Wireless energy consumption management method based on cloud platform

Abstract

The invention discloses a wireless energy consumption management method based on a cloud platform. The method comprises the following steps that S1, real-time energy consumption data of all energy consumption devices are collected through wireless signal transmission modules connected to the energy consumption devices; s2, transmitting the data from the energy consumption equipment to a cloud platform through an encrypted wireless network, and processing the received energy consumption data by the cloud platform; s3, adjusting the weight of the equipment in energy consumption management according to the predicted service life and the current state of the equipment; s4, constructing an energy consumption model to simulate and predict the energy consumption condition of the equipment, and analyzing energy consumption data based on the energy consumption model; and S5, according to the distribution strategy, a control instruction is dynamically generated. The wireless energy consumption management method is safe, real-time, intelligent and flexible, not only can effectively manage and optimize energy consumption, but also can adapt to constantly changing environments and requirements, and has wide application prospects and important practical value.

Description

Technical Field

[0001] The present invention belongs to the field of energy consumption management, and more specifically, particularly relates to a wireless energy consumption management method based on a cloud platform. Background Art

[0002] With the continuous development of Internet of Things (IoT) technology, more and more energy-consuming devices are connected to the network, realizing real-time monitoring and management. However, the existing technology has the following shortcomings:

[0003] Data security issues: In existing wireless energy management systems, security during data transmission is a major issue. Since energy consumption data contains sensitive information, such as device operating status and energy consumption patterns, it is crucial to ensure that the data is not intercepted or tampered with during transmission;

[0004] Lack of real-time performance: The energy management system needs to be able to monitor and adjust the energy consumption of the equipment in real time. However, existing wireless energy management systems often have latency issues and cannot collect and process energy consumption data in a timely manner, thus affecting the accuracy and efficiency of energy distribution.

[0005] Limited data processing capacity: With the development of IoT technology, the number of devices connected to the network continues to increase, and the amount of energy consumption data generated is also increasing. Existing wireless energy consumption management systems often show insufficient processing capacity when processing large amounts of data and are unable to effectively analyze and predict energy consumption trends.

[0006] Lack of intelligent optimization: Many existing wireless energy management systems lack intelligent optimization algorithms and cannot automatically adjust energy allocation strategies based on real-time data. This leads to inefficient energy utilization and inability to achieve optimal energy management.

[0007] Device compatibility issues: Different energy-consuming devices may use different communication protocols and standards. Existing wireless energy management systems lack compatibility, making it difficult to achieve seamless connection and collaborative work between different devices.

[0008] Inaccurate energy consumption model: Building an accurate energy consumption model is crucial for predicting and optimizing energy consumption. However, the energy consumption models used by many existing wireless energy consumption management systems are overly simplified and cannot accurately reflect the actual energy consumption of the device, resulting in inaccurate prediction results.

[0009] Lack of flexibility and scalability: Existing wireless energy management systems often lack flexibility and scalability, and are difficult to adapt to changing energy needs and device types. When new devices or technologies emerge, existing systems may need to be modified or replaced on a large scale;

[0010] Based on the above, we propose a wireless energy consumption management method based on cloud platform to solve the above problems. Summary of the invention

[0011] The purpose of the present invention is to solve the shortcomings of the prior art and propose a wireless energy consumption management method based on a cloud platform. This method is a safe, real-time, intelligent and flexible wireless energy consumption management method that can not only effectively manage and optimize energy consumption, but also adapt to the ever-changing environment and needs. It has broad application prospects and important practical value.

[0012] To achieve the above object, the present invention provides the following technical solutions:

[0013] The wireless energy consumption management method based on the cloud platform includes the following steps:

[0014] S1, collecting real-time energy consumption data of each energy consuming device through a wireless signal transmission module connected to each energy consuming device;

[0015] S2, transmitting data from the energy consumption device to the cloud platform via an encrypted wireless network, and the cloud platform processes the received energy consumption data;

[0016] S3, applying a weighted algorithm to adjust the weight of the equipment in energy consumption management according to its expected life and current status;

[0017] S4. Build an energy consumption model to simulate and predict the energy consumption of equipment, and based on the energy consumption model, analyze the energy consumption data and generate a weighted allocation strategy considering the equipment life;

[0018] S5. Dynamically generate control instructions according to the allocation strategy.

[0019] Preferably, in step S1, the cloud platform assigns a unique identifier to each group of wireless signal transmission modules and performs corresponding registration on the device. The real-time energy consumption data of each energy consuming device is collected specifically as follows:

[0020] S11, the wireless signal transmission module continuously monitors the operating status and energy consumption data of energy consuming equipment;

[0021] S12, according to the preset time interval or event triggering condition, the wireless signal transmission module automatically collects the energy consumption data of the device;

[0022] S13, packaging the collected energy consumption data in a certain format for easy transmission and analysis;

[0023] S14, transmitting the packaged energy consumption data to the cloud platform via an encrypted wireless network, during which the integrity and security of the data are ensured;

[0024] S15. After receiving the data from the wireless signal transmission module, the cloud platform performs data verification and decryption to ensure the validity and accuracy of the data.

[0025] Preferably, the cloud platform in step S2 processes the received energy consumption data, specifically:

[0026] S21. Each energy consumption device collects real-time energy consumption data through a wireless signal transmission module, and transmits the data to the cloud platform through an encrypted wireless network;

[0027] S22. After receiving the encrypted data, the cloud platform first performs a decryption operation on it. The decrypted data needs to be verified to ensure its integrity and accuracy.

[0028] S23. The cloud platform will clean the data to remove invalid or erroneous information, including checking the data format, unit, and whether there are outliers;

[0029] S24, the cloud platform converts the data to convert data in different units into a unified standard unit;

[0030] S25. Storing the converted data in the application database of the cloud platform.

[0031] Preferably, step S3 specifically comprises:

[0032] S31. Relevant information of each device, including the expected lifespan, current service life, operating status and historical energy consumption data of the device;

[0033] S32. Determine a weight factor according to the estimated life span and current status of the device. A device with a longer estimated life span and a good current status is assigned a higher weight factor. A device with a shorter estimated life span or a poor current status is assigned a lower weight factor.

[0034] S33. Use a weighted algorithm to calculate the weight value of each device. The weight value calculation formula is:

[0035] ;

[0036] Where W i represents the weight value of the i-th device, L i Indicates the expected life of the device, S i Indicates the current state of the device, f is about L i and S i Function of

[0037] S34, normalizing the calculated weight values, and the sum of the normalized weight values ​​is 1;

[0038] S35. Apply the normalized weight value to energy consumption management.

[0039] Preferably, the expression for the normalization process in step S34 is:

[0040] ;

[0041] In the formula, represents the normalized weight value, n represents the total number of devices, W i Represents the weight value of the i-th device, W j Represents the weight value of the jth device;

[0042] The main purpose of normalization is to convert values ​​in different units to the same standard scale. In the energy management scenario, normalization ensures that the weight values ​​of different devices are fair and consistent in relative proportion;

[0043] Among them, using W i and W j The reason for this is to ensure that the sum of all weights is 1, so that the weights remain consistent and comparable in relative proportion.

[0044] Preferably, the specific process of constructing an energy consumption model in step S4 to simulate and predict the energy consumption of the equipment is as follows:

[0045] S41. Design a network with multiple GRU layers, each containing a certain number of neurons;

[0046] S42, taking the expected life span and current state of the equipment as input features;

[0047] S43, setting a fully connected layer as an output layer for predicting future energy consumption;

[0048] S44, compiling the energy consumption model to measure the difference between the predicted value and the actual value and updating the energy consumption model weight;

[0049] S45, dividing the data set into a training set and a validation set, adjusting the energy consumption model parameters through a back propagation algorithm according to the training set data, evaluating the energy consumption model performance on the validation set, and adjusting the hyperparameters or the energy consumption model structure as needed;

[0050] The energy consumption model expression is:

[0051] ;

[0052] in: is the predicted energy consumption of the ith device at time t, f RNN is the model, with parameters θ, L i is the expected life of the equipment, S iis the current state of the device, X i,t It is the historical energy consumption data sequence of the equipment up to time t.

[0053] Preferably, in step S4, based on the energy consumption model, the energy consumption data is analyzed, and the allocation strategy is generated by weighting the equipment life. Specifically, the strategy is:

[0054] Use the trained energy consumption model to predict the energy consumption of each device in the future, and analyze the prediction accuracy and generalization ability of the energy consumption model;

[0055] Calculate weights based on the estimated lifespan and current status of the equipment, and formulate energy allocation strategies based on the predicted energy consumption and calculated weights;

[0056] Deploy the trained energy consumption model to the actual environment, monitor the energy consumption of the equipment in real time, and continuously adjust and optimize the energy consumption model according to the actual operation results to adapt to changes in equipment energy consumption.

[0057] Preferably, step S5 is specifically:

[0058] S51. Based on the energy allocation strategy, formulate specific control logic and generate corresponding control instructions for each device;

[0059] S52, sending the control instruction to the corresponding device through the wireless signal transmission module, and the device performs the corresponding control operation after receiving the instruction;

[0060] S53, continuously monitor the operating status and energy consumption of the equipment, and collect feedback information after the equipment executes the control instructions, including actual energy consumption and operating efficiency;

[0061] S54. Evaluate the effect of the control instruction based on the feedback information, and make necessary adjustments and optimizations to the energy consumption model and energy allocation strategy based on the evaluation results.

[0062] Preferably, the wireless signal transmission module includes:

[0063] Antennas, which send and receive radio waves;

[0064] RF transceiver, which converts baseband signals into high-frequency signals for transmission, or extracts baseband signals from received high-frequency signals;

[0065] Filters are used to remove noise and other unwanted frequency components from the signal to ensure signal clarity;

[0066] processors, which perform various data processing tasks, including signal encoding, decoding, encryption, and decryption;

[0067] Memory, which stores program code and data and supports processor operation;

[0068] Digital-to-analog conversion circuit, which converts between digital signals and analog signals to meet different transmission requirements;

[0069] The power management chip provides stable voltage and current for the module to ensure the normal operation of each component.

[0070] Technical effects and advantages of the present invention: Compared with the prior art, the wireless energy consumption management method based on the cloud platform provided by the present invention has the following advantages:

[0071] First, data is transmitted via an encrypted wireless network, ensuring the security and integrity of energy consumption data during transmission. The cloud platform verifies and decrypts the data after receiving it, further improving data security. The wireless signal transmission module can continuously monitor the operating status and energy consumption data of energy-consuming equipment, and automatically collect energy consumption data according to preset time intervals or event trigger conditions, ensuring the real-time nature of the data.

[0072] Secondly, the cloud platform processes the received energy consumption data, including decryption, verification, cleaning, conversion and storage steps, to ensure the validity and accuracy of the data; at the same time, the cloud platform has strong data processing capabilities and can handle a large amount of energy consumption data; it applies weighted algorithms to adjust the weight of the equipment in energy consumption management according to its expected life and current status, builds an energy consumption model to simulate and predict the energy consumption of the equipment, and generates allocation strategies based on the analysis of energy consumption data based on the energy consumption model; these intelligent operations improve energy utilization efficiency;

[0073] Finally, control instructions are dynamically generated according to the allocation strategy and sent to the corresponding devices through the wireless signal transmission module. This flexibility enables the method to adjust the energy allocation strategy according to actual conditions and optimize energy use. Due to the high degree of intelligence and automation of the method, the need for human intervention is reduced, thereby reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a flow chart of the wireless energy consumption management method based on the cloud platform of the present invention;

[0075] Figure 2 A flowchart of collecting real-time energy consumption data of each energy consuming device in an embodiment of the present invention;

[0076] Figure 3 This is a flow chart of processing received energy consumption data by a cloud platform in an embodiment of the present invention;

[0077] Figure 4 This is a flow chart of adjusting the weight of the device in energy consumption management according to the expected life span and current status of the device in step S3 in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0079] The present invention provides a wireless energy consumption management method based on a cloud platform. The method uses cloud computing to achieve energy management. By uploading energy consumption data to the cloud for processing and analysis, remote monitoring and management of energy-consuming equipment can be achieved. At the same time, by using big data and artificial intelligence technology, energy consumption data can be deeply mined and analyzed, thereby achieving accurate prediction and optimal control of energy consumption conditions. This wireless energy consumption management method based on a cloud platform has the following advantages: first, it can achieve centralized management and control of a large number of energy-consuming equipment, thereby improving management efficiency; second, through big data analysis technology, the laws and trends of energy consumption data can be discovered, providing a basis for formulating reasonable energy allocation strategies; finally, by using artificial intelligence technology, accurate prediction and dynamic adjustment of energy consumption conditions can be achieved, further improving energy utilization efficiency.

[0080] like Figure 1 As shown, the method comprises the following steps:

[0081] S1, collecting real-time energy consumption data of each energy consuming device through a wireless signal transmission module connected to each energy consuming device;

[0082] like Figure 2 In step S1, the cloud platform assigns a unique identifier to each group of wireless signal transmission modules and performs corresponding registration on the device. The real-time energy consumption data of each energy-consuming device is collected as follows:

[0083] S11, the wireless signal transmission module continuously monitors the operating status and energy consumption data of energy consuming equipment;

[0084] S12, according to the preset time interval or event triggering condition, the wireless signal transmission module automatically collects the energy consumption data of the device;

[0085] Specifically, the time interval or event triggering conditions include:

[0086] Threshold Exceeded: When the energy consumption data of energy-consuming equipment exceeds the preset threshold, the wireless signal transmission module will automatically collect and upload the data; for example, if the energy consumption of an air conditioner suddenly increases and exceeds the set normal range, the system will trigger data collection;

[0087] Equipment fault detection: if the wireless signal transmission module detects that the equipment is faulty or in abnormal operating conditions such as overtemperature or overcurrent, it will immediately collect relevant energy consumption data and report it to the cloud platform;

[0088] In addition to event-based triggering, you can also set up scheduled tasks to regularly collect energy consumption data. Specifically, at 2 a.m. every day, the system will automatically collect data from all devices regardless of whether the energy consumption is abnormal.

[0089] User operation response: When a user manually requests to view the real-time energy consumption data of a device through a mobile application or web interface, the wireless signal transmission module responds to the request and collects the data immediately;

[0090] Changes in environmental parameters. In some cases, the collection of energy consumption data may be related to changes in environmental parameters;

[0091] Mode switching: For devices with multiple working modes, including energy-saving mode, normal mode, and high-efficiency mode, when the mode is switched, the wireless signal transmission module can automatically collect and record the energy consumption data before and after the switch;

[0092] When the maintenance cycle arrives, for equipment that requires regular maintenance, when the preset maintenance cycle is reached, the wireless signal transmission module can automatically collect energy consumption data to facilitate analysis of equipment performance degradation;

[0093] Policy or regulatory requirements: In some regions, there may be policy or regulatory requirements regarding energy consumption and environmental protection; in this case, the wireless signal transmission module can automatically collect energy consumption data according to these requirements to meet the needs of compliance inspection;

[0094] Predictive maintenance, by analyzing historical energy consumption data and machine learning algorithms, the system can predict possible equipment failures or performance degradation; in this case, the wireless signal transmission module can collect data in advance when potential problems are predicted to enable preventive maintenance;

[0095] Energy demand response: During peak hours of electricity demand, in order to balance the grid load, it may be necessary to limit or adjust the energy consumption of certain devices; in this case, the wireless signal transmission module can automatically collect energy consumption data based on the grid’s demand response signal in order to implement corresponding control strategies;

[0096] S13, packaging the collected energy consumption data in a certain format for easy transmission and analysis;

[0097] S14, transmitting the packaged energy consumption data to the cloud platform via an encrypted wireless network, during which the integrity and security of the data are ensured;

[0098] S15. After receiving the data from the wireless signal transmission module, the cloud platform verifies and decrypts the data to ensure the validity and accuracy of the data;

[0099] Furthermore, the wireless signal transmission module includes:

[0100] Antennas, which send and receive radio waves;

[0101] RF transceiver, which converts baseband signals into high-frequency signals for transmission, or extracts baseband signals from received high-frequency signals;

[0102] Filters are used to remove noise and other unwanted frequency components from the signal to ensure signal clarity;

[0103] processors, which perform various data processing tasks, including signal encoding, decoding, encryption, and decryption;

[0104] Memory, which stores program code and data and supports processor operation;

[0105] Digital-to-analog conversion circuit, which converts between digital signals and analog signals to meet different transmission requirements;

[0106] The power management chip provides stable voltage and current for the module to ensure the normal operation of each component;

[0107] S2, transmitting data from the energy consumption device to the cloud platform via an encrypted wireless network, and the cloud platform processes the received energy consumption data;

[0108] like Figure 3 , the cloud platform described in step S2 processes the received energy consumption data, specifically:

[0109] S21. Each energy consumption device collects real-time energy consumption data through a wireless signal transmission module, and transmits the data to the cloud platform through an encrypted wireless network;

[0110] S22. After receiving the encrypted data, the cloud platform first performs a decryption operation on it. The decrypted data needs to be verified to ensure its integrity and accuracy.

[0111] S23. The cloud platform will clean the data to remove invalid or erroneous information, including checking the data format, unit, and whether there are outliers;

[0112] S24, the cloud platform converts the data to convert data in different units into a unified standard unit;

[0113] S25, storing the converted data in the application database of the cloud platform;

[0114] S3, applying a weighted algorithm to adjust the weight of the equipment in energy consumption management according to its expected life and current status;

[0115] like Figure 4 , step S3 is specifically as follows:

[0116] S31. Relevant information of each device, including the expected lifespan, current service life, operating status and historical energy consumption data of the device;

[0117] S32. Determine a weight factor according to the estimated life span and current status of the device. A device with a longer estimated life span and a good current status is assigned a higher weight factor. A device with a shorter estimated life span or a poor current status is assigned a lower weight factor.

[0118] S33. Use a weighted algorithm to calculate the weight value of each device. The weight value calculation formula is:

[0119] ;

[0120] Where W i represents the weight value of the i-th device, L i Indicates the expected life of the device, S i Indicates the current state of the device, f is about L i and S i Function of

[0121] S34, normalize the calculated weight values, and the sum of the normalized weight values ​​is 1; wherein the expression of the normalization process in step S34 is:

[0122] ;

[0123] In the formula, represents the normalized weight value, n represents the total number of devices, W i Represents the weight value of the i-th device, W j Represents the weight value of the jth device;

[0124] The main purpose of normalization is to convert values ​​in different units to the same standard scale. In the energy management scenario, normalization ensures that the weight values ​​of different devices are fair and consistent in relative proportion;

[0125] Among them, using W i and W j The reason for this is to ensure that the sum of all weight values ​​is 1, so that the weight values ​​remain consistent and comparable in relative proportion;

[0126] S35, applying the normalized weight value to energy consumption management;

[0127] For example, for a small factory consisting of three devices, the expected lifespan, current service life, operating status, and historical energy consumption data of each device are as follows:

[0128] Equipment A: Expected life: 5 years; Current service life: 2 years; Operating status: Good;

[0129] Historical energy consumption data: [10, 12, 11, 13, 10.5] kWh / month;

[0130] Equipment B: Expected life: 3 years; Current service life: 1 year; Operating status: General;

[0131] Historical energy consumption data: [8,9,7,9.5,8.5] kWh / month;

[0132] Equipment C: Expected life: 4 years; Current service life: 3 years; Operating status: poor;

[0133] Historical energy consumption data: [15, 16, 14, 15.5, 14.5] kWh / month Based on the above information, the weight value of each device is calculated and normalized according to steps S31 to S34.

[0134] Collect information about the device.

[0135] Determine the weight factor. Assume that a simplified weight factor function f(L i ,S i )=L i ×S i , where Si is a coefficient representing the operating status of the equipment (1 for good, 0.75 for average, and 0.5 for poor).

[0136] Device A: f(5,1)=5×1=5;

[0137] Device B: f(3,0.75)=3×0.75=2.25;

[0138] Device C: f(4,0.5)=4×0.5=2;

[0139] Calculate the weight value.

[0140] Device A: W i =5;

[0141] Device B: W j =2.25 (for all j not equal to i);

[0142] Device C: W k = 2 (for all k not equal to i and j);

[0143] Perform normalization.

[0144] The sum of all weight values ​​= 5 + 2.25 + 2 = 9.25;

[0145] Normalized weight values:

[0146] Device A: =5 / 9.25≈0.54;

[0147] Device B: =2.25 / 9.25≈0.24;

[0148] Device C: =2 / 9.25≈0.22Through the above steps, we get the normalized weight values, which can be used for subsequent energy consumption management and optimization processes;

[0149] S4, construct an energy consumption model to simulate and predict the energy consumption of the equipment, and based on the energy consumption model, analyze the energy consumption data, and generate a weighted allocation strategy considering the equipment life; the specific process of constructing the energy consumption model to simulate and predict the energy consumption of the equipment in step S4 is as follows:

[0150] S41. Design a network with multiple GRU layers, each containing a certain number of neurons;

[0151] S42, taking the expected life span and current state of the equipment as input features;

[0152] S43, setting a fully connected layer as an output layer for predicting future energy consumption;

[0153] S44, compiling the energy consumption model to measure the difference between the predicted value and the actual value and updating the energy consumption model weight;

[0154] S45, dividing the data set into a training set and a validation set, adjusting the energy consumption model parameters through a back propagation algorithm according to the training set data, evaluating the energy consumption model performance on the validation set, and adjusting the hyperparameters or the energy consumption model structure as needed;

[0155] The energy consumption model expression is:

[0156] ;

[0157] in: is the predicted energy consumption of the ith device at time t, f RNN is the model, with parameters θ, L i is the expected life of the equipment, S i is the current state of the device, X i,t is the historical energy consumption data sequence of the equipment up to time t;

[0158] Secondly, in step S4, based on the energy consumption model, the energy consumption data is analyzed, and the allocation strategy is generated by weighting the equipment life. Specifically, the strategy is:

[0159] Use the trained energy consumption model to predict the energy consumption of each device in the future, and analyze the prediction accuracy and generalization ability of the energy consumption model;

[0160] Calculate weights based on the estimated lifespan and current status of the equipment, and formulate energy allocation strategies based on the predicted energy consumption and calculated weights;

[0161] Deploy the trained energy consumption model to the actual environment, monitor the energy consumption of the equipment in real time, and continuously adjust and optimize the energy consumption model according to the actual operation results to adapt to the changes in equipment energy consumption;

[0162] For example, there is a system with three devices, and the estimated lifespan, current status, and historical energy consumption data of each device are as follows:

[0163] Equipment A: Expected life: 5 years; Current status: Good; Historical energy consumption data series: [10, 12, 11, 13,10.5] kWh / month;

[0164] Equipment B: Estimated lifespan: 3 years; Current status: Average; Historical energy consumption data series: [8, 9, 7, 9.5, 8.5] kWh / month;

[0165] Equipment C: Expected life: 4 years; Current status: poor; Historical energy consumption data series: [15, 16, 14, 15.5,14.5] kWh / month;

[0166] Based on the above information, an energy consumption model is constructed and analyzed according to steps S41 to S45:

[0167] Design a network with multiple GRU layers; specifically, a network with two GRU layers, each with 256 neurons;

[0168] The expected life span and current status of the equipment are used as input features. Specifically, for equipment A, the input features can be [5, 1];

[0169] Set a fully connected layer as the output layer to predict future energy consumption. Specifically, set a fully connected layer containing 1 neuron to output the predicted future energy consumption value.

[0170] Compile the energy consumption model, use the training set data to adjust the energy consumption model parameters through the back propagation algorithm, evaluate the performance of the energy consumption model on the validation set, and adjust the hyperparameters or energy consumption model structure as needed;

[0171] The data set is divided into a training set and a validation set. Specifically, the first 80% of the data is used as the training set, and the last 20% of the data is used as the validation set. After training, we get:

[0172] ;

[0173] Among them, E i,t is the predicted energy consumption of the ith device at time t, f RNN is the model, with parameters θ, L i is the expected life of the equipment, S i is the current state of the device, X i,t is the historical energy consumption data sequence of the equipment up to time t. The energy consumption data is analyzed and the allocation strategy is generated according to the method in step S4:

[0174] Use the trained energy consumption model to predict the energy consumption of each device in the future;

[0175] Analyze the prediction accuracy and generalization ability of energy consumption models;

[0176] Calculate weights based on the equipment’s estimated lifespan and current status;

[0177] Combine the predicted energy consumption and the calculated weights to formulate an energy allocation strategy;

[0178] Deploy the trained energy consumption model to the actual environment, monitor the energy consumption of the equipment in real time, and continuously adjust and optimize the energy consumption model based on the actual operation results;

[0179] S5. Dynamically generate control instructions according to the allocation strategy; Step S5 is specifically as follows:

[0180] S51. Based on the energy allocation strategy, formulate specific control logic and generate corresponding control instructions for each device;

[0181] S52, sending the control instruction to the corresponding device through the wireless signal transmission module, and the device performs the corresponding control operation after receiving the instruction;

[0182] S53, continuously monitor the operating status and energy consumption of the equipment, and collect feedback information after the equipment executes the control instructions, including actual energy consumption and operating efficiency;

[0183] S54. Evaluate the effect of the control instruction based on the feedback information, and make necessary adjustments and optimizations to the energy consumption model and energy allocation strategy based on the evaluation results.

[0184] In summary, compared with the prior art, the present invention has the following advantages:

[0185] First, data is transmitted via an encrypted wireless network, ensuring the security and integrity of energy consumption data during transmission. The cloud platform verifies and decrypts the data after receiving it, further improving data security. The wireless signal transmission module can continuously monitor the operating status and energy consumption data of energy-consuming equipment, and automatically collect energy consumption data according to preset time intervals or event trigger conditions, ensuring the real-time nature of the data.

[0186] Secondly, the cloud platform processes the received energy consumption data, including decryption, verification, cleaning, conversion and storage steps, to ensure the validity and accuracy of the data; at the same time, the cloud platform has strong data processing capabilities and can handle a large amount of energy consumption data; it applies weighted algorithms to adjust the weight of the equipment in energy consumption management according to its expected life and current status, builds an energy consumption model to simulate and predict the energy consumption of the equipment, and generates allocation strategies based on the analysis of energy consumption data based on the energy consumption model; these intelligent operations improve energy utilization efficiency;

[0187] Finally, control instructions are dynamically generated according to the allocation strategy and sent to the corresponding devices through the wireless signal transmission module. This flexibility enables the method to adjust the energy allocation strategy according to actual conditions and optimize energy use. Due to the high degree of intelligence and automation of the method, the need for human intervention is reduced, thereby reducing maintenance costs.

[0188] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A wireless energy consumption management method based on a cloud platform, characterized in that: The steps include: S1, collecting real-time energy consumption data of each energy consuming device through a wireless signal transmission module connected to each energy consuming device; S2, transmitting data from the energy consumption device to the cloud platform via an encrypted wireless network, and the cloud platform processes the received energy consumption data; S3, applying a weighted algorithm to adjust the weight of the equipment in energy consumption management according to its expected life and current status; S4. Build an energy consumption model to simulate and predict the energy consumption of equipment, and based on the energy consumption model, analyze the energy consumption data and generate a weighted allocation strategy considering the equipment life; S5. Dynamically generate control instructions according to the allocation strategy.

2. The cloud platform-based wireless energy consumption management method according to claim 1, characterized in that: In step S1, the cloud platform assigns a unique identifier to each group of wireless signal transmission modules and performs corresponding registration on the device. The real-time energy consumption data of each energy consuming device is collected as follows: S11, the wireless signal transmission module continuously monitors the operating status and energy consumption data of energy consuming equipment; S12, according to the preset time interval or event triggering condition, the wireless signal transmission module automatically collects the energy consumption data of the device; S13, packaging the collected energy consumption data in a certain format for easy transmission and analysis; S14, transmitting the packaged energy consumption data to the cloud platform via an encrypted wireless network, during which the integrity and security of the data are ensured; S15. After receiving the data from the wireless signal transmission module, the cloud platform performs data verification and decryption to ensure the validity and accuracy of the data.

3. The cloud platform-based wireless energy consumption management method according to claim 1, characterized in that: The cloud platform described in step S2 processes the received energy consumption data, specifically: S21. Each energy consumption device collects real-time energy consumption data through a wireless signal transmission module, and transmits the data to the cloud platform through an encrypted wireless network; S22. After receiving the encrypted data, the cloud platform first performs a decryption operation on it. The decrypted data needs to be verified to ensure its integrity and accuracy. S23. The cloud platform will clean the data to remove invalid or erroneous information, including checking the data format, unit, and whether there are outliers; S24, the cloud platform converts the data to convert data in different units into a unified standard unit; S25. Storing the converted data in the application database of the cloud platform.

4. The wireless energy consumption management method based on cloud platform according to claim 1, characterized in that: Step S3 is specifically as follows: S31. Relevant information of each device, including the expected life of the device, current service life, operating status and historical energy consumption data; S32. Determine a weight factor according to the estimated life span and current status of the device. A device with a longer estimated life span and a good current status is assigned a higher weight factor. A device with a shorter estimated life span or a poor current status is assigned a lower weight factor. S33. Use a weighted algorithm to calculate the weight value of each device. The calculation formula of the weight value is: ; Where W i represents the weight value of the i-th device, L i Indicates the expected life of the device, S i Indicates the current state of the device, f is about L i and S i Function of S34, normalizing the calculated weight values, and the sum of the normalized weight values ​​is 1; S35. Apply the normalized weight value to energy consumption management.

5. The cloud platform-based wireless energy consumption management method according to claim 4, characterized in that: The expression for the normalization process in step S34 is: ； In the formula, represents the normalized weight value, n represents the total number of devices, W i Represents the weight value of the i-th device, W j Represents the weight value of the jth device; The main purpose of normalization is to convert values ​​in different units to the same standard scale. In the energy management scenario, normalization ensures that the weight values ​​of different devices are fair and consistent in relative proportion; Among them, using W i and W j The reason for this is to ensure that the sum of all weights is 1, thus keeping the weights consistent and comparable in relative proportion.

6. The wireless energy consumption management method based on cloud platform according to claim 1, characterized in that: In step S4, the specific process of building an energy consumption model to simulate and predict the energy consumption of the equipment is as follows: S41. Design a network with multiple GRU layers, each containing a certain number of neurons; S42, taking the expected life span and current state of the equipment as input features; S43, setting a fully connected layer as an output layer for predicting future energy consumption; S44, compiling the energy consumption model to measure the difference between the predicted value and the actual value and updating the energy consumption model weight; S45, dividing the data set into a training set and a validation set, adjusting the energy consumption model parameters through a back propagation algorithm according to the training set data, evaluating the energy consumption model performance on the validation set, and adjusting the hyperparameters or the energy consumption model structure as needed; The energy consumption model expression is: ； in: is the predicted energy consumption of the ith device at time t, f RNN is the model, with parameters θ, L i is the expected life of the equipment, S i is the current state of the device, X i,t It is the historical energy consumption data sequence of the equipment up to time t.

7. The cloud platform-based wireless energy consumption management method according to claim 6, characterized in that: In step S4, based on the energy consumption model, the energy consumption data is analyzed and the allocation strategy is generated by weighting the equipment life. Specifically, the strategy is: Use the trained energy consumption model to predict the energy consumption of each device in the future, and analyze the prediction accuracy and generalization ability of the energy consumption model; Calculate weights based on the estimated lifespan and current status of the equipment, and formulate energy allocation strategies based on the predicted energy consumption and calculated weights; Deploy the trained energy consumption model to the actual environment, monitor the energy consumption of the equipment in real time, and continuously adjust and optimize the energy consumption model according to the actual operation results to adapt to changes in equipment energy consumption.

8. The cloud platform-based wireless energy consumption management method according to claim 1, characterized in that: Step S5 is specifically as follows: S51. Based on the energy allocation strategy, formulate specific control logic and generate corresponding control instructions for each device; S52, sending the control instruction to the corresponding device through the wireless signal transmission module, and the device performs the corresponding control operation after receiving the instruction; S53, continuously monitor the operating status and energy consumption of the equipment, and collect feedback information after the equipment executes the control instructions, including actual energy consumption and operating efficiency; S54. Evaluate the effect of the control instruction based on the feedback information, and make necessary adjustments and optimizations to the energy consumption model and energy allocation strategy based on the evaluation results.

9. The cloud platform-based wireless energy consumption management method according to claim 8, characterized in that: The wireless signal transmission module comprises: Antennas, which send and receive radio waves; RF transceiver, which converts baseband signals into high-frequency signals for transmission, or extracts baseband signals from received high-frequency signals; Filters are used to remove noise and other unwanted frequency components from the signal to ensure signal clarity; processors, which perform various data processing tasks, including signal encoding, decoding, encryption, and decryption; Memory, which stores program code and data and supports processor operation; Digital-to-analog conversion circuit, which converts between digital signals and analog signals to meet different transmission requirements; The power management chip provides stable voltage and current for the module to ensure the normal operation of each component.

Images