Communication power supply optimization method and system based on intelligent reconstruction

Abstract

The invention discloses a communication power supply optimization method and system based on intelligent reconstruction, and relates to the technical field of communication power supply optimization, and the method comprises the steps: collecting the power data of each output end, and obtaining the real-time power data; based on the LSTM neural network and the historical load data, predicting future load power, and establishing a load feature database; obtaining load information, calculating path loss and establishing an objective function based on the load characteristic database, and solving by adopting an improved genetic algorithm to obtain an optimal power supply path combination; and executing real-time monitoring and protection based on the optimal power supply path combination, and triggering a standby path when an abnormality occurs. According to the invention, the improved genetic algorithm is utilized to optimize the power supply path combination, and multi-objective collaborative optimization is realized. On the premise of ensuring the power supply reliability, the circuit loss can be effectively reduced, the power supply efficiency can be improved, the load level of each circuit can be balanced, the power supply stability can be maintained by intelligently switching the standby path, and the safety and reliability of the system can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of communication power supply optimization, and in particular to a communication power supply optimization method and system based on intelligent reconstruction. Background Art

[0002] As the scale of power systems continues to expand and electricity demand continues to grow, the rational planning and optimization of distribution network power supply paths are becoming increasingly important. Traditional distribution network power supply path optimization methods mainly rely on manual experience, lack of systematic optimization means, and are difficult to fully consider network topology characteristics, load distribution, equipment capacity and other factors, often leading to low power supply efficiency, large line losses, and uneven load distribution. At the same time, most existing optimization methods focus on static planning, lack of real-time monitoring of operating status and rapid response capabilities to abnormal situations, and are difficult to switch to backup paths in time when facing faults or abnormalities, affecting power supply reliability.

[0003] The current optimization algorithms generally have shortcomings such as low solution efficiency, local optimality, and poor feasibility, which are difficult to meet the needs of actual engineering applications. In the process of power supply path optimization, how to balance multiple goals such as power supply reliability, economy, and safety, how to deal with complex network topology relationships and operation constraints, and how to ensure the practicality of optimization results are all key issues that need to be solved. Especially in the context of smart grid construction, the operation optimization of distribution networks faces higher requirements, and it is necessary to develop advanced optimization methods and intelligent means to improve the operation efficiency, reliability, and intelligence level of distribution networks. Therefore, it is urgent to develop a power supply path optimization method that can comprehensively consider multiple optimization objectives, has real-time monitoring and protection functions, and has good algorithm performance to meet the development needs of modern distribution networks. Summary of the invention

[0004] In view of the problems existing in the existing communication power supply optimization method based on intelligent reconstruction, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the current optimization algorithms generally have shortcomings such as low solution efficiency, local optimum, poor feasibility, etc., which are difficult to meet the needs of actual engineering applications.

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

[0007] In the first aspect, an embodiment of the present invention provides a communication power supply optimization method based on intelligent reconstruction, which includes collecting power supply data of each output terminal to obtain real-time power data; based on an LSTM neural network, predicting future load power based on historical load data, and establishing a load characteristic database; based on the load characteristic database, obtaining load information, calculating path loss, establishing an objective function, and using an improved genetic algorithm to solve and obtain an optimal power supply path combination; performing real-time monitoring and protection based on the optimal power supply path combination, and triggering a backup path when an abnormality occurs.

[0008] As a preferred solution of the communication power supply optimization method based on intelligent reconstruction described in the present invention, the power supply data is collected and the instantaneous power is calculated and expressed as:

[0009] P i (t) = V i (t)×I i (t)

[0010] Among them, P i (t) represents the instantaneous power of node i at time t.

[0011] As a preferred solution of the communication power supply optimization method based on intelligent reconstruction described in the present invention, the future load power is predicted based on the LSTM neural network, and the time step is set to Δt. Then, the load power at the future time t+Δt is set to According to the prediction results, a load characteristic database is constructed.

[0012] As a preferred solution of the communication power supply optimization method based on intelligent reconstruction described in the present invention, wherein: based on the load characteristic database, the load cycle characteristics are analyzed by fast Fourier transform, and the time domain signal is converted into a frequency domain signal for periodic characteristic analysis;

[0013] The various periodic components contained in the load are analyzed by power spectrum, the period is extracted, the periodic features are identified, and the load pattern is identified by K-means clustering algorithm, including:

[0014] Construct the objective function:

[0015]

[0016] Where k is the number of clusters, x j represents the sample feature vector, μ i is the i-th cluster center, ||·|| represents the Euclidean distance;

[0017] Determine the number of clusters k, randomly select k cluster centers, calculate the distance from each sample to each cluster center, assign the sample to the nearest cluster, update the cluster center, and repeat until convergence;

[0018] Through load pattern recognition, typical load patterns are automatically identified, similar load characteristics are classified, the common characteristics of each type of load are extracted, the description of load behavior is simplified, and a special prediction model is established for each pattern.

[0019] As a preferred solution of the communication power supply optimization method based on intelligent reconstruction described in the present invention, wherein: based on the load feature database, basic load information is obtained, including: load rated power, power factor, load location coordinates, load level and power supply reliability requirements,

[0020] And obtain load characteristic parameter information, including: daily load curve, load rate, peak-to-valley difference rate and daily load rate, and obtain path loss based on the load basic information and the load characteristic parameter information.

[0021] As a preferred solution of the communication power supply optimization method based on intelligent reconstruction of the present invention, wherein: based on the objective function, solving by an improved genetic algorithm and calculating the optimal path specifically include:

[0022] The load nodes are sorted according to the distance from the power source, and the power supply paths with shorter distances are given priority to reduce the number of invalid individuals in the population. The regional load density distribution is calculated, and the trunk lines are arranged preferentially in load-intensive areas. By improving the fitness function, the quality of the local optimal solution is evaluated. Based on the improved genetic algorithm, the optimal distribution network topology and the optimal connection relationship of the load nodes are output, and the optimal power supply path combination is output.

[0023] As a preferred solution of the communication power supply optimization method based on intelligent reconstruction described in the present invention, wherein: based on the optimal power supply path combination, data of each monitoring point is collected in real time to determine possible abnormalities, including electrical faults, equipment faults and environmental abnormalities; when the monitoring system detects any abnormality, the corresponding protection measures will be started according to the fault type, and the backup power supply path will be switched if necessary; specifically, if a short circuit fault is detected, the fault section will be removed within the specified time; if a heavy overload occurs, the circuit breaker will be tripped according to the delay characteristic curve; if a single-phase grounding occurs, the circuit breaker will be selectively operated according to the grounding method; if a phase failure is detected, the fault phase will be quickly removed and an alarm will be issued; if it is confirmed that the nature of the fault is a continuous fault, the availability and capacity margin of the backup path will be verified, the impact of the switching operation on the system will be evaluated, and the switching operation will be executed; if the path switching is executed, the timing arrangement of the load transfer will be confirmed, the impact current of the switching process will be controlled, the voltage fluctuation of the switching process will be monitored, and the data of the whole process of the switching operation will be recorded; if the path switching is completed, the power distribution will be adjusted, the loads of each line will be balanced, the voltage distribution will be optimized, the user voltage will be ensured to be qualified, the switching effect will be analyzed, the system stability will be evaluated, a recovery plan will be formulated, and the recovery time will be clarified.

[0024] In the second aspect, an embodiment of the present invention provides a communication power supply optimization system based on intelligent reconstruction, which includes: a collection module, which is used to collect power supply data of each output terminal and obtain real-time power data; a prediction module, which is used to predict future load power based on historical load data according to an LSTM neural network, and establish a load characteristic database; a calculation module, which obtains load information, calculates path loss, establishes an objective function, and uses an improved genetic algorithm to solve and obtain an optimal power supply path combination based on the load characteristic database; a monitoring module, which performs real-time monitoring and protection based on the optimal power supply path combination, and triggers a backup path when an abnormality occurs.

[0025] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned communication power supply optimization method based on intelligent reconstruction.

[0026] In a fourth aspect, an embodiment of 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 above-mentioned communication power supply optimization method based on intelligent reconstruction is implemented.

[0027] The beneficial effect of the present invention is that the present invention realizes multi-objective collaborative optimization by constructing a model based on the topological information of the distribution network, optimizing the power supply path combination by using an improved genetic algorithm, and matching the real-time monitoring and protection mechanism. It can effectively reduce line losses, improve power supply efficiency, and balance the load levels of each line while ensuring the reliability of power supply; by introducing constraints such as voltage deviation and equipment capacity, the practicality and feasibility of the optimization results are guaranteed; the matching real-time monitoring and protection mechanism can timely detect and handle operational anomalies, maintain power supply stability by intelligently switching backup paths, and improve the safety and reliability of the system. The overall solution has strong practical value and promotion significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] 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 work. Among them:

[0029] Figure 1 The present invention is a flow chart of a communication power supply optimization method based on intelligent reconstruction. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned purposes, 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 drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0031] 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.

[0032] 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.

[0033] Example 1

[0034] Reference Figure 1 , which is the first embodiment of the present invention, and provides a communication power supply optimization method based on intelligent reconstruction, comprising:

[0035] S1: Collect power data and calculate instantaneous power, expressed as:

[0036] P i (t) = V i (t)×I i (t)

[0037] Among them, P i (t) represents the instantaneous power of node i at time t.

[0038] Furthermore, in order to accurately capture the dynamic changes of the power grid, the frequency and accuracy of the sensor to collect electrical parameters are set, and the collected data are stored in the database according to the timestamp; the original data is detected for outliers, and the sliding average method is used to smooth the data; the processed data is normalized to obtain high-quality original data.

[0039] S2: Based on the LSTM neural network, the future load power is predicted. The time step is set to Δt, and the load power at the future time t+Δt is set to According to the prediction results, a load characteristic database is constructed.

[0040] Furthermore, based on the LSTM neural network, the future load power is predicted. First, the time step is set, and the future load power is predicted at fixed intervals. For each future moment, the corresponding load power value is predicted. These prediction results can not only understand the future load change trend, but also have important guiding significance for the dispatch and management of the power system. In order to make more effective use of these prediction data, a load characteristic database is constructed. The database stores the load power value at each prediction time point, and may also include relevant prediction errors, historical data based on the prediction, external influencing factors and other information. In this way, the prediction model is continuously analyzed and optimized to ensure that it can more accurately reflect the actual load changes, thereby supporting more intelligent and efficient power dispatch decisions.

[0041] The basic data of the load characteristic database include power fluctuation rate, peak-to-valley ratio, multi-time scale fluctuation characteristics, fluctuation pattern data, periodic parameters, spectrum characteristics and typical periodic pattern data.

[0042] The power fluctuation rate, peak-to-valley ratio, multi-time scale fluctuation characteristics and fluctuation pattern data are obtained through fluctuation characteristic analysis;

[0043] The periodic parameters, spectrum characteristics and typical periodic pattern data are obtained through periodic feature analysis.

[0044] Fluctuation characteristic analysis evaluates the stability of the load through power fluctuation rate, helps identify fluctuating loads that may affect the stability of the power grid, and provides early warning basis for the safe operation of the system.

[0045] The load cycle characteristics are analyzed by fast Fourier transform, and the time domain signal is converted into a frequency domain signal for periodic feature analysis, which is expressed as:

[0046] X(k)=∑[x(n)·e (-j2πnk / N )], k = 0, 1, ..., N-1

[0047] Among them, x(n) represents the power time series, X(k) represents the frequency domain component, N represents the number of FFT points, j is the imaginary unit, n is the time domain number, and k is the frequency number.

[0048] The various periodic components contained in the load are further analyzed through the power spectrum, the main cycle is extracted, the periodic features are identified, and the load pattern is identified through the K-means clustering algorithm, including:

[0049] Construct the objective function:

[0050]

[0051] Where k is the number of clusters, x j represents the sample feature vector, μi is the i-th cluster center, and ||·|| represents the Euclidean distance.

[0052] Determine the number of clusters k, randomly select k cluster centers, calculate the distance from each sample to each cluster center, assign the sample to the nearest cluster, update the cluster center, and repeat until convergence.

[0053] Through load pattern recognition, typical load patterns can be automatically identified, similar load characteristics can be classified, the common characteristics of each type of load can be extracted, the description of load behavior can be simplified, and a special prediction model can be established for each pattern to improve prediction accuracy and reduce prediction difficulty.

[0054] S3: Obtain basic load information based on the load characteristic database, including load rated power, power factor, load location coordinates, load level, and power supply reliability requirements.

[0055] And obtain load characteristic parameter information, including: daily load curve, load rate, peak-to-valley difference rate and daily load rate, and obtain path loss based on load basic information and load characteristic parameter information.

[0056] Furthermore, based on the load characteristic database, we first obtain the basic information of the load, including key parameters such as the rated power, power factor, location coordinates, load level, and power supply reliability requirements of the load. These basic information are helpful to understand the basic characteristics of each load and the specific needs for power supply. The characteristic parameter information of the load is extracted from the database, such as the daily load curve, load rate, peak-to-valley difference rate, and daily load rate. These data reflect the power consumption pattern and changing trend of the load in different time periods. Combined with the basic information and characteristic parameter information of the load, in-depth analysis can be performed, such as calculating the path loss. The calculation of the path loss needs to take into account the actual power consumption of the load and its position in the power grid. By analyzing characteristic parameters such as the daily load curve and load rate, the loss in the power transmission process can be more accurately evaluated, thereby providing a scientific basis for optimizing the power grid layout, improving power supply efficiency, and reducing costs.

[0057] Preferably, the crossover selection strategy identifies key nodes of the power supply path, performs crossover at the key nodes, and maintains excellent gene fragments.

[0058] The fitness level determines the size of the mutation probability, and the penalty term guides the direction of directional mutation, thereby promoting the population to converge to a feasible solution.

[0059] The optimal distribution network topology and the optimal connection relationship of load nodes are output by the improved genetic algorithm, the topology is optimized to reduce the impact range of faults, the system stability is improved through reasonable connection relationships, and the system failure rate and power outage time are reduced.

[0060] Through the optimized network topology, the system can quickly isolate the fault when a local fault occurs, and use the interconnection switch to quickly restore power supply to the faulty section, effectively reducing the scope of the fault impact and improving the power supply reliability level of the system.

[0061] S4: Perform real-time monitoring and protection based on the optimal power supply path combination, and trigger the backup path when an abnormality occurs.

[0062] Collect data from each monitoring point in real time, monitor electrical parameters, equipment status and environmental conditions, and determine possible abnormalities, including electrical failures, equipment failures and environmental abnormalities.

[0063] When the monitoring system detects any abnormality, it will initiate corresponding protection measures according to the fault type and switch to the backup power supply path if necessary. During the switching process, the system will control the switching inrush current and voltage fluctuation to ensure stable power supply quality. After the switching is completed, the system will automatically optimize the operation mode and continuously monitor the operation status to provide a basis for the subsequent restoration of the normal power supply path.

[0064] Specifically, if a short-circuit fault is detected, the fault section will be removed within the specified time; if a heavy overload occurs, the circuit breaker will be tripped according to the delay characteristic curve; if a single-phase grounding occurs, the circuit breaker will selectively operate according to the grounding method; if a phase failure is detected, the fault phase will be quickly removed and an alarm will be issued;

[0065] If the main protection fails to operate, the backup protection will be activated and a graded delay coordination method will be adopted to ensure the selectivity of the protection, optimize time coordination, and avoid false operation and failure to operate.

[0066] When performing backup power supply path switching, comprehensively evaluate factors such as the nature of the fault, the availability of the backup path, and the impact of load transfer to determine the optimal switching plan.

[0067] If the fault is confirmed to be a persistent fault, the availability and capacity margin of the backup path are verified, the impact of the switching operation on the system is evaluated, and the switching operation is performed;

[0068] If path switching is performed, the timing arrangement of load transfer is confirmed, the inrush current of the switching process is controlled, the voltage fluctuation of the switching process is monitored, and the data of the entire switching operation is recorded;

[0069] If the path switching is completed, the power distribution is adjusted, the load of each line is balanced, the voltage distribution is optimized, the user voltage is ensured to be qualified, the switching effect is analyzed, the system stability is evaluated, a recovery plan is formulated, and the recovery timing is clarified.

[0070] In summary, the present invention achieves multi-objective collaborative optimization by constructing a model based on the topological information of the distribution network, optimizing the power supply path combination using an improved genetic algorithm, and matching real-time monitoring and protection mechanisms. It can effectively reduce line losses, improve power supply efficiency, and balance the load levels of each line while ensuring power supply reliability; by introducing constraints such as voltage deviation and equipment capacity, the practicality and feasibility of the optimization results are guaranteed; the matching real-time monitoring and protection mechanism can promptly detect and handle operational anomalies, maintain power supply stability by intelligently switching backup paths, and improve the safety and reliability of the system. The overall solution has strong practical value and promotion significance.

[0071] Example 2

[0072] Reference Figure 1 Based on the first embodiment, this embodiment further provides a communication power supply optimization system based on intelligent reconstruction, including:

[0073] A collection module is used to collect power data of each output terminal and obtain real-time power data;

[0074] The prediction module is used to predict future load power based on historical load data according to the LSTM neural network and establish a load feature database;

[0075] The calculation module obtains load information based on the load characteristic database, calculates the path loss, establishes the objective function, and uses the improved genetic algorithm to solve and obtain the optimal power supply path combination;

[0076] The monitoring module performs real-time monitoring and protection based on the optimal power supply path combination and triggers the backup path when an abnormality occurs.

[0077] This embodiment also provides a computer device, which is suitable for the case of a communication power supply optimization method based on intelligent reconstruction, 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 communication power supply optimization method based on intelligent reconstruction as proposed in the above embodiment.

[0078] 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 via a system bus. 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 covering 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.

[0079] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing the power supply of a communication power supply based on intelligent reconstruction as proposed in the above embodiment is implemented.

[0080] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0081] Example 3

[0082] On the basis of the previous two embodiments, this embodiment provides a communication power supply optimization method based on intelligent reconstruction. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0083] In order to verify the effectiveness of the method of the present invention, a typical distribution network was selected for simulation experiments. The distribution network consists of 2 main transformers, 12 feeders, 36 distribution transformers, and the total capacity of conventional loads is 25MVA. The experiment compares the performance of the traditional genetic algorithm, the improved particle swarm algorithm and the method of the present invention in power supply path optimization. The experimental environment is an Inteli7 processor with 16GB memory, and MATLABR2023a is used for simulation. Each method was run 50 times to take the average value, and the results are shown in Table 1:

[0084] Table 1 Comparative experimental results

[0085] Evaluation indicators Traditional genetic algorithm Improved particle swarm optimization algorithm Method of the present invention Line loss rate % 4.82 4.35 3.76 Voltage deviation % ±6.8 ±5.9 ±4.2 Load balance % 82.5 85.7 91.3 Algorithm convergence time s 186 142 95 Fault response time ms 320 280 150 Switching success rate % 92.4 94.8 98.5 Evaluation indicators Traditional genetic algorithm Improved particle swarm optimization algorithm Method of the present invention

[0086] From the comparative analysis of the experimental results, it can be seen that the method of the present invention is significantly superior to the existing technical solutions in various key performance indicators: the line loss rate is reduced from 4.82% of the traditional genetic algorithm and 4.35% of the improved particle swarm algorithm to 3.76%, an average reduction of about 20%, reflecting the economic advantage of the present invention; the voltage deviation is better controlled, improving from ±6.8% and ±5.9% to ±4.2%, and the power supply quality is significantly improved; the load balance is improved from 82.5% and 85.7% to 91.3%, indicating that the present invention can more reasonably distribute the network load and avoid local overload.

[0087] The algorithm convergence time is shortened from 186 seconds and 142 seconds to 95 seconds, and the computing efficiency is improved by about 40%, which is more suitable for actual engineering applications. In terms of fault response, the response time of the present invention is only 150ms, which is significantly shorter than the 320ms and 280ms of the existing methods, and can carry out fault isolation and backup path switching more quickly. The power supply reliability is also significantly improved, and the switching success rate reaches 98.5%, which is significantly improved compared with the 92.4% and 94.8% of the existing methods.

[0088] These experimental data fully demonstrate the comprehensive advantages of the present invention in terms of power supply efficiency, power supply quality, operation reliability and algorithm performance, verify the advanced nature and practical value of the proposed method, and provide an effective technical solution for the optimization of distribution network operation.

[0089] 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 communication power supply optimization method based on intelligent reconstruction, characterized in that: include, Collect power data from each output terminal and obtain real-time power data; Based on LSTM neural network, future load power is predicted based on historical load data, and a load feature database is established; Based on the load characteristic database, load information is obtained, path loss is calculated, an objective function is established, and an improved genetic algorithm is used to solve the problem to obtain an optimal power supply path combination; Real-time monitoring and protection are performed based on the optimal power supply path combination, and the backup path is triggered when an abnormality occurs.

2. The communication power supply optimization method based on intelligent reconstruction according to claim 1, characterized in that: The power supply data is collected and the instantaneous power is calculated and expressed as: P i (t)=V i (t)×I i (t) Among them, P i (t) represents the instantaneous power of node i at time t.

3. The communication power supply optimization method based on intelligent reconstruction according to claim 2, characterized in that: Based on the LSTM neural network, the future load power is predicted. The time step is set to Δt. Then the load power at the future time t+Δt is set to According to the prediction results, a load characteristic database is constructed.

4. The communication power supply optimization method based on intelligent reconstruction as claimed in claim 3 is characterized in that: Based on the load characteristic database, the load periodic characteristics are analyzed by fast Fourier transform, and the time domain signal is converted into a frequency domain signal for periodic characteristic analysis; The various periodic components contained in the load are analyzed by power spectrum, the period is extracted, the periodic features are identified, and the load pattern is identified by K-means clustering algorithm, including: Construct the objective function: Among them, k is the number of clusters, x j represents the sample feature vector, μ i is the i-th cluster center, ||·|| represents the Euclidean distance; Determine the number of clusters k, randomly select k cluster centers, calculate the distance from each sample to each cluster center, assign the sample to the nearest cluster, update the cluster center, and repeat until convergence; Through load pattern recognition, typical load patterns are automatically identified, similar load characteristics are classified, the common characteristics of each type of load are extracted, the description of load behavior is simplified, and a special prediction model is established for each pattern.

5. The communication power supply optimization method based on intelligent reconstruction according to claim 4, characterized in that: Based on the load characteristic database, basic load information is obtained, including load rated power, power factor, load location coordinates, load level, and power supply reliability requirements. And obtain load characteristic parameter information, including: daily load curve, load rate, peak-to-valley difference rate and daily load rate, and obtain path loss based on the load basic information and the load characteristic parameter information.

6. The communication power supply optimization method based on intelligent reconstruction according to claim 5, characterized in that: Based on the objective function, an improved genetic algorithm is used to solve and calculate the optimal path, which specifically includes: The load nodes are sorted according to the distance from the power source, and the power supply paths with shorter distances are given priority to reduce the number of invalid individuals in the population. The regional load density distribution is calculated, and the trunk lines are arranged preferentially in load-intensive areas. By improving the fitness function, the quality of the local optimal solution is evaluated. Based on the improved genetic algorithm, the optimal distribution network topology and the optimal connection relationship of the load nodes are output, and the optimal power supply path combination is output.

7. The communication power supply optimization method based on intelligent reconstruction according to claim 6 is characterized in that: Based on the optimal power supply path combination, data from each monitoring point is collected in real time to determine possible abnormalities, including electrical faults, equipment faults, and environmental abnormalities; When the monitoring system detects any abnormality, it will initiate corresponding protection measures according to the fault type and switch to the backup power supply path; Specifically, if a short-circuit fault is detected, the fault section will be removed within the specified time; if a heavy overload occurs, the circuit breaker will be tripped according to the delay characteristic curve; if a single-phase grounding occurs, the circuit breaker will selectively operate according to the grounding method; if a phase failure is detected, the fault phase will be quickly removed and an alarm will be issued; If the fault is confirmed to be a persistent fault, the availability and capacity margin of the backup path are verified, the impact of the switching operation on the system is evaluated, and the switching operation is performed; If path switching is performed, the timing arrangement of load transfer is confirmed, the inrush current of the switching process is controlled, the voltage fluctuation of the switching process is monitored, and the data of the entire switching operation is recorded; If the path switching is completed, the power distribution is adjusted, the load of each line is balanced, the voltage distribution is optimized, the user voltage is ensured to be qualified, the switching effect is analyzed, the system stability is evaluated, a recovery plan is formulated, and the recovery timing is clarified.

8. A communication power supply optimization system based on intelligent reconstruction, based on the communication power supply optimization method based on intelligent reconstruction according to any one of claims 1 to 7, characterized in that: include, A collection module is used to collect power data of each output terminal and obtain real-time power data; The prediction module is used to predict future load power based on historical load data according to the LSTM neural network and establish a load feature database; A calculation module, based on the load characteristic database, obtains load information, calculates path loss, establishes an objective function, and uses an improved genetic algorithm to solve and obtain an optimal power supply path combination; The monitoring module performs real-time monitoring and protection based on the optimal power supply path combination and triggers the backup path when an abnormality occurs.

9. 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 communication power supply optimization method based on intelligent reconstruction according to any one of claims 1 to 7 are implemented.

10. 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 communication power supply optimization method based on intelligent reconstruction according to any one of claims 1 to 7 are implemented.

Images