An Internet of Things remote sensing monitoring system and method based on big data

Abstract

The present invention discloses an Internet of Things remote sensing and monitoring system and method based on big data. The present invention relates to the technical field of Internet of Things communication. The remote sensing and monitoring system includes a sensing layer, a network layer, a data layer, and an application layer. The sensing layer is provided with a data acquisition module. Different types of sensors are provided in the data acquisition module. The data acquisition module obtains the energy losses of different types of sensors, marks the energy losses of different types of sensors as type A, and marks the data collected by different types of sensors as type B. The advantages of the present invention are as follows: The type B data is classified and stored through the network layer and the data layer. The application layer retrieves the classified and stored data, constructs an energy loss database based on type A data and type B data, and then uses the energy loss database to adjust the working states of different sensors, thereby optimizing the energy losses of the sensors, achieving the optimization of energy losses while ensuring the working state of the monitoring system.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things communication, and specifically to an Internet of Things remote sensing and monitoring system and method based on big data. Background Technique

[0002] An Internet of Things system generally includes a large number of Internet of Things nodes, such as terminal device nodes and server nodes. The terminal device nodes are used to collect various data, and the server nodes establish a communication channel with the terminal device nodes to transmit data and perform data analysis and processing;

[0003] However, in the existing Internet of Things remote sensing and monitoring system, since the sensing system needs to collect target data in real time to ensure the accuracy of the sensing and monitoring system, such a method also increases the energy consumption of the sensing system. For this reason, we propose an Internet of Things remote sensing and monitoring system and method based on big data. Summary of the Invention

[0004] The purpose of the present invention is to provide an Internet of Things remote sensing and monitoring system and method based on big data.

[0005] To achieve the above purpose, the present invention provides the following technical solutions: an Internet of Things remote sensing and monitoring system and method based on big data. The remote sensing and monitoring system includes a sensing layer, a network layer, a data layer, and an application layer;

[0006] The sensing layer is provided with a data collection module. Different types of sensors are provided in the data collection module. The data collection module obtains the energy losses of different types of sensors, marks the energy losses of different types of sensors as type A, and marks the data collected by different types of sensors as type B;

[0007] The network layer is provided with a data cleaning module, a transmission monitoring module, and a data encryption module. The data cleaning module is used to clean the type B data. The data encryption module uses the AES algorithm to encrypt the cleaned type B data, and then transmits the encrypted type B data to the data layer. The transmission monitoring module is used for the monitoring of the encrypted type B data and the transmission of the data marked as type A in the sensing layer;

[0008] The data layer is provided with a data extraction module, a local storage module, and a cloud storage module. The cloud storage module establishes multiple types of storage areas according to different types of sensors, transmits the type B data to the cloud storage module, and stores the type B data according to the corresponding storage areas. The local storage module stores the type A data after receiving it. The data extraction module extracts the characteristic data from the type B data;

[0009] The application layer is provided with a data processing module and an energy management module. The data processing module is used to analyze and predict the development status of Class B data, and the energy management module is used to manage Class A data. The data processing module analyzes and predicts Class B data by using digital twin technology;

[0010] The energy management module is provided with an energy loss database, an energy optimization unit and a dynamic adjustment unit. The energy loss database is used to store the historical energy loss data of different types of sensor nodes and Class A data, where the Class A data further includes data related to sensor type, operating frequency and environmental parameters associated with the energy loss data. The energy optimization unit constructs an energy loss model through the energy loss database, and the dynamic adjustment unit adjusts the energy loss of different types of sensors according to the energy loss model;

[0011] The energy optimization unit expresses the energy loss through a formula, and the specific formula is as follows:

[0012] ;

[0013] Among them, represents the energy loss of the th sensor, represents the square term of the operating frequency, reflecting the non-linear energy loss, represents the operating frequency of the th sensor, represents the th sensor's environmental temperature, represents the interaction term of the operating frequency and environmental temperature of the th sensor, reflecting the influence of their combined action on the energy loss, represents the energy loss constant of the th sensor, , and respectively represent the weight coefficients of the operating frequency and environmental temperature obtained by fitting historical data, thereby optimizing the energy loss of different types of sensors;

[0014] The data accuracy of the sensing layer is proportional to the operating frequency , and the following relationship is introduced:

[0015] ;

[0016] Among them, represents the proportionality coefficient, represents a constant, and the energy loss model is brought into the dynamic adjustment unit to generate a sensor frequency optimization strategy through a formula. The specific formula is as follows:

[0017] ;

[0018] Among them, represents the energy loss function of the th sensor, and its expression is:

[0019] ;

[0020] By adjusting the working frequency of the sensors, the total energy loss of all sensors is minimized. Among them, represents the optimization strategy of the working frequency of the th sensor, represents the variable value when the objective function takes the minimum value, and then the unit adjusts the working frequencies of different sensors in real time dynamically;

[0021] The constraint conditions are:

[0022] ;

[0023] Among them, represents the lower threshold of data accuracy, represents the th sensor's data accuracy.

[0024] As a further solution of the present invention: The data processing module analyzes the type B data, obtains the accuracy of different sensors in collecting the type B data, and transmits the type B data and the accuracy data of different sensors to the energy management module, and then the energy management module adjusts the working state data of different sensors according to the accuracy of the type B data.

[0025] As a further solution of the present invention: A prediction model is set in the data processing module. The prediction model retrieves historical type B data, and the prediction model analyzes the future 24-hour prediction data according to the historical trends of different types of type B data. The prediction model adopts a three-level progressive prediction of 4h + 8h + 12h, and each level of prediction is based on the previous level's result:

[0026] Level 1: The 0-4h prediction is a high-precision short-term;

[0027] Level 2: The 4-12h prediction is an 8h extension based on the 4h result;

[0028] Level 3: The 12-24h prediction is a 12h extension based on the 12h result;

[0029] The prediction model obtains the result data of the historical trend of type B data in the future 24h through a formula. The specific formula is as follows:

[0030] ;

[0031] ;

[0032] Among them, represents the result data of the prediction model for 12 hours of Class B data, represents the prediction result data of the prediction model based on the first level, represents the result data of the prediction model directly predicted for 12 hours, represents the result data of the prediction model for 24 hours of Class B data, represents the prediction result data of the prediction model based on the second level, represents the result data of the prediction model directly predicted for 24 hours, and respectively represent the dynamic weight coefficients.

[0033] As a further solution of the present invention: a backup sensing unit is provided in the data acquisition module, and the backup sensing unit is used to temporarily acquire Class B data. An energy loss threshold is set in the energy management module. When the transmission monitoring module monitors that the sensor is abnormal and the energy loss threshold is reached, the data acquisition module switches to the backup sensing unit to acquire Class B data.

[0034] As a further solution of the present invention: a warning unit is provided in the application layer, and the warning unit is used to acquire the data in the data processing module and the energy management module, and perform warning processing when abnormal data appears in the data processing module and the energy management module.

[0035] In addition, the present invention also provides a remote sensing monitoring method based on big data, and the specific steps are as follows:

[0036] S1. Construct multiple different types of sensors to collect the sensing data of the target object, and then mark the data about the sensor itself as Class A data, and mark the data collected by the sensor as Class B data;

[0037] S2. Then the network layer performs cleaning and classified transmission on the Class B data, and then performs classified transmission on the Class B data and the Class A data, and encrypts and stores the Class B data;

[0038] S3. After receiving the Class A data and the Class B data, perform feature extraction on the Class B data, and classify and store the Class A data and the Class B data;

[0039] S4. Build an energy loss database. The database records the historical energy loss data of each sensor node and is associated with different types of sensors, operating frequencies, and environmental parameters, thereby adjusting the energy loss between different types of sensors and optimizing the energy loss of the overall monitoring system.

[0040] Adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] 1. The present invention obtains sensing data through the sensing layer, marks the sensing target data collected by the sensor as type B data, that is, the sensing target data is the data collected by the sensor, and then classifies and stores the type B data using the network layer and the data layer. The application layer retrieves the classified and stored data, constructs an energy loss database based on type A data and type B data, and then adjusts the operating states of different sensors using the energy loss database, thereby optimizing the energy loss of the sensors and achieving the optimization of the energy loss of the monitoring system while ensuring the working state.

[0042] 2. The present invention analyzes type A data and type B data through the energy optimization unit to obtain energy loss data, and adjusts the energy loss of different sensors through the energy loss data, facilitating the monitoring system to adjust the operating states of different sensors in real time.

[0043] 3. The present invention analyzes the operating frequencies of different sensors in real time through the dynamic adjustment unit to optimize the optimal operating state of the sensors, effectively avoiding the problem of data redundancy caused by too high operating frequencies.

[0044] 4. The present invention performs prediction processing on the data in different time periods to obtain type B data in future time periods, enabling the monitoring system to generate corresponding processing plans according to different time periods, facilitating timely adjustment when abnormalities occur in the sensing layer, network layer, data layer, and application layer.

[0045] Other advantages, objectives, and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flowchart of the remote sensing monitoring system in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following further describes the specific embodiments of the present invention with reference to the drawings. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not limit the present invention.

[0048] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0049] Embodiment 1:

[0050] Please refer to the attached Figure 1 , a big data-based Internet of Things remote sensing monitoring system and method of the present invention, the remote sensing monitoring system includes a sensing layer, a network layer, a data layer, and an application layer;

[0051] The sensing layer is provided with a data acquisition module. Different types of sensors are provided in the data acquisition module. The data acquisition module obtains the energy losses of different types of sensors, marks the energy losses of different types of sensors as type A, and marks the data collected by different types of sensors as type B;

[0052] The network layer is provided with a data cleaning module, a transmission monitoring module, and a data encryption module. The data cleaning module is used to clean the type B data. The data encryption module uses the AES algorithm to encrypt the cleaned type B data, and then transmits the encrypted type B data to the data layer. The transmission monitoring module is used for the monitoring of the encrypted type B data and the transmission of the data marked as type A in the sensing layer;

[0053] The data layer is provided with a data extraction module, a local storage module, and a cloud storage module. The cloud storage module establishes multiple types of storage areas according to different types of sensors, transmits the type B data to the cloud storage module, and stores the type B data according to the corresponding storage areas. The local storage module stores the type A data after receiving it. The data extraction module extracts the feature data in the type B data;

[0054] The application layer is provided with a data processing module and an energy management module. The data processing module is used to analyze and predict the development status of the type B data. The energy management module is used to manage the type A data. The data processing module uses digital twin technology to analyze and predict the type B data.

[0055] Specific working process: Construct multiple different types of sensors to collect the sensing data of the target object, then mark the data about the sensor itself as type A data, mark the data collected by the sensor as type B data, then the network layer performs cleaning and classified transmission on the type B data, and then performs classified transmission on the type B data and the type A data, encrypts and stores the type B data, after receiving the type A data and the type B data, extracts the feature data from the type B data, and stores the type A data and the type B data separately, constructs an energy loss database, the database records the historical energy loss data of each sensor node, and associates it with the sensor type, working frequency, and environmental parameters, and then adjusts the energy losses between the sensors, thereby optimizing the energy loss of the overall monitoring system.

[0056] Further, perception data is obtained through the perception layer, and the perception target data collected by the sensor is marked as type B data, that is, the perception target data is the data collected by the sensor. Then, the network layer and the data layer are used to classify and store the type B data. The application layer retrieves the classified and stored data, constructs an energy loss database based on type A data and type B data, and then uses the energy loss database to adjust the working states of different sensors, thereby optimizing the energy loss of the sensors, achieving the optimization of energy loss while ensuring the working state of the monitoring system.

[0057] Embodiment 2:

[0058] Based on Embodiment 1, please refer to the attached Figure 1 As shown, an energy loss database, an energy optimization unit, and a dynamic adjustment unit are provided in the energy management module. The energy loss database is used to store the historical energy loss data of different types of sensor nodes and type A data, where type A data further includes data related to the sensor type, working frequency, and environmental parameters associated with the energy loss data. The energy optimization unit constructs an energy loss model through the energy loss database, and the dynamic adjustment unit adjusts the energy loss of different types of sensors according to the energy loss model. The energy optimization unit expresses the energy loss through a formula, and the specific formula is as follows:

[0059] ;

[0060] Wherein, represents the energy loss of the th sensor, represents the square term of the working frequency, reflecting the non-linear energy loss, represents the working frequency of the th sensor, represents the environmental temperature of the th sensor, represents the interaction term of the working frequency and environmental temperature of the th sensor, reflecting the influence of their combined action on the energy loss, represents the energy loss constant of the th sensor, , and respectively represent the weight coefficients of the working frequency and environmental temperature obtained by fitting historical data, thereby optimizing the energy loss of different types of sensors.

[0061] Specific work process: Sensor data acquisition: The heterogeneous sensor array collects the perception data of the target object in real time, such as temperature, humidity, vibration, light, etc., and synchronously records the working frequency, ambient temperature and sensor type identifier of each sensor node. Environmental parameter monitoring: The real-time environmental parameters (such as temperature, humidity, electromagnetic interference intensity) of the sensor deployment area are obtained through an independent environmental monitoring module to ensure the correlation between the data and the sensor energy consumption. Data cleaning and standardization: Outlier removal: The 3σ principle or box plot method is used to filter out abnormal energy consumption data (such as instantaneous current spikes). Data normalization: Min-Max normalization is performed on the working frequency and ambient temperature to eliminate the influence of dimensions. Missing value filling: Time series interpolation (such as linear interpolation) or the mean value of data from similar sensors is used to fill in the missing values. At the same time, multiple linear regression is used to fit the historical data to obtain the , and data.

[0062] Furthermore, the energy optimization unit analyzes based on Class A data and Class B data to obtain the energy loss data, and adjusts the energy loss of different sensors through the energy loss data, so as to facilitate the monitoring system to adjust the working states of different sensors in real time.

[0063] Embodiment 3:

[0064] Based on Embodiment 2, please refer to the attached Figure 1 As shown, the data accuracy of the perception layer is proportional to the working frequency and the following relationship is introduced:

[0065] ;

[0066] wherein, represents the proportionality coefficient, is a constant, and the energy loss model is brought into the dynamic adjustment unit to generate the sensor frequency optimization strategy through the formula. The specific formula is as follows:

[0067] ;

[0068] wherein, represents the energy loss function of the th sensor, and its expression is:

[0069] ;

[0070] By adjusting the sensor working frequency , the total energy loss of all sensors is minimized, wherein, represents the Optimization strategy for the operating frequencies of sensors Represents the variable values when the objective function takes the minimum value, and then dynamically adjusts the unit to adjust the operating frequencies of different sensors in real time;

[0071] The constraint conditions are:

[0072] ;

[0073] Among them, Represents the lower threshold of data accuracy, Represents the th sensor's data accuracy. The data processing module analyzes the type-B data to obtain the accuracies of different sensors for collecting type-B data, and transmits the type-B data and the accuracy data of different sensors to the energy management module. Then, the energy management module adjusts the operating state data of different sensors according to the accuracy of the type-B data.

[0074] Specific working process: Data collection: Collect historical data, including the operating frequencies of sensors , ambient temperature , energy loss and data accuracy , and use the historical data to fit the , and in the energy loss model, and use the historical data to fit the and in the data accuracy model. Use the optimization algorithm to solve , ensure the minimization of energy loss while meeting the data accuracy constraints, and dynamically adjust the operating frequencies of sensors according to real-time data , ensure that the system is always in an optimal state, and ensure the sensor operating state data when the perception layer obtains target data by setting the lowest target threshold.

[0075] Furthermore, by analyzing the operating frequencies of different sensors in real time through the dynamic adjustment unit, the best operating states of different sensors can be obtained, effectively preventing data duplication caused by high sensor operating frequencies.

[0076] Embodiment 4:

[0077] Based on Embodiment 3, please refer to the attached Figure 1 as shown. A prediction model is set in the data processing module. The prediction model retrieves historical type-B data, and the prediction model analyzes the future 24-hour prediction data based on the historical trends of different types of type-B data. The prediction model adopts a three-level progressive prediction of 4h + 8h + 12h, and each level of prediction is based on the previous level's results:

[0078] Level 1: 0 - 4h prediction is for high-precision short-term;

[0079] Level 2: 4 - 12h prediction is an 8h extension based on the 4h result;

[0080] Level 3: 12 - 24h prediction is a 12h extension based on the 12h result;

[0081] The prediction model obtains the result data of the historical trend of Class B data in the next 24h through a formula. The specific formula is as follows:

[0082] ;

[0083] ;

[0084] Among them, represents the result data of the prediction model for 12 hours of Class B data, represents the prediction result data of the prediction model based on Level 1, represents the result data of the direct 12-hour prediction of the prediction model, represents the result data of the prediction model for 24 hours of Class B data, represents the prediction result data of the prediction model based on Level 2, represents the result data of the direct 24-hour prediction of the prediction model, and respectively represent dynamic weight coefficients. A backup sensing unit is set in the data acquisition module, and the backup sensing unit is used to temporarily obtain Class B data. An energy loss threshold is set in the energy management module. When the transmission monitoring module detects an abnormality in the sensor and the energy loss threshold, the data acquisition module switches to the backup sensing unit to obtain Class B data. An early warning unit is set in the application layer, and the early warning unit is used to obtain the data in the data processing module and the energy management module, and perform early warning processing when abnormal data appears in the data processing module and the energy management module.

[0085] Furthermore, by performing prediction processing on data in different time periods, the Class B data at different times is obtained, and then the monitoring system generates corresponding processing schemes according to different time periods, which is convenient for the monitoring system to make timely adjustments when abnormalities occur in the perception layer, network layer, data layer, and application layer.

[0086] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A remote sensing monitoring system for the Internet of Things based on big data, characterized in that: The remote sensing monitoring system includes a sensing layer, a network layer, a data layer and an application layer; The perception layer is provided with a data acquisition module, in which different types of sensors are provided, and the data acquisition module obtains different types of sensor energy losses, marks different types of sensor energy losses as Class A, and marks data collected by different types of sensors as Class B; The network layer is provided with a data cleaning module, a transmission monitoring module and a data encryption module. The data cleaning module is used to clean the Class B data. The data encryption module uses the AES algorithm to encrypt the cleaned Class B data and then transmits the encrypted Class B data to the data layer. The transmission monitoring module is used to monitor the encrypted Class B data and transmit the Class A data marked in the perception layer. The data layer is provided with a data extraction module, a local storage module and a cloud storage module. The cloud storage module establishes various types of storage areas according to different types of sensors, transmits Class B data to the cloud storage module, and stores Class B data according to the corresponding storage area. The local storage module stores Class A data after receiving it, and the data extraction module extracts feature data from Class B data; The application layer is provided with a data processing module and an energy management module. The data processing module is used to analyze and predict the development status of Class B data, and the energy management module is used to manage Class A data. The data processing module uses digital twin technology to analyze and predict Class B data; The energy management module is provided with an energy loss database, an energy optimization unit and a dynamic adjustment unit, the energy loss database is used to store historical energy loss data and Class A data of different types of sensor nodes, wherein the Class A data further includes data of sensor type, operating frequency and environmental parameters associated with the energy loss data, the energy optimization unit constructs an energy loss model through the energy loss database, and the dynamic adjustment unit adjusts the energy loss of different types of sensors according to the energy loss model; The energy optimization unit expresses energy loss through a formula, and the specific formula is as follows: ； in, Indicates The energy loss of each sensor is It represents the square term of the operating frequency, reflecting the nonlinear energy loss. Indicates The operating frequency of the sensor is Indicates The ambient temperature of each sensor, Indicates The interaction term between the operating frequency of each sensor and the ambient temperature reflects the impact of the two on energy loss. Indicates The energy loss constant of each sensor is , as well as They respectively represent the weight coefficients of the operating frequency and ambient temperature obtained by fitting historical data, thereby optimizing the energy loss of different types of sensors; The data accuracy of the perception layer With the operating frequency Proportional, introduce the following relationship: ； in, represents the proportionality coefficient, is expressed as a constant, and the energy loss model is brought into the dynamic adjustment unit to generate the sensor frequency optimization strategy through the formula. The specific formula is as follows: ； in, Indicates The energy loss function of each sensor is expressed as: ； By adjusting the sensor operating frequency , making the total energy loss of all sensors Minimize, where Indicates The optimization strategy of the sensor operating frequency is It represents the variable value when the objective function takes the minimum value, and then the dynamic adjustment unit adjusts the working frequency of different sensors in real time; The constraints are: ； in, Indicates the lower threshold of data accuracy, Indicates The data accuracy of each sensor.

2. According to the big data-based IoT remote sensing monitoring system of claim 1, it is characterized by: The data processing module analyzes Class B data, obtains the accuracy of Class B data collected by different sensors, and transmits Class B data and accuracy data of different sensors to the energy management module, which then adjusts the working status data of different sensors according to the accuracy of Class B data.

3. According to the big data-based IoT remote sensing monitoring system of claim 2, it is characterized by: The data processing module is provided with a prediction model, which retrieves historical Class B data and analyzes the prediction data for the next 24 hours based on the historical trends of different types of Class B data. The prediction model adopts a three-level progressive prediction of 4h+8h+12h, and each level of prediction is based on the results of the previous level: Level 1: 0-4h forecast is short-term with high accuracy; Level 2: 4-12h prediction is an 8h extension based on the 4h result; Level 3: 12-24h prediction is a 12h extension based on the 12h result; The prediction model obtains the result data of the historical trend of Class B data in the next 24 hours through the formula. The specific formula is as follows: ； ； in, It represents the result data of the prediction model for Class B data for 12 hours. Indicates the prediction result data of the prediction model based on the first level. It represents the 12-hour result data directly predicted by the prediction model. It represents the result data of the prediction model for Class B data for 24 hours. Indicates the prediction result data based on the prediction model at level 2. It represents the 24-hour result data directly predicted by the prediction model. and Represent the dynamic weight coefficients respectively.

4. The IoT remote sensing monitoring system based on big data according to claim 3 is characterized in that: The data acquisition module is provided with a backup sensor unit, which is used to temporarily obtain Class B data. The energy management module is provided with an energy loss threshold. When the transmission monitoring module detects that the sensor is abnormal and When the energy loss threshold is reached, the data acquisition module switches to the backup sensor unit to obtain Class B data.

5. The IoT remote sensing monitoring system based on big data according to claim 4 is characterized in that: An early warning unit is provided in the application layer, and the early warning unit is used to obtain data in the data processing module and the energy management module, and to perform early warning processing when abnormal data appears in the data processing module and the energy management module.

6. A remote sensing monitoring method applicable to a big data-based Internet of Things remote sensing monitoring system as described in any one of claims 1 to 5, characterized in that: The specific steps are as follows: S1. Construct multiple sensors of different types to collect the perception data of the target object, then mark the data about the sensor itself as Class A data, and mark the data collected by the sensor as Class B data; S2. The network layer then cleans and classifies the Class B data for transmission, and then classifies and transmits the Class B data and Class A data, and encrypts and stores the Class B data; S3. After receiving the A-type data and the B-type data, extract features from the B-type data, and classify and store the A-type data and the B-type data; S4. Construct an energy loss database, which records the historical energy loss data of each sensor node and associates it with different types of sensors, operating frequencies and environmental parameters, thereby adjusting the energy loss between different types of sensors and optimizing the energy loss of the overall monitoring system.

Images