New power system satellite-ground integrated communication load modeling and situation awareness method and system

Abstract

The present invention discloses a new type of power system satellite-ground fusion communication load modeling and situation awareness method and system. The method comprises: classifying communication load based on load characteristic information of the new type of satellite-ground fusion power system, constructing a communication load model according to the load classification result, generating a load demand regulation strategy according to the response characteristic information of the communication load, aggregating the communication load based on the communication load model and the load demand regulation strategy, performing dependency analysis on the communication load aggregation result, obtaining the spatiotemporal dependency information between each aggregated load, predicting the load situation of the power system according to the spatiotemporal dependency information, aggregating the communication load, thereby improving the analysis efficiency and effectively reducing the analysis complexity, and performing spatiotemporal dependency analysis on the communication load, thereby greatly improving the communication load prediction accuracy of the new type of satellite-ground fusion power system, ensuring the timeliness of the prediction result, and effectively guaranteeing the communication quality of the power business.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a novel method and system for load modeling and situation awareness of satellite-ground fusion communication in a power system. Background Art

[0002] In modern power systems, communication guarantee has become a key factor in supporting the stable operation of power services. With the increasing complexity of power systems, communication networks are taking on more and more tasks. They not only need to support conventional power dispatching, control and data transmission, but also need to cope with multi-dimensional communication needs such as power load forecasting, equipment monitoring, fault detection, and system optimization. The communication demand of power services has significant multi-time and space scale distribution characteristics. In terms of time and space scale, the communication load is not only affected by the time period and geographical location, but also highly coupled with factors such as changes in power load, weather changes, and equipment operating status. This complex and changeable characteristic makes the power communication demand show significant time-varying and spatial heterogeneity. Communication demand not only fluctuates in daily operation, but also surges sharply when special events (such as fault handling, load dispatching, disaster emergency, etc.) occur.

[0003] Although traditional statistical analysis methods can make predictions to a certain extent based on historical load data, they do not analyze the complex spatiotemporal coupling relationship, and the prediction accuracy is limited by the quality and timeliness of the data, resulting in large errors in the prediction results of the communication load of the power system, which cannot guarantee the communication effect of the power business. Summary of the invention

[0004] The main purpose of the present invention is to provide a new method and system for modeling and situational awareness of satellite-ground integrated communication load in a power system, aiming to solve the technical problem that the prediction results of the communication load in the prior art often have large errors, cannot accurately predict the communication load of the power system, and cannot guarantee the communication quality of the power business.

[0005] To achieve the above object, the present invention provides a novel power system satellite-ground fusion communication load modeling and situation awareness method, the method comprising the following steps:

[0006] Classifying the communication load based on the load characteristic information of the communication load of each communication node in the new satellite-ground integrated power system to obtain a load classification result;

[0007] Constructing a communication load model corresponding to each load type according to the load classification result;

[0008] generating a load demand regulation strategy according to the response characteristic information of the communication load, wherein the response characteristic information includes a driving characteristic, a response period characteristic, and a response speed characteristic;

[0009] Aggregating the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result, wherein the communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load;

[0010] Performing dependency analysis on the communication load aggregation result to obtain spatiotemporal dependency information between the aggregated loads;

[0011] The load situation of the new satellite-ground integrated power system is predicted according to the time-space dependency information to obtain a load situation perception result.

[0012] Optionally, aggregating the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result includes:

[0013] Determine the data demand capacity and load demand time of each communication load according to the communication load model;

[0014] Determine the load peak and valley time distribution information of the satellite-ground integrated new power system based on the data demand capacity and the load demand time;

[0015] Determining the task priority of each communication load according to the load type;

[0016] The peak-valley allocation strategy of each communication load is determined based on the load peak-valley time distribution information and the task priority, wherein the peak-valley allocation strategy includes a task translation strategy and a task transfer strategy, and the constraint conditions of the peak-valley allocation strategy include:

[0017]

[0018] in, represents the time aggregated load, is the translation capacity and / or transfer capacity of the communication load, It is the valley period;

[0019] Based on the load peak-valley time distribution information and the task priority, the communication load is time aggregated to obtain a communication load aggregation result:

[0020]

[0021] in, represents the time-aggregated communication load demand capacity during the peak period, Indicates the load demand time of each communication load.

[0022] Optionally, aggregating the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result includes:

[0023] Acquire the geographical distribution information of the power grid and the coverage information of the satellite-ground network of the new satellite-ground integrated power system;

[0024] Determine the spatial distribution information of each communication load based on the geographical distribution information of the power grid and the satellite-to-ground network coverage information;

[0025] Perform similarity analysis on each communication load according to the communication load model to obtain load similarity information;

[0026] The communication load is spatially aggregated based on the spatial distribution information and the load similarity information to obtain a communication load aggregation result:

[0027]

[0028] in, represents a sub-area in the space aggregation area of ​​the new satellite-ground integrated power system, represents the communication load demand capacity of each sub-area, The spatial aggregation load represents the spatial aggregation load of the spatial aggregation area, where the spatial aggregation load is the sum of the communication loads of all sub-areas in the spatial aggregation area.

[0029] Optionally, the spatiotemporal dependency information includes spatial dependency information; and performing dependency analysis on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads includes:

[0030] Acquire historical communication load data of the new satellite-ground integrated power system;

[0031] The historical communication load data is normalized:

[0032]

[0033] Among them, the historical communication load data after normalization is For the The communication nodes are in the time step Communication load data, and are the mean and standard deviation of the historical communication load data respectively;

[0034] Constructing a graph structure according to the normalized historical communication load data, wherein the graph structure includes a plurality of adjacency matrices, the adjacency matrix includes a plurality of communication nodes, and each communication node is connected based on a dependency relationship;

[0035] A spatial dependency analysis is performed on the communication load aggregation result based on the adjacency matrix to obtain spatial dependency information between each aggregated load.

[0036] Optionally, the spatiotemporal dependency information includes time dependency information; and performing dependency analysis on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads includes:

[0037] Construct a temporal convolutional network:

[0038]

[0039] in, is the convolution kernel, is the expansion factor, is the convolution kernel size, represents the offset at each time step in the convolution operation, Represents the convolution kernel at time The coefficient of Indicates the current time index. Represents the input time series data;

[0040] Based on the historical communication load data of the satellite-ground integrated new power system, historical time series data of each communication load is obtained;

[0041] A time dependency analysis is performed on the communication load aggregation result based on the historical time series data according to the time convolution network to obtain time dependency information between each aggregated load.

[0042] Optionally, the load classification result includes a demand response classification result, the load types in the demand response classification result include a shiftable communication load, a transferable communication load and a reducible communication load, and the communication load model includes a shiftable communication load model, a transferable communication load model and a reducible communication load model;

[0043] The constructing of a communication load model corresponding to each load type according to the load classification result includes:

[0044] Obtain the load demand data volume, time demand information and space demand information of each load type;

[0045] Generate load distribution constraint conditions corresponding to each load type according to the load demand data volume, the time demand information and the space demand information, wherein the load distribution constraint conditions include data volume constraint conditions, distribution time constraint conditions and distribution space constraint conditions;

[0046] A communication load model corresponding to each load type is constructed based on the load distribution constraint condition.

[0047] In addition, to achieve the above-mentioned purpose, the present invention also proposes a new power system satellite-ground fusion communication load modeling and situation awareness system, the new power system satellite-ground fusion communication load modeling and situation awareness system comprising:

[0048] A load classification module, used to classify the communication load of each communication node in the new satellite-ground integrated power system based on load characteristic information of the communication load, and obtain a load classification result;

[0049] A model building module, used to build a communication load model corresponding to each load type according to the load classification result;

[0050] A demand control module, used to generate a load demand control strategy according to the response characteristic information of the communication load, wherein the response characteristic information includes a driving characteristic, a response period characteristic and a response speed characteristic;

[0051] A load aggregation module, configured to aggregate the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result, wherein the communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load;

[0052] A dependency analysis module, used to perform dependency analysis on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads;

[0053] The situation awareness module is used to predict the load situation of the satellite-ground integrated new power system according to the time-space dependency information to obtain load situation awareness results.

[0054] In addition, to achieve the above-mentioned objectives, the present application also proposes a new type of power system satellite-ground fusion communication load modeling and situational awareness device, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the new type of power system satellite-ground fusion communication load modeling and situational awareness method as described above.

[0055] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the new power system satellite-ground fusion communication load modeling and situational awareness method as described above are implemented.

[0056] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the new power system satellite-ground fusion communication load modeling and situational awareness method as described above.

[0057] The present invention classifies the communication load based on the load characteristic information of the communication load of each communication node in the satellite-ground fusion new power system, obtains the load classification result, constructs the communication load model corresponding to each load type according to the load classification result, generates the load demand regulation strategy according to the response characteristic information of the communication load, the response characteristic information includes the driving characteristic, the response period characteristic and the response speed characteristic, aggregates the communication load based on the communication load model and the load demand regulation strategy, obtains the communication load aggregation result, the communication load aggregation result includes multiple aggregated loads, the aggregated load includes the time aggregated load and the space aggregated load, performs dependency analysis on the communication load aggregation result, obtains the spatiotemporal dependency information between the aggregated loads, predicts the load situation of the satellite-ground fusion new power system according to the spatiotemporal dependency information, and obtains the load situation perception result; because the present invention classifies and spatiotemporally aggregates the communication load of the satellite-ground fusion new power system, thereby effectively reducing the complexity of data analysis and greatly improving the analysis efficiency, and performs spatiotemporal dependency analysis on the communication load aggregation result, thereby greatly improving the prediction accuracy of the communication load of the satellite-ground fusion new power system, ensuring the timeliness of the prediction result, and effectively ensuring the communication quality of the power business. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0060] Figure 1 It is a structural schematic diagram of a new type of power system satellite-ground fusion communication load modeling and situation awareness device in the hardware operating environment involved in the embodiment of the present invention;

[0061] Figure 2 It is a flow chart of the first embodiment of the novel power system satellite-ground fusion communication load modeling and situation awareness method of the present invention;

[0062] Figure 3 It is a schematic diagram of the process of constructing a communication load model in an embodiment of a novel method for satellite-ground fusion communication load modeling and situation awareness of a power system of the present invention;

[0063] Figure 4It is a schematic diagram of the time aggregation process of an embodiment of a novel method for load modeling and situation awareness of satellite-ground fusion communication of a power system according to the present invention;

[0064] Figure 5 It is a schematic diagram of the spatial aggregation process of an embodiment of a novel method for load modeling and situation awareness of satellite-ground fusion communication of a power system according to the present invention;

[0065] Figure 6 It is a schematic diagram of the spatial dependency analysis process of an embodiment of a novel method for load modeling and situation awareness of satellite-ground fusion communication of a power system according to the present invention;

[0066] Figure 7 It is a schematic diagram of the time-dependent analysis process of an embodiment of a novel method for load modeling and situation awareness of satellite-ground fusion communication of a power system according to the present invention;

[0067] Figure 8 It is a structural block diagram of the first embodiment of the novel power system satellite-ground fusion communication load modeling and situation awareness system of the present invention.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0070] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of a new type of power system satellite-ground fusion communication load modeling and situation awareness equipment in the hardware operating environment involved in the embodiment of the present invention.

[0071] like Figure 1As shown, the new power system satellite-ground fusion communication load modeling and situation awareness device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0072] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the new power system satellite-ground fusion communication load modeling and situational awareness equipment, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0073] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a new power system satellite-ground fusion communication load modeling and situation awareness program.

[0074] exist Figure 1 In the new type of power system satellite-ground fusion communication load modeling and situation awareness device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the new type of power system satellite-ground fusion communication load modeling and situation awareness device of the present invention can be set in the new type of power system satellite-ground fusion communication load modeling and situation awareness device, and the new type of power system satellite-ground fusion communication load modeling and situation awareness device calls the new type of power system satellite-ground fusion communication load modeling and situation awareness program stored in the memory 1005 through the processor 1001, and executes the new type of power system satellite-ground fusion communication load modeling and situation awareness method provided in the embodiment of the present invention.

[0075] The embodiment of the present invention provides a novel power system satellite-ground fusion communication load modeling and situation awareness method, referring to Figure 2 , Figure 2 It is a flow chart of the first embodiment of the novel power system satellite-ground fusion communication load modeling and situation awareness method of the present invention.

[0076] In this embodiment, the novel power system satellite-ground fusion communication load modeling and situation awareness method includes the following steps:

[0077] Step S10: classifying the communication loads of each communication node in the satellite-ground integrated new power system based on the load characteristic information of the communication loads, and obtaining load classification results.

[0078] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a computer, etc., or a terminal electronic device capable of realizing the above functions, etc. The following takes a new type of power system satellite-ground fusion communication load modeling and situation awareness device (referred to as the awareness device) as an example to illustrate this embodiment and the following embodiments.

[0079] It should be noted that the load characteristic information may include demand response characteristics, timeliness characteristics, communication mode characteristics and urgency characteristics of the communication load.

[0080] In some embodiments, the sensing device may classify the communication load from multiple dimensions, for example, according to demand response, it may be classified into basic communication load, reducible communication load, shiftable communication load, and transferable communication load.

[0081] The above basic communication loads can be the core and uninterruptible communication requirements in the power system. They usually need to ensure connection and stable transmission at all times in any situation of the satellite-ground fusion network, and have high priority. Even in the case of tight load or high network latency, the load requirements of these communications cannot be reduced. For example, real-time control information in the power dispatching system and the status and fault alarm data transmission of generator sets and substations.

[0082] The above-mentioned communication load that can be reduced can be those communication flows that can be partially interrupted or reduced in load usage when necessary. This type of load has a certain degree of flexibility and can be partially or completely reduced when the load demand is high. Usually, this type of load can tolerate interruption or reduced transmission rate, but it will have a certain impact on the efficiency of the system or user experience. Its reduction will be dynamically adjusted according to the supply and demand of load resources. For example, the resolution of a video conference can be adjusted to reduce load occupancy.

[0083] The above-mentioned shiftable communication load can be that the load power supply time can be changed according to the plan, the load needs to be shifted as a whole, and the power consumption time spans multiple scheduling periods. For drone inspections, some data transmission tasks can be performed within a fixed time, but the data volume cannot be interrupted or adjusted. The transmission of data can only be adjusted according to the plan, but the size or flow of the transmission content cannot be adjusted.

[0084] The above-mentioned transferable communication load can be a flexible adjustment of the power consumption in each time period, but the total load of the entire cycle after the transfer must remain unchanged from that before the transfer. For example, during the peak communication period, some low-priority data flows can be suspended or the transmission rate can be reduced, and they can be transferred to the off-peak period for uploading, thereby optimizing the use of load resources.

[0085] In some embodiments, the sensing device can be divided into real-time communication load, quasi-real-time communication load and non-real-time communication load according to timeliness.

[0086] The above-mentioned real-time communication loads can be those with extremely high latency requirements, requiring the network to be able to transmit data with the lowest latency. Although the latency of satellite links is large, real-time performance is still crucial for specific critical tasks, especially when there are multiple communication links in the network, and seamless switching between satellite and ground networks must be ensured. For example, emergency dispatch commands and real-time data transmission in power systems.

[0087] The above-mentioned quasi-real-time communication load can be a load that has a certain tolerance for delay but still needs to be transmitted in a relatively short time, mainly transferable communication load and shiftable communication load. It is suitable for applications that do not require instantaneous response but still need to respond in time. For example, the status update of power equipment usually transmits data once a minute or hour.

[0088] The above non-real-time communication loads may have low latency requirements and can tolerate longer delays, mainly transferable communication loads and translatable communication loads. They are usually used for tasks such as batch processing, file transfer or data archiving, such as the backup and transmission of some power big data.

[0089] In some embodiments, the sensing devices can be divided into satellite communication load, ground communication load and hybrid communication load according to the communication mode.

[0090] The satellite communication loads mentioned above may be communications that are usually conducted via satellite links, which have large delays and load limitations and are usually very important in remote areas and disaster situations, such as power data acquisition and control in remote areas.

[0091] The above-mentioned ground communication load can be mainly transmitted through the ground network. This type of load has a lower latency and a higher load, and is therefore usually used for daily power system operation and management, such as power dispatching data within a city or region.

[0092] The above hybrid communication load can be a load that requires the use of satellite and ground communication links at the same time. It is usually used for applications that require wide coverage and high reliability. For example, emergency communications in the post-disaster recovery phase, satellite and ground networks work together.

[0093] In some embodiments, the sensing equipment can be divided into emergency communication load and normal communication load according to the degree of urgency.

[0094] The above-mentioned normal communication load may be the communication demand that needs to be met during daily and normal operations, which is mainly ground communication load, and also includes satellite communication load and hybrid communication load.

[0095] The above emergency communication load can be the communication demand that needs to be responded quickly in the event of a disaster or other emergency, mainly satellite communication load. Since satellite networks have the advantages of global coverage and independence from ground networks, satellite links are usually used as backup communication means when disasters occur, and can continue to provide services independently of ground networks. Satellite communications will become a key means of emergency communications.

[0096] Step S20: constructing a communication load model corresponding to each load type according to the load classification result.

[0097] It should be noted that the communication load model can be a multi-time and space scale electric power business satellite-ground integrated communication load mathematical model.

[0098] In the specific implementation, the sensing equipment can design a load analysis framework for multi-scale space-time fusion, analyze the distribution characteristics and evolution laws of the satellite-ground fusion communication load of the power business at multiple space-time scales, combine the dynamic evolution characteristics of multiple loads, and establish a mathematical model of the satellite-ground fusion communication load of the power business at multiple space-time scales, providing a theoretical basis for the aggregation of power business communication loads.

[0099] Furthermore, in order to accurately construct the communication load model and provide an accurate theoretical basis for the aggregation of power business communication load, Figure 3 , Figure 3 This is a flow chart of building a communication load model in an embodiment of the present invention. The above step S20 may include:

[0100] Step S201: Obtain the load demand data volume, time demand information and space demand information of each load type;

[0101] Step S202: generating load distribution constraint conditions corresponding to each load type according to the load demand data volume, time demand information and space demand information;

[0102] Step S203: constructing a communication load model corresponding to each load type based on the load distribution constraint condition.

[0103] It should be noted that the load classification result includes the demand response classification result, the load types in the demand response classification result include shiftable communication load, transferable communication load and reducible communication load, and the communication load model includes a shiftable communication load model, a transferable communication load model and a reducible communication load model. The load distribution constraint condition includes a data volume constraint condition, a distribution time constraint condition and a distribution space constraint condition.

[0104] In some embodiments, constructing a translatable communication load model may include: assuming that in multiple regions Data transmission is performed in each area. In time period The load demand is , the total amount of data in each region is , then there exists:

[0105]

[0106] Spatial load translation constraint: Between different regions, the load can be translated in time, but the amount of data in each region remains unchanged. The constraints are:

[0107]

[0108] The load demand of each area cannot be changed: The load demand of each area It can only be adjusted in different time periods and its total demand cannot be changed. Its constraints are:

[0109]

[0110] In some embodiments, constructing a transferable communication load model may include: assuming that the total load demand Can be used in multiple spatial areas and time period Each area In the period The load demand is , the amount of data in each region is , and the total load demand and total data volume remain unchanged during the transfer process, then:

[0111]

[0112] Spatial and temporal load balancing constraints: The load and data volume of each region can be flexibly adjusted in different time periods, but the total load and total data volume remain unchanged. The constraints are:

[0113]

[0114] Flexible adjustment of load and data transmission volume: The load and data volume of each area and time period can be flexibly adjusted to ensure network load balance. The constraints are:

[0115]

[0116] In some embodiments, constructing a model for reducing communication load may include: setting each area In time period The load demand is , the data transmission volume in each period is , and load demand can be reduced in some areas. If the total load demand and data volume remain consistent, then:

[0117]

[0118] The curtailable communication load model may include load curtailment constraints, allowing load demand in certain areas to be curtailed. The load can be reduced in some periods of time. The constraints are:

[0119]

[0120] The curtailable communication load model may include load interruption constraints, where certain tasks may be suspended in certain areas and load demands may be zero.

[0121] Step S30: generating a load demand regulation strategy according to the response characteristic information of the communication load.

[0122] It should be noted that the response characteristic information includes driving characteristics, response period characteristics and response speed characteristics.

[0123] In the specific implementation, the sensing device can analyze the communication load demand response mechanism of the power business based on load characteristics such as communication load driving mode, response period, and response speed, and generate a load demand control strategy for the power business that can be dynamically adjusted during load fluctuation periods.

[0124] In some embodiments, the load demand regulation strategy can be divided into incentive-based demand response and price-based demand response based on the driving mode. For incentive-based demand response, users can be attracted to participate in the communication load reduction project required by the system by adopting incentive policies and compensation methods. For example, during the peak period of communication load, operators can encourage users to adjust their communication behavior or reduce the amount of data transmission through price discounts, point rewards, or cash rewards. Users reduce load demand by adjusting usage time, delaying non-important communication tasks, or using local cache, thereby obtaining "compensation" provided by operators. For price-based demand response, user behavior is guided by dynamically adjusting communication costs. Similar to the peak and valley mechanism of time-of-use electricity prices, operators can use different pricing strategies, such as real-time traffic rates, time-divided data charges, etc., to allow users to adjust their communication behavior in different time periods. For example, during peak load periods, operators increase data transmission fees to encourage users to reduce load usage; while during load trough periods, operators provide lower traffic fees to attract users to increase load demand.

[0125] In some embodiments, the load demand regulation strategy can be divided into peak-shaving demand response and valley-filling demand response based on the response period. For peak-shaving demand response, users are required to reduce load usage during the peak period of communication load. Operators can encourage users to postpone large data transmission or adjust the load occupancy of applications by informing users of the expected peak period in advance or providing relevant incentives during the peak period. Network intelligent scheduling technology can be combined to allow users to automatically adjust data transmission time to avoid occupying a large amount of load resources during peak periods. For valley-filling demand response, users are encouraged to increase data transmission during load trough periods. For example, operators can encourage users to perform non-real-time, low-priority file downloads or data backups during load trough periods (such as late at night or non-peak hours on weekdays). This type of demand response can encourage users to increase load demand during trough periods through price discounts or point rewards, thereby balancing the overall network load.

[0126] In some embodiments, the load demand regulation strategy can be divided into scheduled demand response and real-time demand response based on the response speed. For scheduled demand response, the operator can send communication load demand information to users through the platform (such as SMS, application notification, etc.) in advance to inform users of the communication demand and load requirements for a specific period of time. Users can adjust the data transmission volume independently according to the notification to ensure that the load will not be overloaded during the specified period. Operators can optimize the allocation of load resources based on the timeliness and response volume of user responses. For example, the earlier the user responds, the more likely they are to receive more compensation. For real-time demand response, when an emergency occurs in the network, the operator can send an emergency communication load adjustment instruction to the user within a short time (for example, within 30 minutes or 1 minute), requiring the user to reduce load occupancy or postpone the transmission of non-emergency data. In order to cope with sudden peaks in communication demand, user equipment needs to have a certain degree of flexibility, such as automatically adjusting data traffic or automatically limiting load usage through smart terminals to cooperate with emergency adjustments of the network. The key to real-time communication demand response is to achieve rapid feedback and instant control to ensure that the network load can be quickly reduced in an emergency to avoid network congestion or communication interruption.

[0127] Step S40: Aggregating the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result.

[0128] It should be noted that aggregating the communication load may include time aggregation and space aggregation. The communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load.

[0129] In some embodiments, the sensing device can extract the spatiotemporal distribution characteristics of multivariate communication loads, construct a spatiotemporal multidimensional aggregation method for communication loads, reduce the computational complexity of power business communication load situation awareness, alleviate the pressure on the power network and improve the utilization rate of loads. In the period of the total load.

[0130] Furthermore, in order to accurately aggregate the communication load in the time dimension, refer to Figure 4 , Figure 4 This is a schematic diagram of a time aggregation process according to an embodiment of the present invention. The above step S40 may include:

[0131] Step S401: determining the data demand capacity and load demand time of each communication load according to the communication load model;

[0132] Step S402: Determine the load peak and valley time distribution information of the satellite-ground integrated new power system based on the data demand capacity and the load demand time;

[0133] Step S403: determining the task priority of each communication load according to the load type;

[0134] Step S404: determining a peak-valley allocation strategy for each communication load based on the load peak-valley time distribution information and the task priority;

[0135] Step S405: performing time aggregation on the communication load based on the load peak and valley time distribution information and the task priority to obtain a communication load aggregation result.

[0136] It should be noted that this embodiment analyzes the dynamic communication load presented by the power business in different time periods, and aggregates the low-capacity communication load at different time peaks into a higher-capacity communication load through communication load time aggregation. This is used to describe the communication load in this period, and avoids load pressure during network peak periods through task translation and transfer, thereby achieving the effect of peak shaving and valley filling and reducing load pressure.

[0137] It should be noted that the study of a peak period Multiple different low capacity loads (such as low-priority tasks or communication loads of different nodes), and the time point at which the load is generated is , aggregate the communication load to form a higher capacity load , time aggregation refers to the following formula:

[0138]

[0139] in, represents the time aggregated load, It represents the time-aggregated communication load demand capacity during the peak period (i.e., the peak period of communication load demand in the power system), Indicates the load demand time of each communication load.

[0140] In some embodiments, the sensing device can reasonably distribute the aggregated higher capacity load to multiple valley periods through task translation and transfer, and distribute the load based on the peak-valley allocation strategy, wherein the peak-valley allocation strategy includes a task translation strategy and a task transfer strategy, and the constraints of the peak-valley allocation strategy include:

[0141]

[0142] in, represents the time aggregated load, is the translation capacity and / or transfer capacity of the communication load, wherein the translation capacity and / or transfer capacity represents the load increase amount in each valley period, The actual load in the valley period after load shifting and / or transfer is the valley period (i.e., the valley period of power system communication load demand). for:

[0143]

[0144] In some embodiments, the sensing device can construct an objective function and perform time aggregation on the communication load based on the objective function, thereby minimizing the difference between the load during the valley period and the target load, ensuring that the load during the valley period is more stable and avoiding excessive load fluctuations. The objective function is as follows:

[0145]

[0146] in, represents the set of valley periods (i.e., all valley periods in the power system), Indicates the low period after the communication load is shifted and / or transferred The actual load, Low period The target load (i.e. the preset expected value), Indicates the absolute difference between the actual load and the target load.

[0147] Furthermore, in order to accurately aggregate the communication load in the spatial dimension, refer to Figure 5 , Figure 5 This is a schematic diagram of a spatial aggregation process according to an embodiment of the present invention. The above step S40 may include:

[0148] Step S4001: Acquire the geographical distribution information of the power grid and the coverage information of the satellite-ground integrated new power system;

[0149] Step S4002: Determine the spatial distribution information of each communication load based on the geographical distribution information of the power grid and the satellite-to-ground network coverage information;

[0150] Step S4003: performing similarity analysis on each communication load according to the communication load model to obtain load similarity information;

[0151] Step S4004: spatially aggregate the communication load based on the spatial distribution information and the load similarity information to obtain a communication load aggregation result.

[0152] It should be noted that this embodiment realizes spatial aggregation of communication loads in the spatial dimension by analyzing the geographical distribution characteristics of the power grid, load similarity and satellite-to-ground network coverage capabilities, and aggregates multiple low-capacity communication loads in different regions into a higher-capacity load. The spatial aggregation of communication loads includes:

[0153] Set up research area ,in is a sub-region of the study area, The load demand at a certain moment is , and the aggregate load in the study area It is the sum of the loads of all sub-areas in the area at a certain moment. The mathematical formula is as follows:

[0154]

[0155] in, represents a sub-area in the space aggregation area of ​​the new satellite-ground integrated power system, represents the communication load demand capacity of each sub-area, The spatial aggregation load represents the spatial aggregation load of the spatial aggregation area, where the spatial aggregation load is the sum of the communication loads of all sub-areas in the spatial aggregation area.

[0156] Step S50: performing dependency analysis on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads.

[0157] It should be noted that the above-mentioned time-space dependency information may include time dependency information and space dependency information between each aggregated load.

[0158] It can be understood that the sensing device can analyze the historical load characteristics of the power business communication network nodes through time and space aggregation, and capture the time dependency and space dependency of each communication node based on the analysis results of the historical load characteristics.

[0159] Furthermore, in order to accurately analyze the dependencies between communication loads from a spatial dimension, refer to Figure 6 , Figure 6 This is a schematic diagram of a spatial dependency analysis process according to an embodiment of the present invention. The above step S50 may include:

[0160] Step S501: Acquire historical communication load data of the satellite-ground integrated new power system;

[0161] Step S502: normalizing the historical communication load data;

[0162] Step S503: constructing a graph structure according to the normalized historical communication load data;

[0163] Step S504: performing spatial dependency analysis on the communication load aggregation result based on the adjacency matrix to obtain spatial dependency information between each aggregated load.

[0164] It should be noted that the sensing device can analyze the historical load characteristics of the nodes of the multi-power business communication network after spatiotemporal aggregation, capture the spatial dependency of the communication network nodes based on the adaptive adjacency matrix technology, and propose a method for extracting the spatial dependency of the communication load based on the graph convolution layer. The method for extracting the spatial dependency of the communication load based on the graph convolution layer is as follows:

[0165] Based on the historical load data of each node in the power communication network after spatiotemporal aggregation, a three-dimensional tensor is used to represent the spatiotemporal data of communication load. The mathematical formula is as follows:

[0166]

[0167] in, Indicates The communication nodes are in the time step The load characteristics, is the number of nodes, The spatiotemporal data in the historical communication load data can be normalized to improve the analysis efficiency and accuracy. The normalization process refers to the following formula:

[0168]

[0169] Among them, the historical communication load data after normalization is For the The communication nodes are in the time step Communication load data, and are the mean and standard deviation of the historical communication load data respectively.

[0170] It should be noted that the perception device describes the spatial dependency relationship between nodes in the communication network by constructing a graph structure, wherein the graph structure includes multiple adjacency matrices, and the adjacency matrix includes multiple communication nodes, and each communication node is connected based on the dependency relationship.

[0171] Each communication node is a node in the graph structure, and the edges between nodes represent the dependencies between communication loads. To express, is the node set, and E is the edge set. Indicates communication nodes, edge Representation Node and Establish an adaptive adjacency matrix to represent the connection between nodes. Assume that each node in the graph is connected to other nodes through edges. Elements Defined as a node and The connection strength between them can be expressed as follows:

[0172]

[0173] An adaptive adjacency matrix is ​​constructed to capture spatial dependencies, and its formula is expressed as:

[0174]

[0175] in, and are the embedding vectors of the source node and the target node respectively, and is the activation function (for example, the activation function can be ReLU and Softmax).

[0176] In some embodiments, the perception device may perform dependency analysis by proposing a method for extracting spatial dependency of communication load based on a graph convolution layer. In a graph neural network, the basic operation of graph convolution is the diffusion of information between nodes. The graph convolution formula is specifically designed as follows:

[0177]

[0178] in, It is The output after diffusion, is the learned convolution weight, is the transfer matrix, is the input feature matrix. Finally, the output of the graph convolution layer is the weighted sum of all diffusion steps:

[0179]

[0180] in, is the number of diffusion steps, is the transfer matrix during the diffusion process.

[0181] Furthermore, in order to accurately analyze the dependency of communication load from the time dimension, refer to Figure 7 , Figure 7 This is a schematic diagram of a time-dependent analysis process according to an embodiment of the present invention. The above step S50 may include:

[0182] Step S5001: constructing a temporal convolutional network;

[0183] Step S5002: acquiring historical time series data of each communication load based on the historical communication load data of the satellite-ground integrated new power system;

[0184] Step S5003: Performing a time dependency analysis on the communication load aggregation result based on the historical time series data according to the time convolution network to obtain time dependency information between each aggregated load.

[0185] It should be noted that the sensing device can analyze the statistical characteristics and time-varying laws of the communication load characteristics and propose a communication load time feature mining technology based on a causal convolutional network. The communication load time feature mining technology based on a causal convolutional network may include:

[0186] By using a temporal convolutional network and causal convolution to process time series data, the model can only use the current and previous time step data for prediction, thus avoiding data leakage. The causal convolution formula is as follows:

[0187]

[0188] in, is the convolution kernel, is the expansion factor, is the convolution kernel size, represents the offset at each time step in the convolution operation, Represents the convolution kernel at time The coefficient of Indicates the current time index. Represents the input time series data.

[0189] Step S60: predicting the load situation of the satellite-ground integrated new power system according to the spatiotemporal dependency information to obtain a load situation perception result.

[0190] In some embodiments, the sensing device can combine the temporal and spatial characteristics of the communication load to establish a Graph WaveNet framework based on the residual connection mechanism, integrate the multi-temporal and spatial scale dependencies of the communication load, and present the temporal and spatial distribution of the power business communication load in the form of a visual graph structure, providing a scientific basis for the resource scheduling of the new power system satellite-ground fusion network. Establishing the Graph WaveNet framework may include:

[0191] The Graph WaveNet framework is constructed by combining graph convolution and temporal convolution. Graph convolution is used to extract spatial dependencies, while temporal convolution is used to extract temporal features. The final output is obtained by stacking multiple graph convolution and temporal convolution layers. The output formula of the Graph WaveNet framework is:

[0192]

[0193] in, is the number of diffusion steps, is the learned convolution weight, is the input feature matrix, is the weighted sum of all diffusion steps, Representing adaptive adjacency matrices in graph structures.

[0194] Use the Adam optimizer for back propagation training to optimize the weights of the graph neural network by minimizing the loss function. The formula for minimizing the loss function is:

[0195]

[0196] in, is the predicted value, is the true value, is the number of samples in the test set.

[0197] In this embodiment, the communication load is classified based on the load characteristic information of the communication load of each communication node in the satellite-ground fusion new power system, and the load classification result is obtained. A communication load model corresponding to each load type is constructed according to the load classification result, and a load demand regulation strategy is generated according to the response characteristic information of the communication load. The response characteristic information includes a driving characteristic, a response period characteristic, and a response speed characteristic. The communication load is aggregated based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result. The communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load. A dependency analysis is performed on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads. The load situation of the satellite-ground fusion new power system is predicted according to the spatiotemporal dependency information to obtain a load situation perception result. Since this embodiment classifies and spatiotemporally aggregates the communication load of the satellite-ground fusion new power system, the complexity of data analysis is effectively reduced, and the analysis efficiency is greatly improved. By performing spatiotemporal dependency analysis on the communication load aggregation result, the accuracy of communication load prediction of the satellite-ground fusion new power system is greatly improved, the timeliness of the prediction result is ensured, and the communication quality of the power business is effectively guaranteed.

[0198] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which is stored a new power system satellite-ground fusion communication load modeling and situational awareness program. When the new power system satellite-ground fusion communication load modeling and situational awareness program is executed by a processor, the steps of the new power system satellite-ground fusion communication load modeling and situational awareness method as described above are implemented.

[0199] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0200] The above-mentioned computer-readable storage medium may be included in the new power system satellite-ground integrated communication load modeling and situation awareness device; or it may exist independently without being assembled into the new power system satellite-ground integrated communication load modeling and situation awareness device.

[0201] In addition, an embodiment of the present invention also proposes a computer program product, including a new power system satellite-ground fusion communication load modeling and situational awareness program, which, when executed by a processor, implements the steps of the new power system satellite-ground fusion communication load modeling and situational awareness method as described above.

[0202] The specific implementation manner of the computer program product of the present invention is basically the same as the various embodiments of the above-mentioned novel power system satellite-ground integrated communication load modeling and situation awareness method, and will not be repeated here.

[0203] Reference Figure 8 , Figure 8 It is a structural block diagram of the first embodiment of the novel power system satellite-ground fusion communication load modeling and situation awareness system of the present invention.

[0204] like Figure 8 As shown, the novel power system satellite-ground fusion communication load modeling and situation awareness system proposed in the embodiment of the present invention includes:

[0205] The load classification module 10 is used to classify the communication load of each communication node in the satellite-ground integrated new power system based on the load characteristic information of the communication load and obtain the load classification result;

[0206] A model building module 20, used to build a communication load model corresponding to each load type according to the load classification result;

[0207] A demand control module 30, configured to generate a load demand control strategy according to the response characteristic information of the communication load, wherein the response characteristic information includes a driving characteristic, a response period characteristic, and a response speed characteristic;

[0208] A load aggregation module 40, configured to aggregate the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result, wherein the communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load;

[0209] A dependency analysis module 50, configured to perform dependency analysis on the communication load aggregation result to obtain spatiotemporal dependency information between the aggregated loads;

[0210] The situation awareness module 60 is used to predict the load situation of the satellite-ground integrated new power system according to the time-space dependency information to obtain a load situation awareness result.

[0211] In this embodiment, the communication load is classified based on the load characteristic information of the communication load of each communication node in the satellite-ground integrated new power system, and the load classification result is obtained. A communication load model corresponding to each load type is constructed according to the load classification result, and a load demand regulation strategy is generated according to the response characteristic information of the communication load. The response characteristic information includes a driving characteristic, a response period characteristic, and a response speed characteristic. The communication load is aggregated based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result. The communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load. A dependency analysis is performed on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads. The load situation of the satellite-ground integrated new power system is predicted according to the spatiotemporal dependency information to obtain a load situation perception result. Since this embodiment classifies and spatiotemporally aggregates the communication load of the satellite-ground integrated new power system, the complexity of data analysis is effectively reduced, and the analysis efficiency is greatly improved. By performing spatiotemporal dependency analysis on the communication load aggregation result, the accuracy of communication load prediction of the satellite-ground integrated new power system is greatly improved, the timeliness of the prediction result is ensured, and the communication quality of the power business is effectively guaranteed.

[0212] The new power system satellite-ground fusion communication load modeling and situation awareness system provided by the present application adopts the new power system satellite-ground fusion communication load modeling and situation awareness method in the above-mentioned embodiment, which can solve the technical problems of new power system satellite-ground fusion communication load modeling and situation awareness. Compared with the prior art, the beneficial effects of the new power system satellite-ground fusion communication load modeling and situation awareness system provided by the present application are the same as the beneficial effects of the new power system satellite-ground fusion communication load modeling and situation awareness method provided by the above-mentioned embodiment, and other technical features of the new power system satellite-ground fusion communication load modeling and situation awareness system are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0213] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0214] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0215] In addition, for technical details not described in detail in this embodiment, reference can be made to the novel power system satellite-ground integrated communication load modeling and situation awareness method provided in any embodiment of the present invention, which will not be repeated here.

[0216] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0217] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0218] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0219] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A new method for load modeling and situation awareness of satellite-ground fusion communication in power system, characterized in that: The method comprises: Classifying the communication load based on the load characteristic information of the communication load of each communication node in the new satellite-ground integrated power system to obtain a load classification result; Constructing a communication load model corresponding to each load type according to the load classification result; generating a load demand regulation strategy according to the response characteristic information of the communication load, wherein the response characteristic information includes a driving characteristic, a response period characteristic, and a response speed characteristic; Aggregating the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result, wherein the communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load; Performing dependency analysis on the communication load aggregation result to obtain spatiotemporal dependency information between the aggregated loads; The load situation of the new satellite-ground integrated power system is predicted according to the time-space dependency information to obtain a load situation perception result.

2. The novel power system satellite-ground fusion communication load modeling and situation awareness method according to claim 1 is characterized in that: The aggregating the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result includes: Determine the data demand capacity and load demand time of each communication load according to the communication load model; Determine the load peak and valley time distribution information of the satellite-ground integrated new power system based on the data demand capacity and the load demand time; Determining the task priority of each communication load according to the load type; The peak-valley allocation strategy of each communication load is determined based on the load peak-valley time distribution information and the task priority, wherein the peak-valley allocation strategy includes a task translation strategy and a task transfer strategy, and the constraint conditions of the peak-valley allocation strategy include: in, represents the time aggregated load, is the translation capacity and / or transfer capacity of the communication load, It is the valley period; Based on the load peak-valley time distribution information and the task priority, the communication load is time aggregated to obtain a communication load aggregation result: in, represents the time-aggregated communication load demand capacity during the peak period, Indicates the load demand time of each communication load.

3. The novel power system satellite-ground fusion communication load modeling and situation awareness method according to claim 2 is characterized in that: The aggregating the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result includes: Acquire the geographical distribution information of the power grid and the coverage information of the satellite-ground network of the new satellite-ground integrated power system; Determine the spatial distribution information of each communication load based on the geographical distribution information of the power grid and the satellite-to-ground network coverage information; Perform similarity analysis on each communication load according to the communication load model to obtain load similarity information; The communication load is spatially aggregated based on the spatial distribution information and the load similarity information to obtain a communication load aggregation result: in, represents a sub-area in the space aggregation area of ​​the new satellite-ground integrated power system, represents the communication load demand capacity of each sub-area, The spatial aggregation load represents the spatial aggregation load of the spatial aggregation area, where the spatial aggregation load is the sum of the communication loads of all sub-areas in the spatial aggregation area.

4. The novel power system satellite-ground fusion communication load modeling and situation awareness method according to claim 1 is characterized in that: The spatiotemporal dependency information includes spatial dependency information; the performing dependency analysis on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads includes: Acquire historical communication load data of the new satellite-ground integrated power system; The historical communication load data is normalized: Among them, the historical communication load data after normalization is For the The communication nodes are in the time step Communication load data, and are the mean and standard deviation of the historical communication load data respectively; Constructing a graph structure according to the normalized historical communication load data, wherein the graph structure includes a plurality of adjacency matrices, the adjacency matrix includes a plurality of communication nodes, and each communication node is connected based on a dependency relationship; A spatial dependency analysis is performed on the communication load aggregation result based on the adjacency matrix to obtain spatial dependency information between each aggregated load.

5. The novel power system satellite-ground fusion communication load modeling and situation awareness method according to claim 4 is characterized in that: The spatiotemporal dependency information includes time dependency information; the performing dependency analysis on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads includes: Construct a temporal convolutional network: in, is the convolution kernel, is the expansion factor, is the convolution kernel size, represents the offset at each time step in the convolution operation, Represents the convolution kernel at time The coefficient of Indicates the current time index. Represents the input time series data; Based on the historical communication load data of the satellite-ground integrated new power system, historical time series data of each communication load is obtained; A time dependency analysis is performed on the communication load aggregation result based on the historical time series data according to the time convolution network to obtain time dependency information between each aggregated load.

6. The novel power system satellite-ground fusion communication load modeling and situation awareness method according to any one of claims 1 to 5, characterized in that: The load classification result includes a demand response classification result, the load types in the demand response classification result include a shiftable communication load, a transferable communication load and a reducible communication load, and the communication load model includes a shiftable communication load model, a transferable communication load model and a reducible communication load model; The constructing of a communication load model corresponding to each load type according to the load classification result includes: Obtain the load demand data volume, time demand information and space demand information of each load type; Generate load distribution constraint conditions corresponding to each load type according to the load demand data volume, the time demand information and the space demand information, wherein the load distribution constraint conditions include data volume constraint conditions, distribution time constraint conditions and distribution space constraint conditions; A communication load model corresponding to each load type is constructed based on the load distribution constraint condition.

7. A new type of power system satellite-ground fusion communication load modeling and situation awareness system, characterized by: The new power system satellite-ground fusion communication load modeling and situation awareness system includes: A load classification module, used to classify the communication load of each communication node in the new satellite-ground integrated power system based on load characteristic information of the communication load, and obtain a load classification result; A model building module, used to build a communication load model corresponding to each load type according to the load classification result; A demand control module, used to generate a load demand control strategy according to the response characteristic information of the communication load, wherein the response characteristic information includes a driving characteristic, a response period characteristic and a response speed characteristic; A load aggregation module, configured to aggregate the communication load based on the communication load model and the load demand regulation strategy to obtain a communication load aggregation result, wherein the communication load aggregation result includes multiple aggregated loads, and the aggregated load includes a time aggregated load and a space aggregated load; A dependency analysis module, used to perform dependency analysis on the communication load aggregation result to obtain the spatiotemporal dependency information between the aggregated loads; The situation awareness module is used to predict the load situation of the satellite-ground integrated new power system according to the time-space dependency information to obtain load situation awareness results.

8. A new type of power system satellite-ground fusion communication load modeling and situation awareness equipment, characterized by: The new power system satellite-to-ground fusion communication load modeling and situational awareness device includes: a memory, a processor, and a new power system satellite-to-ground fusion communication load modeling and situational awareness program stored in the memory and executable on the processor. The new power system satellite-to-ground fusion communication load modeling and situational awareness program is configured to implement the new power system satellite-to-ground fusion communication load modeling and situational awareness method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a new type of power system satellite-ground fusion communication load modeling and situation awareness program, and when the new type of power system satellite-ground fusion communication load modeling and situation awareness program is executed by the processor, the new type of power system satellite-ground fusion communication load modeling and situation awareness method as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a new power system satellite-ground fusion communication load modeling and situational awareness program, and when the new power system satellite-ground fusion communication load modeling and situational awareness program is executed by a processor, it implements the steps of the new power system satellite-ground fusion communication load modeling and situational awareness method as described in any one of claims 1 to 6.

Images