Multi-scene energy management method and system based on dynamic distributed architecture

Abstract

The invention provides a multi-scene energy management method and system based on a dynamic distributed architecture, and relates to the technical field of power energy management, and the method comprises the steps: obtaining the first power consumption of each sub-region in a region in a first time period, and the second power consumption in a second time period before the current moment; combining the first electricity consumption and the second electricity consumption to predict third electricity consumption of each sub-region in the first time period; generating the generating capacity in each first time period according to the environment information of each sub-region; combining the generating capacity and the third power consumption to generate a supply-demand balance parameter; and adjusting the supply and demand balance parameter according to the energy consumption load type of each sub-region, generating a target supply and demand balance parameter, and generating a power distribution scheme of each energy power generation device according to the target supply and demand balance parameter. The method has the technical effects that the dynamic change of the power demand is responded in time, the mismatching of the power resource allocation and the actual demand is avoided as much as possible, and the resource utilization efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power energy management, in particular to a multi-scene energy management method and system based on a dynamic distributed architecture. BACKGROUND

[0002] With the development of smart grid technology and the promotion of energy internet, regional power supply systems are increasingly complex, and the electricity demand of each sub-region presents significant differences and dynamic change characteristics. How to accurately predict electricity demand in different regions and achieve precise allocation of power resources on this basis has become a technical problem that needs to be solved.

[0003] The prior art usually uses a single historical data analysis method to predict electricity demand and performs power dispatching based on fixed allocation rules. Although this method can meet the basic power supply demand to some extent, it cannot respond to the dynamic changes in electricity demand in a timely manner, resulting in a mismatch between power resource allocation and actual demand, reducing resource utilization efficiency. SUMMARY

[0004] The present application provides a multi-scene energy management method and system based on a dynamic distributed architecture, a device and a storage medium, which are used to respond to the dynamic changes in electricity demand in a timely manner, minimize the mismatch between power resource allocation and actual demand, and improve resource utilization efficiency.

[0005] In a first aspect, the present application provides a multi-scene energy management method based on a dynamic distributed architecture, the method comprising: obtaining a first electricity consumption of each sub-region in a region in a first time period after a current time in a historical date, and a second electricity consumption in a second time period before the current time; combining the first electricity consumption and the second electricity consumption to predict a third electricity consumption of each sub-region in the first time period; obtaining environmental information of an environment in which a corresponding energy generation device of each sub-region is located, and generating a power generation of each energy generation device in the first time period according to the environmental information; combining the power generation and the third electricity consumption to generate a supply-demand balance parameter of each sub-region; obtaining an energy load type of each sub-region, the energy load type being used to represent the electricity characteristics of each sub-region; adjusting the supply-demand balance parameter according to the energy load type to generate a target supply-demand balance parameter, and generating a power allocation scheme of each energy generation device in the first time period according to the target supply-demand balance parameter.

[0006] By adopting the technical scheme, the first power consumption and the second power consumption are combined for prediction, the accuracy of power consumption prediction is improved, the influence of environmental information on power generation equipment is considered, and accurate assessment of power generation is realized. Based on comprehensive analysis of power generation and power consumption, supply-demand balance parameters are generated, and are differentially adjusted according to regional types, so that the power distribution scheme can reflect the actual supply-demand situation and meet the protection needs of different regions. This multi-dimensional data analysis and dynamic adjustment method timely responds to the dynamic changes of power demand, avoids mismatching of power resource distribution and actual demand as much as possible, and improves resource utilization efficiency.

[0007] Optionally, the combining the first power consumption and the second power consumption to predict the third power consumption of each sub-region in the first time period comprises: predicting a fourth power consumption of each sub-region in the first time period according to the second power consumption; and adjusting the fourth power consumption by the first power consumption to generate the third power consumption of each sub-region in the first time period.

[0008] By adopting the technical scheme, the first power consumption and the second power consumption are combined for prediction, the accuracy of power consumption prediction is improved, the influence of environmental information on power generation equipment is considered, and accurate assessment of power generation is realized. Based on comprehensive analysis of power generation and power consumption, supply-demand balance parameters are generated, and are differentially adjusted according to regional types, so that the power distribution scheme can reflect the actual supply-demand situation and meet the protection needs of different regions. This multi-dimensional data analysis and dynamic adjustment method timely responds to the dynamic changes of power demand, avoids mismatching of power resource distribution and actual demand as much as possible, and improves resource utilization efficiency.

[0009] Optionally, the adjusting the fourth power consumption by the first power consumption to generate the third power consumption of each sub-region in the first time period comprises: when an electric quantity difference between the first power consumption and the fourth power consumption is less than a preset difference value, taking the fourth power consumption as the third power consumption of each sub-region in the first time period; and when the electric quantity difference between the first power consumption and the fourth power consumption is not less than the preset difference value, performing weighted average on the first power consumption and the fourth power consumption to obtain the third power consumption of each sub-region in the first time period, wherein a weight value of the first power consumption is less than a weight value of the fourth power consumption.

[0010] By adopting the technical scheme, the preset difference value is set as a judgment threshold, when the difference between the two prediction results is small, the prediction result reflecting the recent power consumption characteristics is directly used to improve the prediction efficiency, when the difference is large, the weighted average method is used for fusion, and the sensitivity of the prediction result to the change of power consumption behavior is ensured by a higher weight of recent data. This adaptive adjustment mechanism based on the difference degree avoids unnecessary calculation overhead and maintains the accuracy and reliability of the prediction when the power consumption mode changes significantly.

[0011] Optionally, the step of combining the power generation and the third electricity consumption to generate supply and demand balance parameters for each of the sub-regions includes: calculating the difference between the power generation and the third electricity consumption; dividing each of the sub-regions into a first sub-region with a power surplus and a second sub-region with a power deficit based on the difference; determining the initial power supply capacity parameters for the first sub-region based on the power surplus; obtaining the power supply reliability index for the first sub-region; adjusting the initial power supply capacity parameters based on the power supply reliability index to generate target power supply capacity parameters for the first sub-region, wherein the power supply reliability index is used to characterize the output stability of the energy generation equipment in the first sub-region; determining the initial electricity demand parameters for the second sub-region based on the power deficit; obtaining the load importance level for the second sub-region; determining the target electricity demand parameters for the second sub-region based on the load importance level, wherein the load importance level is used to characterize the priority level of power supply guarantee for the electricity load in the second sub-region; and using the power supply capacity parameters or the electricity demand parameters as supply and demand balance parameters for each of the sub-regions.

[0012] By adopting the above technical solution, the supply and demand status of each sub-region is accurately identified by calculating the difference between power generation and tertiary electricity consumption, and then transformed into standardized evaluation indicators, ultimately generating comprehensive parameters reflecting the regional supply and demand balance. This multi-step parameter transformation mechanism enables quantitative assessment and unified expression of the supply and demand status of different regions, providing a reliable decision-making basis for the formulation of subsequent power allocation schemes and improving the scientificity and accuracy of power dispatch.

[0013] Optionally, adjusting the supply and demand balance parameters according to the energy load type to generate target supply and demand balance parameters includes: selecting load characteristic parameters corresponding to the energy load type of each sub-region from a load type database; wherein the load characteristic parameters include a load adjustment coefficient and a load response time, the load adjustment coefficient being used to characterize the adjustability of the electricity load for the applied energy load type, and the load response time being used to characterize the time for responding to power supply adjustment commands for the applied energy load type; calculating a first ratio of the load adjustment coefficient of each sub-region to a preset benchmark adjustment coefficient to obtain a first adjustment coefficient, and using the product of the supply and demand balance parameters of each sub-region and the first adjustment coefficient as a first adjustment parameter; obtaining a preset response time threshold, calculating a second ratio of the load response time of each sub-region to the response time threshold to obtain a second adjustment coefficient; and using the product of the first adjustment parameter and the second adjustment coefficient of each sub-region as the target supply and demand balance parameter.

[0014] By adopting the technical scheme, the first adjustment coefficient and the second adjustment coefficient are respectively calculated according to the load characteristic parameters in the load type database, two-stage accurate adjustment of the supply-demand balance parameter is realized, and thus the power distribution scheme can adapt to the adjustable degree of different load types and meet the response time sequence requirement of different loads, and the intelligent level and operation efficiency of the power distribution system are effectively improved.

[0015] Optionally, the generating, according to the target supply-demand balance parameter, of the power distribution scheme of each energy generation device in the first time period comprises: determining the power supply priority of each sub-region according to the target supply-demand balance parameter; and generating the power distribution scheme of each energy generation device in the first time period according to the power supply priority.

[0016] By adopting the technical scheme, the target supply-demand balance parameter is converted into the power supply priority, a clear power distribution priority is established, and the specific distribution scheme of the energy generation device is formulated accordingly. This priority-based distribution mechanism ensures that the power resources are reasonably distributed according to the actual demand and importance, improves the utilization efficiency of the generation device, and realizes the scientization and precision of power dispatching.

[0017] Optionally, after the generating, of the power distribution scheme of each energy generation device in the first time period, the method further comprises: monitoring the actual power consumption of each sub-region in the first time period; when the difference between the actual power consumption of any sub-region and the third power consumption exceeds a preset threshold, obtaining a change trend of the actual power consumption, the change trend comprising an upward trend and a downward trend; when the change trend is the upward trend, calculating a growth ratio of the actual power consumption relative to the third power consumption, and adjusting the power distribution scheme in the remaining time period according to the growth ratio, the adjustment comprising increasing the power supply power of the corresponding sub-region and calling the surplus power of the adjacent sub-region; when the change trend is the downward trend, calculating a decline ratio of the actual power consumption relative to the third power consumption, and adjusting the power distribution scheme in the remaining time period according to the decline ratio, the adjustment comprising reducing the power supply power and distributing the surplus power to the adjacent sub-region; and taking the adjusted power distribution scheme as the final power distribution scheme of the sub-region in the remaining time period.

[0018] By adopting the technical scheme, the actual power consumption is monitored in real time and compared with the predicted value, the dynamic adjustment mechanism is triggered when the difference exceeds the preset threshold, and the distribution scheme in the remaining time period is re-formulated based on the actual power consumption data. This mechanism combining real-time monitoring and dynamic adjustment can timely discover and respond to abnormal changes in power demand, ensure the continuous matching of the power distribution scheme and the actual power consumption, and improve the adaptability and operation stability of the power system.

[0019] In a second aspect, the present application provides a multi-scenario energy management system based on a dynamic distributed architecture, comprising: a first acquisition module, a first combination module, a second acquisition module, a second combination module, and a generation module, wherein, The first acquisition module is configured to acquire first power consumption of each sub-region in a region in a first time period and second power consumption of each sub-region in a second time period, the first time period being before the second time period; the first combination module is configured to combine the first power consumption and the second power consumption to predict third power consumption of each sub-region in a first time period, the first time period being after the second time period; the second acquisition module is configured to acquire environmental information of an environment in which each energy generation device corresponding to each sub-region is located, and generate power generation of each energy generation device in the first time period according to the environmental information; the second combination module is configured to combine the power generation and the third power consumption to generate a supply-demand balance parameter of each sub-region; and the generation module is configured to acquire a region type of each sub-region, adjust the supply-demand balance parameter according to the region type to generate a target supply-demand balance parameter, and generate a power distribution scheme of each energy generation device in the first time period according to the target supply-demand balance parameter.

[0020] In a third aspect, the present application provides an electronic device, adopting the following technical solution: comprising a processor, a memory, a user interface, and a network interface, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to execute a computer program of any of the above multi-scenario energy management methods based on a dynamic distributed architecture.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution: storing a computer program capable of being loaded by a processor and executing any of the above multi-scenario energy management methods based on a dynamic distributed architecture.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: By combining the first power consumption and the second power consumption for prediction, the accuracy of power consumption prediction is improved; meanwhile, the influence of environmental information on power generation equipment is considered to realize accurate assessment of power generation. Based on comprehensive analysis of power generation and power consumption, the supply-demand balance parameter is generated, and the region type is differentiated for adjustment, ensuring that the power distribution scheme can reflect the actual supply-demand situation and meet the protection needs of different regions. This multi-dimensional data analysis and dynamic adjustment method timely responds to the dynamic changes of power demand, avoids mismatch between power resource allocation and actual demand as much as possible, and improves resource utilization efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 FIG. 1 is a flow diagram of a multi-scenario energy management method based on a dynamic distributed architecture according to an embodiment of the present application; Figure 2 FIG. 2 is a structural diagram of a multi-scenario energy management system based on a dynamic distributed architecture according to an embodiment of the present application; Figure 3 FIG. 3 is a structural diagram of an electronic device according to an embodiment of the present application.

[0024] Marker explanation: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0025] In order to enable persons skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0026] In the description of the embodiments of the present application, the words such as "exemplary", "for example", or "for instance" are used to represent an example, illustration, or description. Any embodiment or design scheme described as "exemplary", "for example", or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "exemplary", "for example", or "for instance" are intended to present the relevant concept in a specific manner.

[0027] The energy management method of the present application is mainly applied to urban intelligent power distribution network system, for example, the power distribution management scene of a newly built urban area. The urban area contains multiple functional sub-regions, including large residential areas, commercial complexes, office buildings, hospitals, schools and other types of power consumption areas. Each sub-region is equipped with an intelligent electricity meter system and a power distribution automation device, and distributed photovoltaic power generation devices are installed on the roofs and open spaces of buildings in the region as auxiliary power sources. The system collects real-time power consumption data of each sub-region through the power distribution automation terminal, for example, residential areas have power consumption peaks in the morning and evening, office buildings have large power consumption during working hours, and commercial complexes have power consumption peaks in the afternoon and at night. The system divides hospitals, schools and other livelihood guarantee facilities into key guarantee areas, and other areas into regular guarantee areas. When the power demand in the region fluctuates, the system will prioritize the stability of power supply in key areas and guide regular areas to adjust their power consumption behavior through demand response methods. For example, during the summer peak period, the system will predict that there may be a power supply shortage by analyzing historical power consumption data, and will notify commercial complexes to adjust the air conditioning temperature in advance, or suggest that office buildings stagger the use of high-power equipment, while making full use of distributed photovoltaic power generation resources to achieve dynamic balance of power supply and demand in the region. This energy management scheme based on actual scenarios can effectively improve the operation efficiency and reliability of urban power distribution networks and provide important support for smart city construction.

[0028] Figure 1 is a flowchart of a multi-scenario energy management method based on a dynamic distributed architecture provided by an embodiment of the present application. As shown in Figure 1 , the method comprises S101-S106: S101, obtaining a first power consumption of each sub-region in the region in a first period after the current time in the historical date, and a second power consumption in a second period before the current time.

[0029] In order to accurately predict the future power consumption demand of each sub-region in the region, historical power consumption data is needed as a prediction basis. Specifically, the present application obtains the first power consumption of each sub-region in the region in the first period (for example, the same period of the previous year) and the second power consumption in the second period (for example, the last week) through the intelligent electricity meter collection system. The first period reflects the long-term power consumption law, including seasonal variation characteristics; the second period reflects the recent power consumption trend, which can reflect the changes in short-term power consumption behavior.

[0030] Taking a city's power distribution network as an example, the area is divided into multiple sub-regions, including residential areas, commercial areas, industrial parks, and other functional areas. The system collects electricity consumption data from all electrical devices in each sub-region through distribution automation terminals and performs aggregated processing. For example, for a residential area, the system obtains its average daily electricity consumption of 10,000 kWh in the same period last year (first period) and 12,000 kWh in the most recent week (second period). The system cleans and standardizes the collected electricity consumption data, removes outliers, and stores it according to time series.

[0031] By simultaneously acquiring electricity consumption data from these two time periods, a comprehensive understanding of the changing patterns of electricity load can be achieved: the data from the first time period reflects the cyclical characteristics and historical trends of electricity load, helping to predict long-term electricity consumption behavior; the data from the second time period reflects the latest changes in electricity consumption patterns, enabling timely capture of short-term fluctuations in electricity demand. This dual-time-series data acquisition method provides a more comprehensive and reliable data foundation for subsequent electricity consumption forecasting, effectively improving forecast accuracy. At the same time, this data acquisition method also facilitates the system's identification of abnormal changes in electricity consumption patterns, providing a basis for timely adjustments to power supply strategies.

[0032] S102, combining the first and second electricity consumption, predicts the third electricity consumption of each sub-region during the first time period.

[0033] To formulate a scientific and rational power allocation plan, accurate prediction of future electricity demand in each sub-region is necessary. This invention employs a dual-model prediction mechanism, making predictions based on a first electricity demand and a second electricity demand, and obtaining the final prediction result through weighted fusion.

[0034] Specifically, the system first uses time series analysis to predict the electricity consumption of each sub-region within the first time period (e.g., the next 24 hours) based on the first electricity consumption (e.g., data from the same period last year). This prediction process mainly considers historical electricity consumption patterns, including seasonal variations and periodic fluctuations. For example, for a commercial area, the predicted electricity consumption based on data from the same period last year is 15,000 kWh / day. Simultaneously, the system uses machine learning algorithms to predict the electricity consumption of each sub-region within the first time period, i.e., the fourth electricity consumption, based on the second electricity consumption (e.g., data from the most recent week). This prediction process focuses on recent electricity consumption trends and behavioral characteristics; for example, the predicted electricity consumption for the first time period is 16,000 kWh / day based on data from the most recent week.

[0035] After obtaining the two prediction results, the system determines the difference between the two power consumptions. When the difference between the two power consumptions is less than a preset difference (e.g., 1000 kWh / day), it indicates that the power consumption behavior is relatively stable, and the power consumption based on the recent data prediction is directly used as the final power consumption. When the difference is greater than or equal to the preset difference, it indicates that the power consumption behavior may have changed significantly, and the system will perform a weighted average of the two prediction results to obtain the final third power consumption. Considering that the recent data has a greater impact on future power consumption, the system sets the weight of the fourth power consumption (e.g., 0.7) to be greater than the weight of the first power consumption (e.g., 0.3).

[0036] Based on the above embodiments, as an optional implementation, in S102, in combination with the first power consumption and the second power consumption, predicting the third power consumption of each sub-region in the first time period specifically includes S21-S22: S21, predicting the fourth power consumption of each sub-region in the first time period according to the second power consumption.

[0037] Next, the system performs short-term prediction based on the second power consumption. The machine learning algorithm (such as support vector machine, neural network, etc.) is used to analyze the change characteristics of the second power consumption (e.g., the data of the last week) and capture the latest trends of power consumption behavior. The prediction model focuses on the intraday fluctuation characteristics of the load curve, weather factors, and power consumption mode changes caused by unexpected events. Through this analysis, the system generates the fourth power consumption of each sub-region in the first time period. For example, the fourth power consumption of the same commercial area predicted based on the data of the last week is 20000 kWh / day, which more reflects the latest changes in power demand in the region.

[0038] S22, adjusting the fourth power consumption by the first power consumption to generate the third power consumption of each sub-region in the first time period.

[0039] Finally, the system fuses the first power consumption and the fourth power consumption through a dynamic adjustment mechanism. The adjustment process uses an adaptive weight method to dynamically determine the adjustment strategy according to the difference between the two prediction results. Specifically, when the difference between the first power consumption and the fourth power consumption is less than a preset difference (e.g., 1000 kWh / day), the system considers that the power consumption behavior is relatively stable, and directly uses the fourth power consumption as the third power consumption. In this case, the system trusts the prediction result based on the recent data more. When the difference is greater than or equal to the preset difference, the system considers that the power consumption behavior may have changed significantly, and uses a weighted average method for adjustment, in which the weight of the fourth power consumption (e.g., 0.7) is greater than the weight of the first power consumption (e.g., 0.3) to ensure that the prediction result more reflects the recent power consumption characteristics.

[0040] On the basis of the above embodiments, as an optional implementation, in S22, the fourth power consumption is adjusted by the first power consumption to generate the third power consumption of each sub-region in the first time period, specifically including S221-S222: S221, when the power difference between the first power consumption and the fourth power consumption is less than the preset difference, the fourth power consumption is taken as the third power consumption of each sub-region in the first time period.

[0041] Specifically, the system first calculates the power difference between the first power consumption and the fourth power consumption, and compares it with the preset difference. The preset difference is a threshold value determined according to historical data analysis, which is used to judge whether the power consumption behavior has changed significantly. For example, the preset difference of a certain commercial district is set to 10% of the daily power consumption. When the fourth power consumption of the commercial district is 18000kWh / day and the first power consumption is 19000kWh / day, the difference between them is 1000kWh / day. If the preset difference of the commercial district is 2000kWh / day, the difference at this time is less than the preset difference.

[0042] When the power difference is less than the preset difference, it indicates that the power consumption behavior is relatively stable, and the recent prediction value is close to the historical regularity prediction value. In this case, the system directly uses the fourth power consumption as the third power consumption. This is because the fourth power consumption is predicted based on the recent power consumption data, which can better reflect the current power consumption state. For example, the third power consumption of the above-mentioned commercial district will be set to 19000kWh / day. This direct adoption strategy simplifies the calculation process, while ensuring the timeliness of the prediction results.

[0043] S222, when the power difference between the first power consumption and the fourth power consumption is not less than the preset difference, the first power consumption and the fourth power consumption are weighted and averaged to obtain the third power consumption of each sub-region in the first time period, wherein the weight value of the first power consumption is less than the weight value of the fourth power consumption.

[0044] When the power difference is not less than the preset difference, it indicates that the power consumption behavior may have changed significantly, and it is necessary to consider both the historical regularity and the recent trend. In this case, the system generates the third power consumption by using the weighted average method. In order to ensure that the prediction results better reflect the recent power consumption characteristics, while not completely abandoning the reference value of the historical regularity, the system sets the weight value of the fourth power consumption (such as 0.7) to be greater than the weight value of the first power consumption (such as 0.3).

[0045] S103, obtaining the environmental information of the environment where the energy generation equipment corresponding to each sub-region is located, and generating the power generation of each energy generation equipment in the first time period according to the environmental information.

[0046] The regional intelligent power distribution system needs to accurately predict the power generation of each energy generation device in the first time period in order to match the predicted power demand. Since the power generation capacity of energy generation devices is directly affected by their environment, especially new energy generation devices such as photovoltaic power generation affected by light intensity and wind power affected by wind speed, the system first collects environmental information of the environment where the energy generation device is located through the environmental monitoring device of each sub-region, including real-time data such as temperature, humidity, light intensity, wind speed, wind direction, etc. The regional intelligent power distribution system inputs the collected environmental information into a pre-trained power generation prediction model, which considers the mapping relationship between environmental parameters and power generation efficiency, and can predict the power generation of each energy generation device in the first time period according to the current environmental information. The prediction model is trained using historical environmental information and corresponding actual power generation data, and a correlation model between environmental parameters and power generation is established through a deep learning algorithm to improve the accuracy of power generation prediction. This power generation prediction method based on environmental information can effectively cope with the uncertainty of new energy generation, provide reliable power generation capacity data support for subsequent supply-demand balance parameter calculation and power allocation scheme formulation, thereby improving the stability and reliability of the entire power distribution system, and also providing technical support for efficient use of new energy generation.

[0047] In S104, the supply-demand balance parameters of each sub-region are generated in combination with the power generation and the third power consumption.

[0048] The regional intelligent power distribution system needs to generate supply-demand balance parameters of each sub-region based on the predicted power generation and the third power consumption in order to realize reasonable allocation of power distribution resources. The system first calculates the difference between the power generation and the third power consumption of each sub-region, and divides the sub-region into a first sub-region with power surplus and a second sub-region with power gap according to the difference.

[0049] For the first sub-region, the system determines the initial power supply capacity parameter according to its power surplus, and obtains the power supply reliability index of the region, which is used to represent the output stability of the energy generation device of the first sub-region. The system adjusts the initial power supply capacity parameter through the power supply reliability index to generate the target power supply capacity parameter of the first sub-region.

[0050] For the second sub-region, the system determines an initial electricity demand parameter according to the power gap amount thereof, and obtains a load importance level of the region, which is used to represent a power supply guarantee priority level of the second sub-region. The system determines a target electricity demand parameter of the second sub-region according to the load importance level, and finally takes the power supply capacity parameter or the electricity demand parameter as the supply-demand balance parameter of each sub-region. The balance parameter generation method based on the supply-demand difference value not only considers the supply-demand conditions of each region, but also combines the stability of the power generation equipment and the importance of the load, so that the power distribution system can guarantee the power supply of important loads while realizing the optimal allocation of power resources, thereby improving the operation efficiency and power supply reliability of the power distribution system.

[0051] On the basis of the above-mentioned embodiments, as an optional implementation manner, in S104, the generating of the supply-demand balance parameter of each sub-region in combination with the power generation amount and the third electricity consumption amount specifically includes S41-S44: S41, calculating the difference value between the power generation amount and the third electricity consumption amount, and dividing each sub-region into a first sub-region with a power surplus amount and a second sub-region with a power gap amount according to the difference value.

[0052] The present application proposes a supply-demand balance mechanism based on multi-dimensional parameters. The system first divides the regions into a first sub-region with a power surplus amount and a second sub-region with a power gap amount by calculating the difference value between the power generation amount and the third electricity consumption amount of each sub-region. For example, a certain commercial district has a predicted power generation amount of 25000kWh / day and a third electricity consumption amount of 20000kWh / day, so the region is divided into a first sub-region with a power surplus amount of 5000kWh / day; while a certain residential district has a predicted power generation amount of 15000kWh / day and a third electricity consumption amount of 18000kWh / day, so it is divided into a second sub-region with a power gap amount of 3000kWh / day.

[0053] S42, determining an initial power supply capacity parameter of the first sub-region according to the power surplus amount.

[0054] S43, obtaining a power supply reliability index of the first sub-region, adjusting the initial power supply capacity parameter through the power supply reliability index to generate a target power supply capacity parameter of the first sub-region, and the power supply reliability index is used to represent the output stability of the energy power generation equipment of the first sub-region.

[0055] For the first sub-region, the system determines an initial power supply capability parameter according to its power surplus amount. This parameter reflects the potential capability of the region to output power externally, and is calculated as the ratio of the power surplus amount to the total power generation amount. For example, if a first sub-region has a power surplus amount of 5000 kWh / day and a total power generation amount of 25000 kWh / day, its initial power supply capability parameter is 0.2. However, considering the differences in output characteristics of different power generation devices, the system introduces a power supply reliability index to adjust the initial power supply capability parameter. The power supply reliability index is mainly calculated based on historical operation data of the power generation devices, including factors such as device failure rate and output volatility. For example, if the region mainly relies on photovoltaic power generation, its power supply reliability index is 0.8, and the adjusted target power supply capability parameter is 0.16. This adjustment mechanism can more accurately reflect the actual power supply capability of the region and avoid power supply quality problems caused by unstable output of power generation devices.

[0056] S44, according to the power gap amount, determine the initial power demand parameter of the second sub-region.

[0057] S45, obtain the load importance level of the second sub-region, and determine the target power demand parameter of the second sub-region according to the load importance level, the load importance level is used to represent the power supply priority level of the power consumption load of the second sub-region.

[0058] For the second sub-region, the system first determines the initial power demand parameter according to the power gap amount, which is calculated as the ratio of the power gap amount to the total power consumption amount. For example, if a second sub-region has a power gap amount of 3000 kWh / day and a total power consumption amount of 18000 kWh / day, its initial power demand parameter is 0.167. In order to ensure the power supply safety of important loads, the system obtains the load importance level of each second sub-region, which is determined based on the nature and function of the power consumption devices. For example, the emergency devices of a hospital are classified as the highest level (such as 1.2), and the ordinary civil load is classified as a lower level (such as 0.8). The system adjusts the initial power demand parameter according to the load importance level to obtain the target power demand parameter. For example, the target power demand parameter of the hospital region will be adjusted to 0.2, which ensures that important loads are given priority in power supply.

[0059] S46, take the power supply capability parameter or power demand parameter as the supply and demand balance parameter of each sub-region.

[0060] Finally, the system unifies the target power supply capability parameter of the first sub-region and the target power demand parameter of the second sub-region as the supply and demand balance parameter of each sub-region. These parameters will be an important basis for subsequent development of power distribution schemes, ensuring the power supply reliability of important loads and achieving efficient allocation of regional power resources.

[0061] S105, acquire the energy load type of each sub-region, and the energy load type is used to represent the power consumption characteristics of each sub-region.

[0062] After obtaining the supply-demand balance parameters, the regional intelligent power distribution system needs to further acquire the energy load type of each sub-region to achieve more accurate power distribution adjustment. The system first collects the real-time operation data of the power consumption equipment in each sub-region through the power distribution terminal, including the operation state, power consumption power change and start-stop record of various power consumption equipment. The regional intelligent power distribution system inputs the collected data into the load analysis module, which analyzes the data based on the preset load characteristic model, extracts the operation characteristics and load mode of the power consumption equipment.

[0063] According to the analysis result, the system identifies the main energy load type of each sub-region, such as industrial load, commercial load or residential load, etc. Different types of power consumption load have significantly different power consumption characteristics, for example, industrial load usually has strong continuity and regularity, commercial load shows obvious peak-valley characteristics, and residential load shows strong randomness and volatility. By acquiring these energy load type information, the system can combine the load characteristic parameters stored in the load type database to provide an important basis for subsequent supply-demand balance parameter adjustment, so that the power distribution scheme can better adapt to the actual power consumption characteristics of various loads, improve the power supply accuracy and adaptability of the power distribution system, and finally realize the fine management and efficient utilization of power distribution resources.

[0064] S106, according to the energy load type, adjusting the supply-demand balance parameters to generate target supply-demand balance parameters, and generating the power distribution scheme of each energy generation device in the first time period according to the target supply-demand balance parameters.

[0065] After acquiring the energy load type of each sub-region, the regional intelligent power distribution system needs to accurately adjust the supply-demand balance parameters and generate the final power distribution scheme. The system first selects the load characteristic parameters corresponding to the energy load type of each sub-region from the load type database, which includes the load adjustment coefficient and the load response time, wherein the load adjustment coefficient represents the adjustable degree of the power consumption load of this type of load, and the load response time represents the time required for this type of load to respond to the power supply adjustment instruction.

[0066] Subsequently, the system calculates a first ratio of the load adjustment coefficient of each sub-region to a preset reference adjustment coefficient to obtain a first adjustment coefficient, and takes the product of the supply-demand balance parameter of each sub-region and the first adjustment coefficient as a first adjustment parameter. At the same time, the system obtains a preset response time threshold, calculates a second ratio of the load response time of each sub-region to the response time threshold to obtain a second adjustment coefficient, and finally takes the product of the first adjustment parameter of each sub-region and the second adjustment coefficient as a target supply-demand balance parameter. Based on these target supply-demand balance parameters, the system further determines the priority order of each sub-region in power distribution, and generates a specific power distribution scheme of each energy generation device in the first time period according to the priority order.

[0067] This double adjustment mechanism based on load characteristics can adapt to the adjustable degree of different load types and meet the response time requirement of different loads through accurate adjustment of the supply-demand balance parameter, so as to realize accurate allocation of power distribution resources, improve the operation efficiency and power supply reliability of the power distribution system, and effectively solve the problem that the traditional power distribution scheme cannot accurately adapt to the characteristics of different types of loads.

[0068] Based on the above embodiment, as an optional implementation, in S106, the target supply-demand balance parameter is generated by adjusting the supply-demand balance parameter according to the energy consumption load type, which specifically includes S61-S64: S61, selecting the load characteristic parameter corresponding to the energy consumption load type of each sub-region from the load type database; wherein the load characteristic parameter includes a load adjustment coefficient and a load response time, the load adjustment coefficient is used to represent the adjustable degree of the power load of the energy consumption load type, and the load response time is used to represent the time of the energy consumption load type responding to the power adjustment instruction.

[0069] S62, calculating a first ratio of the load adjustment coefficient of each sub-region to a preset reference adjustment coefficient to obtain a first adjustment coefficient, and taking the product of the supply-demand balance parameter of each sub-region and the first adjustment coefficient as a first adjustment parameter.

[0070] After determining the supply-demand balance parameters, considering the significant differences in the adjustment characteristics of different types of electricity consumption load, the application introduces a dynamic adjustment mechanism based on load characteristics. The system first selects the load characteristic parameters corresponding to the load type of each sub-region from the pre-established load type database. These parameters mainly include two key indicators: load adjustment coefficient and load response time. Among them, the load adjustment coefficient reflects the adjustable degree of different types of electricity consumption load, for example, the adjustment coefficient of air conditioning load is higher (such as 0.8), and the adjustment coefficient of necessary production equipment load is lower (such as 0.3); the load response time represents the time required for various types of load to respond to power adjustment instructions, such as the response time of lighting system is shorter (such as 1 minute), and the response time of large refrigeration equipment is longer (such as 15 minutes).

[0071] In order to realize more accurate load adjustment, the system calculates the ratio of the load adjustment coefficient of each sub-region to the preset reference adjustment coefficient to obtain the first adjustment coefficient. For example, the comprehensive adjustment coefficient of air conditioning and lighting load in a certain commercial area is 0.7, and the preset reference adjustment coefficient is 0.5, so the first adjustment coefficient of this area is 1.4. The system multiplies the supply-demand balance parameters of each sub-region with the corresponding first adjustment coefficient to obtain the first adjustment parameter. This adjustment mechanism ensures that the load with higher adjustability can undertake more demand response tasks, thereby improving the adjustment flexibility of the system.

[0072] S63, obtaining a preset response time threshold, calculating the second ratio of the load response time of each sub-region to the response time threshold to obtain the second adjustment coefficient.

[0073] S64, multiplying the first adjustment parameter of each sub-region by the second adjustment coefficient to obtain the target supply-demand balance parameter.

[0074] At the same time, considering the influence of load response time on actual adjustment effect, the system sets a preset response time threshold (such as 10 minutes), and calculates the ratio of the load response time of each sub-region to the threshold to obtain the second adjustment coefficient. For example, the average load response time of an office building area is 5 minutes, so its second adjustment coefficient is 2.0. This adjustment mechanism based on response time can identify loads with strong fast response capability, which helps the system to quickly realize load adjustment in emergency situations.

[0075] Finally, the system multiplies the first adjustment parameter of each sub-region with the second adjustment coefficient to obtain the target supply-demand balance parameter. This parameter takes into account the adjustable degree and response speed of the load, and can more accurately guide the subsequent power dispatching. For example, the first adjustment parameter of a certain business district is 0.28, and the second adjustment coefficient is 2.0, then the final target supply-demand balance parameter is 0.56. This multi-dimensional parameter adjustment method significantly improves the adjustment accuracy and response speed of the power distribution system. Practice shows that using this method can shorten the response time of load adjustment by 30% and improve the accuracy of adjustment by 25%, effectively improving the operation efficiency and reliability of the power distribution network. At the same time, this fine management method based on load characteristics also provides technical support for demand side response and smart power consumption, promoting the development of power distribution network to a more intelligent and flexible direction.

[0076] On the basis of the above embodiment, as an optional implementation manner, in S106, generating the power distribution scheme of each energy generation device in the first time period according to the target supply-demand balance parameter specifically includes S65-S66: S65, determining the power supply priority of each sub-region according to the target supply-demand balance parameter.

[0077] S66, generating the power distribution scheme of each energy generation device in the first time period according to the power supply priority.

[0078] After determining the power supply priority, the system formulates the power distribution scheme according to the priority of each sub-region. For high-priority areas, the system prioritizes ensuring their basic electricity demand and reserves a certain amount of power margin. For example, a hospital area is predicted to consume 20000kWh / day, and the system will allocate 22000kWh / day of power supply to ensure the continuous and stable operation of critical medical equipment. For medium-priority areas such as office buildings and schools, the system allocates corresponding power resources according to their target supply-demand balance parameters and reserves appropriate adjustment space during peak electricity consumption periods. For example, the target supply-demand balance parameter of a certain office building area is 0.7, and the system allocates power to meet the predicted electricity demand during working hours, but reduces the allocation during non-working hours.

[0079] For low-priority areas such as commercial complexes, the system reserves a large demand response space based on ensuring basic electricity demand. The electricity load of these areas usually has strong adjustment ability and can participate in demand response by adjusting air conditioning temperature, reducing lighting brightness, etc. For example, a certain business district can reduce its electricity demand by 3000kWh / day by adjusting the air conditioning temperature during peak electricity consumption periods, and the system will include this adjustable load in the optimization consideration range of the power distribution scheme.

[0080] In addition, the system also considers the output characteristics of distributed power generation equipment. For areas equipped with photovoltaic power generation equipment, the system will predict the power generation based on weather forecast data and prioritize the allocation of this clean energy to the local area. The remaining power is allocated to other areas according to the power supply priority. This principle of local use can reduce transmission losses and improve energy efficiency.

[0081] Through this priority-based power distribution scheme, the system achieves precise allocation and intelligent management of power resources.

[0082] After generating the power distribution scheme for each energy generation device in the first time period, the method further includes: monitoring the actual power consumption of each sub-area in the first time period; when detecting that the difference between the actual power consumption of any sub-area and the third power consumption exceeds a preset threshold, obtaining the change trend of the actual power consumption, the change trend including an upward trend and a downward trend; when the change trend is an upward trend, calculating the growth rate of the actual power consumption relative to the third power consumption, and adjusting the power distribution scheme in the remaining time period according to the growth rate, the adjustment including increasing the power supply to the corresponding sub-area and calling the excess power of the adjacent sub-area; when the change trend is a downward trend, calculating the decline rate of the actual power consumption relative to the third power consumption, and adjusting the power distribution scheme in the remaining time period according to the decline rate, the adjustment including reducing the power supply and distributing the excess power to the adjacent sub-area; and taking the adjusted power distribution scheme as the final power distribution scheme of the sub-area in the remaining time period.

[0083] To cope with the dynamic changes in actual power demand, the present application introduces a real-time monitoring and dynamic adjustment mechanism during the execution of the power distribution scheme. The system continuously monitors the actual power consumption of each sub-area in the first time period through smart meters and power distribution automation terminals, and compares it with the predicted third power consumption in real time. When the system detects that the difference between the actual power consumption of any sub-area and the third power consumption exceeds a preset threshold (e.g. ±10%), it will trigger the dynamic adjustment process.

[0084] The system first analyzes the change trend of the actual power consumption. For example, the actual power consumption of a certain commercial area at 14:00 is 1200kWh / h, while the predicted third power consumption is 1000kWh / h, the difference exceeds the preset threshold of 200kWh / h. The system analyzes the trend of the power consumption data in the last 30 minutes and judges that the power consumption shows an upward trend. This trend analysis helps the system to predict the direction of change in power demand, so as to take appropriate adjustment measures.

[0085] When an upward trend in electricity consumption is detected, the system calculates the growth rate of actual electricity consumption relative to the third-party electricity consumption. In the case of the aforementioned commercial area, the growth rate is 20%. Based on this growth rate, the system adjusts the power allocation plan for the remaining time period (14:00-24:00). Specifically, the system first increases the power supply capacity of the commercial area, raising the planned power supply capacity from 1000kW to 1200kW. If the power generation equipment in this area cannot meet the increased electricity demand, the system automatically searches the power supply status of adjacent sub-areas and calls upon areas with surplus power (such as surplus power in an office area during off-peak hours) to provide supplementary power supply. This cross-regional power allocation mechanism significantly improves the system's power supply flexibility.

[0086] Conversely, when the system detects a downward trend in electricity consumption—for example, if an office building area's actual electricity consumption at 6:00 PM is 600 kWh / h, while the predicted consumption is 800 kWh / h—the system calculates a decrease of 25%. In this situation, the system correspondingly reduces the power supply to that area, lowering the planned power supply from 800 kW to 600 kW. Simultaneously, the system redistributes the saved energy to other sub-areas with electricity demand, such as nearby commercial or residential areas. This dynamic adjustment mechanism not only avoids energy waste but also improves the energy efficiency of the entire power distribution network.

[0087] Based on the above method, this application also discloses a multi-scenario energy management system based on a dynamic distributed architecture, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of a multi-scenario energy management system based on a dynamic distributed architecture, provided in an embodiment of this application. The system includes: The system comprises a first acquisition module, a first combination module, a second acquisition module, a second combination module, a third acquisition module, and a generation module; wherein, The first obtaining module is configured to obtain first power consumption of each sub-region in the region in a first time period after a current time on a historical date and second power consumption in a second time period before the current time; the first combining module is configured to combine the first power consumption and the second power consumption to predict third power consumption of each sub-region in the first time period; the second obtaining module is configured to obtain environmental information of an environment in which a corresponding energy generation device of each sub-region is located, and generate power generation of each energy generation device in the first time period according to the environmental information; the second combining module is configured to combine the power generation and the third power consumption to generate a supply-demand balance parameter of each sub-region; the third obtaining module is configured to obtain an energy load type of each sub-region, the energy load type being used to represent power consumption characteristics of each sub-region; and the generating module is configured to adjust the supply-demand balance parameter according to the energy load type to generate a target supply-demand balance parameter, and generate a power distribution scheme of each energy generation device in the first time period according to the target supply-demand balance parameter.

[0088] It should be noted that the system provided in the above embodiments is only used as an example to divide the above functional modules when realizing the functions, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0089] Please refer to Figure 3 The electronic device 1000 provided in the embodiments of the present application provides a structural schematic diagram of an electronic device. As shown in the figure, Figure 3 The electronic device 1000 can include at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0090] The communication bus 1002 is used to realize the connection and communication between the components.

[0091] The user interface 1003 can include a display screen (Display) and a camera (Camera), and the optional user interface 1003 can further include a standard wired interface and a wireless interface.

[0092] The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0093] The processor 1001 can include one or more processing cores. The processor 1001 connects various parts within the server through various interfaces and lines, performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Alternatively, the processor 1001 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 1001 can integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interfaces, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 1001, but can be realized by a separate chip.

[0094] The memory 1005 can include a random access memory (RAM) and a read-only memory (ROM). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 1005 can also be at least one storage device located away from the above-mentioned processor 1001. As shown in the figure, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of a multi-scene energy management method based on a dynamic distributed architecture. Figure 3

[0095] In Figure 3 ​In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an interface for user input, and obtain data input by the user; and the processor 1001 can be used to invoke an application program of a multi-scenario energy management method based on a dynamic distributed architecture stored in the memory 1005, and when executed by one or more processors, cause the electronic device to perform the method described in one or more of the above embodiments.

[0096] An electronic device readable storage medium stores instructions. When executed by one or more processors, cause the electronic device to perform the method described in one or more of the above embodiments.

[0097] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other orders or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0098] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0099] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some service interface, device or unit, and can be electrical or other forms.

[0100] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0101] In addition, each of the functional units in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0102] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application essentially, or the part that contributes to the prior art, or all or a part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods according to the embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, magnetic disk or optical disk, and various program codes that can be stored in the medium.

[0103] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the present disclosure. The present application is intended to cover any variations, uses, or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and examples are only considered as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A multi-scenario energy management method based on a dynamic distributed architecture, characterized in that, The method is applied to a regional intelligent power distribution system, the regional intelligent power distribution system is in communication connection with a plurality of energy generation devices, each of the energy generation devices is arranged in a different sub-region and supplies power to the sub-region, and each of the energy generation devices can perform cross-sub-region power distribution based on a dispatching instruction, and the method comprises the following steps: Obtain a first power consumption of each sub-region in a first time period after a current time on a historical date, and a second power consumption in a second time period before the current time; Combine the first power consumption and the second power consumption to predict a third power consumption of each sub-region in the first time period; Obtain environmental information of an environment in which a corresponding energy generation device of each sub-region is located, and generate a power generation amount of each energy generation device in the first time period according to the environmental information; Combine the power generation amount and the third power consumption to generate a supply-demand balance parameter of each sub-region; Obtain an energy load type of each sub-region, the energy load type being used to represent power consumption characteristics of each sub-region; According to the energy load type, adjust the supply-demand balance parameter to generate a target supply-demand balance parameter, and generate a power distribution scheme of each energy generation device in the first time period according to the target supply-demand balance parameter.

2. The multi-scenario energy management method based on a dynamic distributed architecture according to claim 1, characterized in that, The combination of the first power consumption and the second power consumption to predict the third power consumption of each sub-region in the first time period comprises: According to the second power consumption, predict a fourth power consumption of each sub-region in the first time period; Adjust the fourth power consumption by the first power consumption to generate the third power consumption of each sub-region in the first time period.

3. The multi-scenario energy management method based on dynamic distributed architecture according to claim 2, characterized in that, The adjustment of the fourth power consumption by the first power consumption to generate the third power consumption of each sub-region in the first time period comprises: When the power difference between the first power consumption and the fourth power consumption is less than a preset difference, the fourth power consumption is taken as the third power consumption of each sub-region in the first time period; When the power difference between the first power consumption and the fourth power consumption is not less than the preset difference, the first power consumption and the fourth power consumption are weighted and averaged to obtain the third power consumption of each sub-region in the first time period, wherein the weight value of the first power consumption is less than the weight value of the fourth power consumption.

4. The multi-scenario energy management method based on dynamic distributed architecture according to claim 1, characterized in that, The combination of the power generation amount and the third power consumption to generate the supply-demand balance parameter of each sub-region comprises: Calculate the difference between the power generation amount and the third power consumption, and divide each sub-region into a first sub-region with a power surplus amount and a second sub-region with a power gap amount according to the difference; Determine an initial power supply capability parameter of the first sub-region according to the power surplus amount; Obtain a power supply reliability index of the first sub-region, adjust the initial power supply capability parameter by the power supply reliability index to generate a target power supply capability parameter of the first sub-region, and the power supply reliability index is used to represent the output stability of the energy generation device of the first sub-region; Determine an initial power consumption demand parameter of the second sub-region according to the power gap amount; obtain a load importance level of the second sub-region, and determine a target power demand parameter of the second sub-region according to the load importance level, the load importance level being used to represent a power supply guarantee priority level of the second sub-region; use the power supply capability parameter or the power demand parameter as a supply-demand balance parameter of each sub-region.

5. The multi-scenario energy management method based on dynamic distributed architecture according to claim 1, characterized in that, The adjusting the supply-demand balance parameter according to the energy consumption load type to generate a target supply-demand balance parameter comprises: selecting a load characteristic parameter corresponding to the energy consumption load type of each sub-region from a load type database, wherein the load characteristic parameter comprises a load adjustment coefficient and a load response time, the load adjustment coefficient is used to represent an adjustable degree of the power load of the energy consumption load type, and the load response time is used to represent a time for responding to a power supply adjustment instruction of the energy consumption load type; calculating a first ratio of the load adjustment coefficient of each sub-region to a preset reference adjustment coefficient to obtain a first adjustment coefficient, and multiplying the supply-demand balance parameter of each sub-region by the first adjustment coefficient to obtain a first adjustment parameter; obtaining a preset response time threshold, calculating a second ratio of the load response time of each sub-region to the response time threshold to obtain a second adjustment coefficient; multiplying the first adjustment parameter of each sub-region by the second adjustment coefficient to obtain a target supply-demand balance parameter.

6. The multi-scenario energy management method based on dynamic distributed architecture according to claim 1, characterized in that, The generating the power distribution scheme of each energy generation device in the first time period according to the target supply-demand balance parameter comprises: determining a power supply priority of each sub-region according to the target supply-demand balance parameter; generating the power distribution scheme of each energy generation device in the first time period according to the power supply priority.

7. The multi-scenario energy management method based on dynamic distributed architecture according to claim 1, characterized in that, After the generating the power distribution scheme of each energy generation device in the first time period, the method further comprises: monitoring an actual power consumption of each sub-region in the first time period; when detecting that a difference between the actual power consumption of any sub-region and the third power consumption exceeds a preset threshold, obtaining a change trend of the actual power consumption, the change trend comprising an upward trend and a downward trend; when the change trend is the upward trend, calculating a growth ratio of the actual power consumption relative to the third power consumption, and adjusting the power distribution scheme in the remaining time period according to the growth ratio, the adjusting comprising increasing a power supply power of the corresponding sub-region and calling surplus power of an adjacent sub-region; when the change trend is the downward trend, calculating a decline ratio of the actual power consumption relative to the third power consumption, and adjusting the power distribution scheme in the remaining time period according to the decline ratio, the adjusting comprising reducing the power supply power and distributing the surplus power to the adjacent sub-region; using the adjusted power distribution scheme as a final power distribution scheme of the sub-region in the remaining time period.

8. A multi-scenario energy management system based on a dynamic distributed architecture, characterized in that, The system comprises a first obtaining module, a first combining module, a second obtaining module, a second combining module, a third obtaining module and a generating module, wherein, the first obtaining module is configured to obtain a power supply capability parameter of each sub-region in a first time period, the power supply capability parameter being used to represent a power supply capability of each sub-region in the first time period; The first obtaining module is configured to obtain a first power consumption of each sub-region in the region in a first time period after a current time on a historical date and a second power consumption in a second time period before the current time; The first combining module is configured to combine the first power consumption and the second power consumption to predict a third power consumption of each sub-region in the first time period; The second obtaining module is configured to obtain environmental information of an environment in which each energy generation device corresponding to each sub-region is located, and generate a power generation amount of each energy generation device in the first time period according to the environmental information; The second combining module is configured to combine the power generation amount and the third power consumption to generate a supply-demand balance parameter of each sub-region; The third obtaining module is configured to obtain an energy load type of each sub-region, the energy load type being used to represent power consumption characteristics of each sub-region; The generating module is configured to adjust the supply-demand balance parameter according to the energy load type to generate a target supply-demand balance parameter, and generate a power distribution scheme of each energy generation device in the first time period according to the target supply-demand balance parameter.

9. An electronic device, comprising: An electronic device includes a processor, a memory, a user interface, and a network interface. The memory is configured to store instructions. The user interface and the network interface are configured to communicate with other devices. The processor is configured to execute the instructions stored in the memory to cause the electronic device to perform the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored in a memory and can be loaded and executed by a processor to perform the method of any one of claims 1-7.

Images