A method for constructing an EMS system based on modular chocolate design

Abstract

The invention discloses a method for constructing an EMS system of chocolate modular design, and relates to the technical field of chocolate modular design EMS system. The method comprises collecting power data and energy consumption data of load equipment and preprocessing them to obtain an energy data set; constructing an anomaly detection model based on an isolation forest algorithm, inputting the energy data set into the anomaly detection model, and outputting anomaly values ​​of the energy data set; setting a threshold value based on the energy data set, filtering out anomaly values ​​of the energy data set that are less than the threshold value, and obtaining a verified energy data set; constructing an energy consumption prediction model based on a machine learning algorithm, inputting the verified energy data set into the energy consumption prediction model, and outputting an energy consumption prediction value; calculating the power supply during peak hours and valley hours in the energy consumption process, optimizing the charging and discharging time of a battery of a load equipment according to the power supply, and obtaining a power distribution strategy.

Description

Technical Field

[0001] The invention relates to the technical field of chocolate modular design EMS system, in particular to a chocolate modular design EMS system construction method. Background Art

[0002] The chocolate modular designed EMS system refers to a specially designed energy management system. The system adopts a modular design concept, so that its various functional units can be flexibly combined, replaced or expanded like "chocolate blocks". The design method allows the system to be customized according to actual needs, increasing the flexibility and adaptability of the system.

[0003] However, in the existing energy management system, due to the lack of effective data collection and preprocessing mechanisms, the data used for analysis often contains noise and outliers, which not only affects the accuracy of subsequent models and easily misleads decision-making, but also the previous energy consumption prediction models cannot fully consider the long-term dependence characteristics in time series data, resulting in inaccurate prediction results. Secondly, the traditional power management method lacks a scientific and reasonable power distribution strategy, resulting in energy waste or insufficient supply. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an EMS system construction method with a chocolate modular design to solve the problem in the existing energy management system that, due to the lack of effective data collection and preprocessing mechanisms, the data used for analysis often contains noise and outliers, which not only affects the accuracy of subsequent models but also easily misleads decision-making.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for constructing an EMS system of chocolate modular design, comprising:

[0008] Collect and pre-process the power data and energy consumption data of the load equipment to obtain an energy data set;

[0009] An anomaly detection model is constructed based on the isolation forest algorithm, the energy data set is input into the anomaly detection model, and the outlier values ​​of the energy data set are output;

[0010] A threshold is set based on the energy data set, and outliers of the energy data set that are smaller than the threshold are filtered out to obtain a verified energy data set;

[0011] Building an energy consumption prediction model based on machine learning algorithms, inputting the verified energy data set into the energy consumption prediction model, and outputting the energy consumption prediction value;

[0012] Calculate the power supply during peak and off-peak periods of energy consumption, optimize the charging and discharging time of the load equipment battery according to the power supply, and obtain the power distribution strategy;

[0013] Design modular functional units and integrate unified communication protocols to obtain functional module designs with standardized interface connections.

[0014] As a preferred solution of the chocolate modular design EMS system construction method of the present invention, wherein: the power data and energy consumption data of the load device are collected and preprocessed to obtain the energy data set, and the specific steps are:

[0015] The energy consumption data refers to the electricity consumption of the load equipment;

[0016] The preprocessing includes data cleaning, normalization and smoothing;

[0017] The preprocessed power data and energy consumption data are collected as energy data set D.

[0018] As a preferred solution of the chocolate modular design EMS system construction method of the present invention, wherein: the anomaly detection model is constructed based on the isolation forest algorithm, the energy data set is input into the anomaly detection model, and the anomaly value of the energy data set is output. The specific steps are:

[0019] The isolation forest algorithm is used as the basic model of the anomaly detection model;

[0020] Randomly extract a sample subset of size μ from the energy data set D, construct multiple single isolated trees, and combine multiple single isolated trees into an anomaly detection model;

[0021] Input the energy data set D into each isolated tree, and obtain the path length of the energy data set D on each isolated tree;

[0022] Based on the path length of the energy dataset D on each isolated tree, the anomaly score Q of the energy dataset D is calculated.

[0023] As a preferred solution of the EMS system construction method for chocolate modular design of the present invention, wherein: the threshold is set based on the energy data set, and outliers of the energy data set less than the threshold are filtered out to obtain the verified energy data set. The specific steps are:

[0024] Based on the distribution of anomaly scores of the energy dataset D, a threshold q is set;

[0025] When the anomaly score Q of the energy dataset D is less than the threshold q, the energy dataset D is abnormal, and the anomaly score Q of the energy dataset D is an abnormal value;

[0026] The outliers smaller than the threshold q are filtered out to obtain the verified energy dataset A.

[0027] As a preferred solution of the EMS system construction method for chocolate modular design of the present invention, wherein: the energy consumption prediction model is constructed based on the machine learning algorithm and the verified energy data set, the verified energy data set is input into the energy consumption prediction model, and the energy consumption prediction value is output, the specific steps are:

[0028] The long short-term memory network LSTM is used to build the energy consumption prediction model M;

[0029] The verified data set A is input into the energy consumption prediction model M, and the energy consumption prediction value is output.

[0030] As a preferred solution of the EMS system construction method of the chocolate modular design of the present invention, wherein: based on the energy consumption prediction value, the power supply during the peak period and the valley period of the energy consumption process is calculated, and the specific steps are:

[0031] Based on the energy consumption forecast value P, the power forecast value for each time period t is defined as ;

[0032] Use the power forecast value for each time period t , calculate the total electricity consumption during peak and off-peak hours.

[0033] As a preferred solution of the chocolate modular design EMS system construction method of the present invention, wherein: the charging and discharging time of the battery is optimized according to the power supply to obtain the power distribution strategy, the specific steps are:

[0034] Based on total electricity consumption during peak hours Total power consumption during off-peak hours Calculate the maximum capacity of the load device battery and maximum charge and discharge rate ;

[0035] Using linear programming algorithm Determine the optimal power distribution strategy.

[0036] As a preferred solution of the chocolate modular design EMS system construction method of the present invention, wherein: based on the power distribution strategy, modular functional units are designed, and a unified communication protocol is integrated to obtain a functional module design with standardized interface connection, the specific steps are:

[0037] Obtaining a power distribution plan from the optimal power distribution strategy S;

[0038] Configure energy management module, data acquisition and monitoring module and communication module;

[0039] Define the energy management module, data acquisition and monitoring module, and communication module according to the optimal power distribution strategy S;

[0040] The energy management module is used to control the logic to execute the charging and discharging operations in the power distribution strategy;

[0041] The data acquisition and monitoring module is used to configure sensors and monitoring equipment to collect system operation data;

[0042] The communication module is used to integrate the unified communication protocol Modbus and maintain wireless communication between various modules.

[0043] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for constructing an EMS system for modular design of chocolate as described in the first aspect of the present invention is implemented.

[0044] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for constructing an EMS system for modular design of chocolate as described in the first aspect of the present invention is implemented.

[0045] The beneficial effects of the present invention are as follows: by installing power sensors and high-precision smart meters on load devices to collect power data and its corresponding energy consumption data, and combining the data into time series data, comprehensive monitoring of the energy consumption of load devices is achieved; an anomaly detection model is constructed using the isolation forest algorithm, and applied to the preprocessed energy data set, outliers in the data can be efficiently identified; a reasonable threshold is set based on the anomaly score output by the isolation forest algorithm, outliers are filtered out to obtain a more accurate energy data set, and extreme anomalies that mislead subsequent analysis are effectively removed, ensuring the data quality used to train machine learning models; an energy consumption prediction model is constructed based on the verified energy data set using a long short-term memory network machine learning algorithm; the LSTM model can well capture the long-term dependencies in time series data, which is crucial for predicting power demand during peak and trough periods, and provides a powerful tool to predict future power consumption patterns, thereby helping to formulate more scientific and reasonable battery charging and discharging plans, achieving the purpose of optimizing energy efficiency, while also reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0047] Figure 1 Flow chart of the EMS system construction method for chocolate modular design in Example 1.

[0048] Figure 2 This is a flow chart of the energy data set in Example 1. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0052] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for constructing an EMS system with a modular design of chocolate, comprising the following steps:

[0053] S1, collect power data and energy consumption data of load equipment and pre-process them to obtain energy data set;

[0054] Furthermore, energy consumption data refers to the electricity consumption of load equipment;

[0055] Preprocessing includes data cleaning, normalization and smoothing;

[0056] Install power sensors on load devices to collect their power data during operation, and use high-precision smart meters to monitor the power usage of load devices and record the total energy consumption per hour as energy consumption data corresponding to the power data;

[0057] The power data and the energy consumption data corresponding to the power data are collected as time series data W;

[0058] Perform data cleaning on time series data and remove obvious outliers;

[0059] The Min-Max normalization method is used to normalize the time series data after data cleaning. The expression is:

[0060] ;

[0061] in, and are the minimum and maximum values ​​in the time series data W, is the normalized time series data;

[0062] The normalized time series data is smoothed using the moving average method. The expression is:

[0063] ;

[0064] Among them, ε represents the position index in the time series, is the time series data after smoothing at time point t, N is the size of the moving average window, is the index variable, For time point The normalized data value;

[0065] The pre-processed power data and energy consumption data are collected as an energy data set D;

[0066] It should be noted that the energy dataset obtained by the above method not only effectively removes noise and outliers, but also undergoes normalization and smoothing, making the energy dataset more suitable for the input of subsequent analysis models. The preprocessing method improves the quality of the energy dataset and enhances the accuracy and reliability of subsequent anomaly detection model and energy consumption prediction model training.

[0067] S2. Build an anomaly detection model based on the isolation forest algorithm, input the energy data set into the anomaly detection model, and output the anomaly value of the energy data set;

[0068] Furthermore, the isolation forest algorithm is used as the base model of the anomaly detection model;

[0069] Randomly extract a sample subset of size μ from the energy data set D, construct multiple single isolated trees, and combine multiple single isolated trees into an anomaly detection model. The expression is:

[0070] ;

[0071] in, A sample subset of size μ is randomly selected from the energy dataset D. An isolation tree constructed for a subset of samples, It represents the process of constructing multiple isolation trees and generating multiple isolation trees. F is the anomaly detection model;

[0072] Input the energy data set D into each isolated tree, and obtain the path length of the energy data set D on each isolated tree;

[0073] Based on the path length of the energy dataset D on each isolated tree, the anomaly score Q of the energy dataset D is calculated, and the expression is:

[0074] ;

[0075] Where N is the number of data points in the energy dataset D, represents the sum of the path lengths in the energy dataset D, Q is the anomaly score of the energy dataset D, L is the loss function, and T is the true value corresponding to the energy dataset D;

[0076] It should be noted that the anomaly detection model built based on the isolation forest algorithm can efficiently identify outliers in energy data sets. The algorithm does not need to define the specific form of the anomaly and is suitable for anomaly detection tasks in high-dimensional data sets, thereby ensuring the data purity of the subsequent energy consumption prediction model.

[0077] S3, setting a threshold based on the energy data set, filtering out abnormal values ​​of the energy data set that are less than the threshold, and obtaining a verified energy data set;

[0078] Furthermore, based on the distribution of anomaly scores of the energy dataset D, a threshold q is set;

[0079] When the anomaly score Q of the energy dataset D is less than the threshold q, the energy dataset D is abnormal, and the anomaly score Q of the energy dataset D is an abnormal value;

[0080] Filter out the outliers that are smaller than the threshold q to obtain the verified energy dataset A;

[0081] It should be noted that in the process of setting thresholds to filter outliers, various interference factors encountered in actual application scenarios are taken into account to ensure that the verified energy dataset retains key information and excludes irrelevant noise. This step is crucial to improving the prediction accuracy of the energy consumption prediction model.

[0082] S4. construct an energy consumption prediction model based on the machine learning algorithm and the verified energy data set, input the verified energy data set into the energy consumption prediction model, and output the energy consumption prediction value;

[0083] Furthermore, the long short-term memory network LSTM is used to construct the energy consumption prediction model M;

[0084] The verified data set A is input into the energy consumption prediction model M, and the energy consumption prediction value is output. The expression is:

[0085] ;

[0086] ;

[0087] Among them, LSTM is a long short-term memory network framework, LSTM(A) means using the verified energy dataset A to build an energy consumption prediction model, M is the energy consumption prediction model, is the energy consumption prediction function, P is the predicted energy consumption value, and A is the verified energy dataset;

[0088] It should be noted that when using the LSTM model to predict energy consumption, the long-term dependency characteristics of time series data are taken into account, making the prediction results closer to the actual situation. In addition, by calculating the total power consumption during peak and off-peak hours, it can provide accurate data support for the energy management of load equipment and optimize the battery charging and discharging strategy.

[0089] S5. Based on the predicted value of energy consumption, calculate the power supply during peak and valley periods of energy consumption, optimize the charging and discharging time of the battery of the load device according to the power supply, and obtain the power distribution strategy;

[0090] Furthermore, based on the total electricity consumption during peak hours Total power consumption during off-peak hours Calculate the maximum capacity of the load device battery and maximum charge and discharge rate , the expression is:

[0091] ;

[0092] ;

[0093] Among them, α and β are adjustment coefficients, Indicates the length of peak hours;

[0094] Using linear programming algorithm Determine the optimal power allocation strategy, the expression is:

[0095] ;

[0096] Among them, S is the optimal power allocation strategy, is a linear programming algorithm, is the maximum capacity of the load device battery, is the maximum charge and discharge rate of the load device;

[0097] Based on the energy consumption forecast value P, the power forecast value for each time period t is defined as ;

[0098] Use the power forecast value for each time period t , calculate the total power consumption during peak hours and off-peak hours, the expression is:

[0099]

[0100]

[0101] in, is the total electricity consumption during peak hours, To traverse all time points belonging to the peak period, To traverse all the time points belonging to the trough period, is the total electricity consumption during the off-peak period;

[0102] It should be noted that calculating the maximum capacity and maximum charge and discharge rate of the battery based on power consumption during peak and off-peak hours is a key step in realizing an intelligent energy management system. Using a linear programming algorithm to solve the optimal power distribution strategy can minimize costs while meeting system performance requirements, further improving the economy and sustainability of the system.

[0103] S6. Based on the power distribution strategy, design modular functional units and integrate unified communication protocols to obtain functional module designs with standardized interface connections;

[0104] Furthermore, a power distribution plan is obtained from the optimal power distribution strategy S;

[0105] Introducing the time variable Represents the battery charge and discharge amount at each time point t:

[0106] ;

[0107] Use a linear programming solver to solve the time variable Solve and get the solution result , and based on the solution results Develop electricity distribution plans;

[0108] when >0, it indicates that the battery is charged at time point t, and the charging amount is ;

[0109] when When <0, it indicates that the battery is discharged at time point t, and the discharge amount is ;

[0110] when =0, the state remains unchanged;

[0111] Configure energy management module, data acquisition and monitoring module and communication module;

[0112] Define the energy management module, data acquisition and monitoring module, and communication module according to the optimal power distribution strategy S;

[0113] An energy management module for controlling logic to perform charging and discharging operations in a power distribution strategy;

[0114] Data acquisition and monitoring module, used to configure sensors and monitoring equipment to collect system operation data;

[0115] Communication module, used to integrate the unified communication protocol Modbus and maintain wireless communication between various modules;

[0116] It should be noted that in the process of designing modular functional units and integrating the unified communication protocol Modbus, seamless collaboration between the functional modules is ensured, precise control of battery charging and discharging operations and real-time monitoring of system operation data are achieved, which not only improves the reliability and stability of the system, but also provides convenient conditions for future expansion.

[0117] This embodiment also provides a computer device, which is suitable for the EMS system construction method of chocolate modular design, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the EMS system construction method of chocolate modular design proposed in the above embodiment.

[0118] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0119] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the EMS system construction method for realizing chocolate modular design proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0120] In summary, the present invention collects power data and its corresponding energy consumption data by installing power sensors and high-precision smart meters on load devices, and combines the data into time series data, thereby realizing comprehensive monitoring of the energy consumption of load devices. An anomaly detection model is constructed using the isolation forest algorithm, and is applied to the preprocessed energy data set, so that outliers in the data can be efficiently identified. A reasonable threshold is set based on the anomaly score output by the isolation forest algorithm, and outliers are filtered out to obtain a more accurate energy data set, effectively removing extreme anomalies that mislead subsequent analysis, thereby ensuring the data quality used to train machine learning models, and using the long short-term memory network machine learning algorithm to construct an energy consumption prediction model based on the verified energy data set. The LSTM model can well capture the long-term dependencies in time series data, which is crucial for predicting electricity demand during peak and trough periods, and provides a powerful tool to predict future electricity consumption patterns, thereby helping to formulate more scientific and reasonable battery charging and discharging plans, thereby achieving the purpose of optimizing energy utilization efficiency, while also reducing operating costs.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing an EMS system for modular chocolate design, characterized in that: include: Collect and pre-process the power data and energy consumption data of the load equipment to obtain an energy data set; An anomaly detection model is constructed based on the isolation forest algorithm, the energy data set is input into the anomaly detection model, and the outlier values ​​of the energy data set are output; A threshold is set based on the energy data set, and outliers of the energy data set that are smaller than the threshold are filtered out to obtain a verified energy data set; Building an energy consumption prediction model based on machine learning algorithms, inputting the verified energy data set into the energy consumption prediction model, and outputting the energy consumption prediction value; Calculate the power supply during peak and off-peak periods of energy consumption, optimize the charging and discharging time of the load equipment battery according to the power supply, and obtain the power distribution strategy; Design modular functional units and integrate unified communication protocols to obtain functional module designs with standardized interface connections; The energy consumption prediction model is constructed based on the machine learning algorithm and the verified energy data set, the verified energy data set is input into the energy consumption prediction model, and the energy consumption prediction value is output. The specific steps are as follows: Using long short-term memory network LSTM to build energy consumption prediction model ; The validated dataset Input to energy consumption prediction model , output the predicted value of energy consumption; The modular functional unit is designed based on the power distribution strategy, and a unified communication protocol is integrated to obtain a functional module design with standardized interface connection. The specific steps are as follows: From the optimal power distribution strategy Obtain power distribution plan from Configure energy management module, data acquisition and monitoring module and communication module; According to the optimal power distribution strategy Define energy management module, data acquisition and monitoring module, and communication module; The energy management module is used to control the logic to execute the charging and discharging operations in the power distribution strategy; The data acquisition and monitoring module is used to configure sensors and monitoring equipment to collect system operation data; The communication module is used to integrate the unified communication protocol Modbus and maintain wireless communication between various modules.

2. The method for constructing an EMS system for modular design of chocolate according to claim 1, characterized in that: The power data and energy consumption data of the load device are collected and preprocessed to obtain an energy data set. The specific steps are as follows: The energy consumption data refers to the electricity consumption of the load equipment; The preprocessing includes data cleaning, normalization and smoothing; The pre-processed power data and energy consumption data are combined into an energy data set .

3. The method for constructing an EMS system for modular design of chocolate according to claim 2, characterized in that: The anomaly detection model is constructed based on the isolation forest algorithm, the energy data set is input into the anomaly detection model, and the anomaly value of the energy data set is output. The specific steps are as follows: The isolation forest algorithm is used as the basic model of the anomaly detection model; From the energy dataset The random sampling size is , construct multiple single isolated trees, and combine multiple single isolated trees into an anomaly detection model; Energy Dataset Input into each isolated tree and get the energy dataset The path length on each isolated tree; Based on energy dataset The path length on each isolated tree is calculated for the energy dataset Anomaly score .

4. The method for constructing an EMS system for modular design of chocolate according to claim 3, characterized in that: The specific steps of setting a threshold based on the energy data set, filtering out abnormal values ​​of the energy data set that are less than the threshold, and obtaining a verified energy data set are as follows: Based on energy dataset The distribution of anomaly scores, setting the threshold ; When the energy data set Less than threshold Energy Dataset If it is abnormal, then the energy dataset It is an outlier; Filter out the values ​​less than the threshold The outliers are obtained to obtain the verified energy data set .

5. The method for constructing an EMS system for modular design of chocolate according to claim 4, characterized in that: The specific steps of calculating the power supply during peak and valley periods of energy consumption based on the predicted energy consumption value are as follows: Based on energy consumption forecast , define each time period The power forecast value is ; Use each time period Electricity forecast value , calculate the total electricity consumption during peak and off-peak hours.

6. The method for constructing an EMS system for modular design of chocolate according to claim 5, characterized in that: The specific steps of optimizing the charging and discharging time of the battery according to the power supply to obtain the power distribution strategy are as follows: Based on total electricity consumption during peak hours Total power consumption during off-peak hours Calculate the maximum capacity of the load device battery and maximum charge and discharge rate ; Using linear programming algorithm Determine the optimal power distribution strategy.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the EMS system construction method for chocolate modular design according to any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the EMS system construction method for chocolate modular design according to any one of claims 1 to 6 are implemented.

Images