Bus load prediction method and device, storage medium and electronic equipment

Abstract

The invention discloses a bus load prediction method and device, a storage medium and electronic equipment. Relates to the technical field of data processing, the technical field of electronics and other related technical fields, and comprises the following steps: aggregating a plurality of buses in a target power grid to obtain a virtual bus corresponding to the target power grid; obtaining a plurality of first historical bus loads of the virtual bus in a historical time period; predicting the load of the virtual bus according to the plurality of first historical bus loads to obtain an initial load prediction result; and determining a target load prediction result corresponding to each bus in the target power grid according to the target matching factor and the initial load prediction result. Through the bus load prediction method and device, the problem that the prediction efficiency of the bus load is relatively low due to the fact that the load of each bus in a power grid is predicted manually in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the fields of data processing technology, electronic technology and other related technical fields, and specifically, to a bus load prediction method and device, a storage medium and an electronic device. Background Art

[0002] With the rapid development of economy, the development of power grid technology is also very rapid. Various new equipments are introduced into the power grid, and the interconnection of regional power grids has become a reality. While people are enjoying the progress of power grid technology, the potential threat of power grid is also increasing. Improving the safe and stable operation level of large power grid has become a basic issue of power grid construction. Bus load prediction is the basis of dynamic state estimation, safety and stability analysis, reactive power optimization and local control of power plants and stations, and is a major tool to improve the safe and stable operation level of large power grids. The methods of bus load prediction are mainly divided into two categories: one is the prediction method based on system load, and the other is the prediction method based on the law of bus itself. Of these two methods, the former does not fully consider the law of each bus, which restricts the improvement of prediction accuracy; while the latter requires independent analysis and independent modeling of each bus, which consumes huge human resources and computing resources.

[0003] With regard to the problem that the related technology predicts the load of each bus in the power grid manually, resulting in relatively low efficiency in predicting the bus load, no effective solution has been proposed so far. Summary of the invention

[0004] The main purpose of this application is to provide a bus load prediction method and device, storage medium and electronic device to solve the problem that the related technology predicts the load of each bus in the power grid manually, resulting in relatively low bus load prediction efficiency.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a bus load prediction method is provided. The method comprises: aggregating multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid; obtaining multiple first historical bus loads of the virtual bus in a historical time period; predicting the load of the virtual bus according to the multiple first historical bus loads to obtain an initial load prediction result; and determining a target load prediction result corresponding to each bus in the target power grid according to a target ratio factor and the initial load prediction result.

[0006] Furthermore, aggregating multiple buses in the target power grid to obtain a virtual bus corresponding to the target power grid includes: determining the section and section length corresponding to each bus, and screening the section corresponding to each bus according to a first threshold and the section length to obtain multiple target sections; for each bus, calculating the generator output power transfer distribution factor value of the bus for each target section to obtain multiple generator output power transfer distribution factor values; aggregating the multiple buses according to the multiple generator output power transfer distribution factor values ​​to obtain the virtual bus.

[0007] Furthermore, the multiple buses are aggregated according to the multiple generator output power transfer distribution factor values ​​to obtain the virtual bus, including: constructing a matrix according to the multiple generator output power transfer distribution factor values ​​to obtain a target matrix; performing calculations according to the target matrix to obtain a generator output power transfer distribution factor vector corresponding to each bus; and aggregating the multiple buses based on the generator output power transfer distribution factor vector corresponding to each bus through a target aggregation algorithm to obtain the virtual bus.

[0008] Furthermore, predicting the load of the virtual bus based on the multiple first historical bus loads to obtain an initial load prediction result includes: obtaining target attribute information of the virtual bus, wherein the target attribute information at least includes: the temperature change rate, humidity change rate, wind speed change rate and air pressure change rate of the virtual bus; calculating according to preset weight values ​​and the target attribute information to obtain the target attribute value corresponding to the virtual bus; matching the target attribute value with the multiple first historical bus loads to obtain the initial load prediction result.

[0009] Furthermore, matching the target attribute value with the multiple first historical bus loads to obtain the initial load forecast result includes: matching the target attribute value with the attribute value corresponding to each historical bus load to obtain multiple matching scores; filtering the multiple matching scores according to a second threshold to obtain a target score; and determining the first historical bus load corresponding to the target score as the initial load forecast result.

[0010] Furthermore, before determining the target load prediction result corresponding to each bus in the target power grid based on the target matching factor and the initial load prediction result, the method also includes: obtaining multiple second historical bus loads for each bus within the historical time period; calculating based on the multiple second historical bus loads and the multiple first historical bus loads to obtain multiple target ratios; fitting the multiple target ratios to obtain a target fitting function; and determining the target matching factor based on the target fitting function.

[0011] Furthermore, obtaining the target attribute information of the virtual bus includes: obtaining initial attribute information of the virtual bus; discretizing the initial attribute information to obtain discretized initial attribute information; and performing attribute simplification on the discretized initial attribute information through a target greedy algorithm to obtain the target attribute information.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a bus load prediction device is provided. The device includes: an aggregation unit, which is used to aggregate multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid; a first acquisition unit, which is used to obtain multiple first historical bus loads of the virtual bus in a historical time period; a prediction unit, which is used to predict the load of the virtual bus according to the multiple first historical bus loads to obtain an initial load prediction result; a first determination unit, which is used to determine the target load prediction result corresponding to each bus in the target power grid according to the target ratio factor and the initial load prediction result.

[0013] Furthermore, the aggregation unit includes: a determination module, used to determine the section and section length corresponding to each bus, and screen the section corresponding to each bus according to the first threshold and the section length to obtain multiple target sections; a first calculation module, used to calculate the generator output power transfer distribution factor value of the bus for each target section for each bus, and obtain multiple generator output power transfer distribution factor values; an aggregation module, used to aggregate the multiple buses according to the multiple generator output power transfer distribution factor values ​​to obtain the virtual bus.

[0014] Furthermore, the aggregation module includes: a construction submodule, used to construct a matrix based on the output power transfer distribution factor values ​​of the multiple generators to obtain a target matrix; a calculation submodule, used to perform calculations based on the target matrix to obtain the generator output power transfer distribution factor vector corresponding to each bus; and an aggregation submodule, used to aggregate the multiple buses based on the generator output power transfer distribution factor vector corresponding to each bus through a target aggregation algorithm to obtain the virtual bus.

[0015] Furthermore, the prediction unit includes: an acquisition module, used to acquire target attribute information of the virtual bus, wherein the target attribute information includes at least: the temperature change rate, humidity change rate, wind speed change rate and air pressure change rate of the virtual bus; a second calculation module, used to calculate according to a preset weight value and the target attribute information to obtain the target attribute value corresponding to the virtual bus; a matching module, used to match according to the target attribute value and the multiple first historical bus loads to obtain the initial load prediction result.

[0016] Furthermore, the matching module includes: a matching sub-module, used to match the target attribute value with the attribute value corresponding to each historical bus load to obtain multiple matching scores; a screening sub-module, used to screen the multiple matching scores according to a second threshold to obtain a target score; and a determination sub-module, used to determine the first historical bus load corresponding to the target score as the initial load forecast result.

[0017] Furthermore, the device also includes: a second acquisition unit, used to obtain multiple second historical bus loads of each bus within the historical time period before determining the target load prediction result corresponding to each bus in the target power grid based on the target ratio factor and the initial load prediction result; a calculation unit, used to calculate based on the multiple second historical bus loads and the multiple first historical bus loads to obtain multiple target ratios; a fitting unit, used to fit the multiple target ratios to obtain a target fitting function; a second determination unit, used to determine the target ratio factor based on the target fitting function.

[0018] Furthermore, the acquisition module includes: an acquisition sub-module, used to acquire the initial attribute information of the virtual bus; a discretization sub-module, used to discretize the initial attribute information to obtain the discretized initial attribute information; and a simplification sub-module, used to perform attribute simplification on the discretized initial attribute information through a target greedy algorithm to obtain the target attribute information.

[0019] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the bus load prediction methods described above.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is also provided, the electronic device includes one or more processors and a memory, and the memory is used to store one or more processors to implement any of the bus load prediction methods described above.

[0021] Through this application, the following steps are adopted: aggregating multiple buses in the target power grid to obtain a virtual bus corresponding to the target power grid; obtaining multiple first historical bus loads of the virtual bus in the historical time period; predicting the load of the virtual bus according to the multiple first historical bus loads to obtain the initial load prediction result; determining the target load prediction result corresponding to each bus in the target power grid according to the target ratio factor and the initial load prediction result. Through this application, the problem that the load of each bus in the power grid is predicted manually in the related technology, resulting in low prediction efficiency of the bus load, is solved. In this scheme, multiple buses in the target power grid are aggregated to generate a virtual bus. And the initial load prediction result corresponding to the virtual bus is determined according to the multiple first historical bus load data of the virtual bus in the historical time period. Finally, the target load prediction result corresponding to each bus in the target power grid is determined based on the target ratio factor according to the initial load prediction result. Through the virtual bus, the load situation of the entire power grid can be considered more comprehensively, thereby improving the accuracy of load prediction. At the same time, by determining the target load forecast result of each bus through the target ratio factor and the initial load forecast result, the ratio factor can be adjusted more flexibly to better adapt to the load forecast requirements under different circumstances. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 is a flow chart of a bus load prediction method provided according to an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of a bus load prediction method provided according to an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of a bus load prediction device provided according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0031] Virtual bus: A local network existing in the power grid system structure. The networks are closely connected. The GSDF (Generator Output Power Transfer Distribution Factor) of the key sections of each bus within the network is the same or similar, and the load curves have certain similarities.

[0032] Generator Output Power Transfer Distribution Factor (GSDF): It measures the power distribution between different generators in the system, that is, the distribution ratio of the generator output power in the system. This factor can help system operators better manage the generators in the system and ensure the stable operation of the system.

[0033] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0034] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a bus load prediction method provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0035] Step S101, aggregating multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid.

[0036] Optionally, the key sections corresponding to multiple buses in the target power grid are first screened out, and the GSDF of each bus to the key section is calculated. Based on the hierarchical clustering method, buses with similar GSDF are aggregated into virtual buses.

[0037] It should be noted that the virtual bus is a bus group that meets the following aggregation criteria: ① The sub-buses of the virtual bus have the same or similar GSDF for key sections; ② The load curves of the sub-buses are similar; ③ The sub-buses meet the topological connectivity.

[0038] Step S102, obtaining a plurality of first historical bus loads of the virtual bus within a historical time period.

[0039] Optionally, all load data (i.e., multiple first historical bus loads) of the virtual bus within a historical time period (e.g., one week, one month, or one year) are collected through a power grid monitoring system, historical records, or other data sources, including information such as bus name, load value, and timestamp.

[0040] Step S103, predicting the load of the virtual bus according to the plurality of first historical bus loads to obtain an initial load prediction result.

[0041] Optionally, by combining the advantages of rough set method and virtual bus technology with the prediction model, irrelevant environmental factors are removed from multiple environmental factors, factors with greater impact on bus load are retained, and load forecasting is performed based on this to obtain initial load forecasting results.

[0042] Step S104, determining the target load forecast result corresponding to each bus in the target power grid according to the target matching factor and the initial load forecast result.

[0043] Optionally, the initial load forecast result is multiplied by the target ratio factor through the ratio model to obtain the load forecast value (ie, target load forecast result) of the sub-bus (ie, each bus in the target power grid).

[0044] In summary, multiple buses in the target power grid are aggregated to generate a virtual bus. And the initial load forecast result corresponding to the virtual bus is determined based on multiple first historical bus load data of the virtual bus in the historical time period. Finally, based on the target ratio factor according to the initial load forecast result, the target load forecast result corresponding to each bus in the target power grid is determined. Through the virtual bus, the load situation of the entire power grid can be considered more comprehensively, thereby improving the accuracy of load forecasting. At the same time, by determining the target load forecast result of each bus through the target ratio factor and the initial load forecast result, the ratio factor can be adjusted more flexibly, so as to better adapt to the load forecasting needs under different situations.

[0045] Optionally, in the bus load prediction method provided in an embodiment of the present application, multiple buses in the target power grid are aggregated to obtain a virtual bus corresponding to the target power grid, including: determining the section and section length corresponding to each bus, and screening the section corresponding to each bus according to a first threshold and the section length to obtain multiple target sections; for each bus, calculating the generator output power transfer distribution factor value of the bus for each target section to obtain multiple generator output power transfer distribution factor values; and aggregating multiple buses according to the multiple generator output power transfer distribution factor values ​​to obtain a virtual bus.

[0046] In an optional embodiment, the section and section length corresponding to each busbar in the target power grid are determined by two methods: the actual power grid operation situation and the key section search algorithm. The section with the smallest safety margin and the greatest impact on the safety of the target power grid is determined as the key section K (i.e., multiple target sections) from the target power grid. K=[k 1 ,k 2 ,…,k m ] (where m is the number of sections). For different buses, the GSDF (i.e., the generator output power transfer distribution factor) for the key section K is calculated respectively, and the virtual bus of the target power grid is determined based on all the calculation results.

[0047] It should be noted that the safety margin in the power cable design specifications is usually set at 5% to 10% of the cable length, and sections smaller than this value can be determined as critical sections.

[0048] By screening and calculating the sections corresponding to each bus, the virtual bus of the target power grid can be determined more accurately, thereby better describing the operating status and characteristics of the power grid.

[0049] Optionally, in the bus load prediction method provided in an embodiment of the present application, multiple buses are aggregated according to multiple generator output power transfer distribution factor values ​​to obtain a virtual bus, including: constructing a matrix based on multiple generator output power transfer distribution factor values ​​to obtain a target matrix; performing calculations based on the target matrix to obtain a generator output power transfer distribution factor vector corresponding to each bus; and aggregating multiple buses based on the generator output power transfer distribution factor vector corresponding to each bus through a target aggregation algorithm to obtain a virtual bus.

[0050] In an optional embodiment, for different buses, the GSDF (i.e., the generator output power transfer distribution factor) for the key section K is calculated respectively, and all the calculation results are combined into a matrix S k (i.e., target matrix), matrix S k The expression is as follows:

[0051]

[0052] Among them, S ij represents the GSDF of busbar i to key section j, S ij The calculation expression is as follows:

[0053]

[0054] Where X represents the reactance matrix, x j represents the reactance of branch j, e i represents the unit column vector. The non-zero element 1 only exists at the position corresponding to node i, and the numbers at other positions are all 0. is the node-branch association vector of branch j.

[0055] For busbar i, the GSDF vector for m key sections [S i1 ,S i2 ,…,S im ] (i.e., the generator output power transfer distribution factor vector corresponding to each bus) defines the position of bus i in the m-dimensional space. Buses with similar positions in the m-dimensional space are aggregated into identifiable virtual buses.

[0056] It should be noted that the distance between different buses in the aggregation process is expressed by Euclidean distance, the farthest distance method is used as the calculation method for the distance between different classes, and the minimum distance threshold between classes is set to exclude buses that do not meet the conditions. Multiple buses are aggregated through a hierarchical aggregation algorithm to obtain N virtual buses, expressed as V 1 、V 2 ,……,V N .

[0057] By aggregating multiple buses into a virtual bus, the number of nodes in the system can be reduced, the complexity of the system can be reduced, and the reliability and stability of the system can be improved.

[0058] Optionally, in the bus load prediction method provided in the embodiment of the present application, the load of the virtual bus is predicted based on multiple first historical bus loads to obtain an initial load prediction result, including: obtaining target attribute information of the virtual bus, wherein the target attribute information at least includes: the temperature change rate, humidity change rate, wind speed change rate and air pressure change rate of the virtual bus; calculating according to preset weight values ​​and target attribute information to obtain the target attribute value corresponding to the virtual bus; matching the target attribute value with multiple first historical bus loads to obtain an initial load prediction result.

[0059] In an optional embodiment, the target attribute information of the virtual bus is obtained, including but not limited to: the load change rate of the virtual bus at the same time one day before the prediction date, the load change rate at the corresponding time two days before the prediction date, the load change rate at the corresponding time one week before the prediction date, the week type, holiday type, weather type, daily temperature difference change rate, temperature, temperature change rate, air pressure change rate, wind speed change rate, humidity and humidity change rate and other attribute information. And according to the preset weight value and the target attribute information, a weighted calculation is performed to obtain the target attribute value corresponding to the virtual bus to determine the characteristics of the environment in which the virtual bus is located. The target attribute value of the virtual bus is matched with multiple first historical bus loads, the load situation of the virtual bus is predicted, and the initial load prediction result is obtained.

[0060] Through the above steps, the target attribute information and historical load data of the virtual bus can be used for prediction, which helps to estimate the load condition of the virtual bus more accurately and provide support for system operation.

[0061] Optionally, in the bus load prediction method provided in an embodiment of the present application, matching is performed based on the target attribute value and multiple first historical bus loads to obtain an initial load prediction result, including: matching the target attribute value and the attribute value corresponding to each historical bus load to obtain multiple matching scores; screening the multiple matching scores based on a second threshold to obtain a target score; and determining the first historical bus load corresponding to the target score as the initial load prediction result.

[0062] In an optional embodiment, for each historical bus load, a matching algorithm (e.g., Euclidean distance, cosine similarity, etc.) is used to evaluate the similarity between its attribute value (i.e., the attribute value corresponding to each historical bus load) and the target attribute value, and a matching score is calculated to obtain multiple matching scores. For each historical bus load, the matching score obtained will form a list, and according to the set second threshold, the historical bus loads with matching scores higher than the threshold are screened out to obtain the target score. The historical bus load with the highest score is selected as the prediction result that best meets the target attribute value (i.e., the initial load prediction result).

[0063] By matching and screening the target attribute value and the attribute value of the historical bus load, the accuracy and reliability of the load forecast can be improved.

[0064] Optionally, in the bus load prediction method provided in an embodiment of the present application, before determining the target load prediction result corresponding to each bus in the target power grid based on the target matching factor and the initial load prediction result, the method also includes: obtaining multiple second historical bus loads for each bus within a historical time period; calculating based on the multiple second historical bus loads and the multiple first historical bus loads to obtain multiple target ratios; fitting the multiple target ratios to obtain a target fitting function; and determining the target matching factor based on the target fitting function.

[0065] In an optional embodiment, the bus loads l at the same time n days ago are obtained. n (That is, the multiple second historical bus loads of each bus in the historical time period are l n ) and virtual bus load l n ′ (i.e., multiple first historical bus loads), then the sub-bus load at the same time n days ago accounts for p of the virtual bus load n for According to the proportion of the sub-bus load in the virtual bus load 10 days before the forecast date, n Form a data point set {(n, p n )}(n=1, 2, ..., 10) (i.e., multiple target ratios), the least squares method is used to fit the data point set to obtain the fitting function f(n) (i.e., the target fitting function). Substituting n=0 into f(n), the predicted daily matching factor (i.e., the target matching factor) is obtained.

[0066] By fitting multiple target ratios to obtain a target fitting function, the relationship between loads can be described more accurately, providing a more scientific basis for determining the target ratio factor.

[0067] Optionally, in the bus load prediction method provided in an embodiment of the present application, obtaining target attribute information of the virtual bus includes: obtaining initial attribute information of the virtual bus; discretizing the initial attribute information to obtain discretized initial attribute information; and performing attribute simplification on the discretized initial attribute information through a target greedy algorithm to obtain target attribute information.

[0068] In an optional embodiment, some attributes in the initial attribute information are discrete (for example, week type, holiday type, weather type, etc.), and some are continuous (for example, temperature, humidity, temperature change rate, etc.). The initial attribute information in the virtual bus is discretized by an equal frequency division algorithm to obtain the discretized initial attribute information.

[0069] It should be noted that some of the initial attribute information is recorded in natural language, such as wind direction, and the discretization process converts such attribute information into digital form. The discretization results of wind direction attribute information are shown in Table 1:

[0070] Table 1 Discretization results of wind direction attribute information

[0071] category wind direction 1 North Wind 2 Northeast Wind 3 Dongfeng 4 Southeast Wind 5 south wind 6 Southwest Wind 7 West Wind 8 Northwest Wind 9 No wind

[0072] The target greedy algorithm is used to simplify the discretized initial attribute information, select the attribute information that has the greatest impact on the overall performance of the system and retain it, while deleting the attribute information that has a smaller impact on the system performance, so as to obtain the target attribute information.

[0073] By optimizing and simplifying attribute information, the attribute information with less impact on system performance can be reduced, thereby improving the system's operating efficiency and reducing the system's operating costs.

[0074] It should be noted that Figure 2 Schematic diagram of a bus load prediction method provided according to an embodiment of the present application. Figure 2 As shown, first, multiple buses in the target power grid are aggregated to obtain a virtual bus corresponding to the target power grid. Then, the target attribute value corresponding to the virtual bus is calculated based on the preset weight value and the target attribute information of the virtual bus. The target attribute value is matched with multiple first historical bus loads of the virtual bus in the historical time period, and multiple matching scores are screened by the second threshold, and the first historical bus load with the highest score is determined as the initial load forecast result. Finally, the target load forecast result corresponding to each bus in the target power grid is determined based on the target matching factor and the initial load forecast result.

[0075] The bus load prediction method provided in the embodiment of the present application aggregates multiple buses in the target power grid to obtain a virtual bus corresponding to the target power grid; obtains multiple first historical bus loads of the virtual bus in the historical time period; predicts the load of the virtual bus based on multiple first historical bus loads to obtain an initial load prediction result; determines the target load prediction result corresponding to each bus in the target power grid based on the target ratio factor and the initial load prediction result, which solves the problem that the load of each bus in the power grid is predicted manually in the related technology, resulting in a relatively low prediction efficiency of the bus load. In summary, in this scheme, multiple buses in the target power grid are aggregated to generate a virtual bus. And the initial load prediction result corresponding to the virtual bus is determined based on the multiple first historical bus load data of the virtual bus in the historical time period. Finally, based on the initial load prediction result, the target load prediction result corresponding to each bus in the target power grid is determined based on the target ratio factor. Through the virtual bus, the load situation of the entire power grid can be considered more comprehensively, thereby improving the accuracy of load prediction. At the same time, by determining the target load forecast result of each bus through the target ratio factor and the initial load forecast result, the ratio factor can be adjusted more flexibly to better adapt to the load forecast requirements under different circumstances.

[0076] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0077] The embodiment of the present application also provides a bus load prediction device. It should be noted that the bus load prediction device of the embodiment of the present application can be used to execute the bus load prediction method provided in the embodiment of the present application. The bus load prediction device provided in the embodiment of the present application is introduced below.

[0078] Figure 3 Schematic diagram of a bus load prediction device according to an embodiment of the present application. Figure 3 As shown, the device includes: an aggregation unit 301, a first acquisition unit 302, a prediction unit 303, and a first determination unit 304.

[0079] Aggregation unit 301, used for aggregating multiple buses in the target power grid to obtain a virtual bus corresponding to the target power grid;

[0080] A first acquisition unit 302 is used to acquire a plurality of first historical bus loads of a virtual bus within a historical time period;

[0081] A prediction unit 303 is used to predict the load of the virtual bus according to the plurality of first historical bus loads to obtain an initial load prediction result;

[0082] The first determination unit 304 is used to determine the target load prediction result corresponding to each bus in the target power grid according to the target matching factor and the initial load prediction result.

[0083] The bus load prediction device provided by the embodiment of the present application comprises: an aggregation unit 301 aggregates multiple buses in the target power grid to obtain a virtual bus corresponding to the target power grid; a first acquisition unit 302 obtains multiple first historical bus loads of the virtual bus in the historical time period; a prediction unit 303 predicts the load of the virtual bus according to multiple first historical bus loads to obtain an initial load prediction result; a first determination unit 304 determines the target load prediction result corresponding to each bus in the target power grid according to the target ratio factor and the initial load prediction result, thereby solving the problem that the load of each bus in the power grid is predicted manually in the related technology, resulting in a relatively low prediction efficiency of the bus load. In this scheme, multiple buses in the target power grid are aggregated to generate a virtual bus. And the initial load prediction result corresponding to the virtual bus is determined according to the multiple first historical bus load data of the virtual bus in the historical time period. Finally, the target load prediction result corresponding to each bus in the target power grid is determined based on the target ratio factor according to the initial load prediction result. Through the virtual bus, the load situation of the entire power grid can be considered more comprehensively, thereby improving the accuracy of load prediction. At the same time, by determining the target load forecast result of each bus through the target ratio factor and the initial load forecast result, the ratio factor can be adjusted more flexibly to better adapt to the load forecast requirements under different circumstances.

[0084] Optionally, in the bus load prediction device provided in the embodiment of the present application, the aggregation unit includes: a determination module, used to determine the section and section length corresponding to each bus, and screen the section corresponding to each bus according to the first threshold and the section length to obtain multiple target sections; a first calculation module, used to calculate the generator output power transfer distribution factor value of the bus for each target section for each bus, and obtain multiple generator output power transfer distribution factor values; an aggregation module, used to aggregate multiple buses according to multiple generator output power transfer distribution factor values ​​to obtain a virtual bus.

[0085] Optionally, in the bus load prediction device provided in the embodiment of the present application, the aggregation module includes: a construction sub-module, used to construct a matrix based on multiple generator output power transfer distribution factor values ​​to obtain a target matrix; a calculation sub-module, used to perform calculations based on the target matrix to obtain the generator output power transfer distribution factor vector corresponding to each bus; an aggregation sub-module, used to aggregate multiple buses based on the generator output power transfer distribution factor vector corresponding to each bus through a target aggregation algorithm to obtain a virtual bus.

[0086] Optionally, in the bus load prediction device provided in the embodiment of the present application, the prediction unit includes: an acquisition module, used to obtain target attribute information of the virtual bus, wherein the target attribute information includes at least: the temperature change rate, humidity change rate, wind speed change rate and air pressure change rate of the virtual bus; a second calculation module, used to calculate according to a preset weight value and the target attribute information to obtain a target attribute value corresponding to the virtual bus; a matching module, used to match the target attribute value with multiple first historical bus loads to obtain an initial load prediction result.

[0087] Optionally, in the bus load prediction device provided in the embodiment of the present application, the matching module includes: a matching sub-module, used to match the target attribute value and the attribute value corresponding to each historical bus load to obtain multiple matching scores; a screening sub-module, used to screen the multiple matching scores according to a second threshold to obtain a target score; and a determination sub-module, used to determine the first historical bus load corresponding to the target score as the initial load prediction result.

[0088] Optionally, in the bus load prediction device provided in the embodiment of the present application, the device also includes: a second acquisition unit, used to obtain multiple second historical bus loads for each bus in a historical time period before determining the target load prediction result corresponding to each bus in the target power grid based on the target ratio factor and the initial load prediction result; a calculation unit, used to calculate based on the multiple second historical bus loads and the multiple first historical bus loads to obtain multiple target ratios; a fitting unit, used to fit the multiple target ratios to obtain a target fitting function; a second determination unit, used to determine the target ratio factor based on the target fitting function.

[0089] Optionally, in the bus load prediction device provided in the embodiment of the present application, the acquisition module includes: an acquisition sub-module, used to obtain the initial attribute information of the virtual bus; a discrete sub-module, used to discretize the initial attribute information to obtain the discretized initial attribute information; and a simplification sub-module, used to perform attribute simplification on the discretized initial attribute information through a target greedy algorithm to obtain target attribute information.

[0090] The bus load prediction device includes a processor and a memory. The above-mentioned aggregation unit 301, the first acquisition unit 302, the prediction unit 303, the first determination unit 304, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize accurate prediction of the bus load.

[0091] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the accurate prediction of the bus load can be achieved by adjusting the kernel parameters.

[0092] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0093] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, and the program implements a bus load prediction method when executed by a processor.

[0094] An embodiment of the present invention provides a processor, which is used to run a program, wherein the bus load prediction method is executed when the program is running.

[0095] like Figure 4 As shown, an embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: aggregating multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid; obtaining multiple first historical bus loads of the virtual bus within a historical time period; predicting the load of the virtual bus based on the multiple first historical bus loads to obtain an initial load prediction result; and determining a target load prediction result corresponding to each bus in the target power grid based on a target matching factor and the initial load prediction result.

[0096] Optionally, aggregating multiple busbars in the target power grid to obtain a virtual busbar corresponding to the target power grid includes: determining the section and section length corresponding to each busbar, and screening the section corresponding to each busbar according to a first threshold and the section length to obtain multiple target sections; for each busbar, calculating the generator output power transfer distribution factor value of the busbar for each target section to obtain multiple generator output power transfer distribution factor values; aggregating multiple buses according to the multiple generator output power transfer distribution factor values ​​to obtain a virtual bus.

[0097] Optionally, a plurality of buses are aggregating according to a plurality of generator output power transfer distribution factor values ​​to obtain a virtual bus, including: constructing a matrix according to a plurality of generator output power transfer distribution factor values ​​to obtain a target matrix; performing calculations according to the target matrix to obtain a generator output power transfer distribution factor vector corresponding to each bus; and aggregating a plurality of buses based on the generator output power transfer distribution factor vector corresponding to each bus through a target aggregation algorithm to obtain a virtual bus.

[0098] Optionally, predicting the load of the virtual bus based on multiple first historical bus loads to obtain an initial load prediction result includes: obtaining target attribute information of the virtual bus, wherein the target attribute information at least includes: the temperature change rate, humidity change rate, wind speed change rate and air pressure change rate of the virtual bus; calculating according to preset weight values ​​and target attribute information to obtain a target attribute value corresponding to the virtual bus; matching the target attribute value with multiple first historical bus loads to obtain an initial load prediction result.

[0099] Optionally, matching the target attribute value with multiple first historical bus loads to obtain an initial load forecast result includes: matching the target attribute value with the attribute value corresponding to each historical bus load to obtain multiple matching scores; screening the multiple matching scores according to a second threshold to obtain a target score; and determining the first historical bus load corresponding to the target score as the initial load forecast result.

[0100] Optionally, before determining the target load prediction result corresponding to each bus in the target power grid based on the target matching factor and the initial load prediction result, the method also includes: obtaining multiple second historical bus loads for each bus within a historical time period; calculating based on the multiple second historical bus loads and the multiple first historical bus loads to obtain multiple target ratios; fitting the multiple target ratios to obtain a target fitting function; and determining the target matching factor based on the target fitting function.

[0101] Optionally, obtaining target attribute information of the virtual bus includes: obtaining initial attribute information of the virtual bus; discretizing the initial attribute information to obtain discretized initial attribute information; and performing attribute simplification on the discretized initial attribute information by a target greedy algorithm to obtain target attribute information.

[0102] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0103] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: aggregating multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid; obtaining multiple first historical bus loads of the virtual bus within a historical time period; predicting the load of the virtual bus based on the multiple first historical bus loads to obtain an initial load prediction result; and determining a target load prediction result corresponding to each bus in the target power grid based on a target matching factor and the initial load prediction result.

[0104] Optionally, aggregating multiple busbars in the target power grid to obtain a virtual busbar corresponding to the target power grid includes: determining the section and section length corresponding to each busbar, and screening the section corresponding to each busbar according to a first threshold and the section length to obtain multiple target sections; for each busbar, calculating the generator output power transfer distribution factor value of the busbar for each target section to obtain multiple generator output power transfer distribution factor values; aggregating multiple buses according to the multiple generator output power transfer distribution factor values ​​to obtain a virtual bus.

[0105] Optionally, a plurality of buses are aggregating according to a plurality of generator output power transfer distribution factor values ​​to obtain a virtual bus, including: constructing a matrix according to a plurality of generator output power transfer distribution factor values ​​to obtain a target matrix; performing calculations according to the target matrix to obtain a generator output power transfer distribution factor vector corresponding to each bus; and aggregating a plurality of buses based on the generator output power transfer distribution factor vector corresponding to each bus through a target aggregation algorithm to obtain a virtual bus.

[0106] Optionally, predicting the load of the virtual bus based on multiple first historical bus loads to obtain an initial load prediction result includes: obtaining target attribute information of the virtual bus, wherein the target attribute information at least includes: the temperature change rate, humidity change rate, wind speed change rate and air pressure change rate of the virtual bus; calculating according to preset weight values ​​and target attribute information to obtain a target attribute value corresponding to the virtual bus; matching the target attribute value with multiple first historical bus loads to obtain an initial load prediction result.

[0107] Optionally, matching the target attribute value with multiple first historical bus loads to obtain an initial load forecast result includes: matching the target attribute value with the attribute value corresponding to each historical bus load to obtain multiple matching scores; screening the multiple matching scores according to a second threshold to obtain a target score; and determining the first historical bus load corresponding to the target score as the initial load forecast result.

[0108] Optionally, before determining the target load prediction result corresponding to each bus in the target power grid based on the target matching factor and the initial load prediction result, the method also includes: obtaining multiple second historical bus loads for each bus within a historical time period; calculating based on the multiple second historical bus loads and the multiple first historical bus loads to obtain multiple target ratios; fitting the multiple target ratios to obtain a target fitting function; and determining the target matching factor based on the target fitting function.

[0109] Optionally, obtaining target attribute information of the virtual bus includes: obtaining initial attribute information of the virtual bus; discretizing the initial attribute information to obtain discretized initial attribute information; and performing attribute simplification on the discretized initial attribute information by a target greedy algorithm to obtain target attribute information.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0111] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0116] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0119] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A bus load prediction method, characterized in that: include: Aggregating multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid; Acquire a plurality of first historical bus loads of the virtual bus within a historical time period; Predicting the load of the virtual bus according to the plurality of first historical bus loads to obtain an initial load prediction result; The target load forecast result corresponding to each bus in the target power grid is determined according to the target matching factor and the initial load forecast result.

2. The method according to claim 1, characterized in that Aggregating multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid includes: Determine the section and section length corresponding to each busbar, and screen the section corresponding to each busbar according to the first threshold and the section length to obtain multiple target sections; For each bus, calculate the generator output power transfer distribution factor value of the bus for each target section to obtain multiple generator output power transfer distribution factor values; The plurality of buses are aggregated according to the output power transfer distribution factor values ​​of the plurality of generators to obtain the virtual bus.

3. The method according to claim 2, characterized in that Aggregating the plurality of buses according to the plurality of generator output power transfer distribution factor values ​​to obtain the virtual bus comprises: Constructing a matrix according to the output power transfer distribution factor values ​​of the plurality of generators to obtain a target matrix; Calculating according to the target matrix to obtain a generator output power transfer distribution factor vector corresponding to each bus; The multiple buses are aggregated based on the generator output power transfer distribution factor vector corresponding to each bus through a target aggregation algorithm to obtain the virtual bus.

4. The method according to claim 1, characterized in that Predicting the load of the virtual bus according to the plurality of first historical bus loads to obtain an initial load prediction result includes: Acquire target attribute information of the virtual bus, wherein the target attribute information at least includes: a temperature change rate, a humidity change rate, a wind speed change rate, and an air pressure change rate of the virtual bus; Calculating according to the preset weight value and the target attribute information to obtain the target attribute value corresponding to the virtual bus; The initial load forecast result is obtained by matching the target attribute value with the multiple first historical bus loads.

5. The method according to claim 4, characterized in that According to the target attribute value and the plurality of first historical bus loads, the initial load forecast result is obtained by matching: Matching the target attribute value with the attribute value corresponding to each historical bus load to obtain multiple matching scores; Filtering the multiple matching scores according to a second threshold to obtain a target score; The first historical bus load corresponding to the target score is determined as the initial load forecast result.

6. The method according to claim 1, characterized in that Before determining the target load forecast result corresponding to each bus in the target power grid according to the target matching factor and the initial load forecast result, the method further includes: Obtaining a plurality of second historical bus loads of each bus within the historical time period; Calculating according to the plurality of second historical bus loads and the plurality of first historical bus loads to obtain a plurality of target ratios; Fitting the multiple target ratios to obtain a target fitting function; The target matching factor is determined according to the target fitting function.

7. The method according to claim 4, characterized in that Acquiring the target attribute information of the virtual bus includes: Acquiring initial attribute information of the virtual bus; Discretizing the initial attribute information to obtain discretized initial attribute information; The target attribute information is obtained by performing attribute simplification on the discretized initial attribute information through a target greedy algorithm.

8. A bus load prediction device, characterized in that: include: An aggregation unit, used for aggregating multiple buses in a target power grid to obtain a virtual bus corresponding to the target power grid; A first acquisition unit, configured to acquire a plurality of first historical bus loads of the virtual bus within a historical time period; A prediction unit, configured to predict the load of the virtual bus according to the plurality of first historical bus loads to obtain an initial load prediction result; The first determination unit is used to determine the target load prediction result corresponding to each bus in the target power grid according to the target matching factor and the initial load prediction result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the storage medium is controlled to execute the bus load prediction method according to any one of claims 1 to 7 on a device.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the bus load prediction method described in any one of claims 1 to 7.

Images