Intelligent energy-saving control system based on big data and cloud platform technology

Abstract

The invention discloses a smart energy-saving control system based on big data and a cloud platform technology, and relates to the field of big data. Comprising a cloud platform server which serves as a data processing and storage center and is responsible for receiving data from a data acquisition module, storing and analyzing the data and sending an analysis result and a control instruction to a control module and a user terminal; and the data acquisition module comprises a meter and a sensor which are deployed at main energy consumption nodes of a user and is used for acquiring energy consumption data of different energy media, and the data acquisition module transmits the acquired data to the cloud platform server through the communication gateway. By collecting energy consumption data and utilizing big data analysis and cloud platform technologies, real-time monitoring and intelligent control of energy consumption are achieved, the purpose of energy-saving optimization is achieved, and the system has the advantages of being efficient, accurate, real-time and the like, can be widely applied to various energy consumption fields and provides a new solution for energy management.

Description

Technical Field

[0001] The present invention relates to the field of big data, and in particular to an intelligent energy-saving control system based on big data and cloud platform technologies. Background Art

[0002] With the continuous increase in energy consumption, energy management and energy-saving optimization have become the focus of social attention.

[0003] Big data technology and cloud platform technology are two important pillars in the field of information technology today, and they play a key role in data processing, storage, analysis, and service provision.

[0004] Big data technology is a technical system for processing and analyzing massive data, aiming to quickly obtain valuable information from various types of data. These data usually have the characteristics of high growth rate and diversification, and new processing modes are required to enhance decision-making ability, insight, and process optimization ability.

[0005] Cloud platform technology is a mode of providing services such as computing resources, storage resources, and application programs to users through the Internet. Users do not need to purchase and maintain expensive hardware devices and software systems. They only need to rent the required resources through the cloud platform and pay according to the actual usage.

[0006] Traditional energy management systems often rely on manual monitoring and manual adjustment, which are not only inefficient but also difficult to achieve real-time and accurate energy consumption control.

[0007] Therefore, the present invention proposes an intelligent energy-saving control system based on big data and cloud platform technologies. Summary of the Invention

[0008] The purpose of the present invention is to solve the deficiencies in the prior art, and to propose an intelligent energy-saving control system based on big data and cloud platform technologies.

[0009] To achieve the above purpose, the present invention adopts the following technical solutions:

[0010] An intelligent energy-saving control system based on big data and cloud platform technologies, comprising:

[0011] A cloud platform server, which serves as the center for data processing and storage. The cloud platform server is responsible for receiving data from the data acquisition module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal;

[0012] A data acquisition module, which includes meters and sensors deployed at the main energy consumption nodes of users, and is used to collect energy consumption data of different energy media. The data acquisition module transmits the collected data to the cloud platform server through a communication gateway;

[0013] A data analysis module that uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions;

[0014] A control module that intelligently controls the energy-consuming devices according to the energy-saving strategies and optimization suggestions generated by the data analysis module and adjusts their operating states;

[0015] User terminals, including web browsers, mobile phones, and tablets, through which users can access the cloud platform server anytime and anywhere, view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0016] Preferably, the energy medium data collected by the data collection module includes electricity, water, gas, cold, and heat.

[0017] Preferably, the data collection model of the data collection module is D = {d 1 , d 2 ,......d n}, where D represents the collected energy consumption data, and d i represents the i-th energy consumption data point.

[0018] Preferably, the analysis logic of the data analysis module is as follows:

[0019] A1: Data preprocessing, cleaning, denoising, and standardizing the collected data;

[0020] A2: Feature extraction, extracting the features of the energy consumption data;

[0021] A3: Data analysis, using big data analysis and machine learning algorithms to analyze and model the features, identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set, and f represents the function of feature extraction and data analysis.

[0022] Preferably, in step A1, data cleaning includes the following steps:

[0023] A11a: Detect missing values using the isnull() method to detect missing values in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they are filled;

[0024] A12a: Process outliers, use a distance-based method to find outlier data points, and then eliminate the data points;

[0025] A13a: Then perform equal-frequency or equal-width binning on the data for smoothing;

[0026] In the step A1, the standardization process adopts any one of maximum - minimum normalization, Z - score normalization, decimal scaling normalization, and Box - Cox transformation.

[0027] Preferably: The maximum - minimum normalization includes the following steps:

[0028] a1: First, find the minimum value (min) and the maximum value (max) in the dataset;

[0029] a2: Then, use the formula (x - min) / (max - min) to transform each data point x into the interval [0, 1].

[0030] Preferably: The Z - score normalization includes the following steps:

[0031] b1: First, calculate the mean (μ) and the standard deviation (σ) of the dataset;

[0032] b2: Use the formula (x - μ) / σ to transform each data point x into a standard normal distribution.

[0033] Preferably: The decimal scaling normalization includes the following steps:

[0034] c1: Select an integer value k whose absolute value is less than 1;

[0035] c2: Then use the formula x / 10^k to scale the data to a fixed decimal point position.

[0036] Preferably: The Box - Cox transformation includes the following steps:

[0037] d1: Determine a λ value;

[0038] d2: Perform the transformation according to the formula (x^λ - 1) / λ (when λ ≠ 0) or log(x) (when λ = 0);

[0039] In the step d2, λ is determined by maximum likelihood estimation or cross - validation.

[0040] Preferably: In the step A2, the feature extraction includes the following steps:

[0041] A21: Feature selection, obtaining new features from the original data by using principal component separation or linear discriminant analysis;

[0042] A22: Feature dimensionality reduction, performing dimensionality reduction processing on the extracted features;

[0043] A23: Feature representation, representing the features by using any one of binary coding, polynomial coding, and basis function coding;

[0044] A24: Feature fusion. According to the formula fuses multiple features. T is the fused feature, n represents a total of n features, and t i represents the i-th feature before fusion.

[0045] The beneficial effects of the present invention are as follows:

[0046] 1. By collecting energy consumption data and using big data analysis and cloud platform technology, the present invention realizes real-time monitoring and intelligent control of energy consumption, achieves the purpose of energy-saving optimization, and has the advantages of high efficiency, accuracy, real-time, etc. It can be widely applied to various energy consumption fields and provides a new solution for energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 FIG. is an architecture diagram of a smart energy-saving control system based on big data and cloud platform technology proposed by the present invention;

[0048] Figure 2 FIG. is a data analysis flow chart of a smart energy-saving control system based on big data and cloud platform technology proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The technical solutions of the present invention will be further described in detail below in conjunction with the specific embodiments.

[0050] In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, the terms "installation", "connection", "connection", "setting" should be understood in a broad sense. For example, it can be fixedly connected, set, or detachably connected, set, or integrally connected, set. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0051] Embodiment 1:

[0052] A smart energy-saving control system based on big data and cloud platform technology, which includes:

[0053] A cloud platform server, which serves as the center for data processing and storage. The cloud platform server is responsible for receiving data from the data acquisition module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal;

[0054] A data acquisition module, which includes meters and sensors deployed at the main energy consumption nodes of users, and is used to collect energy consumption data of different energy media. The data acquisition module transmits the collected data to the cloud platform server through a communication gateway;

[0055] The data analysis module uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions.

[0056] The control module intelligently controls the energy-consuming devices according to the energy-saving strategies and optimization suggestions generated by the data analysis module, and adjusts their operating states.

[0057] The user terminal includes a Web browser, a mobile phone, and a tablet computer. Users can access the cloud platform server through these devices at any time and place to view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0058] The energy medium data collected by the data collection module includes electricity, water, gas, cooling capacity, and heat.

[0059] Embodiment 2:

[0060] A smart energy-saving control system based on big data and cloud platform technology, which includes:

[0061] The cloud platform server, as the center for data processing and storage, is responsible for receiving data from the data collection module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal.

[0062] The data collection module includes meters and sensors deployed at the main energy consumption nodes of users to collect energy consumption data of different energy media. The data collection module transmits the collected data to the cloud platform server through a communication gateway.

[0063] The data analysis module uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions.

[0064] The control module intelligently controls the energy-consuming devices according to the energy-saving strategies and optimization suggestions generated by the data analysis module, and adjusts their operating states.

[0065] The user terminal includes a Web browser, a mobile phone, and a tablet computer. Users can access the cloud platform server through these devices at any time and place to view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0066] The energy medium data collected by the data collection module includes electricity, water, gas, cooling capacity, and heat.

[0067] The data collection model of the data collection module is D = {d 1 , d 2 , …… d n}, where D represents the collected energy consumption data, and d i represents the i-th energy consumption data point.

[0068] Embodiment 3:

[0069] A smart energy-saving control system based on big data and cloud platform technology, which includes:

[0070] A cloud platform server, which serves as the center for data processing and storage. The cloud platform server is responsible for receiving data from the data collection module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal;

[0071] A data collection module, which includes meters and sensors deployed at the main energy consumption nodes of users, and is used to collect energy consumption data of different energy media. The data collection module transmits the collected data to the cloud platform server through a communication gateway;

[0072] A data analysis module, which uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions;

[0073] A control module, which intelligently controls the energy consumption equipment according to the energy-saving strategies and optimization suggestions generated by the data analysis module, and adjusts its operating state;

[0074] A user terminal, including a Web browser, a mobile phone, and a tablet computer. Users can access the cloud platform server anytime and anywhere through these devices, view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0075] The energy medium data collected by the data collection module includes electricity, water, gas, cold, and heat.

[0076] The data collection model of the data collection module is D = {d 1 , d 2 , …… d n}, where D represents the collected energy consumption data, and d i represents the i-th energy consumption data point.

[0077] The analysis logic of the data analysis module is as follows:

[0078] A1: Data preprocessing, cleaning, denoising, and standardizing the collected data;

[0079] A2: Feature extraction, extracting the features of the energy consumption data;

[0080] A3: Data analysis: Use big data analysis and machine learning algorithms to analyze and model features and identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set and f represents the function of feature extraction and data analysis.

[0081] In step A1, data cleaning includes the following steps:

[0082] A11a: Detect missing values ​​The isnull() method detects missing values ​​in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they can be filled.

[0083] A12a: To handle outliers, we use a distance-based approach to find outlier data points and then remove them.

[0084] A13a: Then the data is binned with equal frequency or width for smoothing.

[0085] Embodiment 4:

[0086] A smart energy-saving control system based on big data and cloud platform technology, comprising:

[0087] The cloud platform server, as the center of data processing and storage, is responsible for receiving data from the data acquisition module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal;

[0088] The data collection module includes meters and sensors deployed at the main energy consumption nodes of users, which are used to collect energy consumption data of different energy media. The data collection module transmits the collected data to the cloud platform server through the communication gateway;

[0089] The data analysis module uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions;

[0090] The control module intelligently controls energy-consuming equipment and adjusts its operating status according to the energy-saving strategies and optimization suggestions generated by the data analysis module;

[0091] User terminals, including web browsers, mobile phones, and tablet computers, can be used by users to access the cloud platform server anytime and anywhere, view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0092] The energy medium data collected by the data collection module includes electricity, water, gas, cold and heat.

[0093] The data acquisition model of the data acquisition module is D={d1 , d 2 , …… d n} , where D represents the collected energy consumption data, and d i represents the i-th energy consumption data point.

[0094] The analysis logic of the data analysis module is as follows:

[0095] A1: Data preprocessing, cleaning, denoising, and standardizing the collected data;

[0096] A2: Feature extraction, extracting the features of the energy consumption data;

[0097] A3: Data analysis, using big data analysis and machine learning algorithms to analyze and model the features, identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set and f represents the function of feature extraction and data analysis.

[0098] In the step A1, data cleaning includes the following steps:

[0099] A11a: Detecting missing values, using the isnull() method to detect missing values in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they are filled;

[0100] A12a: Handling outliers, using a distance-based method to find outlier data points and then removing them;

[0101] A13a: Then binning the data using equal frequency or equal width and performing smoothing processing.

[0102] In the step A1, the standardization process uses maximum - minimum normalization.

[0103] The maximum - minimum normalization includes the following steps:

[0104] a1: First, find the minimum value (min) and the maximum value (max) in the dataset;

[0105] a2: Then, use the formula (x - min) / (max - min) to transform each data point x into the interval [0, 1].

[0106] Example 5:

[0107] A smart energy-saving control system based on big data and cloud platform technology, which includes:

[0108] A cloud platform server, which serves as the center for data processing and storage. The cloud platform server is responsible for receiving data from the data collection module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal;

[0109] A data acquisition module, which includes meters and sensors deployed at the main energy consumption nodes of users, is used to collect energy consumption data of different energy media. The data acquisition module transmits the collected data to the cloud platform server through a communication gateway;

[0110] A data analysis module uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions;

[0111] A control module intelligently controls the energy consumption equipment according to the energy-saving strategies and optimization suggestions generated by the data analysis module, and adjusts its operating state;

[0112] A user terminal includes a Web browser, a mobile phone, and a tablet computer. Users can access the cloud platform server anytime and anywhere through these devices to view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0113] The energy medium data collected by the data acquisition module includes electricity, water, gas, cooling capacity, and heat.

[0114] The data acquisition model of the data acquisition module is D = {d 1 , d 2 , …… d n}, where D represents the collected energy consumption data, and d i represents the i-th energy consumption data point.

[0115] The analysis logic of the data analysis module is as follows:

[0116] A1: Data preprocessing, cleaning, denoising, and standardizing the collected data;

[0117] A2: Feature extraction, extracting the features of the energy consumption data;

[0118] A3: Data analysis, using big data analysis and machine learning algorithms to analyze and model the features, identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set, and f represents the function of feature extraction and data analysis.

[0119] In the step A1, the data cleaning includes the following steps:

[0120] A11a: Detecting missing values, using the isnull() method to detect missing values in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they are filled;

[0121] A12a: Process outliers. Use a distance-based method to find outlier data points and then eliminate the data points.

[0122] A13a: Then perform equal-frequency or equal-width binning on the data and conduct smoothing processing.

[0123] In the A1 step, Z-score normalization is adopted for the standardization process.

[0124] The Z-score normalization includes the following steps:

[0125] b1: First, calculate the mean (μ) and standard deviation (σ) of the data set;

[0126] b2: Use the formula (x - μ) / σ to convert each data point x into a standard normal distribution.

[0127] Example 6:

[0128] A smart energy-saving control system based on big data and cloud platform technology, which includes:

[0129] A cloud platform server, which serves as the center for data processing and storage. The cloud platform server is responsible for receiving data from the data acquisition module, storing and analyzing it, and sending the analysis results and control instructions to the control module and user terminal;

[0130] A data acquisition module, which includes meters and sensors deployed at the main energy consumption nodes of users, and is used to collect energy consumption data of different energy media. The data acquisition module transmits the collected data to the cloud platform server through a communication gateway;

[0131] A data analysis module, which uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions;

[0132] A control module, which intelligently controls the energy consumption equipment according to the energy-saving strategies and optimization suggestions generated by the data analysis module and adjusts its operating state;

[0133] A user terminal, including a Web browser, mobile phone, and tablet computer. Users can access the cloud platform server anytime and anywhere through these devices to view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0134] The energy medium data collected by the data acquisition module includes electricity, water, gas, cold, and heat.

[0135] The data acquisition model of the data acquisition module is D = {d 1 , d 2 , …… d n}, where D represents the collected energy consumption data, d i Represents the i-th energy consumption data point.

[0136] The analysis logic of the data analysis module is:

[0137] A1: Data preprocessing: cleaning, denoising and standardizing the collected data;

[0138] A2: Feature extraction, extracting the features of energy consumption data;

[0139] A3: Data analysis: Use big data analysis and machine learning algorithms to analyze and model features and identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set and f represents the function of feature extraction and data analysis.

[0140] In step A1, data cleaning includes the following steps:

[0141] A11a: Detect missing values ​​The isnull() method detects missing values ​​in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they can be filled.

[0142] A12a: To handle outliers, we use a distance-based approach to find outlier data points and then remove them.

[0143] A13a: Then the data is binned with equal frequency or width for smoothing.

[0144] In the step A1, the standardization process uses decimal ratio normalization.

[0145] The decimal ratio normalization comprises the following steps:

[0146] c1: Select an integer value k whose absolute value is less than 1;

[0147] c2: The data is then scaled to a fixed decimal point using the formula x / 10^k.

[0148] Embodiment 7:

[0149] A smart energy-saving control system based on big data and cloud platform technology, comprising:

[0150] The cloud platform server, as the center of data processing and storage, is responsible for receiving data from the data acquisition module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal;

[0151] The data acquisition module, which includes meters and sensors deployed at the main energy consumption nodes of users, is used to collect energy consumption data of different energy media. The data acquisition module transmits the collected data to the cloud platform server through a communication gateway;

[0152] The data analysis module uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions;

[0153] The control module intelligently controls the energy consumption equipment according to the energy-saving strategies and optimization suggestions generated by the data analysis module and adjusts its operating state;

[0154] The user terminal includes a Web browser, a mobile phone, and a tablet computer. Users can access the cloud platform server anytime and anywhere through these devices to view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0155] The energy medium data collected by the data acquisition module includes electricity, water, gas, cold, and heat.

[0156] The data acquisition model of the data acquisition module is D = {d 1 , d 2 , …… d n}, where D represents the collected energy consumption data, and d i represents the i-th energy consumption data point.

[0157] The analysis logic of the data analysis module is as follows:

[0158] A1: Data preprocessing, cleaning, denoising, and standardizing the collected data;

[0159] A2: Feature extraction, extracting the features of the energy consumption data;

[0160] A3: Data analysis, using big data analysis and machine learning algorithms to analyze and model the features, identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set, and f represents the function of feature extraction and data analysis.

[0161] In the step A1, the data cleaning includes the following steps:

[0162] A11a: Detecting missing values, using the isnull() method to detect missing values in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they are filled;

[0163] A12a: Handling outliers, using a distance-based method to find outlier data points and then removing them;

[0164] A13a: Then, the data is binned using equal frequency or equal width binning and smoothed.

[0165] In the A1 step, the standardization process uses the Box-Cox transformation.

[0166] The Box-Cox transformation includes the following steps:

[0167] d1: Determine a λ value;

[0168] d2: Transform according to the formula (x^λ - 1) / λ (when λ ≠ 0) or log(x) (when λ = 0);

[0169] In the d2 step, λ is determined by maximum likelihood estimation or cross-validation.

[0170] Example 8:

[0171] A smart energy-saving control system based on big data and cloud platform technology, which includes:

[0172] A cloud platform server, which serves as the center for data processing and storage. The cloud platform server is responsible for receiving data from the data acquisition module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal;

[0173] A data acquisition module, which includes meters and sensors deployed at the main energy consumption nodes of users, and is used to collect energy consumption data of different energy media. The data acquisition module transmits the collected data to the cloud platform server through a communication gateway;

[0174] A data analysis module, which uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions;

[0175] A control module, which intelligently controls the energy consumption equipment according to the energy-saving strategies and optimization suggestions generated by the data analysis module and adjusts its operating state;

[0176] A user terminal, including a Web browser, a mobile phone, and a tablet computer. Users can access the cloud platform server anytime and anywhere through these devices to view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

[0177] The energy medium data collected by the data acquisition module includes electricity, water, gas, cold, and heat.

[0178] The data acquisition model of the data acquisition module is D = {d 1 , d 2 , …… d n}, where D represents the collected energy consumption data, d i Represents the i-th energy consumption data point.

[0179] The analysis logic of the data analysis module is:

[0180] A1: Data preprocessing: cleaning, denoising and standardizing the collected data;

[0181] A2: Feature extraction, extracting the features of energy consumption data;

[0182] A3: Data analysis: Use big data analysis and machine learning algorithms to analyze and model features and identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set and f represents the function of feature extraction and data analysis.

[0183] In step A1, data cleaning includes the following steps:

[0184] A11a: Detect missing values ​​The isnull() method detects missing values ​​in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they can be filled.

[0185] A12a: To handle outliers, we use a distance-based approach to find outlier data points and then remove them.

[0186] A13a: Then the data is binned with equal frequency or width for smoothing.

[0187] In the step A1, the normalization process adopts any one of maximum-minimum normalization, Z-score normalization, decimal ratio normalization and Box-Cox transformation.

[0188] In step A2, feature extraction includes the following steps:

[0189] A21: Feature selection, using principal component separation or linear discriminant analysis to obtain new features from the original data;

[0190] A22: Feature dimensionality reduction, which is to reduce the dimensionality of the extracted features;

[0191] A23: Feature representation, using any one of binary coding, polynomial coding, and basis function coding to represent the features;

[0192] A24: Feature fusion, according to the formula Fusion of multiple features, T is the fused feature, n represents a total of n features, t i Represents the i-th feature before fusion.

[0193] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention should cover within the protection scope of the present invention any equivalent replacement or change made according to the technical solution of the present invention and its inventive concept.

Claims

1. A smart energy-saving control system based on big data and cloud platform technology, characterized in that: include: The cloud platform server, as the center of data processing and storage, is responsible for receiving data from the data acquisition module, storing and analyzing it, and sending the analysis results and control instructions to the control module and the user terminal; The data collection module includes meters and sensors deployed at the main energy consumption nodes of users, which are used to collect energy consumption data of different energy media. The data collection module transmits the collected data to the cloud platform server through the communication gateway; The data analysis module uses big data analysis and machine learning algorithms to process and analyze the energy consumption data received by the cloud platform server, identify energy consumption patterns and trends, and generate energy-saving strategies and optimization suggestions; The control module intelligently controls energy-consuming equipment and adjusts its operating status according to the energy-saving strategies and optimization suggestions generated by the data analysis module; User terminals, including web browsers, mobile phones, and tablet computers, can be used by users to access the cloud platform server anytime and anywhere, view energy consumption data, energy-saving strategies, and optimization suggestions, and perform corresponding operations.

2. According to claim 1, a smart energy-saving control system based on big data and cloud platform technology is characterized in that: The energy medium data collected by the data collection module includes electricity, water, gas, cold and heat.

3. According to claim 1, a smart energy-saving control system based on big data and cloud platform technology is characterized in that: The data acquisition model of the data acquisition module is D={d1, d2, ... d n }, where D represents the collected energy consumption data, d i Represents the i-th energy consumption data point.

4. According to claim 1, a smart energy-saving control system based on big data and cloud platform technology is characterized in that: The analysis logic of the data analysis module is: A1: Data preprocessing: cleaning, denoising and standardizing the collected data; A2: Feature extraction, extracting the features of energy consumption data; A3: Data analysis: Use big data analysis and machine learning algorithms to analyze and model features and identify energy consumption patterns and trends. The data analysis model is F = f(D), where F represents the extracted feature set and f represents the function of feature extraction and data analysis.

5. According to claim 4, a smart energy-saving control system based on big data and cloud platform technology is characterized in that: In step A1, data cleaning includes the following steps: A11a: Detect missing values ​​The isnull() method detects missing values ​​in the data. For variables with a high missing rate, they can be directly deleted; for variables with a low missing rate, they can be filled. A12a: To handle outliers, we use a distance-based approach to find outlier data points and then remove them. A13a: Then the data is binned with equal frequency or width for smoothing; In the step A1, the normalization process adopts any one of maximum-minimum normalization, Z-score normalization, decimal ratio normalization and Box-Cox transformation.

6. The intelligent energy-saving control system based on big data and cloud platform technology according to claim 5 is characterized in that: The maximum-minimum normalization comprises the following steps: a1: First find the minimum value (min) and maximum value (max) in the data set; a2: Then, use the formula (x-min) / (max-min) to transform each data point x into the interval [0,1].

7. The intelligent energy-saving control system based on big data and cloud platform technology according to claim 5 is characterized in that: The Z-score is normalized The following steps are involved: b1: First calculate the mean (μ) and standard deviation (σ) of the data set; b2: Convert each data point x to a standard normal distribution using the formula (x-μ) / σ.

8. The intelligent energy-saving control system based on big data and cloud platform technology according to claim 5 is characterized in that: The decimal ratio normalization comprises the following steps: c1: Select an integer value k whose absolute value is less than 1; c2: The data is then scaled to a fixed decimal point using the formula x / 10^k.

9. The intelligent energy-saving control system based on big data and cloud platform technology according to claim 5 is characterized in that: The Box-Cox transformation includes the following steps: d1: determine a lambda value; d2: Convert according to the formula (x^λ-1) / λ (when λ≠0) or log(x) (when λ=0); In the step d2, λ is determined by maximum likelihood estimation or cross validation.

10. The intelligent energy-saving control system based on big data and cloud platform technology according to claim 4 is characterized in that: In step A2, feature extraction includes the following steps: A21: Feature selection, using principal component separation or linear discriminant analysis to obtain new features from the original data; A22: Feature dimensionality reduction, which is to reduce the dimensionality of the extracted features; A23: Feature representation, using any one of binary coding, polynomial coding, and basis function coding to represent the features; A24: Feature fusion, according to the formula Fusion of multiple features, T is the fused feature, n represents a total of n features, t i Represents the i-th feature before fusion.

Images