Power utilization area monitoring management method and system based on intelligent fusion terminal

Abstract

The invention relates to the technical field of power utilization area monitoring management, in particular to a power utilization area monitoring management method and system based on an intelligent fusion terminal, and the method comprises the steps: collecting the outlet side data of a multi-phase transformer through the intelligent fusion terminal; according to the data of the outlet side of the multi-phase transformer, calculating monitoring indexes including the total load rate of the multi-phase transformer, the split-phase load rate of each phase of the multi-phase transformer and the multi-phase current unbalance degree; according to the monitoring indexes, through the constructed hierarchical early warning decision model, performing hierarchical early warning and generating corresponding multi-level decisions; wherein the grading early warning decision model carries out grading early warning and generates corresponding multi-level decisions according to preset trigger conditions, namely analysis, sum and corresponding thresholds, to which, the analysis, sum and the corresponding thresholds belong; the difference is calculated according to the two-phase load rate difference. According to the scheme, the operation condition of the multi-phase transformer can be effectively and accurately identified, targeted early warning and decision making are carried out, operation and maintenance are assisted, and electricity utilization and electricity utilization safety of an electricity utilization area are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power consumption area monitoring and management, and specifically provides a power consumption area monitoring and management method and system based on an intelligent fusion terminal. Background Art

[0002] The intelligent fusion terminal is the core intelligent device in the power grid distribution and power consumption link, deployed at key nodes such as distribution transformers, switch stations, and power distribution areas, and is the edge brain for realizing distribution automation, power consumption information collection, and new service integration. Its main functions include: integrating modules such as distribution transformer monitoring, power metering, intelligent switch control, distributed energy access, and load management, replacing traditional multiple terminals, and achieving centralized unity of hardware and data; having local data processing and analysis capabilities, capable of quickly executing instructions such as fault identification, reactive power compensation, and orderly power consumption, reducing dependence on the main station, and improving response speed. With the increase in power demand, the intelligent fusion terminal significantly improves the perception ability, control efficiency, and operation flexibility of the distribution network through an integrated design, and is an important infrastructure for promoting the intelligence of the power grid and realizing energy interconnection, so it is widely used in the power grid.

[0003] In the existing power grid, power is often supplied to the power consumption area through a polyphase transformer. The intelligent fusion terminal can obtain data of the polyphase transformer and users in the power consumption area, but the analysis of the acquired data is relatively single, and the accuracy of reflecting the operating conditions of the polyphase transformer is limited. It mainly focuses on judging whether the polyphase transformer is faulty, without prior targeted warning, and mainly considers preventing the polyphase transformer from burning out.

[0004] Therefore, there is an urgent need for a power consumption area monitoring and management method and system based on an intelligent fusion terminal, which can effectively and accurately identify the operating conditions of the polyphase transformer, conduct targeted warning and decision-making, and assist in operation and maintenance to ensure the power consumption and power safety in the power consumption area. Summary of the Invention

[0005] One of the purposes of the present invention is to provide a power consumption area monitoring and management method based on an intelligent fusion terminal, which can effectively and accurately identify the operating conditions of the polyphase transformer, conduct targeted warning and decision-making, and assist in operation and maintenance to ensure the power consumption and power safety in the power consumption area.

[0006] The basic solution one provided by the present invention: A power consumption area monitoring and management method based on an intelligent fusion terminal includes: Collecting data on the outlet side of the polyphase transformer through the intelligent fusion terminal; Calculating monitoring indicators based on the data on the outlet side of the polyphase transformer, including: the total load rate of the polyphase transformer 、the phase-by-phase load rate of each phase of the polyphase transformer 、the polyphase current unbalance degree ; Based on the monitoring indicators, a hierarchical early warning decision-making model is constructed to conduct hierarchical early warning and generate corresponding multi-level decisions; The hierarchical early warning decision-making model is based on , , and Based on the preset trigger conditions, tiered early warnings and corresponding multi-level decisions are generated; among them, the preset trigger conditions are analyzed. , , and The relationship between the magnitude of the corresponding threshold and the value of the threshold, where According to Calculate the difference in load rates between the two phases.

[0007] Beneficial effects: This solution monitors and collects data from the output side of multiphase transformers through intelligent fusion terminals. Based on this data, it calculates monitoring indicators, including the total load rate of the multiphase transformers. Phase load rate of each phase of a multiphase transformer Multiphase current imbalance ;in It can assess the utilization rate of transformer capacity. It can reflect the degree of utilization of each phase. It can quantify the severity of multiphase load asymmetry; Based on monitoring indicators, a hierarchical early warning decision-making model is constructed to conduct hierarchical early warnings and generate corresponding multi-level decisions. This allows for multi-faceted analysis of multiple monitoring indicators, including overall and single-phase analysis of multiphase transformers, taking into account the load symmetry of each phase. The hierarchical early warning decision-making model also considers… According to The difference in load rate between the two phases is calculated to quantify the differences between each phase, thereby enabling a more accurate analysis. The hierarchical early warning decision-making model constructed therein is based on... , , and The preset trigger conditions are used to perform early warning analysis and generate corresponding multi-level decisions, and the preset trigger conditions are analysis. , , and By considering the relationship between the magnitude of the corresponding thresholds, the determination of multiple indicators can more accurately reflect the current operating status of multiphase transformers, accurately identify existing problems, and make timely adjustments. This enables an intelligent upgrade from preventing multiphase transformer burnout to ensuring the healthy operation of multiphase transformers, reducing power outages and economic losses caused by multiphase transformer faults, providing a time window for proactive operation and maintenance, avoiding power outages caused by the expansion of faults, and ensuring power consumption and safety in the power consumption area.

[0008] In summary, this solution can effectively and accurately identify the operating status of multiphase transformers, provide targeted early warnings and decision-making, and assist in operation and maintenance to ensure electricity use and safety in the power consumption area.

[0009] The second objective of this invention is to provide a power consumption area monitoring and management system based on an intelligent fusion terminal, which can effectively and accurately identify the operating status of multi-phase transformers, and provide targeted early warnings and decision-making to assist in operation and maintenance, so as to ensure the power consumption and safety of the power consumption area.

[0010] The present invention provides a second basic solution: a power consumption area monitoring and management system based on intelligent converged terminals, used to execute the above-mentioned power consumption area monitoring and management method based on intelligent converged terminals.

[0011] Beneficial effects: This system can effectively and accurately identify the operating status of multiphase transformers, and provide targeted early warnings and decision-making to assist in operation and maintenance, so as to ensure the power consumption and safety of the power consumption area, and facilitate the application and promotion of power consumption area monitoring and management methods based on intelligent fusion terminals. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating an embodiment of the power consumption area monitoring and management method based on an intelligent fusion terminal according to the present invention. Detailed Implementation

[0013] The following detailed description illustrates the specific implementation method: Example 1 This implementation example is attached. Figure 1 As shown, a method for monitoring and managing electricity consumption areas based on an intelligent converged terminal is provided, including the following: S1. Collect data from the output side and user side of the multiphase transformer through the intelligent fusion terminal; The intelligent fusion terminal collects data from the output side and user side of multiphase transformers through high-speed communication networks, such as HPLC (high-speed carrier communication for low-voltage power lines). The data from the output side of the multiphase transformer includes: multiphase voltage. Multiphase current Total active power Total reactive power ; including multiphase voltage and multiphase current middle express The phase is determined based on the multiphase transformer. For example, in this embodiment, a three-phase transformer is used, then the multiphase voltage... ,include: , , Multiphase current, including: , , ; User-side data includes: environmental information of the user's electricity consumption area; the environmental information includes: season, temperature, humidity, weather, month, and holidays; S2. Based on the data from the output side of the multiphase transformer, calculate the monitoring indicators, including: the total load rate of the multiphase transformer. Phase load rate of each phase of a multiphase transformer Multiphase current imbalance ; Specifically, the total load factor of multiphase transformers Used to assess the utilization rate of transformer capacity: ; in The rated capacity (kVA) of the multiphase transformer is a fixed value on the nameplate. The total apparent power (kVA) currently output by the multiphase transformer characterizes the overall stress of the multiphase transformer, specifically: .

[0014] Phase load factor of each phase of a multiphase transformer for: ; in for Phase load rate; for The apparent power (kVA) borne by the phase is as follows: ; For phase number, It is an approximation used to assess the load pressure borne by each phase winding; Taking phase A of a three-phase transformer as an example: ; .

[0015] Multiphase current imbalance for: ; in The degree of multiphase current imbalance quantifies the severity of multiphase load asymmetry; The average value (kA) of the multiphase current is as follows: ; The maximum current deviation (kA) is as follows: ; Taking a three-phase transformer as an example: ; .

[0016] S3. Based on the monitoring indicators, a hierarchical early warning decision-making model is constructed to conduct hierarchical early warning and generate corresponding multi-level decisions; The tiered early warning decision-making model is a rule-based judgment model, specifically including: Based on the total load rate of the multiphase transformer Phase load rate of each phase of a multiphase transformer and multiphase current imbalance Based on the preset trigger conditions, graded early warnings and corresponding multi-level decisions are generated; Among them, preset trigger conditions are analyzed. , , and The relationship between the magnitude of the corresponding threshold and the value of the threshold, where The difference between the two-phase load rates includes: First preset trigger condition: , , , If a multiphase transformer is under overall heavy load or overload, or if there is a single-phase overload but the three phases are balanced, a Level 1 warning will be issued; among which... The total load rate threshold is set to 90% in this implementation. for Phase load rate threshold, in this embodiment All are set to 110%. Taking a three-phase transformer as an example, the load rate thresholds for different single phases can also be set to different values. This is the difference in load rates between the two phases. Taking a three-phase transformer as an example: include: , , ; To balance the judgment threshold, this embodiment sets it to 10% to assess the maximum difference in load rate among phases; The first current imbalance, This is the second current imbalance, and In this embodiment Set to 25%, Set to 15%; Multiphase transformers are subject to overall heavy load or overload, single-phase overload, three-phase balance, and all windings are subjected to high voltage. The overall temperature rise risk of multiphase transformers is high, thus generating corresponding multi-level decision-making processes, including: Emergency decision: Initiate load transfer in the power consumption area, such as cutting off secondary loads according to the orderly power consumption plan; Short-term decision: Request a mobile transformer for emergency use; Long-term decision: If the number of times the first preset trigger condition is met is greater than the first preset number of times, or the time for the first preset trigger condition to be met is greater than the first preset duration, then capacity expansion and modification will be carried out.

[0017] Second preset trigger condition: , , , If a multiphase transformer is under heavy load or overload, or if there is a single-phase overload or a severe three-phase imbalance, a Level 1 warning will be issued. When a multiphase transformer is under heavy load or overload, or when there is single-phase overload and severe three-phase imbalance, the overloaded single phase faces an extremely high risk of overheating and damage, while the lightly loaded phases suffer capacity waste and the total loss increases dramatically, a multi-level decision-making process is generated, including: Emergency decision: Initiate load transfer and emergency load leveling in the power consumption area, prioritizing the adjustment of large-capacity interruptible loads on overloaded single phases; Short-term decision: Implement an intelligent phase-switching switch control scheme to balance the load on each phase; Long-term decision: If the number of times the second preset trigger condition is met is greater than the second preset number of times, or the time for the second preset trigger condition to be met is greater than the second preset duration, then capacity expansion and distribution network reconstruction will be carried out.

[0018] Third preset trigger condition: , , , If a multiphase transformer is under heavy load or overload, or if there is a single-phase overload or a moderate imbalance in the three phases, a Level 1 warning will be issued. When a multiphase transformer is under heavy load or overload, there may be single-phase overload, moderate three-phase imbalance, and the overloaded single phase faces a high risk of overheating and damage. Meanwhile, the lightly loaded phases suffer capacity waste, and the total losses increase dramatically. Therefore, corresponding multi-level decisions are generated, including: Emergency decision: Initiate load transfer and load balancing in the power consumption area, prioritizing the adjustment of large-capacity interruptible loads on overloaded single phases; Short-term decision: Implement an intelligent phase-switching switch control scheme to balance the load on each phase; Long-term decision: If the number of times the third preset trigger condition is met is greater than the third preset number of times, or the time for the third preset trigger condition to be met is greater than the third preset duration, then capacity expansion and / or distribution network reconstruction will be carried out.

[0019] Fourth preset trigger condition: , , , If the multiphase transformer is under heavy load or overload, but there is no single-phase overload and the three phases are balanced, then a first-level warning will be issued. The multiphase transformer is under overall heavy load or overload, with no single-phase overload, and all three phases are balanced with no overload in any phase winding. The main risk comes from excessive overall temperature rise of the multiphase transformer, potentially leading to excessive top oil temperature or hot spot temperature. However, the risk of localized overheating is low. Therefore, corresponding multi-level decisions are generated, including: Emergency Decision-Making: Monitor the oil temperature and winding temperature of the multiphase transformer. If the oil temperature and winding temperature reach the corresponding threshold, take measures to cool down the transformer, such as starting cooling devices like fans. Inspect the multiphase transformer, especially for noise and oil level, to prevent transformer failure. Initiate load transfer or power rationing in the power consumption area. Short-term decisions: Analyze load growth trends based on user-side data, predict the phase load rate of each phase within a preset time period, and optimize the load distribution of each phase based on the prediction results to further improve the three-phase balance; increase temporary ventilation or cooling measures; apply for emergency mobile transformers; Long-term decision: If the number of times the fourth preset trigger condition is met is greater than the fourth preset number of times, or the time for the fourth preset trigger condition to be met is greater than the fourth preset duration, then capacity expansion and / or distribution network reconstruction will be carried out.

[0020] Fifth preset trigger condition: , , , If the multiphase transformer is under heavy load or overload, but there is no single-phase overload, and the three phases are severely unbalanced, then a level one warning will be issued. When a multiphase transformer is under heavy load or overload, with no single-phase overload and severe three-phase imbalance, in addition to the risk of overall temperature rise, unbalanced operation also increases additional losses and reduces the efficiency and load-carrying capacity of the multiphase transformer. Therefore, corresponding multi-level decisions are generated, including: Emergency Decision-Making: Monitor the temperature of the heavily loaded phase; if the temperature reaches the corresponding threshold, cool it down; add capacitors to support the heavily loaded phase; initiate load transfer for the power consumption area. Short-term decision: Implement an intelligent phase-switching switch control scheme to balance the load on each phase; Long-term decision: If the number of times the fifth preset trigger condition is met is greater than the fifth preset number of times, or the time for the fifth preset trigger condition to be met is greater than the fifth preset duration, then capacity expansion and load adjustment for each phase will be carried out.

[0021] Sixth preset trigger condition: , , , If the multiphase transformer is under heavy load or overload, but there is no single-phase overload and the three phases are moderately unbalanced, then a level one warning will be issued. When a multiphase transformer is under overall heavy load or overload, with no single-phase overload and moderate three-phase imbalance, in addition to the risk of overall temperature rise, unbalanced operation also increases additional losses and reduces the efficiency and load-carrying capacity of the multiphase transformer. Therefore, corresponding multi-level decisions are generated, including: Emergency Decision-Making: Monitor the temperature of the heavily loaded phase; if the temperature reaches the corresponding threshold, cool it down; add capacitors to support the heavily loaded phase; prepare to initiate load transfer to the power consumption area. Short-term decision: Implement an intelligent phase-switching switch control scheme to balance the load on each phase; Long-term decision: If the number of times the sixth preset trigger condition is met is greater than the sixth preset number of times, or the time for the sixth preset trigger condition to be met is greater than the sixth preset duration, then capacity expansion and load adjustment for each phase will be carried out.

[0022] For the fifth and sixth preset trigger conditions, the situation where the total load rate exceeds the threshold while the phase load rate does not not only exists, but also accounts for a considerable proportion in actual power distribution networks, especially in power consumption areas that have undergone certain load management. Therefore, setting corresponding preset trigger conditions allows for more refined risk identification and more accurate handling.

[0023] Seventh preset trigger condition: , , , If there is a single-phase severe overload and a three-phase severe imbalance, a Level 1 warning will be issued. The presence of a single-phase severe overload and a severe three-phase imbalance represents the most dangerous hidden fault. While the multi-phase transformer is generally healthy, a severe overload in one phase causes localized overheating of the winding in that phase, accelerating insulation aging and easily triggering a single-phase fault. Therefore, a corresponding multi-level decision-making process is generated, including: Emergency Decision: Activate the backup capacitor of the heavily loaded phase to increase the voltage support of that phase, monitor the temperature of the heavily loaded phase, and force the load balancing to start. Short-term decision: Set an installation plan for phase load protection devices; Long-term decision: If the number of times the seventh preset trigger condition is met is greater than the seventh preset number of times, or the time for the seventh preset trigger condition to be met is greater than the seventh preset duration, then the load of each phase will be adjusted.

[0024] Eighth preset trigger condition: , , , If a single-phase overload exists and the three phases are moderately unbalanced, a level-two warning will be issued. There is a single-phase overload and a moderate three-phase imbalance, but the three-phase current imbalance is still acceptable. The heavily loaded phase still faces the risk of overheating and requires close monitoring. Therefore, a corresponding multi-level decision is generated, including: Emergency decision: Activate the backup capacitor for the heavily loaded phase, monitor the temperature of the heavily loaded phase, and prepare to initiate load balancing; Short-term decision: If the time for meeting the eighth preset trigger condition is longer than the eighth preset duration, then load balancing will be initiated. Long-term decision: If the number of times the eighth preset trigger condition is met is greater than the eighth preset number of times, or the time for the eighth preset trigger condition to be met is greater than the eighth preset duration, then the load of each phase will be adjusted.

[0025] Ninth preset trigger condition: , , , If everything is normal, no warning will be issued; Tenth preset trigger condition: , , , The three phases are severely unbalanced, triggering a level-two early warning. The load level is safe, but the severe three-phase imbalance leads to a significant increase in additional transformer losses, making operation uneconomical and potentially causing voltage quality problems. Therefore, a corresponding multi-level decision is generated, including: Emergency decision-making: Analyze the causes of severe three-phase imbalance based on user-side data and multiphase transformer output data; Short-term decision: If the number of times the tenth preset trigger condition is met is greater than the tenth preset number of times, or the time for the tenth preset trigger condition to be met is greater than the tenth preset duration, then adjust the load of each phase. Long-term decision: Check whether the load access plan for the power consumption area is reasonable.

[0026] Eleventh preset trigger condition: , , , If the three phases are moderately unbalanced, a level three warning will be issued. The load level is safe, but the three-phase moderate imbalance will increase network losses, reduce transformer output and lifespan, and affect voltage quality over long-term operation. Therefore, a corresponding multi-level decision is generated, including: Emergency Decision: If the time for meeting the eleventh preset trigger condition is longer than the eleventh preset duration, then analyze the cause of the severe three-phase imbalance based on user-side data. Short-term and long-term decisions: If the number of times the eleventh preset trigger condition is met is greater than the eleventh preset number of times, or the time for the eleventh preset trigger condition to be met is greater than the eleventh preset duration, then the constructed power quality assessment function, combined with user-side data, will generate the optimal load balancing scheme through an optimized model.

[0027] In this embodiment, the higher the level, the lower the severity of the warning. A level 1 warning triggers a red warning on the terminal of the central control system, a level 2 warning triggers an orange warning on the terminal of the central control system, a level 3 warning triggers a yellow warning on the terminal of the central control system, and no warning is displayed in green, thus making it easy to distinguish the severity.

[0028] The corresponding multi-level decision-making system allows for direct activation of emergency decisions to address current issues, or it can be pushed to the central control system for activation upon receiving a start signal, thus incorporating a manual verification process to prevent incorrect direct activation. Short-term and long-term decisions are pushed to the central control system to assist users in making decisions and helping them develop better strategies to solve current problems, thereby achieving accurate and effective monitoring and management of the power consumption area.

[0029] The determination of multiple indicators can more accurately reflect the current operating status of multiphase transformers, accurately identify existing problems, so as to make timely adjustments, realize the intelligent upgrade from preventing multiphase transformer burnout to ensuring the healthy operation of multiphase transformers, reduce power outages and economic losses caused by multiphase transformer failures, provide a time window for proactive operation and maintenance, avoid the expansion of faults leading to power outages, and ensure the power consumption and safety of the power consumption area. By setting multiple preset trigger conditions, the main operating conditions of multiphase transformers can be covered as much as possible, so as to carry out different levels of early warning and corresponding multi-level decision-making, assist users to intervene in advance, ensure the normal operation of multiphase transformers, avoid the occurrence of faults, and thus ensure the normal power supply in the power consumption area.

[0030] In other embodiments, for and The judgment can be changed to and The judgment, among which This represents the maximum phase load factor. ; The load rate is extremely poor. ;Specifically, for ,in This is the threshold for phase load rate; for ; for , for For multiphase transformers, this reduces the need for judgment and analysis, and allows for faster identification of the preset triggering conditions.

[0031] This embodiment also provides a power consumption area monitoring and management system based on a smart converged terminal, used to execute a power consumption area monitoring and management method based on a smart converged terminal, including: Intelligent fusion terminal is used to collect data from the output side of multiphase transformers; It is also used to calculate monitoring indicators based on data from the output side of multiphase transformers, including: the total load rate of multiphase transformers. Phase load rate of each phase of a multiphase transformer Multiphase current imbalance ; It is also used to generate tiered early warning instructions and corresponding multi-level decisions based on monitoring indicators and through the constructed tiered early warning decision model, and send them to the external central control system.

[0032] This embodiment also provides an electricity consumption area monitoring and management system based on a smart fusion terminal, used to execute an electricity consumption area monitoring and management method based on a smart fusion terminal, including: a smart fusion terminal and a server; Intelligent fusion terminal is used to collect data from the output side of multiphase transformers; It is also used to calculate monitoring indicators based on data from the output side of multiphase transformers, including: the total load rate of multiphase transformers. Phase load rate of each phase of a multiphase transformer Multiphase current imbalance ; The server is used to generate tiered early warning instructions and corresponding multi-level decisions based on monitoring indicators and a constructed tiered early warning decision model, and then send them to the external central control system.

[0033] Example 2 This embodiment is basically the same as the above embodiment, except that: in actual monitoring, other situations may occur during the operation of multiphase transformers. In order to more comprehensively analyze various operating conditions of multiphase transformers, other preset triggering conditions are also set, as follows: Twelfth preset trigger condition: , , , ; Thirteenth preset trigger condition: , , , ; Fourteenth preset trigger condition: , , , ; Fifteenth preset trigger condition: , , , ; Sixteenth preset trigger condition: , , , ; Seventeenth preset trigger condition: , , , ; Eighteenth preset trigger condition: , , , ; Nineteenth preset trigger condition: , , , ; Twentieth preset trigger condition: , , , ; Twenty-first preset trigger condition: , , , ; Twenty-second preset trigger condition: , , , ; Twenty-third preset trigger condition: , , , ; Twenty-fourth preset trigger condition: , , , .

[0034] The data in the above preset trigger conditions are contradictory, therefore a contradiction warning is issued to prompt the user to check the acquired data and its corresponding device, confirm the cause of the data contradiction, and avoid misjudgment; taking the twelfth preset trigger condition as an example: , , , If the three-phase load rates are close (small range), it means that the three-phase current or power should be relatively balanced. In this case, the current imbalance should theoretically be small, rather than greater than the corresponding threshold. Therefore, the data obtained may be problematic, the calculation may be flawed, or it may be affected by external factors. It should be investigated.

[0035] Example 3 This embodiment is basically the same as the above embodiment, except that it also includes: multi-phase transformer output side data, and also includes: active power of each phase. and reactive power ; Based on the output side data and user side data of the multiphase transformer, the load growth trend is analyzed, the phase load rate of each phase is predicted within a preset time period, and the load distribution of each phase is optimized based on the prediction results. The specific process is as follows: Input characteristics are obtained based on the output-side data and user-side data of the multiphase transformer; The input features include: historical load features, time features, meteorological features, and load statistics features; Historical load characteristics, including: historical active power of each phase. reactive power Apparent power Phase load rate The dimension of each historical load feature is the number of phases. ; Time features include: sine periodic encoding, cosine periodic encoding, month encoding, and holiday markers; among which, sine periodic encoding includes: , Cosine periodic encoding, including: , The month code is a normalized version of the month 1-12, and the holiday flag is 0 or 1, where 0 indicates no holidays and 1 indicates holidays; correspondingly, the feature dimensions are 2, 2, 1, and 1. Meteorological characteristics, including: seasonal code, temperature, humidity (relative humidity), and weather code; the seasonal code is spring. ,summer ,Autumn ,winter The weather code is sunny. Cloudy sky ,cloudy day ,rain Correspondingly, the feature dimensions are 2, 1, 1, and 2. Load statistical characteristics, including: multiphase current imbalance Total load factor of multiphase transformers Load variation rate of each phase Correspondingly, the feature dimensions are 1, 1, and 1. ; Where the input feature dimension , ; Standardize the input features; Get window length The standardized input features are used as input to the constructed LSTM model to obtain the phase load rate of each phase of the multiphase transformer within a preset future time period, which is then used as the output. The input to the constructed LSTM model is: , shape ; The output is: , shape ,in .

[0036] The constructed LSTM model is trained using historical data, and the LSTM model that meets the preset requirements is used as the constructed LSTM model for application. Based on the phase load rate of each phase of the multiphase transformer within a predetermined future time period, optimize the load distribution of each phase, including: Calculate the corresponding phase load rate of each phase of the multiphase transformer within a predetermined time period. ; If the phase load rate of each phase of the multiphase transformer is within the preset time period in the future... Greater than ,or Greater than or equal to Then, the load of each phase is adjusted to generate a load adjustment scheme for each phase at a future preset time; the load of each phase can be allocated in advance to avoid the development of a three-phase imbalance. Monitoring can also continue, and if it corresponds to a preset future time, if ,or Then, the user adjustment plan for each phase load corresponding to the preset future time will be activated, so as to respond quickly and make timely adjustments. This includes adjusting the load of each phase, either manually or adaptively. This includes adaptive adjustments, including: Adjust the preset proportion of users on the overloaded single-phase adjustable user to a non-overloaded state, and On the smallest single phase; After the judgment adjustment , , and If the preset trigger condition generates a decision to adjust the load of each phase, then a preset proportion of users on the overloaded single phase will be adjusted to a non-overloaded state. On the smallest single phase. The preset ratio can be set according to actual needs. Different preset ratios can be set for different single phases, thereby gradually adjusting and reducing the rate of change, ensuring that the adjustment is as level as possible when the adjustment rate is small, and ensuring the stable operation of the power grid. Furthermore, in other embodiments, adjustments can be set to be made within a preset time period, further reducing the impact of the adjustments.

[0037] Example 4 This embodiment is basically the same as the above embodiment, except that it also includes: predicting the multi-phase transformer outlet side data within a future preset time period, calculating monitoring indicators, analyzing whether there will be a situation that exceeds the corresponding threshold, and if so, monitoring is performed, and the optimal user adjustment scheme for the load distribution of each phase is generated by optimizing the improved genetic algorithm, and executed when the monitoring indicators exceed the corresponding threshold.

[0038] The specific steps are as follows: Data prediction steps: Predict the output-side data of multiphase transformers within a preset time period; the output-side data of multiphase transformers also includes: the number of users connected to multiple transformers and the parameters of each user, and the active power of each phase. and reactive power The number of users is The user set is User parameters include user Current phase Active power reactive power Apparent power and adjustment costs ; Specifically, it includes: Based on historical multiphase transformer output side data, the first prediction result is to pre-determine the multiphase transformer output side data within a pre-determined time period in the future. Alternatively, based on historical user-side data on temperature and humidity, predict the temperature and humidity within a preset time period in the future; Based on historical multiphase transformer output side data and combined with user side data for a future preset time period, the second prediction result is obtained by predicting the multiphase transformer output side data for the future preset time period. The aforementioned multiphase transformer output side data for a predetermined future time period are modeled using an LSTM model. Indicator calculation steps: Based on the forecast results, calculate the monitoring indicators for the future preset time period; Specifically, it includes: Based on the first prediction result, the monitoring indicators for the future preset time period are calculated and used as the first reference data; Based on the second prediction results, the monitoring indicators for the future preset time period are calculated and used as the second reference data; Time determination step: Analyze whether there are any monitoring indicators that are greater than the corresponding threshold within the future preset time period. If so, perform abnormal time analysis, obtain the monitoring time, and execute the monitoring analysis step. If no monitoring time is obtained, execute the allocation optimization step. If not, execute the data prediction step after a preset pause time. Specifically, it includes: Analyze whether there are any monitoring indicators in the first and second reference data that are greater than the corresponding threshold. If so, the corresponding future time is regarded as an abnormal time. If not, the data prediction step is executed after a preset pause time. Determine whether the time interval between the abnormal moment and the current moment is greater than the preset time interval. If so, use the time before the abnormal moment that is a distance from the preset monitoring time interval as the monitoring moment and execute the monitoring and analysis steps; otherwise, execute the allocation optimization steps. Monitoring and analysis steps: Obtain the multiphase transformer outlet side data between the current time and the monitoring time, analyze the similarity between the multiphase transformer outlet side data and the predicted multiphase transformer outlet side data (there are predicted results corresponding to monitoring indicators that are greater than the corresponding threshold), determine whether the similarity is greater than the preset similarity, if yes, then perform the allocation optimization step, if no, then perform the trend analysis step. Trend analysis steps: If the change trends of the multiphase transformer outlet side data between the current time and the monitoring time are the same, then the allocation optimization step is executed; otherwise, after a preset pause time, the data prediction step is executed. Where the change trends are the same, they are either all increasing or all decreasing. For fluctuating data, the overall change trend is taken. Allocation optimization steps: Based on the users connected to each phase of the multiphase transformer, generate user adjustment schemes for load allocation of each phase, and iteratively optimize the user adjustment schemes using the constructed fitness function to obtain the optimal user adjustment scheme; Specifically, based on the users connected to each phase of the multiphase transformer, generate Each phase load distribution user adjustment scheme and its corresponding decision matrix are considered as individual schemes. Inappropriate individual schemes are discarded, and the resulting group is combined into an initial population. Inappropriate individual schemes include those where either the individual scheme or its corresponding decision matrix is ​​unreasonable, such as when a user is connected to multiple phases. and Mismatch; In other embodiments, a user importance level can also be set. Users whose importance level is higher than the preset level will not be adjusted. If an adjustment is made, the individual plan will be an unreasonable individual plan, thereby ensuring power supply in special areas. The individual plan is as follows: And the corresponding decision matrix is The length of an individual solution is equal to the number of users. , The gene value is 0, which indicates that the user... Keep the current phase, set the value to 1, indicating the user Randomly assigned to a phase with a lighter load (i.e., another phase with a load rate lower than the user's current phase), with a value of 2, indicating that the user must be... Move out of the current phase, and prioritize moving to the phase with the lightest load (i.e., the phase with the lowest load rate). The user adjustment plan can be generated using either a random generation method or a heuristic generation method, or a user adjustment plan with a first preset percentage can be generated using a random generation method, and a user adjustment plan with a second preset percentage can be generated using a heuristic generation method; wherein the sum of the first preset percentage and the second preset percentage is 1; Random generation methods produce more random individual schemes, resulting in a more diverse initial population, which is beneficial for finding the globally optimal individual scheme. Heuristic generation methods produce individual schemes with certain optimization results, that is, they can provide optimization directions, and the initial population can better optimize in the direction of optimization, which is beneficial for finding the optimal individual scheme more quickly. This embodiment combines the advantages of both schemes. It uses a random generation method to generate a user adjustment scheme with a first preset proportion, and a heuristic generation method to generate a user adjustment scheme with a second preset proportion. This ensures the genetic diversity of the initial population, avoids subsequent optimization from getting stuck in local optima, and limits the optimization direction to ensure that the optimal individual scheme can be found in the end.

[0039] In this embodiment, both the first preset percentage and the second preset percentage are set to 50%; Random generation method (50%): For each user, the gene value {0,1,2} is randomly assigned with the probability of {0.6, 0.3,0.1}. In other embodiments, the assignment probability can also be set according to the requirements. Heuristic generation method (accounting for 50%): Identifying the overload phase (i.e. Users of this type of gene are forcibly marked with a gene value of 2; for overloaded phases (i.e., ... , The maximum overload threshold, For users of the light-load phase (i.e., those with a high probability of gene value 1), the first preset marker is used; for those of the light-load phase (i.e., those of the light-load phase), the marker is used to assign a gene value of 1. For users with a gene value of 0, the first and second preset high probabilities are set to a higher probability (at least greater than 50%) according to the needs, so as to avoid adjusting users who do not need to be adjusted, while adjusting users who are overloaded or overloaded.

[0040] The corresponding decision matrix is , Indicates user At parting , Indicates user Not parting In other embodiments, the individual solutions can also be constructed as follows: , Indicates user Originally located in different places , Indicates user Not parting , Indicates user Adjusted phase Alternatively, individual solutions can also be constructed as , Indicates user No adjustment Indicates user Adjusted phase Individual solutions can be configured according to specific needs. Constructing the fitness function ; in This represents the decision matrix corresponding to the individual solutions. , Indicates user At parting , Indicates user Not parting ; The overall objective function is as follows: ; in To adjust the cost objective function: ; in For users The adjustment cost is [amount] yuan per instance; if Then adjustments are needed. ;like Then no adjustment is needed. ; For users The current phase difference, ;by For example, a three-phase transformer, then for , for ; The objective function for adjusting the quantity is: ; in For users Apparent power, if the user If adjusted, then If the user If not adjusted, then ; The objective function for three-phase imbalance is: ,or ; in The average apparent power of each phase; For penalty items: ; in This is the coefficient for the penalty term; a larger value is taken, such as 10. 3 ; These are weighting coefficients, reflecting economic efficiency, operational impact, operational quality, and constraint satisfaction, respectively; in this embodiment, they are set as follows: The fitness function comprehensively considers factors such as economy, operability, and impact on operational quality to ensure the accuracy and comprehensiveness of the assessment.

[0041] Based on the fitness function, the initial population is iteratively optimized to obtain the individual solution with the best fitness. Specifically, it includes: S1. Initialize the number of iterations R=1; S2. Calculate the fitness of each individual's scheme in the initial population, and sort them in descending order of fitness to generate the first sorting result; S3. Obtain the top results from the first sorted list. Each individual plan uses a roulette wheel method to determine the prior... Choose from individual options The first selection ensures the superiority of genes in the candidate parent individuals in terms of fitness, while the second selection ensures the randomness of the selected parent. Compared to existing technologies, this approach accelerates the iterative selection of better individual schemes, guarantees randomness, and avoids getting trapped in local optima. and This is a constant for the number of individual schemes, set according to requirements; S4. Perform crossover and mutation on the selected individual schemes, and remove unreasonable individual schemes to form an iterative population; where crossover refers to crossing the gene segments of two individual schemes, and mutation refers to changing the gene values ​​in the individual schemes. S5. Iterate the fitness of each individual's scheme in the population according to the fitness function; S6. Sort the individual schemes in the initial population and the iterative population in descending order of fitness to generate the second sorting result; S7. Obtain the top results from the second sorting results. Individual proposals lead to the formation of new groups; S8. Has the new population converged? If yes, obtain the individual scheme with the highest fitness in the new population as the optimal user adjustment scheme for each phase load allocation; if not, proceed to S9. The convergence criterion for whether the new population converges is: ,in The fitness is the optimal fitness among the new population in the current iteration. For the front The optimal fitness in the new population after the next iteration. A constant for counting the number of iterations. This is the convergence constant, set according to requirements; S9. Determine whether the current iteration number R is greater than the preset iteration number threshold. If yes, obtain the individual scheme with the highest fitness in the new population as the optimal user adjustment scheme for each phase load allocation. If no, update the population to the initial population, R=R+1, and then execute S3.

[0042] The implementation steps are as follows: Obtain the current data of the multiphase transformer outlet side, calculate the monitoring indicators, and if the monitoring indicators are greater than the corresponding thresholds, execute the generated optimal user adjustment scheme for the load distribution of each phase. When the monitoring indicators are greater than the corresponding thresholds, a single-phase overload or heavy load occurs, or a three-phase imbalance occurs. Therefore, execute the generated optimal user adjustment scheme for the load distribution of each phase to adjust the frequency and reduce the overload or heavy load, thereby completing the load balancing and ensuring the stable operation of multiple transformers.

[0043] In other embodiments, the execution steps are as follows: obtain the multi-phase transformer outlet side data at the current moment, calculate the monitoring index, and if the monitoring index is greater than the corresponding threshold and the difference between the current moment and the abnormal moment is less than the preset time difference, then execute the generated optimal user adjustment scheme for each phase load allocation; execute the generated optimal user adjustment scheme for each phase load allocation when the time and monitoring index are close to the prediction result, so as to avoid premature execution, excessive load adjustment, and affecting the stable operation of the power consumption area.

[0044] For adjusting the load of each phase, this solution predicts load changes, generates user adjustment plans in advance, and then makes adjustments when the conditions are met. It can quickly make adjustments when the load is unreasonable, ensuring the stable operation of multiple transformers, power safety, and the rational allocation of power resources.

[0045] For load change prediction, two scenarios were implemented: one considering only the changes in data from the multiphase transformer's output side, and the other combining user-side data. The different inputs to these two predictions affected the results. Considering the varying degrees of influence of user-side data on the multiphase transformer's output side data, two prediction methods were employed. This ensures that the results reflect both the magnitude of the user-side data's impact on the multiphase transformer's output side data. Furthermore, this scheme uses an improved genetic algorithm to generate the optimal user adjustment scheme. By combining randomness and heuristic generation, individual schemes are generated to form an initial population. This ensures that the initial population possesses both genetic superiority and randomness, preventing subsequent iterative optimization from getting trapped in local optima and guaranteeing the global nature of the search. The iterative optimization process involves two selections to generate parent generations. The first selection ensures the superiority of genes in the candidate parent individual schemes in terms of fitness, while the second selection ensures the randomness of the selected parent generation. Compared with existing technologies, this can accelerate the iterative selection of better individual schemes, guarantee randomness, and avoid getting trapped in local optima. In summary, this solution can perform targeted optimization, ensuring the rapid generation of optimal user adjustment plans while avoiding getting stuck in local optima and guaranteeing global effectiveness.

[0046] Example 5 This embodiment is basically the same as the above embodiments, except that: the mutation adopts an adaptive mutation strategy; Specifically, the adaptive mutation strategy generates mutation probabilities based on the number of iterations and fitness; and randomly changes the gene values ​​in the individual scheme according to the mutation probabilities. Where the probability of variation : ; in To preset the fitness threshold, and ; Given the basic mutation probability, and ; The preset iteration count threshold is used. In this scheme, mutation is dynamically adaptive. First, based on the fitness of individual schemes, the mutation probability is set from low to high. For individuals with poor fitness, the overloaded phase is mutated with a higher probability, thus avoiding the retention of inferior genes and acquiring as many superior genes as possible, which is beneficial for finding the optimal individual scheme. For individuals with fitness exceeding a preset extremely high value... First, no mutation is performed directly to avoid excellent genes from mutating during the mutation process, which would affect the overall superiority of individual schemes, thus completing directional mutation. Second, this scheme sets a basic mutation probability. As the number of iterations increases, the fitness of individual schemes in the population becomes better and better, and their mutation probability can be gradually reduced, thereby avoiding the mutation of excellent genes. However, a certain mutation probability is set to avoid getting trapped in local optima. This scheme combines directional mutation and basic mutation, which ensures the preservation of excellent genes, is more conducive to finding the optimal scheme, and avoids getting trapped in local optima.

[0047] In other embodiments, the similarity of individual schemes in the population can be calculated. If the similarity is greater than a preset similarity threshold, the mutation probability is increased, thereby enabling diversified mutation and avoiding getting trapped in local optima during the population optimization process.

[0048] Example 6 This embodiment is basically the same as the above embodiment, except that the analysis of whether there are any monitoring indicators greater than the corresponding threshold within the future preset time period is performed. If either the first reference data or the second reference data has a monitoring indicator greater than the corresponding threshold, a difference warning prompt is generated so that users can analyze the impact of adding user-side data, determine whether user-side data needs to be added for prediction, and ensure the accuracy of the prediction results.

[0049] The above descriptions are merely embodiments of the present invention. Commonly known structures and characteristics of the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A method for monitoring and managing electricity consumption areas based on intelligent converged terminals, characterized in that, include: Data from the output side of multiphase transformers is collected through intelligent fusion terminals; Based on the data from the output side of the multiphase transformer, monitoring indicators are calculated, including: the total load rate of the multiphase transformer. Phase load rate of each phase of a multiphase transformer Multiphase current imbalance ; Based on the monitoring indicators, a hierarchical early warning decision-making model is constructed to conduct hierarchical early warning and generate corresponding multi-level decisions; The hierarchical early warning decision-making model is based on , , and Based on the preset trigger conditions, tiered early warnings and corresponding multi-level decisions are generated; among them, the preset trigger conditions are analyzed. , , and The relationship between the magnitude of the corresponding threshold and the value of the threshold, where According to Calculate the difference in load rates between the two phases.

2. The method for monitoring and managing electricity consumption areas based on intelligent converged terminals according to claim 1, characterized in that, The multiphase transformer output side data includes: multiphase voltage. Multiphase current Total active power Total reactive power ; including multiphase voltage and multiphase current middle express Mutually; The total load rate of the multiphase transformer Used to assess the utilization rate of transformer capacity: ； in This refers to the rated capacity of a multiphase transformer. The total apparent power currently output by the multiphase transformer: ； Phase load rate of each phase of the multiphase transformer for: ； in for Phase load rate; for Apparent power borne by the phase: ; The number of phases; The multiphase current imbalance for: ； in This refers to the multiphase current imbalance. The average value of the multiphase current: ; Maximum current deviation: .

3. The method for monitoring and managing electricity consumption areas based on intelligent converged terminals according to claim 1, characterized in that, The preset triggering conditions include: First preset trigger condition: , , , If a multiphase transformer is under overall heavy load or overload, or if there is a single-phase overload but the three phases are balanced, a Level 1 warning will be issued; among which... The total load rate threshold; for Phase load rate threshold; This is the difference in load rates between the two phases. ; To balance the judgment threshold; The first current imbalance, This is the second current imbalance, and ; Second preset trigger condition: , , , If a multiphase transformer is under heavy load or overload, or if there is a single-phase overload or a severe three-phase imbalance, a Level 1 warning will be issued. Third preset trigger condition: , , , If a multiphase transformer is under heavy load or overload, or if there is a single-phase overload or a moderate imbalance in the three phases, a Level 1 warning will be issued. Fourth preset trigger condition: , , , If the multiphase transformer is under heavy load or overload, but there is no single-phase overload and the three phases are balanced, then a first-level warning will be issued. Fifth preset trigger condition: , , , If the multiphase transformer is under heavy load or overload, but there is no single-phase overload, and the three phases are severely unbalanced, then a level one warning will be issued. Sixth preset trigger condition: , , , If the multiphase transformer is under heavy load or overload, but there is no single-phase overload and the three phases are moderately unbalanced, then a level one warning will be issued. Seventh preset trigger condition: , , , If there is a single-phase severe overload and a three-phase severe imbalance, a Level 1 warning will be issued. Eighth preset trigger condition: , , , If a single-phase overload exists and the three phases are moderately unbalanced, a level-two warning will be issued. Ninth preset trigger condition: , , , If everything is normal, no warning will be issued; Tenth preset trigger condition: , , , The three phases are severely unbalanced, triggering a level-two early warning. Eleventh preset trigger condition: , , , If the three phases are moderately unbalanced, a level three warning will be issued. The higher the level of the multi-level warning, the lower the severity.

4. The method for monitoring and managing electricity consumption areas based on intelligent converged terminals according to claim 2, characterized in that, Also includes: Predict the output data of multiphase transformers within a preset time period, calculate monitoring indicators, analyze whether there will be situations where the values ​​exceed the corresponding thresholds, and if so, monitor the situation. Optimize and generate the best user adjustment scheme for the load distribution of each phase using an improved genetic algorithm, and execute the scheme when the monitoring indicators exceed the corresponding thresholds.

5. The method for monitoring and managing electricity consumption areas based on intelligent converged terminals according to claim 4, characterized in that, The process involves predicting multiphase transformer outlet-side data within a preset future time period, calculating monitoring indicators, analyzing whether any values ​​exceed corresponding thresholds, and if so, performing monitoring. An improved genetic algorithm is then used to optimize and generate the optimal user adjustment scheme for each phase load allocation, which is executed when monitoring indicators exceed corresponding thresholds. This includes: Data prediction steps: Predict the output-side data of multiphase transformers within a preset time period; the output-side data of multiphase transformers also includes: the number of users connected to multiple transformers and the parameters of each user; where the number of users is... The user set is User parameters include user Current phase Active power reactive power Apparent power and adjustment costs ; Indicator calculation steps: Based on the forecast results, calculate the monitoring indicators for the future preset time period; Time determination step: Analyze whether there are any monitoring indicators that are greater than the corresponding threshold within the future preset time period. If so, perform abnormal time analysis, obtain the monitoring time, and execute the monitoring analysis step. If no monitoring time is obtained, execute the allocation optimization step. If not, execute the data prediction step after a preset pause time. Monitoring and analysis steps: Obtain the multiphase transformer outlet side data between the current time and the monitoring time, analyze the similarity between the multiphase transformer outlet side data and the predicted data, determine whether the similarity is greater than the preset similarity, and if so, perform the allocation optimization step; Allocation optimization steps: Based on the users connected to each phase of the multiphase transformer, generate user adjustment schemes for load allocation of each phase, and iteratively optimize the user adjustment schemes using the constructed fitness function to obtain the optimal user adjustment scheme; The implementation steps are as follows: Obtain the current data of the multiphase transformer outlet side, calculate the monitoring indicators, and if the monitoring indicators are greater than the corresponding thresholds, execute the generated optimal user adjustment scheme for the load distribution of each phase.

6. The method for monitoring and managing electricity consumption areas based on intelligent converged terminals according to claim 4, characterized in that, It also includes: collecting user-side data; User-side data includes: environmental information of the user's electricity consumption area; the environmental information includes: temperature and humidity; The output-side data of the multiphase transformer also includes: the active power of each phase. and reactive power ; The data prediction step includes: Based on historical multiphase transformer output side data, the first prediction result is to pre-determine the multiphase transformer output side data within a pre-determined time period in the future. Alternatively, based on historical user-side data on temperature and humidity, predict the temperature and humidity within a preset time period in the future; Based on historical multiphase transformer output side data and combined with user side data for a future preset time period, the second prediction result is obtained by predicting the multiphase transformer output side data for the future preset time period. The calculation steps for the aforementioned indicators include: Based on the first prediction result, the monitoring indicators for the future preset time period are calculated and used as the first reference data; Based on the second prediction results, the monitoring indicators for the future preset time period are calculated and used as the second reference data; The time determination step includes: Analyze whether there are any monitoring indicators in the first and second reference data that are greater than the corresponding threshold. If so, the corresponding future time is regarded as an abnormal time. If not, the data prediction step is executed after a preset pause time. Determine whether the time interval between the abnormal moment and the current moment is greater than the preset time interval. If so, use the time before the abnormal moment that is a distance from the preset monitoring time interval as the monitoring moment and execute the monitoring and analysis steps. If not, execute the allocation optimization steps.

7. The method for monitoring and managing electricity consumption areas based on an intelligent fusion terminal according to claim 6, characterized in that, The allocation optimization step includes: Based on the users connected to each phase of the multiphase transformer, generate Each phase load distribution user adjustment scheme is considered as an individual scheme, and unreasonable individual schemes are eliminated, and combined into an initial group; where the individual schemes are... And the corresponding decision matrix is The length of an individual solution is equal to the number of users. , The gene value is 0, which indicates that the user... Keep the current phase, set the value to 1, indicating the user Randomly assigned to a phase with a lighter load, with a value of 2, indicating that the user must be... Remove from the current phase, prioritizing the phase with the lightest load; Indicates user At parting , Indicates user Not parting ; The user adjustment plan can be generated using a random generation method, or a heuristic generation method, or a user adjustment plan with a first preset percentage can be generated using a random generation method, and a user adjustment plan with a second preset percentage can be generated using a heuristic generation method. Constructing the fitness function ; in The overall objective function is as follows: ； in To adjust the cost objective function: ； in For users The adjustment cost is [amount] yuan per instance; if Then adjustments are needed. ;like Then no adjustment is needed. ; For users The current phase difference, ;by For example, a three-phase transformer, then for , for ; The objective function for adjusting the quantity is: ； in For users Apparent power, if the user If adjusted, then If the user If not adjusted, then ; The objective function for three-phase imbalance is: ,or ; in The average apparent power of each phase; For penalty items: in This is the coefficient for the penalty term; These are the weighting coefficients; Based on the fitness function, the initial population is iteratively optimized to obtain the individual scheme with the best fitness.

8. The method for monitoring and managing electricity consumption areas based on intelligent converged terminals according to claim 7, characterized in that, The initial population is iteratively optimized based on the fitness function to obtain the individual scheme with the optimal fitness. Specifically, it includes: S1. Initialize the number of iterations R=1; S2. Calculate the fitness of each individual's scheme in the initial population, and sort them in descending order of fitness to generate the first sorting result; S3. Obtain the top results from the first sorted list. Each individual plan uses a roulette wheel method to determine the prior... Choose from individual options Individual solutions; S4. Perform crossover mutation on the selected individual schemes and eliminate unreasonable individual schemes to form an iterative population; S5. Iterate the fitness of each individual's scheme in the population according to the fitness function; S6. Sort the individual schemes in the initial population and the iterative population in descending order of fitness to generate the second sorting result; S7. Obtain the top results from the second sorting results. Individual proposals lead to the formation of new groups; S8. Has the new population converged? If so, obtain the individual scheme with the highest fitness in the new population as the optimal user adjustment scheme for load distribution in each phase; otherwise, execute S9. S9. Determine whether the current iteration number R is greater than the preset iteration number threshold. If yes, obtain the individual scheme with the highest fitness in the new population as the optimal user adjustment scheme for each phase load allocation. If no, update the population to the initial population, R=R+1, and then execute S3.

9. The method for monitoring and managing electricity consumption areas based on an intelligent fusion terminal according to claim 8, characterized in that, The mutation employs an adaptive mutation strategy; The adaptive mutation strategy generates mutation probabilities based on the number of iterations and fitness; and randomly changes the gene values ​​in the individual scheme according to the mutation probabilities. Where the probability of variation : ； in To preset the fitness threshold, and ; Given the basic mutation probability, and ; This is a preset threshold for the number of iterations.

10. A power consumption area monitoring and management system based on an intelligent fusion terminal, characterized in that, Used to perform the power consumption area monitoring and management method based on a smart fusion terminal as described in any one of claims 1-9.

Images