Wireless bandwidth control method and system for microgrid intelligent grid connection

Abstract

The present invention relates to the technical field of microgrid node bandwidth control, and discloses a wireless bandwidth control method and system for microgrid intelligent grid connection, comprising collecting power parameters and bandwidth data of microgrid grid-connected nodes, analyzing the power parameters and bandwidth data of the grid-connected nodes, obtaining analysis results, optimizing node power anomalies and optimizing node bandwidth through the analysis results, real-time monitoring of wireless communication environment, adaptively adjusting transmission power and signal frequency, selecting an optimal path for information communication, adjusting energy supply and allocation according to load changes, optimizing node bandwidth through wireless communication feedback, regulating bandwidth, realizing dynamic bandwidth allocation, ensuring that the network can still operate stably under high load, and adjusting bandwidth in real time according to network load and priority.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrid node bandwidth control, and discloses a wireless bandwidth control method and system for microgrid intelligent grid connection. Background Art

[0002] The bandwidth of existing wireless communication technologies is often insufficient to meet the needs of microgrids under high load or multi-user conditions. In application scenarios with intensive data transmission, the delay of wireless networks may affect the effectiveness of real-time monitoring and control. When power dispatch and load balancing require rapid response, wireless signals are susceptible to environmental interference, resulting in unstable signals and affecting the reliability of data transmission. In densely populated urban areas or industrial areas, wireless communications face greater security risks, including data theft and malicious attacks. Ensuring communication security is an important challenge. High-performance wireless communication equipment and technologies are usually costly, which limits their application in some small-scale microgrids. The standards and protocols for wireless bandwidth regulation have not yet been unified, resulting in poor interoperability between different devices and systems. In some cases, the energy consumption of wireless communications is high, affecting the overall energy efficiency and sustainability of the microgrid.

[0003] The dynamic coupling interaction between the power electronic interface devices and the grid passive components in the microgrid will span a certain frequency range, namely the bandwidth. When the bandwidth is not set properly, resonance may occur. For example, when the bandwidth is too large, the effect at the resonance frequency may be weakened, affecting the stability of the system; when the bandwidth is too small, if the grid frequency is offset, it may cause errors due to the small amplitude, which is also not conducive to system stability.

[0004] For example, a Chinese patent with publication number CN118174463A discloses a microgrid distributed event-triggered secondary control method and device based on unidirectional communication, the method includes: obtaining the real-time state variable value of each power supply end-side node; calculating the local error value and the global error value according to the real-time state variable value of each power supply end-side node, the state variable value sent out by each power supply end-side node during the most recent communication, and the state variable value sent by the most recent neighboring power supply end-side node; calculating the event trigger result according to the local error value and the global error, and judging whether the secondary control condition is met according to the result; if the secondary control condition is met, the data is communicated unidirectionally; otherwise, no communication is performed. This application introduces an event trigger mechanism, which only communicates and controls when needed, effectively avoiding the waste of communication resources; in addition, the use of a unidirectional directional communication method reduces the demand for communication bandwidth and improves the reliability and stability of the system.

[0005] The main direction of the above patent is to identify and adjust secondary control, but not many control methods are proposed for the communication bandwidth, and energy optimization and communication optimization are not integrated, which increases the communication time and grid-connected energy loss. The expandable modules are not integrated, resulting in low scalability of the microgrid. Summary of the invention

[0006] In order to solve the above technical problems, the main purpose of the present invention is to provide a wireless bandwidth control method for microgrid intelligent grid connection, including:

[0007] S1. Collect power parameters and bandwidth data of microgrid grid-connected nodes, analyze power parameters and bandwidth data of grid-connected nodes, and obtain analysis results;

[0008] S2. Optimize node power anomalies and optimize node bandwidth through analysis results;

[0009] S3, real-time monitoring of the wireless communication environment, adaptive adjustment of the transmission power and signal frequency, and selection of the optimal path for information communication;

[0010] S4. Adjust energy supply and allocation according to load changes, and optimize node bandwidth through wireless communication feedback to regulate bandwidth.

[0011] As a preferred solution of the wireless bandwidth control method for microgrid intelligent grid connection of the present invention, wherein:

[0012] The grid-connected node power parameter analysis method comprises:

[0013] S1011, cleaning the power parameters of the microgrid grid-connected nodes, removing noise and abnormal values, and correcting sensor errors, and storing them in a database;

[0014] S1012. Establish a power prediction model to make short-term predictions on power parameters of future grid-connected nodes;

[0015] S1013, establishing a power anomaly model and an unknown anomaly detection model, and analyzing power parameters of grid-connected nodes;

[0016] S1014. Optimize the prediction values ​​of the power anomaly model and the unknown anomaly detection model by optimizing the correction unit.

[0017] As a preferred solution of the wireless bandwidth control method for microgrid intelligent grid connection of the present invention, wherein:

[0018] Establishing the power anomaly model, firstly, establishing a time series prediction model of the power parameters of the grid-connected node through an autoregressive integrated moving average model, outputting the power prediction value from the time series prediction model, then calculating the residual between the power prediction value and the actual observed value, and finally calculating the interquartile range of each residual, and setting the lower limit and upper limit, and the residual beyond the range is regarded as abnormal;

[0019] The time series prediction model calculation expression is as follows:

[0020] ;

[0021] in, is the predicted value at time t, is a constant, is the autoregressive coefficient of the power parameter at the first moment, is the power parameter at the first moment, is the moving average coefficient of the power parameter at the first moment, is the white noise error term of the power parameters at the first moment, is the white noise error term, p is the number of autoregressive terms, and q is the number of moving average terms.

[0022] As a preferred solution of the wireless bandwidth control method for microgrid intelligent grid connection of the present invention, wherein:

[0023] Bandwidth data analysis methods include:

[0024] S1021. Clean the collected bandwidth data, remove invalid records, and aggregate the data by timestamp;

[0025] S1022. Calculate the total flow, average flow and peak flow of each day, and establish a flow time series set;

[0026] S1023, establishing a bandwidth data prediction model, and reducing the spatial dimension of the feature map through a pooling layer, while extracting important information of the bandwidth data;

[0027] S1024, flattening the pooled feature map through full connection and mapping it to the output layer;

[0028] S1025. Analyze the bandwidth by outputting a predicted value through a bandwidth data prediction model.

[0029] As a preferred solution of the wireless bandwidth control method for microgrid intelligent grid connection of the present invention, wherein:

[0030] The bandwidth data prediction model calculation expression is as follows:

[0031] ;

[0032] Among them, F[*] is the activation function, is a subsequence of the input bandwidth data time series, is the weight, is the bias value, j is the convolution layer count, is the j-th layer weight, is the j-th layer bias value, and n is the total number of layers of the bandwidth data prediction model;

[0033] The pooling layer includes the pooling window step and the pooling window size;

[0034] The loss between the predicted value and the actual value is fitted through the loss function and fed back to the bandwidth data prediction model to optimize the training of the bandwidth data prediction model.

[0035] As a preferred solution of the wireless bandwidth control method for microgrid intelligent grid connection of the present invention, wherein:

[0036] Methods for optimizing node bandwidth include:

[0037] S201, setting the bandwidth weights of the grid-connected nodes, and sorting the bandwidth weights of the grid-connected nodes by priority selection;

[0038] S202. If the bandwidth of an important node is abnormal, increase the bandwidth allocation of the node, enable the backup communication link, and optimize the data transmission protocol to ensure the timely transmission of key data and the stable operation of the microgrid. If the bandwidth of an ordinary node is abnormal, mark the abnormal node and optimize the data transmission strategy.

[0039] Bandwidth anomalies include excessive bandwidth utilization, increased latency, and increased packet loss rate;

[0040] S203, implementing a bandwidth resource dynamic scheduling strategy and dynamically adjusting bandwidth allocation by receiving a bandwidth data prediction model output bandwidth prediction value;

[0041] S204: Feedback the bandwidth dynamic adjustment result to the bandwidth data prediction model, and predict the bandwidth data at the next moment.

[0042] As a preferred solution of the wireless bandwidth control method for microgrid intelligent grid connection of the present invention, wherein:

[0043] The wireless communication environment includes interference information and load information;

[0044] Pre-process the collected interference information and load information to remove noise and outliers;

[0045] Model the processed data through machine learning algorithms to predict interference conditions and the signal-to-noise ratio at the receiving end;

[0046] By predicting the interference situation and the signal-to-noise ratio of the receiving end, the transmission power is dynamically adjusted. If the interference is greater than the preset maximum interference threshold, the frequency band power is reduced to reduce interference. If the frequency band is clear, the power is increased to enhance the signal.

[0047] A path frequency is calculated by spectrum analysis, and frequency communication is selected by the calculated path frequency.

[0048] As a preferred solution of the wireless bandwidth control method for microgrid intelligent grid connection of the present invention, wherein:

[0049] Through path evaluation and path selection, the optimal path is selected for communication, and a redundant buffer is set for the communication path to perform redundant backup of the communication path;

[0050] Calculating a comprehensive evaluation value for each path through the path priority function;

[0051] The path priority function evaluates the utility obtained by the communication signal from the propagation of the path by setting the path satisfaction coefficient, and prioritizes the paths according to the utility, and the paths with higher priority have higher corresponding comprehensive evaluation values;

[0052] The path with the best comprehensive evaluation value is selected as the current communication path. If the best path changes, re-evaluation and selection are performed.

[0053] Wireless bandwidth control system for microgrid intelligent grid connection, including:

[0054] A node detection module, including a data acquisition unit for collecting power parameters of microgrid grid-connected nodes and an anomaly detection unit for node power anomaly analysis;

[0055] A bandwidth adjustment module, including a bandwidth data unit, a bandwidth analysis unit, a decision unit and a bandwidth adjustment unit;

[0056] A communication module, comprising an interference processing unit and a multi-path optimization unit, wherein the interference processing unit is used to adaptively adjust the transmission power and signal frequency, and the multi-path optimization unit is used to compare and select the optimal communication path among multiple communication paths;

[0057] Energy management module, used to manage the internal power supply of the microgrid;

[0058] An expansion module, used for providing an expansion port;

[0059] The user interface module includes a data visualization unit and a user operation unit, wherein the data visualization unit is used to display an intuitive and easy-to-use graphical interface to display the microgrid node bandwidth, energy operation status and communication performance indicators, and the user operation unit is used for users to manually adjust the bandwidth.

[0060] As a preferred solution of the wireless bandwidth control system for microgrid intelligent grid connection of the present invention, wherein:

[0061] The bandwidth data unit is used to collect microgrid node bandwidth data, the bandwidth analysis unit is used to analyze the collected microgrid node bandwidth data and obtain analysis results, the decision unit is used to receive the analysis results and output the control strategy, and the bandwidth adjustment unit is used to receive the control strategy to adjust the node bandwidth.

[0062] A computer device includes a memory for storing instructions; a processor for executing the instructions, so that the device executes a wireless bandwidth control method for realizing smart grid connection of a microgrid.

[0063] A computer-readable storage medium stores a computer program, which, when executed, implements a wireless bandwidth control method for intelligent microgrid grid connection.

[0064] Beneficial effects of the present invention:

[0065] The present invention ensures that the network can still operate stably under high load through dynamic bandwidth allocation, adjusts the bandwidth in real time according to the network load and priority, selects the optimal solution for the communication path to reduce data transmission time, improves response speed, adopts low-power design and intelligent scheduling to reduce energy consumption, and has an expandable modular design that supports flexible expansion to meet the needs of different scales. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0067] Figure 1 This is a flow chart of the wireless bandwidth control method for smart grid connection of microgrids according to the present invention;

[0068] Figure 2 This is a composition diagram of the wireless bandwidth control system for microgrid intelligent grid connection of the present invention;

[0069] Figure 3 The present invention is a flow chart of bandwidth data analysis in the wireless bandwidth control method for microgrid intelligent grid connection;

[0070] Figure 4 The present invention is a flowchart for optimizing node bandwidth in the wireless bandwidth control method for intelligent microgrid grid connection. DETAILED DESCRIPTION

[0071] 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.

[0072] 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.

[0073] 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.

[0074] Example 1

[0075] like Figure 1 As shown, the wireless bandwidth control method for microgrid intelligent grid connection includes:

[0076] S1. Collect power parameters and bandwidth data of microgrid grid-connected nodes, analyze power parameters and bandwidth data of grid-connected nodes, and obtain analysis results;

[0077] The power parameters of microgrid grid-connected nodes include voltage, current, frequency, power, phase and harmonic content;

[0078] Furthermore, voltage represents the magnitude and stability of the voltage at the grid-connected node, which has a direct impact on the stability and power quality of the power system.

[0079] The current reflects the magnitude and direction of the current at the grid-connected node and is a direct reflection of the energy exchange between the microgrid and the main grid.

[0080] Frequency: The frequency of the grid-connected node should be consistent with the main power grid to ensure the synchronous operation of the power system.

[0081] Power includes active power and reactive power. Active power indicates the rate of energy conversion, while reactive power affects the stability of voltage and the economy of the power system.

[0082] Phase: The voltage and current phase difference of the grid-connected node reflects the power factor and harmonic conditions of the grid.

[0083] Harmonic content refers to the amount of harmonic components in the voltage and current at the grid-connected node. Harmonics can affect the stability of the power system and the safety of equipment.

[0084] Bandwidth data includes uplink bandwidth, downlink bandwidth, latency, and packet loss rate;

[0085] The uplink bandwidth is the rate at which data is transmitted from the microgrid to the main grid or monitoring center.

[0086] Downlink bandwidth is the rate at which instructions or data are sent from the main grid or monitoring center to the microgrid.

[0087] Latency is the time delay during data transmission and is very important for real-time control systems.

[0088] The packet loss rate is the proportion of data packets lost during data transmission, which affects the reliability and integrity of data transmission;

[0089] The grid-connected node power parameter analysis method includes:

[0090] S1011, cleaning the power parameters of the microgrid grid-connected nodes, removing noise and abnormal values, and correcting sensor errors, and storing them in a database;

[0091] S1012. Establish a power prediction model to make short-term predictions on power parameters of future grid-connected nodes;

[0092] S1013, establishing a power anomaly model and an unknown anomaly detection model, and analyzing power parameters of grid-connected nodes;

[0093] Establish a power anomaly model. First, establish a time series prediction model for grid-connected node power parameters through an autoregressive integrated moving average model. The time series prediction model outputs the power prediction value. Then, calculate the residual between the power prediction value and the actual observation value. Finally, calculate the interquartile range of each residual, and set the lower and upper limits. Residuals beyond the range are considered abnormal.

[0094] The time series forecasting model calculation expression is as follows:

[0095] ;

[0096] in, is the predicted value at time t, is a constant, is the autoregressive coefficient of the power parameter at the first moment, is the power parameter at the first moment, is the moving average coefficient of the power parameter at the first moment, is the white noise error term of the power parameters at the first moment, is the white noise error term, p is the number of autoregressive terms, q is the number of moving average terms, is the power parameter at the tp moment, is the moving average coefficient of the power parameter at the qth moment, is the white noise error term at the qth moment;

[0097] Use the fitted time series prediction model to predict future power parameters and calculate the residual between the predicted value and the actual observed value;

[0098] Interquartile Range (IQR) is a commonly used method in statistics to measure the degree of dispersion of data. It represents the range of the middle 50% of the data in the data set, which is the difference between the upper quartile (third quartile, Q3) and the lower quartile (first quartile, Q1).

[0099] The unknown anomaly detection model receives the grid-connected node power anomaly value output by the power anomaly model, and detects whether the anomaly value is a known situation through the data anomaly database. If it is an unknown anomaly, the abnormal grid-connected node power parameter is marked;

[0100] S1014, optimizing the prediction values ​​of the power anomaly model and the unknown anomaly detection model by optimizing the correction unit;

[0101] If it is an abnormal power value, the power anomaly of the grid-connected node is marked by the optimization correction unit, and the grid-connected node power is reconstructed to find an alternative path. The grid-connected node power reconstruction is achieved by constructing the grid-connected node power priority, setting priority weights for all grid-connected nodes, and finding an alternative path according to the weight sorting;

[0102] like Figure 3 As shown, the bandwidth data analysis method includes:

[0103] S1021. Clean the collected bandwidth data, remove invalid records, and aggregate the data by timestamp;

[0104] S1022. Calculate the total flow, average flow and peak flow of each day, and calculate the flow time series set;

[0105] The time series set contains multiple subsequences, each of which has a length of L;

[0106] S1023, establishing a bandwidth data prediction model, and reducing the spatial dimension of the feature map through a pooling layer, while extracting important information of the bandwidth data;

[0107] The bandwidth data prediction model calculation expression is as follows:

[0108] ;

[0109] Among them, F[*] is the activation function, is a subsequence of the input bandwidth data time series, is the weight, is the bias value, j is the convolution layer count, is the j-th layer weight, is the j-th layer bias value, and n is the total number of layers of the bandwidth data prediction model;

[0110] The pooling layer includes the pooling window step and the pooling window size;

[0111] S1024, flattening the pooled feature map through full connection and mapping it to the output layer;

[0112] The loss between the predicted value and the actual value is fitted through the loss function and fed back to the bandwidth data prediction model to optimize the bandwidth data prediction model.

[0113] S1025, analyzing the bandwidth by outputting a predicted value through a bandwidth data prediction model;

[0114] The analysis results include power analysis results and bandwidth analysis results;

[0115] Output power analysis results through grid-connected node power anomaly detection, including power fluctuation anomalies and harmonic anomalies;

[0116] Output bandwidth analysis results through grid-connected node bandwidth anomaly detection, which includes bandwidth detection of key grid-connected nodes, bandwidth detection of common nodes, and bandwidth resource detection;

[0117] S2. Optimize node power anomalies and optimize node bandwidth through analysis results;

[0118] Optimize node power anomalies, including abnormal power fluctuations, which can be stabilized by energy supply, adding energy storage devices, etc., and abnormal harmonics, which can be managed by installing filters, adjusting power supply parameters, etc.

[0119] like Figure 4 As shown, the node bandwidth optimization method includes:

[0120] S201, setting the bandwidth weights of the grid-connected nodes, and sorting the bandwidth weights of the grid-connected nodes by priority selection;

[0121] S202. If the bandwidth of an important node is abnormal, increase the bandwidth allocation of the node, enable the backup communication link, and optimize the data transmission protocol to ensure the timely transmission of key data and the stable operation of the microgrid. If the bandwidth of an ordinary node is abnormal, mark the abnormal node and optimize the data transmission strategy.

[0122] Bandwidth anomalies include excessive bandwidth utilization, increased latency, and increased packet loss rate;

[0123] S203, implementing a bandwidth resource dynamic scheduling strategy and dynamically adjusting bandwidth allocation by receiving a bandwidth data prediction model output bandwidth prediction value;

[0124] S204, feeding back the bandwidth dynamic adjustment result to the bandwidth data prediction model, and predicting the bandwidth data at the next moment;

[0125] S3, real-time monitoring of the wireless communication environment, adaptive adjustment of the transmission power and signal frequency, and selection of the optimal path for information communication;

[0126] The wireless communication environment includes interference information and load information;

[0127] Interference information uses spectrum analysis technology to monitor interference sources within the communication frequency band in real time, including signal strength, frequency distribution, interference type, etc.

[0128] Load information is collected through a network management system or a collaborative measurement mechanism to measure the load of each communication path, including bandwidth utilization, delay, packet loss rate, etc.

[0129] The collected interference information and load information are preprocessed to remove noise and outliers.

[0130] Use statistical analysis or machine learning algorithms to model the processed data and predict environmental change trends in the future.

[0131] The transmission power is dynamically adjusted according to the real-time interference situation and the signal-to-noise ratio of the receiving end. If the interference is large, the frequency band power is reduced to reduce interference. If the frequency band is clear, the power is increased to enhance the signal. At the same time, energy efficiency and battery life are considered, and the power adjustment strategy is optimized to avoid unnecessary energy consumption.

[0132] Through spectrum analysis, select available frequencies with less interference for communication, and implement frequency hopping mechanisms to deal with sudden interference or frequency congestion;

[0133] Through path evaluation and path selection, the optimal path is selected for communication, and a redundant buffer is set for the communication path to perform redundant backup of the communication path;

[0134] Calculate the interference level, load, path loss, delay and other factors of the communication path, and calculate a comprehensive evaluation value for each path through the path priority function;

[0135] The path priority function evaluates the utility obtained by the communication signal from the propagation of the path by setting the path satisfaction coefficient, and prioritizes the paths according to the utility. The paths with higher priority have higher comprehensive evaluation values.

[0136] Select the path with the best comprehensive evaluation value as the current communication path. If the optimal path changes (such as due to interference or load changes), re-evaluate and re-select;

[0137] Considering the reliability of communication, several suboptimal paths can be maintained as redundant backups. If a problem occurs on the primary path, the backup path is switched to ensure the continuity of communication.

[0138] S4. Adjust energy supply and allocation according to load changes, and optimize node bandwidth through wireless communication feedback to regulate bandwidth.

[0139] The energy management module works closely with the bandwidth control method to dynamically adjust power distribution based on energy supply and load demand;

[0140] During the grid connection process, priority will be given to ensuring the power supply of communication equipment and key power equipment to ensure the stable operation of the communication and power systems;

[0141] Optimize node bandwidth through wireless communication feedback and regulate bandwidth;

[0142] Furthermore, if communication resources are insufficient, load balancing technology can be used to distribute data transmission to multiple paths to improve overall communication efficiency.

[0143] Example 2

[0144] like Figure 2 As shown, the wireless bandwidth control system for microgrid intelligent grid connection includes:

[0145] A node detection module, including a data acquisition unit for collecting power parameters of microgrid grid-connected nodes and an anomaly detection unit for node power anomaly analysis;

[0146] The bandwidth adjustment module includes a bandwidth data unit, a bandwidth analysis unit, a decision unit and a bandwidth adjustment unit, wherein the bandwidth data unit is used to collect microgrid node bandwidth data, the bandwidth analysis unit is used to analyze the collected microgrid node bandwidth data and obtain analysis results, the decision unit is used to receive the analysis results and output the control strategy, and the bandwidth adjustment unit is used to receive the control strategy to adjust the node bandwidth;

[0147] A communication module, comprising an interference processing unit and a multi-path optimization unit, wherein the interference processing unit is used to adaptively adjust the transmission power and signal frequency, and the multi-path optimization unit is used to compare and select the optimal communication path among multiple communication paths;

[0148] Energy management module, used to manage the internal power supply of the microgrid;

[0149] An expansion module, used for providing an expansion port;

[0150] The user interface module includes a data visualization unit and a user operation unit, wherein the data visualization unit is used to display an intuitive and easy-to-use graphical interface to display the microgrid node bandwidth, energy operation status and communication performance indicators, and the user operation unit is used for users to manually adjust the bandwidth.

[0151] Example 3

[0152] A computer device includes a memory for storing instructions; a processor for executing the instructions, so that the device executes a wireless bandwidth control method for realizing smart grid connection of a microgrid.

[0153] Example 4

[0154] A computer-readable storage medium stores a computer program, which, when executed, implements a wireless bandwidth control method for intelligent grid connection of a microgrid.

[0155] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only two embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible, for example, the size, scale, structure, shape and ratio of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc., without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. Any "device plus function" clause is intended to cover the structure of the execution function described in this article, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiment. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0156] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0157] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

[0158] 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 wireless bandwidth control method for intelligent microgrid connection, characterized in that: include: S1. Collect power parameters and bandwidth data of microgrid grid-connected nodes, analyze power parameters and bandwidth data of grid-connected nodes, and obtain analysis results; The grid-connected node power parameter analysis method includes: S1011, cleaning the power parameters of the microgrid grid-connected nodes, removing noise and abnormal values, and correcting sensor errors, and storing them in a database; S1012. Establish a power prediction model to make short-term predictions on power parameters of future grid-connected nodes; S1013, establishing a power anomaly model and an unknown anomaly detection model, and analyzing power parameters of grid-connected nodes; S1014, optimizing the prediction values ​​of the power anomaly model and the unknown anomaly detection model by optimizing the correction unit; Establishing the power anomaly model, firstly, establishing a time series prediction model of the power parameters of the grid-connected node through an autoregressive integrated moving average model, outputting the power prediction value from the time series prediction model, then calculating the residual between the power prediction value and the actual observed value, and finally calculating the interquartile range of each residual, and setting the lower limit and upper limit, and the residual beyond the range is regarded as abnormal; The time series prediction model calculation expression is as follows: ； in, is the predicted value at time t, is a constant, is the autoregressive coefficient of the power parameter at the first moment, is the power parameter at the first moment, is the moving average coefficient of the power parameter at the first moment, is the white noise error term of the power parameters at the first moment, is the white noise error term, p is the number of autoregressive terms, q is the number of moving average terms, is the autoregressive coefficient of the power parameter at the pth moment, is the power parameter at the tp moment, is the moving average coefficient of the power parameter at the qth moment, is the white noise error term at the qth moment; S2. Optimize node power anomalies and optimize node bandwidth through analysis results; S3, real-time monitoring of the wireless communication environment, adaptive adjustment of the transmission power and signal frequency, and selection of the optimal path for information communication; S4. Adjust energy supply and allocation according to load changes, and optimize node bandwidth through wireless communication feedback to regulate bandwidth.

2. The wireless bandwidth control method for microgrid intelligent grid connection according to claim 1 is characterized in that: Bandwidth data analysis methods include: S1021. Clean the collected bandwidth data, remove invalid records, and aggregate the data by timestamp; S1022. Calculate the total flow, average flow and peak flow of each day, and calculate the flow time series set; S1023, establishing a bandwidth data prediction model, and reducing the spatial dimension of the feature map through a pooling layer, while extracting important information of the bandwidth data; S1024, flattening the pooled feature map through full connection and mapping it to the output layer; S1025. Analyze the bandwidth by outputting a predicted value through a bandwidth data prediction model.

3. The wireless bandwidth control method for microgrid intelligent grid connection according to claim 2 is characterized in that: The bandwidth data prediction model calculation expression is as follows: ； Among them, F[*] is the activation function, is a subsequence of the input bandwidth data time series, is the weight, is the bias value, j is the convolution layer count, is the j-th layer weight, is the j-th layer bias value, and n is the total number of layers of the bandwidth data prediction model; The pooling layer includes the pooling window step and the pooling window size; The loss function is used to fit the loss between the predicted value and the actual value, and the loss is fed back to the bandwidth data prediction model to optimize the training of the bandwidth data prediction model.

4. The wireless bandwidth control method for microgrid intelligent grid connection according to claim 3 is characterized in that: Methods for optimizing node bandwidth include: S201, setting the bandwidth weights of the grid-connected nodes, and sorting the bandwidth weights of the grid-connected nodes by priority selection; S202. If the bandwidth of an important node is abnormal, increase the bandwidth allocation of the node, enable the backup communication link, and optimize the data transmission protocol to ensure the timely transmission of key data and the stable operation of the microgrid. If the bandwidth of an ordinary node is abnormal, mark the abnormal node and optimize the data transmission strategy. S203, implementing a bandwidth resource dynamic scheduling strategy and dynamically adjusting bandwidth allocation by receiving a bandwidth data prediction model output bandwidth prediction value; S204: Feedback the bandwidth dynamic adjustment result to the bandwidth data prediction model, and predict the bandwidth data at the next moment.

5. The wireless bandwidth control method for microgrid intelligent grid connection according to claim 4 is characterized in that: The wireless communication environment includes interference information and load information; Preprocessing the collected interference information and load information to remove noise and outliers; Model the processed data through machine learning algorithms to predict interference conditions and the signal-to-noise ratio at the receiving end; By predicting the interference situation and the signal-to-noise ratio of the receiving end, the transmission power is dynamically adjusted. If the interference is greater than the preset maximum interference threshold, the frequency band power is reduced to reduce interference. If the frequency band is clear, the power is increased to enhance the signal. The path frequency is calculated by spectrum analysis, and frequency communication is selected according to the calculated path frequency.

6. The wireless bandwidth control method for microgrid intelligent grid connection according to claim 5 is characterized in that: Through path evaluation and path selection, the optimal path is selected for communication, and a redundant buffer is set for the communication path to perform redundant backup of the communication path; Calculate a comprehensive evaluation value for each path through the path priority function; The path priority function evaluates the utility obtained by the communication signal from the propagation of the path by setting the path satisfaction coefficient, and prioritizes the paths according to the utility. The paths with higher priority have higher comprehensive evaluation values. The path with the best comprehensive evaluation value is selected as the current communication path. If the optimal path changes, re-evaluation and selection are performed.

7. A wireless bandwidth control system for microgrid intelligent grid connection, used to implement the wireless bandwidth control method for microgrid intelligent grid connection as claimed in any one of claims 1 to 6, characterized in that: include: A node detection module, including a data acquisition unit for collecting power parameters of microgrid grid-connected nodes and an anomaly detection unit for node power anomaly analysis; A bandwidth adjustment module, including a bandwidth data unit, a bandwidth analysis unit, a decision unit and a bandwidth adjustment unit; A communication module, comprising an interference processing unit and a multi-path optimization unit, wherein the interference processing unit is used to adaptively adjust the transmission power and signal frequency, and the multi-path optimization unit is used to compare and select the optimal communication path among multiple communication paths; Energy management module, used to manage the internal power supply of the microgrid; An expansion module, used for providing an expansion port; The user interface module includes a data visualization unit and a user operation unit, wherein the data visualization unit is used to display a graphical interface to display the microgrid node bandwidth, energy operation status and communication performance indicators, and the user operation unit is used for the user to manually adjust the bandwidth.

8. The wireless bandwidth control system for microgrid intelligent grid connection according to claim 7 is characterized in that: The bandwidth data unit is used to collect microgrid node bandwidth data, the bandwidth analysis unit is used to analyze the collected microgrid node bandwidth data and obtain analysis results, the decision unit is used to receive the analysis results and output the control strategy, and the bandwidth adjustment unit is used to receive the control strategy to adjust the node bandwidth.

Images