CN115526475A - Method for improving voltage quality through multi-stream fusion of intelligent power distribution network - Google Patents
Method for improving voltage quality through multi-stream fusion of intelligent power distribution network Download PDFInfo
- Publication number
- CN115526475A CN115526475A CN202211146383.4A CN202211146383A CN115526475A CN 115526475 A CN115526475 A CN 115526475A CN 202211146383 A CN202211146383 A CN 202211146383A CN 115526475 A CN115526475 A CN 115526475A
- Authority
- CN
- China
- Prior art keywords
- service
- index
- power distribution
- distribution network
- voltage quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000004927 fusion Effects 0.000 title claims abstract description 20
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000011158 quantitative evaluation Methods 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000005094 computer simulation Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 claims description 3
- 230000000977 initiatory effect Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 10
- 230000006872 improvement Effects 0.000 description 9
- 238000007726 management method Methods 0.000 description 9
- 238000012797 qualification Methods 0.000 description 7
- 230000009466 transformation Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention belongs to the field of electric power, and discloses a method for improving voltage quality of an intelligent power distribution network through multi-stream fusion, which comprises the following steps: taking the service flow as a main line, fusing data flow in the service of the service flow, and constructing a full-service flow model to obtain a first-level evaluation index after treatment; carrying out digital modeling of a multi-dimensional index system according to the first-level index evaluated after the business process model is treated to obtain sub-indexes; performing sub-index weight decomposition and quantitative evaluation based on a deep learning-neural network to obtain key sub-indexes influencing voltage quality; establishing a data flow relation between the service and the service output and sub-index by using the key sub-index to obtain a strong correlation service; and (4) by combining a full-service flow model, performing responsibility tracing on the voltage quality problem of the intelligent power distribution network through a strong correlation service. According to the method and the device, the key sub-indexes influencing the voltage quality are obtained by performing sub-index weight decomposition and quantitative evaluation on the first-level indexes in the multi-dimensional full-service process model, and a decision maker is helped to perform responsibility tracing and management control.
Description
Technical Field
The invention belongs to the field of electric power, and particularly relates to a method for improving voltage quality through multi-flow fusion of an intelligent power distribution network.
Background
In recent years, the country continuously increases the investment for the construction of novel power systems and the management of voltage quality problems, and aims to build a safe, reliable, green and efficient smart grid, wherein flexible and reliable power distribution is a very important part. On the one hand, new energy which is developing at a constant speed will bring about voltage quality problems with different degrees, such as voltage unbalance, flicker, overvoltage, high-frequency distortion (ultrahigh harmonic), low-frequency oscillation, system stability and the like, due to different access modes, voltage levels, grid structures and inverter types. On the other hand, as the scale of the power grid is continuously enlarged, the overall level is continuously improved, and the technological content is continuously enhanced, but the development level of the economic society is relatively lagged behind due to dispersed inhabitants in local areas, and the voltage quality problems caused by unreasonable power grid racks, insufficient power supply points, insufficient reactive power compensation configuration of substations, lines, distribution transformers and users, overlong power supply radius of medium and low voltage power supply lines and the like still exist. The intelligent power distribution network is responsible for optimizing the 'last kilometer' of electric energy transmission, and the voltage quality problem of the intelligent power distribution network is directly related to the safe and reliable operation of power supply equipment and the economic development of a power supply area. Therefore, there is an urgent need to develop deep decision and research on the voltage quality of the intelligent power distribution network.
The existing voltage quality treatment technology mainly focuses on local technical points or researches aiming at a single treatment device, and is lack of comprehensive and systematic researches on the voltage quality problem of a power distribution network. The current research idea of improving the voltage quality of the intelligent power distribution network mainly focuses on planning, modifying and constructing the layer, and the following aspects are mainly insufficient:
(1) On the analysis level, a conclusion is obtained through a certain typical case analysis, only a treatment method for a single voltage quality problem can be obtained, meanwhile, energy flow in the power distribution network is only considered when a model is established for assisting decision analysis, real business processes and control constraints are not considered, and the obtained scheme is disconnected from reality to a certain extent;
(2) In the management level, the treatment measures still stay in the general linguistic expression, and the research of fine management in the power grid company level is lacked;
(3) On the aspect of voltage quality treatment, for voltage quality treatment evaluation, economic benefits, treatment equipment utilization conditions and the like are ignored, so that the selection of treatment measures is not facilitated, and the comprehensiveness of the evaluation needs to be enhanced.
In summary, the research on the voltage quality improvement of the intelligent power distribution network needs to consider the close relationship between the voltage quality improvement of the intelligent power distribution network and the actual business process and control constraint, and establish a multi-flow integrated whole-process voltage quality improvement decision method of business flow, data flow, energy flow and control flow.
Disclosure of Invention
In order to solve or improve the problems, the invention provides a method for improving the voltage quality of an intelligent power distribution network by multi-stream fusion, which has the following specific technical scheme:
the invention provides a method for improving voltage quality of an intelligent power distribution network through multi-stream fusion, which comprises the following steps:
taking the service flow as a main line, fusing data flow in the service of the service flow, and constructing a full-service flow model to obtain a first-level evaluation index after treatment;
carrying out digital modeling of a multi-dimensional index system according to the treated evaluation primary index to obtain a sub-index;
performing sub-index weight decomposition and quantitative evaluation based on a deep learning-neural network to obtain key sub-indexes influencing voltage quality;
establishing a data flow relation between the service and the service output and sub-index by using the key sub-index to obtain a strong correlation service; and (4) by combining a full-service flow model, performing responsibility tracing on the voltage quality problem of the intelligent power distribution network through a strong correlation service.
The service flow is a service flow which embodies the coordination of the position and function departments of the power grid company, and the data flow is a data flow which originates from the power distribution network frame flow and is communicated with each online system of the power grid company.
Preferably, the full-service flow model further integrates an energy flow including various physical information of the actual power distribution network and a control flow for initiating a control instruction by the provincial company level.
Preferably, the data of each service of the service flow includes: data input from other services, data input from the outside and data output from services.
Preferably, the multiple dimensions include: planning and construction dimensions, operation and maintenance dimensions, and governance and post-evaluation dimensions.
Preferably, the first-level index is a voltage yield.
Preferably, the sub-index weight decomposition and quantitative evaluation process includes:
establishing a dynamic evaluation and weight demarcation model of indexes based on real historical data of a power distribution network, and solving the basic problem of how to promote and specify a promotion plan around key indexes;
carrying out quantitative evaluation and dynamic simulation of indexes under uncertain conditions and index weight transverse decomposition driven by historical data according to basic problems;
according to the power distribution network scene probability modeling under the uncertain condition of quantitative evaluation and dynamic simulation research and dynamic simulation of the power distribution network under the drive of time sequence data, outputting a power distribution network simulation scene and index numerical distribution;
and meanwhile, according to index weight decomposition, voltage quality oriented index value normalization and neural network-based index weight decomposition are researched, and index weight and a dynamic curve are output.
Preferably, the dynamic simulation of the power distribution network is realized by power distribution network scene probability modeling under an uncertain condition and dynamic power flow calculation of the power distribution network driven by time sequence data;
the uncertain condition refers to the fluctuation of uncertain variables of load, photovoltaic power generation or hydropower.
Preferably, the key sub-indicator includes: distribution transformer load rate, main transformer load rate and substation distribution rate.
Preferably, the tracing result is accurate to the responsibility service department and the post according to the full service flow model.
Preferably, the flow control index includes a primary index and a sub-index.
The invention has the beneficial effects that:
1. the method and the system fuse the four flows of 'business flow', 'energy flow', 'control flow' and 'data flow' into a multi-dimensional full-business flow model, and help a decision maker to trace and control responsibility. The service flow and the data flow are fused into a full service data operation flow, the data operation of three dimensions of planning, construction, operation, maintenance, treatment and post-evaluation is integrated into a whole through the department cooperation relationship among different dimensions, and the service transmission process of a power grid company in the voltage quality improvement process can be clearly seen.
2. According to the method, the one-level index is subjected to multi-dimensional index system digital modeling, sub-index weight decomposition and quantitative evaluation are performed through a deep learning-neural network, and finally key sub-indexes influencing the voltage qualification rate of the one-level index are output, so that a power grid company is helped to carry out symptomatic drug release on voltage quality problems from the whole process.
3. According to the method, the key sub-indexes are combined with the full-service process model, the responsibility of the voltage quality problem of the intelligent power distribution network can be traced, the responsibility is accurate to the responsibility service department and post, and a decision maker of a power grid company can conveniently perform problem assignment.
Drawings
FIG. 1 is a full business process model based on traffic and data flows;
FIG. 2 is a full business process model based on "four-stream" fusion;
FIG. 3 is a flow of weight decomposition and quantitative evaluation of sub-indicators.
Figure 4 is a dynamic simulation of a power distribution network.
FIG. 5 shows the voltage yield at the monitoring point.
FIG. 6 is a graph showing various voltage yield characteristics.
FIG. 7 is a typical daily index weight dynamic weight curve.
FIG. 8 is a typical monthly index weight dynamic weight curve.
FIG. 9 is a stack of exemplary monthly index weight dynamic weights.
Fig. 10 shows sub-index weights obtained based on dynamic simulation analysis.
FIG. 11 is a business-business output-sub-indicator relationship;
fig. 12 is another example service-service output-sub-indicator relationship.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As shown in fig. 1 to 3, a method for improving voltage quality in an intelligent power distribution network by multi-stream fusion includes:
constructing a full-service flow model fusing data flows by taking the service flows as a main line to obtain a first-level evaluation index after treatment;
carrying out digital modeling of a multi-dimensional index system according to the first-level index evaluated after the business process model is treated to obtain sub-indexes;
performing sub-index weight decomposition and quantitative evaluation based on a deep learning-neural network to obtain key sub-indexes influencing voltage quality;
establishing a data flow relation between the service and the service output and sub-index by using the key sub-index to obtain a strong correlation service; and (4) by combining a full-service flow model, performing responsibility tracing on the voltage quality problem of the intelligent power distribution network through a strong correlation service.
According to the method, the key sub-indexes influencing the voltage quality are obtained by carrying out multi-dimensional index system digital modeling, sub-index weight decomposition and quantitative evaluation based on a deep learning-neural network on the primary indexes in the multi-dimensional full-service process model, so that a power grid company is helped to issue medicines to voltage quality problems in an all-process way, and meanwhile, a decision maker is helped to carry out responsibility tracing and control.
Specifically, the service flow is a service flow which embodies the cooperation of the post and function departments of the power grid company, and the data flow is a data flow which originates from the power distribution grid structure and flows to each online system of the power grid company.
The service flow and the data flow are key flows in the whole voltage quality improvement analysis, and data operation of three dimensions of planning, construction, operation, maintenance, treatment and post-evaluation is integrated into a whole through department cooperation relations among different dimensions, so that the whole service data operation of the voltage quality improvement of the intelligent power distribution network is obtained, as shown in fig. 1.
With reference to fig. 1, the data of each service of the service flow mainly includes three parts: data input from other services: the services in the grid company are not isolated but organically connected to other services, so that each service uses some data of the other services to complete the service, which is called the input data of the service. For example, in a reactive power planning service, it is necessary to acquire grid structure data output by the grid planning service as input data; (2) data inputted from outside: during the operation of the service, external input data is also required to complete the completion of the service. For example, in the reactive planning business, the number, specification and compensation mode of reactive equipment, and line loss, investment and maintenance cost data of lines and equipment are required to be determined. (3) data of service output: each service can output data to be supplied to other services for use or output the data to departments/posts/systems/tables to form related KPI indexes of the power grid company and report the KPI indexes layer by layer. For example, in the reactive power planning service, the reactive power planning scheme data is output, and then the reactive power planning scheme data is continuously input to the scheme evaluation service, so that the reactive power planning scheme is comprehensively evaluated and scored, and whether to make an item is finally determined.
In other embodiments, the full business process model also fuses energy flows and management flows. The energy flow is the energy flow of physical quantities such as voltage, current and power in an actual power distribution system. With the rapid development of digital power grids and the continuous maturation of digital mirroring technology, the concept of energy flow is gradually replaced by a mirrored energy flow in which massive data and a physical model cooperate with each other from a concrete and actual physical quantity flow, so in this embodiment, the energy flow originates from an actual power distribution system, but is embodied in the form of data flowing in various departments/stations/systems/tables. The management and control flow is a KPI (Key performance indicator) instruction issued by a higher-level power grid company to a lower-level power grid company, and a power grid company decision maker makes an integral judgment according to the running condition of the integral power distribution network in the last year and issues a specific improvement quantity value requirement of a specific area or a specific power distribution network frame in the next year, so that the management and control flow is more embodied in the cooperation of all levels of power grid companies. Specifically, the index for controlling the flow includes a primary index and a sub-index based on the previous year operation condition. In this embodiment, a "four-stream" fusion full-service process model for improving the voltage quality of the smart distribution network is also established, as shown in fig. 2.
Different from the traditional low-voltage governing business process, the 'four-flow' fused full-business flow model comprehensively considers the point-to-point governing process of governing and post-evaluation dimensionality, also considers the two dimensionalities of early planning, construction, operation and maintenance of the power distribution network, and simultaneously considers the organic fusion of the four flows of business flow, data flow, energy flow and control flow, so that the whole low-voltage problem can be ensured to be considered under the complete space-time dimensionality. After the point-to-point treatment of the low voltage problem is completed, the grid structure, the reactive equipment and the like changed by the treatment measures can further influence the tide distribution of the whole power distribution system, so that the planning, construction, operation and maintenance of the power distribution system can be correspondingly changed. For example, in data transmission, report generation, KPI indicator reporting, and problem study and judgment in each system, the related content will change. In turn, changes in data transmission, report generation, KPI indicator reporting, and problem study and judgment in each system can adversely affect the management of low voltage problems. In addition, due to the occurrence of low voltage treatment problems or the implementation of treatment measures, the planning and construction tasks of the next phase of the power distribution network are also affected. Therefore, the whole business process of the low-voltage treatment of the power distribution network is mutually blended and organically fused, and the analysis and decision of the voltage quality problem are carried out from the whole business process, so that the comprehensive, deep and thorough effects can be achieved.
Specifically, based on a full-service flow model, the voltage qualification rate is used as a first-level index of a power grid company production technology index plan, and is a starting point for voltage quality management analysis and decision. By uniformly integrating and combing indexes respectively related to three dimensions of planning and construction, operation and maintenance, treatment and post-evaluation, a multi-dimensional index system for improving the voltage quality is established as shown in table 1.
TABLE 1 multidimensional index system for improving voltage quality of intelligent power distribution network
In the multidimensional index system for improving the voltage quality of the intelligent power distribution network, 18 sub-indexes related to a first-level index 'voltage qualification rate' are respectively as follows: the method comprises the following steps of substation distribution rate, power supply line diameter, power supply radius, medium-voltage line light load ratio, medium-voltage line heavy overload ratio, three-phase load unbalance rate, main transformer average load rate, reactive power compensation device availability rate, distribution transformer power factor, distribution transformer load rate, grid structure, load characteristic, new power influence, power grid operation mode, voltage monitoring, small hydropower station emergency reactive power, yunnan large hydropower station, AVC reactive voltage control and the like. The 18 indexes are divided into two types of quantization indexes and other indexes according to the characteristic of whether the indexes can be quantized or not, and meanwhile, the 18 sub indexes are derived from different dimensions and main business departments, so that the 18 sub indexes are also divided and displayed in a system.
Specifically, weight decomposition and quantitative evaluation need to be performed on the associated sub-indexes to obtain key sub-indexes affecting voltage quality. The weight decomposition and quantitative evaluation of the sub-indexes are important ways for solving two problems of 'which indexes are mainly surrounded by voltage quality improvement' and 'how much the secondary indexes are specifically improved'. Therefore, the invention provides a weight decomposition and quantitative evaluation flow of the sub-indexes of the voltage quality improvement of the intelligent power distribution network, as shown in fig. 3.
The simulation of the power distribution network scene mainly considers two variables: 1) The fluctuation of uncertain variables such as load, photovoltaic power generation, hydropower and the like. 2) The variation of the secondary indicator variable around the current value is analyzed for sensitivity of voltage yield to it. Multiple uncertain conditions of superposition of the two types of variables are mainly considered to restore energy flow of a real distribution network scene as much as possible and analyze the influence of secondary indexes on the voltage qualification rate. The dynamic simulation of the power distribution network is realized by power distribution network scene probability modeling under uncertain conditions and dynamic load flow calculation of the power distribution network driven by time sequence data, and the method is realized as shown in fig. 4.
Taking a certain low-voltage case as an example, modeling analysis is performed by using the acquired historical data, and a thermodynamic diagram for making the voltage qualification rate of the monitoring point of the distribution transformer area is shown in fig. 5. The time characteristic curve of the various types of voltage yield of the case rack is shown in fig. 6.
Sub-index weight decomposition may also be performed based on deep learning-neural networks. The BP neural network is used as an algorithm model which is most widely applied in the artificial neural network, and has a complete theoretical system and a learning mechanism. The method simulates the reaction process of human brain neurons to external excitation signals, establishes a multilayer sensor model, and successfully establishes an intelligent network model for processing nonlinear information through repeated iterative learning by utilizing a learning mechanism of signal forward propagation and error reverse adjustment.
Based on the historical data and simulation analysis results of the selected cases, the sub-index weight decomposition results based on the deep learning-neural network are as follows. Taking 7/5/2021 as an example, a typical day index weight dynamic weight curve under a time scale of 1h is analyzed, and is shown in fig. 7. As can be seen from fig. 7, the load factor related indexes such as main transformer load factor, distribution transformer load factor, line light load ratio, line heavy load ratio and the like are relatively large, and are main indexes affecting the voltage quality problem. The influence of reactive load related indexes such as power supply radius, power supply line diameter, reactive load characteristic, power factor and the like on the voltage quality is the second. The influence of reactive load related indexes such as large hydropower, AVC, reactive load characteristics, reactive compensation device availability and the like on the voltage quality is small.
As can be seen from the typical monthly index weight dynamic weight curve in fig. 8, the load factor related to load factors, such as main transformer load factor, distribution transformer load factor, line light load ratio, line heavy load ratio, etc., is relatively large, and is a main index affecting the voltage quality problem. The influence of the related indexes of the reactive load such as power supply radius, power supply line diameter, reactive load characteristic, power factor and the like on the voltage quality is the second. The influence of the related indexes of the reactive load such as the characteristics of the purple atmospheric water, AVC, the reactive load, the availability of the reactive compensation device and the like on the voltage quality is small.
As can be seen by combining the monthly index weight dynamic weight stack diagram of fig. 9, the distribution transformer load rate, the main transformer load rate, and the distribution point rate of the transformer substation are the first three key indexes affecting the voltage quality.
Specifically, the sub-indexes which are obtained according to the dynamic simulation analysis index weight of the selected case and have the greatest influence on the primary index "voltage qualification rate" are respectively as follows: fig. 10 shows distribution transformer load factor (16%), main transformer load factor (13%), substation layout rate (12%), and reactive load characteristics (9%). Namely, distribution transformer load rate, main transformer load rate, transformer substation distribution rate and reactive load characteristics are key sub-indexes.
If the first-level index 'voltage qualification rate' is improved by 5% by the order, the indexes of distribution transformer load rate, main transformer load rate, transformer substation distribution rate and reactive load amount are correspondingly reduced by 1.6%, 1.3%, 1.2% and 0.9%.
Taking the index of "distribution transformation load rate" as an example, and referring to fig. 11, by establishing a data flow relationship between a service and a service output sub-index, services related to the distribution transformation load rate can be quickly found, which mainly includes: load prediction and running state evaluation.
Taking the index of the distribution point rate of the transformer substation as an example, and combining with fig. 12, by establishing a data flow relationship between a service and a service output and sub-index, services related to the distribution load rate can be quickly found, which mainly includes: and (6) planning the net rack.
Taking the sub-index of the distribution transformation load rate as an example, the service related to the sub-index of the distribution transformation load rate is determined according to the previous section, and the service related to the sub-index of the distribution transformation load rate mainly comprises the following steps: load prediction and running state evaluation. Therefore, after the strongly-associated service is determined, according to the "four-flow" fusion multi-dimensional full-service flow model shown in fig. 2, it can be quickly determined that in this case, the most responsible department is the power grid planning research center and the power supply station, and the most responsible position is the comprehensive plan responsibility and the distribution management responsibility.
In conclusion, the service flow, the energy flow, the control flow and the data flow are fused into a multi-dimensional full-service flow model, the multi-dimensional index system digital modeling is carried out on the first-level index in the model, and sub-index weight decomposition and quantitative evaluation are carried out on the basis of the deep learning-neural network, so that key sub-indexes influencing voltage quality are obtained, a power grid company is helped to give medicines to voltage quality problems according to symptoms from the whole process, and meanwhile, a decision maker is helped to carry out responsibility tracing and control.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A method for improving voltage quality of an intelligent power distribution network through multi-stream fusion is characterized by comprising the following steps:
taking the service flow as a main line, fusing data flow in the service of the service flow, and constructing a full-service flow model to obtain a first-level evaluation index after treatment;
carrying out digital modeling of a multi-dimensional index system according to the treated evaluation primary index to obtain a sub-index;
performing sub-index weight decomposition and quantitative evaluation based on a deep learning-neural network to obtain key sub-indexes influencing voltage quality;
establishing a data flow relation between the service and the service output and sub-index by using the key sub-index to obtain a strong correlation service; and (4) by combining a full-service flow model, performing responsibility tracing on the voltage quality problem of the intelligent power distribution network through a strong correlation service.
2. The method for improving the voltage quality through the multi-stream fusion of the intelligent power distribution network according to claim 1, wherein the full-service process model further fuses an energy flow including various physical information of the actual power distribution network and a control flow for initiating a control instruction by a provincial company level.
3. The method for improving voltage quality of the intelligent power distribution network based on multi-stream fusion as claimed in claim 1, wherein the data of each service of the service flows comprises: data input from other services, data input from the outside, and data output from services.
4. The method for improving voltage quality of the intelligent power distribution network based on multi-stream fusion as claimed in claim 1, wherein the multi-dimension comprises: planning and construction dimensions, operation and maintenance dimensions, and governance and post-evaluation dimensions.
5. The method for improving the voltage quality of the intelligent power distribution network through multi-stream fusion according to claim 1, wherein the primary index is a voltage qualified rate.
6. The method for improving the voltage quality of the intelligent power distribution network based on the multi-stream fusion as claimed in claim 1, wherein the sub-index weight decomposition and quantitative evaluation process comprises:
establishing a dynamic evaluation and weight demarcation model of indexes based on real historical data of a power distribution network, and solving the basic problem of how to promote and specify a promotion plan around key indexes;
carrying out quantitative evaluation and dynamic simulation of indexes under uncertain conditions and index weight transverse decomposition driven by historical data according to basic problems;
according to the power distribution network scene probability modeling under the uncertain condition of quantitative evaluation and dynamic simulation research and dynamic simulation of the power distribution network under the drive of time sequence data, outputting a power distribution network simulation scene and index numerical distribution;
and meanwhile, according to index weight decomposition, the index value normalization facing the voltage quality and the index weight decomposition based on the neural network are researched, and the index weight and the dynamic curve are output.
7. The intelligent power distribution network multi-stream fusion voltage quality improving method according to claim 6, wherein the dynamic simulation of the power distribution network is realized by power distribution network scene probability modeling under uncertain conditions and dynamic load flow calculation of the power distribution network driven by time sequence data;
the uncertain condition refers to the fluctuation of uncertain variables of load, photovoltaic power generation or hydropower.
8. The method for improving voltage quality in multi-stream convergence of the intelligent power distribution network according to claim 1, wherein the key sub-indicators comprise: distribution transformer load rate, main transformer load rate and substation distribution rate.
9. The method for improving the voltage quality of the intelligent power distribution network through the multi-stream fusion as claimed in claim 2, wherein the tracing result is accurate to responsibility service departments and posts according to a full service flow model.
10. The method for improving voltage quality through multi-stream fusion of the intelligent power distribution network according to claim 2, wherein the indexes for controlling the flow comprise the primary index and the sub-indexes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146383.4A CN115526475A (en) | 2022-09-20 | 2022-09-20 | Method for improving voltage quality through multi-stream fusion of intelligent power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146383.4A CN115526475A (en) | 2022-09-20 | 2022-09-20 | Method for improving voltage quality through multi-stream fusion of intelligent power distribution network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115526475A true CN115526475A (en) | 2022-12-27 |
Family
ID=84697378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211146383.4A Pending CN115526475A (en) | 2022-09-20 | 2022-09-20 | Method for improving voltage quality through multi-stream fusion of intelligent power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115526475A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117374977A (en) * | 2023-12-07 | 2024-01-09 | 能拓能源股份有限公司 | Load prediction and risk analysis method for energy storage system |
-
2022
- 2022-09-20 CN CN202211146383.4A patent/CN115526475A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117374977A (en) * | 2023-12-07 | 2024-01-09 | 能拓能源股份有限公司 | Load prediction and risk analysis method for energy storage system |
| CN117374977B (en) * | 2023-12-07 | 2024-02-20 | 能拓能源股份有限公司 | Load prediction and risk analysis method for energy storage system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106655207A (en) | Power distribution network reactive power optimization system and method based on multi-data analysis | |
| Gao et al. | Robust coordinated optimization of active and reactive power in active distribution systems | |
| CN104331844B (en) | A kind of power network construction project investment decision method | |
| CN104268682B (en) | Planning method and device for active power distribution network | |
| CN110992113A (en) | Neural network intelligent algorithm-based project cost prediction method for capital construction transformer substation | |
| CN102364800B (en) | Passive filter parameter design method based on multi-objective optimization algorithm | |
| CN107464048A (en) | A kind of plan security check method a few days ago based on research state | |
| CN105701715A (en) | Loss reduction and energy conservation method and system | |
| CN111079972A (en) | Method, device and medium for planning reliability of active power distribution network | |
| CN110532596A (en) | A kind of method and system generating grid simulation sample based on LSTM algorithm | |
| CN115526475A (en) | Method for improving voltage quality through multi-stream fusion of intelligent power distribution network | |
| CN103730900B (en) | Province's ground county's integration idle work optimization method of power system Multiple Time Scales | |
| CN109066819A (en) | A kind of idle work optimization method of the power distribution network based on case reasoning | |
| CN108092267A (en) | A kind of power distribution network access planning system and method based on intelligent body | |
| CN114417719A (en) | Power distribution network gridding method and device based on graph attention network | |
| CN111626539A (en) | Power grid operation section dynamic generation method based on Q reinforcement learning | |
| CN114996908A (en) | Active power distribution network extension planning method and system considering intelligent soft switch access | |
| Madruga et al. | Allocation and integrated configuration of capacitor banks and voltage regulators considering multi-objective variables in smart grid distribution system | |
| CN107134790A (en) | A kind of GA for reactive power optimization control sequence based on big data determines method | |
| CN111555293A (en) | Reactive power equipment type selection system and method based on data model analysis | |
| Luo et al. | Research on transmission and transformation engineering cost system based on BIM 3D modelling technology | |
| Xing et al. | Intelligent Diagnosis Method of Distribution Network Fault for Construction of Digital Twin Coordination System | |
| CN106451565B (en) | A kind of power plant's optimization submitting on-line analysis based on perturbation theory | |
| Wen et al. | Construction of power system load models and network equivalence using an evolutionary computation technique | |
| CN111860617A (en) | Comprehensive optimization operation method for power distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |