Intelligent energy digital management system applied to cloud platform

Abstract

The invention relates to a smart energy digital management system applied to a cloud platform, in particular to the field of energy digital management, and specifically comprises a data acquisition module, a data storage and preprocessing module, a data analysis and optimization module and an energy management decision and scheduling module. According to the system, technologies of Internet of Things, big data analysis, artificial intelligence and the like are combined, comprehensive digital monitoring and intelligent optimization management of enterprise energy are realized through real-time acquisition and processing of various energy data, and the energy management efficiency is improved through integration of advanced data mining, trend prediction and optimization scheduling algorithms. The method helps enterprises to reduce energy consumption, improves energy use efficiency, and optimizes energy management strategies.

Description

Technical Field

[0001] The present invention relates to the field of digital energy management, and more specifically, to a smart digital energy management system applied to a cloud platform. Background Art

[0002] With the continuous development and application of the Internet of Things, big data and cloud computing technologies, the application of digitalization, informatization, intelligence and digital wisdom in enterprise transformation and upgrading has become a current hot research direction.

[0003] However, traditional energy management methods often face some problems: first, the data of many companies are scattered in different devices and systems, which is difficult to manage and analyze in a unified manner. Secondly, the management methods are often lagging, and many energy wastes are often discovered only after the fact, making it difficult to adjust in time. Moreover, the efficiency is not high, and energy demand cannot be accurately predicted, resulting in waste or shortage. In many cases, decisions are too dependent on experience, lack intelligent support, and cannot cope with complex production needs. In general, the traditional energy management model is inefficient and requires a more intelligent and integrated system to improve energy utilization and reduce waste.

[0004] Therefore, there is an urgent need for a more intelligent, integrated and efficient energy management system to solve these problems and achieve optimization and sustainable development of energy consumption. Summary of the invention

[0005] In view of the technical problems existing in the prior art, the present invention provides a smart energy digital management system applied to a cloud platform, which solves the problems raised in the above-mentioned background technology through the deep integration of the Internet of Things, big data and cloud computing technologies.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: specifically comprising: a data acquisition module, a data storage and preprocessing module, a data analysis and optimization module, and an energy management decision and scheduling module;

[0007] Data acquisition module: Sensor components are installed at various production links and energy consumption nodes to monitor energy consumption data in real time, and the acquired energy consumption data is transmitted to the data center of the cloud platform in real time through the Internet of Things technology for centralized storage and processing;

[0008] Data storage and preprocessing module: After receiving the energy consumption data transmitted by the data acquisition module, a distributed database is used to store the massive data. At the same time, the energy consumption data is cleaned and denoised, abnormal values ​​and erroneous data are removed, and the preprocessed data is processed through data standardization methods;

[0009] Data Analysis and Optimization Module: Using big data analysis methods, combined with energy consumption data for cluster analysis, mining potential energy waste patterns and optimization potential, generating cluster analysis results, using historical energy consumption data and ARIMA prediction models to generate prediction results, predicting the energy consumption trend in the next period of time, providing an early warning mechanism for enterprises, and optimizing energy scheduling using the objective function of the particle swarm optimization algorithm;

[0010] Energy Management Decision and Scheduling Module: Using the Energy Management System (EMS) to monitor the consumption of various types of energy in real time, generating energy consumption reports and energy consumption rankings, identifying high-energy-consuming links. At the same time, based on the cluster analysis results, providing intelligent decision-making support for management, combining production plans, equipment operation status, and prediction results to perform intelligent scheduling of energy, and optimizing production plans and equipment scheduling strategies.

[0011] In a preferred embodiment, the energy consumption nodes in the data acquisition module include electricity, water, and gas; the sensor components include current sensors, voltage sensors, temperature sensors, pressure sensors, and flow sensors.

[0012] In a preferred embodiment, in the data storage and preprocessing module, the data standardization calculation formula is:

[0013]

[0014] where Z represents the standardized data, X represents the original energy consumption data, represents the mean of the original energy consumption data, represents the standard deviation of the original energy consumption data, X i represents each data point, and N represents the total number of data points.

[0015] In a preferred embodiment, the specific steps of the cluster analysis in the data analysis and optimization module are as follows:

[0016] S1. Use K-means clustering for analysis to divide each production link and energy consumption node into different clusters according to energy consumption characteristics, and select key features related to energy consumption, including equipment type, operation duration, load level, and production output;

[0017] S2. Use the elbow method to determine the value of K. The specific steps are:

[0018] 1). Calculate the sum of squared errors (SSE) for different values of K (such as K = 2, 3, 4,...).

[0019] 2). Plot the graph of SSE against K, and find the "elbow" position of the curve, that is, the place where the downward trend of SSE slows down, as the optimal number of clusters K;

[0020] S3. Use the K-means algorithm to cluster the energy consumption data:

[0021] 1). Initialize the center points (centroids) of K clusters, usually by randomly selecting data points as the initial centers;

[0022] 2). Calculate the distances from each data point to all centroids and assign it to the cluster with the shortest distance;

[0023] 3). Update the centroid of each cluster to the mean of all points in that cluster;

[0024] 4). Repeat the above steps until the centroids no longer change or the maximum number of iterations is reached;

[0025] S4. Use the principal component analysis PCA to reduce the dimensionality of the clustering results to two dimensions and view the distribution of different clusters;

[0026] S5. Analyze each cluster, view its eigenvalues, which include average energy consumption and volatility, identify the clusters with higher energy consumption, compare the energy consumption differences of different clusters, and determine which clusters have poor energy efficiency;

[0027] S6. Identify energy waste patterns

[0028] 1). High energy consumption clusters: For clusters with higher energy consumption, further check whether there are situations such as equipment aging, low efficiency, or improper operation;

[0029] 2). Volatile clusters: For clusters with large fluctuations in energy consumption, analyze whether there are equipment failures, overuse, or unreasonable work schedules;

[0030] 3). Period characteristics: Analyze the energy consumption differences of different clusters at specific times, and find out unnecessary energy waste. Specific times include peak production periods and seasonal changes;

[0031] S7. Explore optimization potential

[0032] 1). Conduct in-depth analysis on high energy consumption clusters to check whether there is room for technical improvement, including replacing equipment and optimizing operation methods;

[0033] 2). Analyze the reasons for low equipment usage efficiency and consider whether equipment upgrades or usage strategies need to be adjusted.

[0034] 3). Identify energy waste during peak production periods and suggest optimizing production scheduling to reduce unnecessary energy consumption

[0035] S8. Develop an optimization plan

[0036] 1). Equipment optimization: For equipment with poor energy efficiency, it is recommended to carry out technical upgrades or replacements, and determine which equipment has the greatest impact on the total energy consumption through data analysis.

[0037] 2) Scheduling optimization: According to the clustering analysis results, adjust the operation time of production or equipment to reduce high-energy consumption periods.

[0038] 3) Regular maintenance: For equipment with frequent high energy consumption, formulate regular inspection and maintenance plans to ensure that the equipment is always in the best operating state.

[0039] In a preferred embodiment, in the data analysis and optimization module, the prediction formula of the ARIMA prediction model is:

[0040] [Y t = μ + φ 1 Y t-1 + φ 2 Y t-2 +... + ε t

[0041] Where Y t represents the predicted value at time t, μ represents the constant term, (φ 1 , φ 2 ) represents the model coefficients, ε t represents the error term at the current time point, and Y t-1 represents the value at the (t - 1)-th moment in the time series.

[0042] In a preferred embodiment, the early warning mechanism is specifically: According to the prediction results, set the early warning threshold of energy consumption. If it is predicted that the energy consumption exceeds a certain percentage of the historical average level within a certain period of time, the system will automatically trigger an alarm. At the same time of the alarm trigger, notify the management layer to take measures to deal with the abnormal high energy consumption situation. The measures taken include adjusting the production plan and optimizing the equipment scheduling.

[0043] In a preferred embodiment, the objective function formula of the particle swarm optimization algorithm is:

[0044]

[0045] Where E i represents the energy consumption of each device, E opt represents the target energy consumption after optimization, and n represents the total number of devices.

[0046] In a preferred embodiment, the particle swarm optimization algorithm iterates multiple times, continuously updates the scheduling plan, and finally finds the optimal energy consumption scheduling strategy, including:

[0047] 1) During high power demand periods, preferentially schedule low energy consumption devices;

[0048] 2) Dynamically adjust the operating state of the equipment according to the real-time load and prediction results; ​

[0049] Secondly, according to the results of particle swarm optimization, adjust the switching state or load distribution of the equipment to reduce the total energy consumption.

[0050] In a preferred embodiment, in the energy management decision-making and scheduling module, the clustering analysis results, energy efficiency patterns, and potential waste points are presented through charts to generate an intuitive report, and specific optimization suggestions are put forward based on the clustering results, including equipment replacement, scheduling optimization, and regular maintenance.

[0051] In a preferred embodiment, the specific methods of intelligent scheduling include:

[0052] 1) Combine the production plan, equipment status, and energy consumption prediction results to perform energy scheduling. During peak power demand, give priority to scheduling energy-saving equipment, or adjust the production process as needed to reduce unnecessary energy consumption;

[0053] 2) Dynamically adjust the switching state or load distribution of the equipment according to the real-time load, prediction trend, and equipment status. When there is a high energy consumption risk, adjust the production process or replace inefficient equipment.

[0054] The beneficial effects of the present invention are as follows: Based on the cloud platform, combined with technologies such as the Internet of Things, big data analysis, and artificial intelligence, through real-time collection and processing of various energy data, comprehensive digital monitoring and intelligent optimization management of enterprise energy are realized. By integrating advanced data mining, trend prediction, and optimization scheduling algorithms, it helps enterprises reduce energy consumption, improve energy use efficiency, and optimize energy management strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flowchart of the method of the present invention;

[0056] Figure 2 It is a block diagram of the system structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0058] In the description of the present application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present application, "a plurality of" means two or more, unless otherwise specifically defined.

[0059] In the description of the present application, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present application is not necessarily to be construed as more preferred or more advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be practiced without these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the present application.

[0060] Embodiment 1

[0061] This embodiment provides a Figure 1-2 smart energy digital management system applied to a cloud platform as shown, specifically including: a data acquisition module, a data storage and preprocessing module, a data analysis and optimization module, and an energy management decision-making and scheduling module;

[0062] Data acquisition module: Sensor components are installed at each production link and energy consumption node to monitor energy consumption data in real time, and the obtained energy consumption data is transmitted to the data center of the cloud platform for centralized storage and processing in real time through Internet of Things (IoT) technology. At the same time, in the present application, the IoT technology can use multiple protocols (such as MQTT, HTTP, CoAP) for data transmission. When the protocol used by the sensor component is incompatible with the IoT protocol, protocol conversion is performed on it through an edge device, for example, converting Modbus to the MQTT protocol;

[0063] Data storage and preprocessing module: After receiving the energy consumption data transmitted by the data acquisition module, a distributed database is used to store massive data. Distributed database types such as Apache Hadoop, Cassandra, MongoDB, etc. ensure data security and high availability. Cloud storage services such as AWS, Azure or Google Cloud Platform are used to support large-scale data storage and management. At the same time, the energy consumption data is cleaned and denoised to remove abnormal values ​​and erroneous data. The preprocessed data is processed through data standardization methods to have a unified standard scale, thereby ensuring consistency and comparability between data collected from different sources and different devices;

[0064] Data analysis and optimization module: Use big data analysis methods to combine energy consumption data for cluster analysis, explore potential energy waste patterns and optimization potential, generate cluster analysis results, use historical energy consumption data and ARI MA prediction model to generate prediction results, predict energy consumption trends in the future, provide early warning mechanisms for enterprises, and use the objective function of the particle swarm optimization algorithm to optimize energy scheduling, reduce energy consumption, and improve system operation efficiency;

[0065] Energy management decision-making and scheduling module: Use the energy management system EMS to monitor the consumption of various energy sources in real time, generate energy consumption reports and energy consumption rankings, identify high-energy consumption links, and provide intelligent decision-making support for management based on cluster analysis results. Combined with production plans, equipment operating status and forecast results, intelligent energy scheduling is carried out to optimize production plans and equipment scheduling strategies, reduce energy consumption and improve production efficiency.

[0066] In this embodiment, what needs to be specifically explained is the data acquisition module. The energy consumption nodes include electricity, water and gas. The nodes that need to be monitored are determined according to the production process and energy usage. For example, electricity consumption points include motors, lighting equipment, heating equipment, etc.; water usage nodes include production lines, cooling systems, etc.; gas usage nodes include gas boilers, compressed air systems, etc.; sensor components include current sensors, voltage sensors, temperature sensors, pressure sensors and flow sensors. In this application, current sensors and voltage sensors are set to monitor power consumption; temperature sensors are set to monitor equipment temperature to avoid overheating or reduced energy efficiency; pressure sensors are set to monitor the pressure of media such as water and gas; flow sensors are set to monitor the flow of water, gas or steam.

[0067] In this embodiment, the data storage and preprocessing module specifically needs to be explained. In order to facilitate the comparison of energy consumption data collected by different devices on the same scale, the data standardization calculation formula is:

[0068]

[0069] Among them, Z represents the standardized data, and X represents the original energy consumption data. represents the mean value of the original energy consumption data. represents the standard deviation of the original energy consumption data, X i represents each data point, and N represents the total number of data points.

[0070] In this embodiment, specifically, it is necessary to explain the data analysis and optimization module. The specific steps of the clustering analysis in the data analysis and optimization module are as follows:

[0071] S1. Use K-means clustering for analysis to divide each production link and energy consumption node into different clusters according to energy consumption characteristics, discover potential energy waste patterns, and select key features related to energy consumption, including equipment type, operation duration, load level, and production output.

[0072] S2. Use the elbow method to determine the value of K. The specific steps are as follows:

[0073] 1). Calculate the sum of squared errors SSE for different values of K (such as K = 2, 3, 4,...).

[0074] 2). Plot the image of SSE against K, and find the "elbow" position of the curve, that is, the place where the downward trend of SSE slows down, as the optimal number of clusters K.

[0075] S3. Use the K-means algorithm to cluster the energy consumption data:

[0076] 1). Initialize the center points (centroids) of K clusters, usually by randomly selecting data points as the initial centers.

[0077] 2). Calculate the distance from each data point to all centroids and assign it to the cluster with the shortest distance.

[0078] 3). Update the centroid of each cluster to the mean value of all points in that cluster.

[0079] 4). Repeat the above steps until the centroids no longer change or reach the maximum number of iterations.

[0080] S4. Use principal component analysis PCA to reduce the dimensionality of the clustering results to two dimensions, view the distribution of different clusters, and analyze the characteristics of each cluster to ensure that the clustering results have obvious differences.

[0081] S5. Analyze each cluster, view its eigenvalues, including average energy consumption and volatility, identify the clusters with high energy consumption, which may be potential energy waste areas, compare the energy consumption differences between different clusters, and determine which clusters have poor energy efficiency.

[0082] S6. Identify energy waste patterns

[0083] 1). High - energy - consumption clusters: For clusters with relatively high energy consumption, further check whether there are situations such as equipment aging, low efficiency, or improper operation;

[0084] 2). Fluctuating clusters: For clusters with large fluctuations in energy consumption, analyze whether there are equipment failures, over - use, or unreasonable work scheduling;

[0085] 3). Time - period characteristics: Analyze the energy - consumption differences of different clusters during specific time periods, and find out unnecessary energy waste. Specific time periods include peak production periods and seasonal changes;

[0086] S7. Explore optimization potential

[0087] 1). Conduct in - depth analysis of high - energy - consumption clusters to check whether there is room for technological improvement, including replacing equipment and optimizing operation methods;

[0088] 2). Analyze the reasons for low equipment - usage efficiency and consider whether equipment upgrades or adjustments to usage strategies are needed.

[0089] 3). Identify energy - consumption waste during peak production periods and recommend optimizing production scheduling to reduce unnecessary energy consumption

[0090] S8. Develop optimization plans

[0091] 1). Equipment optimization: For equipment with poor energy efficiency, it is recommended to carry out technological upgrades or replacements. Determine which equipment has the greatest impact on total energy consumption through data analysis.

[0092] 2). Scheduling optimization: According to the results of cluster analysis, adjust the running time of production or equipment to reduce high - energy - consumption time periods.

[0093] 3). Regular maintenance: For equipment that frequently shows high energy consumption, formulate a regular inspection and maintenance plan to ensure that the equipment is always in the best operating state;

[0094] The prediction formula of the ARIMA prediction model is:

[0095] [Y t = μ + φ 1 Y t-1 + φ 2 Y t-2 +...+ ε t

[0096] Among them, Y t represents the predicted value at time t, μ represents the constant term, usually 0, or it can be set to a non - zero constant and adjusted according to actual needs. (φ 1 , φ 2 ​) represents the model coefficient, ε t represents the error term at the current time point, also known as white noise, also called innovation term, which is the difference between the actual observed value and the model predicted value, Y t-1 represents the value at the (t - 1)th moment in the time series, usually a lagged value of the current moment data;

[0097] The early warning mechanism is specifically as follows: According to the prediction results, set the early warning threshold of energy consumption. If it is predicted that the energy consumption exceeds a certain percentage of the historical average level within a certain period of time, the percentage value can be determined and adjusted according to requirements. The system will automatically trigger an alarm. At the same time of the alarm trigger, notify the management layer to take measures to deal with the abnormal high energy consumption situation. The measures taken include adjusting the production plan and optimizing the equipment scheduling;

[0098] The objective function formula of the particle swarm optimization algorithm is:

[0099]

[0100] Among them, E i represents the energy consumption of each device, E opt represents the optimized target energy consumption, and n represents the total number of devices;

[0101] The particle swarm optimization algorithm finds the optimal energy consumption scheduling strategy by continuously updating the scheduling plan through multiple iterations, including:

[0102] 1), During high power demand periods, preferentially schedule low - energy - consumption devices;

[0103] 2), Dynamically adjust the operating state of the device according to the real - time load and prediction results;

[0104] Secondly, according to the results of the particle swarm optimization, adjust the switch state or load distribution of the device to reduce the total energy consumption. For example, for devices with low load, consider putting them into sleep or reducing the load, and give priority to using high - performance devices to reduce the overall energy consumption.

[0105] In this embodiment, specifically, it should be noted that the energy management decision - making and scheduling module displays the clustering analysis results, energy - efficiency patterns, and potential waste points through charts, generates an intuitive report. The charts include bar charts, pie charts, and scatter plots. Based on the clustering results, specific optimization suggestions are put forward, including equipment replacement, scheduling optimization, and regular maintenance, and a long - term plan for energy - efficiency improvement is formulated and gradually implemented to optimize energy use and conservation. The management layer adjusts the energy management strategy according to the analysis results and formulates future energy - saving goals and policies;

[0106] The specific methods of intelligent scheduling include:

[0107] 1), Combine the production plan, equipment status, and energy consumption prediction results to perform energy scheduling. During peak power demand, preferentially schedule energy-saving equipment, or adjust the production process as needed to reduce unnecessary energy consumption;

[0108] 2), Dynamically adjust the switch status or load distribution of equipment based on real-time load, prediction trends, and equipment status. When there is a high energy consumption risk, adjust the production process or replace inefficient equipment.

[0109] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0110] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0112] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, causing a series of operational steps to be performed on the computer or other programmable apparatus to generate a computer implemented process, such that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for implementing the functions specified in one block or a plurality of blocks.

[0114] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0115] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A smart energy digital management system applied to a cloud platform, characterized in that: Specifically include: Data acquisition module, data storage and preprocessing module, data analysis and optimization module, and energy management decision and scheduling module; Data acquisition module: Sensor components are installed at various production links and energy consumption nodes to monitor energy consumption data in real time, and the acquired energy consumption data is transmitted to the data center of the cloud platform in real time through the Internet of Things technology for centralized storage and processing; Data storage and preprocessing module: After receiving the energy consumption data transmitted by the data acquisition module, a distributed database is used to store the massive data. At the same time, the energy consumption data is cleaned and denoised, abnormal values ​​and erroneous data are removed, and the preprocessed data is processed through data standardization methods; Data analysis and optimization module: Use big data analysis methods to combine energy consumption data for cluster analysis, explore potential energy waste patterns and optimization potential, generate cluster analysis results, use historical energy consumption data and ARIMA forecasting models to generate forecast results, predict energy consumption trends in the future, provide early warning mechanisms for enterprises, and use the objective function of the particle swarm optimization algorithm to optimize energy scheduling; Energy management decision-making and scheduling module: Use the energy management system EMS to monitor the consumption of various energy sources in real time, generate energy consumption reports and energy consumption rankings, identify high-energy consumption links, and provide intelligent decision-making support for management based on cluster analysis results. Combined with production plans, equipment operating status and forecast results, intelligent energy scheduling is carried out to optimize production plans and equipment scheduling strategies.

2. The smart energy digital management system applied to the cloud platform according to claim 1 is characterized in that: The energy consumption nodes in the data acquisition module include electricity, water and gas; the sensor components include current sensors, voltage sensors, temperature sensors, pressure sensors and flow sensors.

3. The smart energy digital management system applied to the cloud platform according to claim 2 is characterized in that: In the data storage and preprocessing module, the data standardization calculation formula is: Among them, Z represents the standardized data, X represents the original energy consumption data, represents the mean of the original energy consumption data, represents the standard deviation of the original energy consumption data, X i represents each data point, and N represents the total number of data points.

4. The smart energy digital management system applied to the cloud platform according to claim 3 is characterized by: The specific steps of cluster analysis in the data analysis and optimization module are: S1. Use K-means clustering to analyze and divide each production link and energy consumption node into different clusters according to energy consumption characteristics, and select key features related to energy consumption, including equipment type, operating time, load level, and production output; S2. Use the elbow rule to determine the K value. The specific steps are: 1) Calculate the total sum of squares of error SSE for different K values ​​(such as K = 2, 3, 4, ...). 2) Plot the SSE versus K value and find the "elbow" of the curve, where the SSE decreases slowly, as the optimal cluster number K; S3. Use K-means algorithm to cluster energy consumption data: 1) Initialize the center points (centers of mass) of K clusters, usually by randomly selecting data points as the initial centers; 2) Calculate the distance from each data point to all centroids and assign it to the cluster with the shortest distance; 3) Update the centroid of each cluster to the mean of all points in the cluster; 4) Repeat the above steps until the centroid no longer changes or the maximum number of iterations is reached; S4. Use principal component analysis (PCA) to reduce the dimension of the clustering results to two dimensions and check the distribution of different clusters. S5. Analyze each cluster and check its characteristic values, including average energy consumption and volatility, identify clusters with higher energy consumption, compare energy consumption differences between different clusters, and determine which clusters have poor energy efficiency; S6. Identify energy waste patterns 1) High energy consumption cluster: For clusters with high energy consumption, further check whether there is equipment aging, low efficiency or improper operation; 2) Volatility clusters: For clusters with large energy consumption fluctuations, analyze whether there are equipment failures, overuse, or unreasonable work scheduling; 3) Time characteristics: Analyze the energy consumption differences of different clusters in specific time periods to find out unnecessary energy waste. Specific time periods include production peaks and seasonal changes; S7. Exploring optimization potential 1) Conduct in-depth analysis of high-energy consumption clusters to see if there is room for technical improvement, including replacing equipment and optimizing operating methods; 2) Analyze the reasons for low equipment utilization efficiency and consider whether it is necessary to upgrade the equipment or adjust the usage strategy. 3) Identify energy waste during peak production periods and recommend optimizing production scheduling to reduce unnecessary energy consumption S8. Develop optimization plan 1) Equipment optimization: For equipment with poor energy efficiency, it is recommended to upgrade or replace the technology, and determine which equipment has the greatest impact on total energy consumption through data analysis. 2) Scheduling optimization: According to the results of cluster analysis, adjust the operation time of production or equipment to reduce high energy consumption periods. 3) Regular maintenance: For equipment that frequently consumes high energy, formulate regular inspection and maintenance plans to ensure that the equipment is always in optimal operating condition.

5. The smart energy digital management system applied to the cloud platform according to claim 4 is characterized in that: In the data analysis and optimization module, the prediction formula of the ARIMA prediction model is: [Y t =μ+φ1Y t-1 +φ2Y t-2 +...+e t ] Among them, Y t represents the predicted value at time t, μ represents the constant term, (φ1, φ2) represents the model coefficient, ε t represents the error term at the current time point, Y t-1 Represents the value at time t-1 in the time series.

6. The smart energy digital management system applied to the cloud platform according to claim 5 is characterized in that: Specifically, the early warning mechanism is as follows: according to the prediction results, an early warning threshold of energy consumption is set. If the energy consumption is expected to exceed a certain percentage of the historical average level within a certain period of time, the system will automatically trigger an alarm. When the alarm is triggered, the management will be notified to take measures to deal with the abnormal high energy consumption, including adjusting the production plan and optimizing equipment scheduling.

7. The smart energy digital management system applied to the cloud platform according to claim 6 is characterized by: The objective function formula of the particle swarm optimization algorithm is: Among them, E i Represents the energy consumption of each device, E opt represents the target energy consumption after optimization, and n represents the total number of devices.

8. The smart energy digital management system applied to the cloud platform according to claim 7 is characterized in that: The particle swarm optimization algorithm continuously updates the scheduling plan through multiple iterations and finally finds the optimal energy consumption scheduling strategy, including: 1) During periods of high power demand, low-energy consumption equipment is prioritized; 2) Dynamically adjust the operating status of the equipment according to the real-time load and forecast results; Secondly, according to the results of particle swarm optimization, the switching state or load distribution of the equipment is adjusted to reduce the total energy consumption.

9. The smart energy digital management system applied to the cloud platform according to claim 8 is characterized in that: In the energy management decision and scheduling module, cluster analysis results, energy efficiency patterns and potential waste points are displayed in charts to generate intuitive reports, and specific optimization suggestions are made based on the clustering results, including equipment replacement, scheduling optimization and regular maintenance.

10. The smart energy digital management system applied to the cloud platform according to claim 9 is characterized in that: Specific methods of intelligent scheduling include: 1) Combine production plan, equipment status and energy consumption forecast results to carry out energy dispatch. When power demand peaks, energy-saving equipment will be dispatched first, or production processes will be adjusted as needed to reduce unnecessary energy consumption. 2) Dynamically adjust the switch status or load distribution of the equipment according to the real-time load, predicted trend and equipment status. When there is a risk of high energy consumption, adjust the production process or replace inefficient equipment.

Images