribution equipment.

[0196] It can be seen that the implementation of this optional embodiment can determine at least one target energy-consuming device and a target controller for each target energy-consuming device in the communication room based on the energy consumption optimization strategy, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy-consuming equipment in the communication room, thereby realizing multi-objective collaborative optimization, and constructing a complete technical chain of "working condition division, equipment classification, factor screening, energy consumption calculation, strategy generation, and closed-loop control", so as to improve the flexibility and accuracy of energy consumption analysis in the communication room at the full-link level.

[0197] In an optional embodiment, if Figure 4 As shown, the above-mentioned acquisition module 301 is also used to collect the actual energy consumption value of the communication room;

[0198] Optional, such as Figure 4 As shown, the device also includes:

[0199] An analysis module 307, used for performing residual analysis between the actual energy consumption value and the real-time energy consumption value of the first energy consumption calculation algorithm;

[0200] The adjustment module 308 is used to fine-tune the parameters in the second energy consumption calculation algorithm of the associated room of the communication room based on the transfer learning technology if the mean absolute percentage error is greater than the preset error threshold, combined with the first energy consumption calculation algorithm of the communication room.

[0201] It can be seen that the implementation of the embodiments of the present invention can further improve the robustness and stability of the energy consumption analysis of the communication room by adding model maintenance mechanisms such as residual analysis, transfer learning, and A / B testing. According to the unique needs of the communication room (such as PUE optimization and harmonic control), a dedicated computing model and control logic are designed, and the electrical characteristics analysis (harmonics) and IT resource scheduling are integrated, which is conducive to solving the problem of cross-domain energy consumption collaborative optimization.

[0202] Embodiment 4

[0203] See also Figure 5 , Figure 5 It is a structural diagram of another intelligent energy consumption analysis device applied to a communication room disclosed in an embodiment of the present invention. The intelligent energy consumption analysis device applied to a communication room can be applied to a communication room, and can also be applied to intelligent devices related to the communication room, and the intelligent devices include but are not limited to one or more of energy consumption devices, energy storage devices, cloud devices, edge computing devices, relay devices, base station devices, urban management devices, and intelligent network devices, which are not limited in the embodiment of the present invention. Figure 5As shown, the energy consumption intelligent analysis device applied to the communication room may include:

[0204] The memory 401 stores executable program codes.

[0205] A processor 402 is coupled to the memory 401 .

[0206] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the intelligent energy consumption analysis method applied to the communication room described in the first embodiment of the present invention or the second embodiment of the present invention.

[0207] Embodiment 5

[0208] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the intelligent energy consumption analysis method applied to a communication room described in Embodiment 1 or Embodiment 2 of the present invention.

[0209] Embodiment 6

[0210] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the intelligent energy consumption analysis method applied to a communication room described in Embodiment 1 or Embodiment 2.

[0211] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0212] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0213] Finally, it should be noted that the intelligent energy consumption analysis method and device for communication rooms disclosed in the embodiment of the present invention only discloses the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent energy consumption analysis method applied to a communication room, characterized in that: The method comprises: Collecting operating parameters and equipment type parameters of each energy-consuming device in the communication room, and at least one multi-dimensional energy consumption influencing factor of the communication room, wherein the multi-dimensional energy consumption influencing factor is used to represent factors influencing the energy consumption level of the energy-consuming device in the communication room; For each of the energy-consuming devices, according to the operating parameters and the device type parameters of the energy-consuming device, a first energy consumption calculation algorithm of the energy-consuming device is matched; according to the first energy consumption calculation algorithm, all the multi-dimensional energy consumption influencing factors are dynamically screened; the screened target energy consumption influencing factors are input into the corresponding first energy consumption calculation algorithm, and the real-time energy consumption value of the energy-consuming device is output; Generate a total energy consumption trajectory parameter of the communication room according to the real-time energy consumption values ​​of all the energy-consuming devices; Based on the total energy consumption trajectory parameters and a preset energy consumption efficiency threshold of the communication room, an energy consumption optimization strategy of the communication room is generated; Based on the energy consumption optimization strategy, at least one target energy consuming device in the communication room and a target controller of each target energy consuming device are determined to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room.

2. The intelligent energy consumption analysis method applied to a communication room according to claim 1 is characterized in that: The energy-consuming equipment includes power supply and distribution equipment, temperature control equipment, IT equipment and other equipment. For each of the energy-consuming equipment; When the energy consumption device is the power supply and distribution device, the first energy consumption calculation algorithm is: Among them, P loss It is used to represent the real-time energy consumption value of the power supply and distribution equipment, A1 is used to represent the weight corresponding to the target energy consumption influencing factor, k1 and k2 are used to represent the equipment characteristic coefficient, I rms It is used to indicate the harmonic component of current, THD is used to indicate the harmonic distortion rate of current, and cosφ is used to indicate the power factor; When the energy consumption device is the temperature control device, the first energy consumption calculation algorithm is: P cool =A2[α*ΔT*f comp +β*(T set -T return )] Among them, P cool It is used to represent the real-time energy consumption value of the temperature control device, A2 is used to represent the weight corresponding to the target energy consumption influencing factor, ΔT is used to represent the indoor and outdoor temperature difference, f comp Used to indicate the compressor frequency, T set Used to indicate the set temperature, T return It is used to represent the return air temperature, and α and β are used to represent the preset weights of the temperature control device; When the energy consumption device is the IT device, the first energy consumption calculation algorithm is: P IT =A3[a1*u CPU +b1*u GPU +c1*u RAM +d1] Among them, P IT A3 is used to represent the real-time energy consumption value of the IT equipment, and u is used to represent the weight corresponding to the target energy consumption influencing factor. CPU Used to indicate CPU utilization, u GPU Used to indicate GPU utilization, u RAM It is used to indicate the RAM usage, and other characters are the corresponding weights and biases; When the energy-consuming device is the other device, the first energy consumption calculation algorithm is the product method of the operating power and the operating time of the energy-consuming device; Among them, different energy-consuming devices have different corresponding weights of the target energy consumption influencing factors.

3. The intelligent energy consumption analysis method applied to a communication room according to claim 1 is characterized in that: The step of dynamically screening all the multi-dimensional energy consumption influencing factors according to the first energy consumption calculation algorithm includes: Obtain the historical energy consumption value trajectory parameters of the energy consuming device; For each of the multi-dimensional energy consumption influencing factors, obtain the current attribute parameter of the multi-dimensional energy consumption influencing factor; calculate the first correlation value between the current attribute parameter and the historical energy consumption value trajectory parameter according to the Pearson correlation coefficient; calculate the second correlation value between the multi-dimensional energy consumption influencing factor and the energy consuming device according to the first correlation value and the historical reference distance value of the historical energy consumption value trajectory parameter, wherein the historical reference distance value is used to indicate the distance degree of the historical energy consumption value trajectory parameter compared to the current moment; Based on the random forest feature importance ranking and all the second correlation values, all the multi-dimensional energy consumption influencing factors are dynamically screened.

4. The intelligent energy consumption analysis method applied to a communication room according to any one of claims 1 to 3, characterized in that: The generating of the energy consumption optimization strategy of the communication room based on the total energy consumption trajectory parameter and the preset room energy consumption efficiency threshold comprises: Determine a multi-dimensional target optimization function according to the total energy consumption trajectory parameter, wherein the multi-dimensional target optimization function includes an energy consumption efficiency optimization function, a device peak power consumption control function, and a device start-stop control function; Calculate the preliminary optimization parameter combination of the multi-dimensional objective optimization function in the communication room according to the preset genetic algorithm; According to the acquired historical operating parameters of the communication room, setting a priority value of each function in the multi-dimensional objective optimization function; According to all the priority values, the preliminary optimization parameter combination is adjusted to generate an energy consumption optimization strategy for the communication room.

5. The intelligent energy consumption analysis method applied to a communication room according to claim 4 is characterized in that: The step of determining at least one target energy consuming device and a target controller of each target energy consuming device in the communication room based on the energy consumption optimization strategy, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room, includes: Based on the energy consumption optimization strategy, determining at least one target energy consuming device in the communication room and a target controller for each of the target energy consuming devices; When the target energy consumption device includes a temperature control device, determining the energy consumption optimization target parameter of the temperature control device according to the energy consumption optimization strategy; calculating the parameter distance value between the real-time energy consumption value of the temperature control device and the energy consumption optimization target parameter; determining at least one target component in the temperature control device according to a preset control algorithm, the parameter distance value and the target controller of the temperature control device, so as to adjust the operating parameters of the target component; When the target energy-consuming device includes an IT device, determining an associated IT device of the IT device, wherein a task processing confidence between the associated IT device and the IT device is greater than or equal to a preset threshold, and the task processing confidence is positively correlated with device attribute parameters between the IT device and the associated IT device, and the device attribute parameters include at least one of a device attribution parameter and an execution task type parameter; determining a transfer task parameter of the IT device according to the energy consumption optimization strategy and the target controller of the IT device; and migrating the corresponding task to the associated IT device according to the transfer task parameter; When the target energy-consuming equipment includes power supply and distribution equipment, the active filter is triggered to be put into operation and the transformer operation group is switched according to the energy consumption optimization strategy and the harmonic content of the power supply and distribution equipment.

6. The intelligent energy consumption analysis method applied to a communication room according to any one of claims 1 to 3 and 5, characterized in that: The method further comprises: Collecting actual energy consumption values ​​of the communication room; A residual analysis is performed on the actual energy consumption value and the real-time energy consumption value of the first energy consumption calculation algorithm. If the mean absolute percentage error is greater than a preset error threshold, based on the transfer learning technology, the parameters in the second energy consumption calculation algorithm of the associated room of the communication room are used as initial values ​​and fine-tuned in combination with the first energy consumption calculation algorithm of the communication room.

7. An intelligent energy consumption analysis device used in a communication room, characterized in that: The device comprises: A collection module, used to collect operating parameters and equipment type parameters of each energy-consuming device in the communication room, and at least one multi-dimensional energy consumption influencing factor of the communication room, wherein the multi-dimensional energy consumption influencing factor is used to represent factors affecting the energy consumption level of the energy-consuming device in the communication room; A matching module, configured to match a first energy consumption calculation algorithm of each energy consuming device according to the operating condition parameter and the device type parameter of the energy consuming device; A screening module, used for dynamically screening all the multi-dimensional energy consumption influencing factors according to the first energy consumption calculation algorithm; A calculation module, used for inputting the screened target energy consumption influencing factor into the corresponding first energy consumption calculation algorithm, and outputting the real-time energy consumption value of the energy consuming device; A generating module, used for generating a total energy consumption trajectory parameter of the communication room according to the real-time energy consumption values ​​of all the energy consuming devices; The generating module is further used to generate an energy consumption optimization strategy for the communication room based on the total energy consumption trajectory parameter and a preset room energy consumption efficiency threshold; A control module is used to determine at least one target energy consuming device and a target controller of each target energy consuming device in the communication room based on the energy consumption optimization strategy, so as to control each target controller and dynamically adjust the operating parameters of the corresponding energy consuming device in the communication room.

8. The intelligent energy consumption analysis device for communication room according to claim 7 is characterized in that: The energy-consuming equipment includes power supply and distribution equipment, temperature control equipment, IT equipment and other equipment. For each of the energy-consuming equipment; When the energy consumption device is the power supply and distribution device, the first energy consumption calculation algorithm is: Among them, P loss It is used to represent the real-time energy consumption value of the power supply and distribution equipment, A1 is used to represent the weight corresponding to the target energy consumption influencing factor, k1 and k2 are used to represent the equipment characteristic coefficient, I rms It is used to indicate the harmonic component of current, THD is used to indicate the harmonic distortion rate of current, and cosφ is used to indicate the power factor; When the energy consumption device is the temperature control device, the first energy consumption calculation algorithm is: P cool =A2[α*ΔT*f comp +β*(T set -T return )] Among them, P cool It is used to represent the real-time energy consumption value of the temperature control device, A2 is used to represent the weight corresponding to the target energy consumption influencing factor, ΔT is used to represent the indoor and outdoor temperature difference, f comp Used to indicate the compressor frequency, T set Used to indicate the set temperature, T return It is used to represent the return air temperature, and α and β are used to represent the preset weights of the temperature control device; When the energy consumption device is the IT device, the first energy consumption calculation algorithm is: P IT =A3[a1*u CPU +b1*u GPU +c1*u RAM +d1] Among them, P IT A3 is used to represent the real-time energy consumption value of the IT equipment, and u is used to represent the weight corresponding to the target energy consumption influencing factor. CPU Used to indicate CPU utilization, u GPU Used to indicate GPU utilization, u RAM It is used to indicate the RAM usage, and other characters are the corresponding weights and biases; When the energy-consuming device is the other device, the first energy consumption calculation algorithm is the product method of the operating power and the operating time of the energy-consuming device; Among them, different energy-consuming devices have different corresponding weights of the target energy consumption influencing factors.

9. An intelligent energy consumption analysis device used in a communication room, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent energy consumption analysis method applied to a communication room as described in any one of claims 1-6.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the intelligent energy consumption analysis method applied to a communication room as described in any one of claims 1-6.

Images