A rule engine driven power distribution network planning problem library construction method

Abstract

This invention discloses a rule engine-driven method for constructing a distribution network planning problem base, comprising: writing factual statements and constructing a fact base file based on a distribution network central database; formulating rules for identifying individual distribution network problems and rules for identifying problems originating from the same source in the distribution network, constructing a distribution network planning problem identification rule base file, and writing the rules using forward reasoning logic; constructing a distribution network planning problem identification rule engine based on PyKe, combining the distribution network planning problem identification rule base and the distribution network fact base; formulating a distribution network planning problem base template, calling the rule engine, adding generated distribution network planning problems to the fact base, and compiling a distribution network planning problem base based on the template, and manually verifying it. This method can fully explore the guiding value of the relationships between problems within the problem base for distribution network planning, allowing staff to modify the rule base according to actual needs, and possessing sustainability and maintainability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network planning, and particularly relates to a rule engine driven power distribution network planning problem library construction method. BACKGROUND

[0002] With the rapid growth of power load and the improvement of user demand for power quality, it is urgent to improve power distribution network planning and improve the operation level of power distribution network; how to accurately plan and construct the power distribution network is a great challenge; the power distribution network planning problem library obtained by analyzing the current situation of the power distribution network is the most direct basis for generating planning schemes and guiding the construction of the power distribution network, therefore, the quality of the power distribution network problem library has a great influence on the effectiveness, rationality and accuracy of the power distribution network planning project.

[0003] Most of the prior art only focuses on strengthening the use of data, and less on the mining of the connection between the problems in the problem library, cannot fully identify the association between the problems in the problem library, cannot further refine the coupling relationship, and does not involve deeper value mining of the problem library, so that the generated power distribution network planning problem library cannot fully and truly reflect the defects of the power distribution network, and the deeper connection between the internal problems cannot be well utilized to guide the power distribution network planning.

[0004] The power distribution network has large amount of operation data, many types of data, and involves many departments, in the process of planning problem analysis, there is a lack of linkage of different technical professional departments, and there is a lack of auxiliary of efficient analysis system, these objective factors seriously affect the quality of the power distribution network planning problem library. SUMMARY

[0005] This section is intended to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, the abstract and the title, and such simplifications or omissions cannot be used to limit the scope of the present application.

[0006] In view of the above problems of the existing rule engine driven power distribution network planning problem library construction method, the present application is proposed.

[0007] Therefore, the purpose of the present application is to provide a rule engine driven power distribution network planning problem library construction method.

[0008] To solve the above technical problems, the present application provides the following technical solutions: based on the power distribution network central database, writing fact statements, and constructing fact library files;

[0009] Formulating power distribution network case problem discrimination rules and power distribution network homologous problem discrimination rules, constructing power distribution network planning problem discrimination rule library files, and writing by using forward reasoning logic;

[0010] Based on Pyke, the distribution network planning problem discrimination rule base and the distribution network fact base are combined to construct a distribution network planning problem discrimination rule engine.

[0011] A distribution network planning problem base template is formulated, the rule engine is called, the generated distribution network planning problem is added to the fact base, the distribution network planning problem base is sorted out based on the distribution network planning problem base template, and the distribution network planning problem base is manually checked.

[0012] As a preferred scheme of the rule engine driven distribution network planning problem base construction method, the distribution network center database is obtained by collecting information by distribution network planning personnel and includes substation, medium-voltage feeder and distribution transformer information.

[0013] As a preferred scheme of the rule engine driven distribution network planning problem base construction method, the fact statement needs to follow the fact statement expression specification of the rule engine Pyke, takes each device as a fact statement, and separately writes the basic conditions of the substation, the medium-voltage feeder and the distribution transformer.

[0014] As a preferred scheme of the rule engine driven distribution network planning problem base construction method, the distribution network individual case problem refers to a problem of a single device, such as distribution transformer overload and low voltage problem.

[0015] The distribution network homologous problem includes the following three cases: multiple problems belong to the same device, multiple devices with the same problem are connected to the same superior device, and multiple same problems occur in the same area.

[0016] As a preferred scheme of the rule engine driven distribution network planning problem base construction method, the individual case problem discrimination rule is formulated according to specific distribution network planning technical guidelines, is a discrimination of whether a certain feature of a device meets the requirements, and the individual case problem discrimination rule can be written according to the rule expression specification of the rule engine Pyke.

[0017] The homologous problem discrimination rule can be divided into three categories and is written according to the rule expression specification of the rule engine Pyke.

[0018] Each distribution network planning problem discrimination rule of the distribution network planning problem discrimination rule base includes a mode part and an action part.

[0019] Among them, the mode part is used to match the fact, judge whether there is a problem, the action part is the operation after the rule and the fact match successfully, collect the problem and put it into the fact base working memory.

[0020] As a preferred scheme of the rule engine driven power distribution network planning problem library construction method, wherein: the rule expression specification of the rule engine Pyke is as follows:

[0021] foreach

[0022] Condition

[0023] assert

[0024] Action

[0025] The homologous problem discrimination rule can be divided into three categories, and is also written according to the rule expression specification of the rule engine Pyke.

[0026] As a preferred scheme of the rule engine driven power distribution network planning problem library construction method, wherein: the order of the rules in the power distribution network planning problem discrimination rule library is as follows:

[0027] The discrimination rule of multiple devices with the same problem accessing the same superior device;

[0028] The discrimination rule of multiple same problems appearing in the same area;

[0029] The discrimination rule of multiple same problems appearing in the same area;

[0030] The discrimination rule of the case problem.

[0031] As a preferred scheme of the rule engine driven power distribution network planning problem library construction method, wherein: based on Pyke, the power distribution network planning problem discrimination rule engine is constructed by combining the power distribution network planning problem discrimination rule library and the power distribution network fact base.

[0032] Firstly, the power distribution network fact base file is loaded, and the data of the power distribution network fact base is read into the working memory;

[0033] Secondly, the power distribution network planning problem discrimination rule library file is compiled by using the compiling function of pyke, and the corresponding power distribution network planning problem discrimination rule library file is obtained;

[0034] Finally, the driving file of the rule engine is written, so as to prepare for subsequent calling of the rule engine.

[0035] As a preferred scheme of the rule engine driven power distribution network planning problem library construction method, wherein: the mode matcher of the rule engine compares the mode part of the fact and the rule;

[0036] If the matching is successful, the corresponding rule is triggered, the execution engine generates the power distribution network planning problem as a new fact and adds it to the fact base;

[0037] If multiple rules and facts match at the same time, they are triggered in order according to the priority. The action of the triggered rule may generate new facts, which are also added to the working memory.

[0038] Based on the power distribution network planning problem base template, the power distribution network planning problem in the fact base is sorted into the standardized problem base by using the pandas library of python.

[0039] As a preferred scheme of the rule engine driven power distribution network planning problem base construction method, the manual checking of the power distribution network planning problem base comprises:

[0040] Checking whether the data is missing, whether the problem is repeatedly written into the individual case problem base and the homologous problem base, and whether the data is filled in the correct position;

[0041] If the checking is qualified, the power distribution network planning problem base construction is successful, the power distribution network planning problem base is output, and the process ends;

[0042] If the checking is unqualified, the power distribution network planning problem discrimination rule base is modified according to the feedback until the checking is qualified.

[0043] The beneficial effects of the present application are that on the basis of the traditional power distribution network planning problem summary, the discrimination principles of individual case problems and homologous problems are analyzed in combination with the actual demand of power distribution network planning, and the related discrimination rules are formulated, so that the connection between the problems in the problem base can be more fully excavated to guide the value of power distribution network planning.

[0044] In addition, the rule engine is used to construct the power distribution network planning problem base, so that the power distribution network planning problem discrimination rules can be separated from the application program code implementation, the planning staff can modify the rule base according to the actual needs, and the complex computer program does not need to be changed, which has sustainability and maintainability. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0046] Figure 1 The flow chart of the rule engine driven power distribution network planning problem base construction method of the present application.

[0047] Figure 2 The structural diagram of the power distribution network planning problem library. DETAILED DESCRIPTION

[0048] In order to make the above objectives, features and advantages of the present application more apparent, specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0049] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details given herein, that the present application can be practiced with other than the described embodiments, and that variations from the particular embodiments described herein can be made and still be within the scope of the present application.

[0050] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is independent of or selected from other embodiments.

[0051] Thirdly, the present application is described in detail in conjunction with the schematic diagram. In the detailed description of the embodiments of the present application, the cross-sectional view of the device structure is locally enlarged without the general proportion for the convenience of description, and the schematic diagram is only an example, which should not limit the scope of protection of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacture.

[0052] Embodiment 1

[0053] Reference Figure 1 A rule engine driven power distribution network planning problem library construction method includes:

[0054] The power distribution network planning problem discrimination rule engine includes three parts: a power distribution network planning problem discrimination rule base (Rule Base), a power distribution network fact base (Fact Base) and an inference engine (Inference Engine).

[0055] The inference engine includes three parts: a pattern matcher (Pattern Matcher), an agenda (Agenda) and an execution engine (Execution Engine).

[0056] S1: Based on the power distribution network center database, a fact statement (Statement) is written to construct a fact base (Fact Base).kfb file. It should be noted that:

[0057] The distribution network center database is collected by the distribution network planning staff, and includes information of substations, medium-voltage feeders, distribution transformers, etc.

[0058] The substation information includes main transformer composition, load ratio, load rate, voltage condition, supply radius, and reactive compensation capacity; the medium-voltage feeder information includes line type, substation, load rate, line type, voltage condition, and supply radius; and the distribution transformer information includes transformer type, load rate, voltage condition, supply radius, reactive compensation capacity, and feeder name.

[0059] The fact statement needs to follow the fact statement expression specification of the rule engine Pyke, and is object-oriented, taking each device condition as a fact statement, and writing the basic conditions of the substation, medium-voltage feeder, and distribution transformer, respectively. The expression specification of the fact statement is: fact type identifier (parameter, parameter, parameter…).

[0060] The distribution transformer fact statement is as follows:

[0061] transformer_of ($TransformerName, $TransformerType, $LoadRate, $Voltage, $SupplyRadius, $ReactiveCapacity, $FeederName)

[0062] S2: Formulate the distribution network individual case problem discrimination rule and the distribution network homologous problem discrimination rule, construct the distribution network planning problem discrimination rule library krb file, and write using the forward reasoning logic. It needs to be noted that:

[0063] Each distribution network planning problem discrimination rule contains a mode part and an action part; the mode part is used to match facts and judge whether there is a problem; and the action part, i.e., the operation after the rule and the fact match successfully, collects the problems and puts them into the fact library working memory.

[0064] The distribution network individual case problem refers to the problem of a single device, such as distribution transformer overload and low voltage.

[0065] The distribution network homologous problem is divided into the following three cases: multiple problems belong to the same device; multiple devices with the same problem are connected to the same superior device; and multiple same problems occur in the same area.

[0066] Case problem discrimination rule is formulated according to specific power distribution network planning technical guidelines, and is a discrimination of whether a certain feature of equipment meets the requirements; a case problem discrimination index system is established, including maximum load rate, voltage and other indicators, and corresponding lower threshold and upper threshold of each index are formulated in combination with the power distribution network planning technical guidelines.

[0067] If the actual value of a certain index of equipment is a real , the lower threshold of the index is a ref1 , and the upper threshold is a ref2 , then the case problem discrimination rule is: if a real ≤a ref1 or a real ≥a ref2 , then it is determined that the case problem reflected by the index exists.

[0068] For example, when the maximum load rate of a distribution transformer exceeds 100%, it is determined that the distribution transformer has an overload problem, and according to the rule expression specification of the rule engine Pyke, the rule is written as follows:

[0069] foreach

[0070] Condition

[0071] assert

[0072] Action;

[0073] Specifically as follows:

[0074]

[0075] Homologous problem discrimination rule can be divided into three categories, and is also written according to the rule expression specification of the rule engine Pyke.

[0076] For example, the discrimination rule for the overload problem of multiple distribution transformers belonging to the same feeder is written as follows:

[0077]

[0078]

[0079] Since the rule calling priority of Pyke is determined according to the specific order of rules in the rule library, the earlier the position of the rule, the higher the priority of the rule; therefore, the order of the rules in the rule library is as follows: discrimination rule for multiple devices with the same problem accessing the same upper-level device, discrimination rule for multiple same problems occurring in the same area, discrimination rule for multiple same problems occurring in the same area, and discrimination rule for case problems.

[0080] S3: Based on Pyke, combined with the above distribution network planning problem discrimination rule base and distribution network fact base, the distribution network planning problem discrimination rule engine is constructed. It should be noted that:

[0081] Firstly, load the distribution network fact base.kfb file, read the data of the distribution network fact base into the working memory; secondly, use pyke / krb_compiler / compiler.krb to compile the distribution network planning problem discrimination rule base.krb file to obtain the corresponding distribution network planning problem discrimination rule base.py file; then, write the driving file of the rule engine to prepare for subsequent calling of the rule engine.

[0082] S4: Formulate the distribution network planning problem base template. It should be noted that:

[0083] The structure of the distribution network planning problem base is shown in Figure 2 .

[0084] Taking the distribution transformer heavy overload problem as an example, the information contained in the distribution transformer heavy overload problem base includes: distribution transformer name, district / county, 10KV line, substation, model, maximum load (%), average load (KV), average load rate, heavy overload, operation life, etc.

[0085] For different distribution network planning problems, they are divided into multiple sub-bases, and the types of problems needed to be summarized in each sub-base are also designed in advance, such as feeder heavy overload low voltage, distribution transformer heavy overload low voltage, multiple distribution transformers with heavy overload on the same feeder, multiple distribution transformers with low voltage on the same feeder, distribution transformer low voltage, distribution transformer heavy overload, feeder low voltage, and feeder heavy overload, etc.

[0086] S5: Call the rule engine, add the generated distribution network planning problem to the fact base, and based on the distribution network planning problem base template, sort out the distribution network planning problem base. It should be noted that:

[0087] The pattern matcher of the rule engine compares the pattern part of the fact and the rule, if the matching is successful, the corresponding rule is triggered, the engine is executed, and the distribution network planning problem is generated as a new fact and added to the fact base.

[0088] If multiple rules and facts match at the same time, they are triggered in turn according to the priority; if the action of the triggered rule produces a new fact, the new fact is also added to the working memory.

[0089] Based on the distribution network planning problem base template, the pandas library of python is used to sort the distribution network planning problems in the fact base into the standardized problem base.

[0090] S6: Manually check the distribution network planning problem base. It should be noted that:

[0091] The main purpose is to check the integrity, non-repetition and rationality of the distribution network planning problem library; check whether the data is missing, whether the problem is repeatedly written into the problem library, and whether the data is filled in the correct position, etc.

[0092] If the inspection is qualified, the distribution network planning problem library is successfully constructed, the distribution network planning problem library is output, and the process is ended.

[0093] If the inspection is not qualified, the distribution network planning problem library is modified according to the feedback, and steps S2-S6 are repeated.

[0094] Example 2

[0095] The difference between this example and the first example is that a verification test of the rule engine driven distribution network planning problem library construction method is provided to verify the technical effect adopted in the method.

[0096] Based on the medium voltage feeder data and distribution transformer data of the distribution network planning data of a certain area in a certain year, the rule engine is used to construct the distribution network planning problem library for the low voltage problem of the equipment and the heavy overload problem of the equipment.

[0097] B1: Based on the data collection, write the fact statement (Statement) and build the fact base (Fact Base).kfb file.

[0098] The data collection of the distribution transformer is shown in Table 1:

[0099]

[0100]

[0101] The data collection of the medium voltage feeder is shown in Table 2:

[0102]

[0103] Table 2 Medium voltage feeder data collection

[0104] According to the fact statement expression specification of the rule engine Pyke, the condition of each device is taken as a fact statement, and the basic conditions of the medium voltage feeder, distribution transformer and the like are written respectively.

[0105] The fact statement in the fact base is written as follows:

[0106] transformer($Transformer Name, $District / County, $10kV Line, $Substation, $Model, $Capacity (kVA), $Commissioning Date, $Reactive Power Compensation Capacity (kVar), $Compensation Control Method, $Power Supply Area Classification, $Transformer Type (Box-type, Pole-mounted, Distribution Room), $Public / Dedicated Transformer, $Urban / Rural, $Annual Active Power (kWh), $Maximum Load Utilization Hours, $Maximum Load (kW), $Maximum Load Rate (%), $Average Load (kW), $Average Load Rate, $Years of Operation, $Terminal Voltage (V))

[0107] ...

[0108] feeder($Serial Number, $Power Supply Station, $Substation, $Line Name, $Public / Dedicated, $Urban / Rural Grid, $Power Supply Zone, $Main Load Characteristics of the Line, $Maximum Allowable Current Carrying Capacity of the Line (A), $Maximum Annual Current (A), $Load Rate (%), $Wiring Mode, $Whether it is a Transferable Line, $Terminal Voltage (kV), $Is it a Bottleneck, $Is there a Safety Hazard, $Is there Insufficient Wind Resistance, $Is there any Restriction on Application, $Is there any Old or Dilapidated Equipment or Lines, $Years of Operation)

[0109] ...

[0110] B2: Develop rules for identifying individual problems in the distribution network and rules for identifying problems originating from the same source in the distribution network. Construct a rule library for identifying distribution network planning problems (.krb file) using forward reasoning logic.

[0111] Since PyKe's rule invocation priority is determined by the specific order of rules in the .krb file, the earlier a rule appears in the file, the higher its priority. Therefore, the following rules should be written in the rule base in sequence:

[0112] 1: Criteria for identifying simultaneous heavy overload and low voltage problems in medium-voltage feeders.

[0113] 2: Rules for identifying simultaneous heavy overload and low voltage problems in distribution transformers.

[0114] 3: Rules for identifying heavy overload problems in multiple distribution transformers belonging to the same feeder.

[0115] 4: Rules for identifying low voltage problems in multiple distribution transformers belonging to the same feeder.

[0116] 5: Criteria for identifying heavy overload problems in medium-voltage feeders.

[0117] 6: Rules for identifying low voltage problems in medium-voltage feeders.

[0118] 7: Rules for identifying heavy overload problems in distribution transformers.

[0119] 8: The discrimination rule of low voltage problem of distribution transformer.

[0120] The discrimination rule of low voltage problem of distribution transformer.

[0121] If the load rate is greater than 0.8 and the terminal voltage is lower than 198V, it is determined that the distribution transformer has both heavy overload problem and low voltage problem.

[0122] B3: Based on the distribution network planning problem discrimination rule library, a distribution network planning problem discrimination rule engine is constructed.

[0123] B4: Set the distribution network planning problem library template, including the distribution network case problem library template and the distribution network homologous problem library template.

[0124] B5: Call the rule engine to add the newly generated distribution network planning problem to the fact library, and based on the distribution network planning problem library template, the distribution network planning problem library is sorted out.

[0125] The distribution network planning problem discrimination rule engine stores the distribution network planning problem identified according to the matching of rules and facts into the fact library.

[0126] Based on the distribution network planning problem library template, the distribution network planning problem in the fact library of the rule engine is sorted into the standardized problem library.xlsx file using the pandas library of python.

[0127] The problem set of distribution transformer with both heavy overload problem and low voltage problem is shown in Table 3:

[0128]

[0129] Table 3 Problem set of distribution transformer with both heavy overload problem and low voltage problem

[0130] It can be seen that only one distribution transformer in the region has both heavy overload problem and low voltage problem.

[0131] The problem set of multiple distribution transformers belonging to the same feeder with low voltage problem is shown in Table 4:

[0132]

[0133] Table 4 Problem set of multiple distribution transformers belonging to the same feeder with low voltage problem

[0134] It can be seen that the terminal voltage of multiple distribution transformers of feeders 1 to 5 in the region is lower than the limit value 198V, and there is low voltage.

[0135] B6: Check the power distribution network planning problem library, the check result is qualified, the power distribution network planning problem library is successfully constructed, output the power distribution network planning problem library, and the process ends.

[0136] Currently, in practical applications, the arrangement of the power distribution network planning problem library is mainly manual arrangement. For the arrangement of a regional power distribution network problem library, the time often takes several days or even several months, and a large amount of time and effort of the staff is required. Similarly, based on the medium-voltage feeder data and the power distribution transformer data of the power distribution network planning data of a certain region in a certain year, the low-voltage problem and the heavy overload problem of the equipment are arranged, which takes much more time than the method proposed in the present patent.

[0137] For the same regional power distribution network data, the power distribution network planning problem library can also be obtained by using the manual method to arrange the excel according to the power distribution network planning problem library template mentioned in B4. Among them,

[0138] The problem set of the power distribution transformer simultaneously occurring heavy overload problem and low-voltage problem is shown in Table 5:

[0139]

[0140] Table 5 Problem set of power distribution transformer simultaneously occurring heavy overload problem and low-voltage problem

[0141] It can be seen that the result also shows that there is only one power distribution transformer in the region that simultaneously occurs heavy overload problem and low-voltage problem.

[0142] The problem set of multiple power distribution transformers belonging to the same feeder occurring low-voltage problem is shown in Table 5:

[0143]

[0144]

[0145] Table 5 Problem set of multiple power distribution transformers belonging to the same feeder occurring low-voltage problem

[0146] From Table 5, it can be seen that the end voltage of multiple power distribution transformers of feeders 1 to 5 in the region is lower than the limit value 198V, and there is low voltage.

[0147] Although the traditional manual arrangement method can achieve the same effect, it requires a lot of time.

[0148] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A rule engine driven power distribution network planning problem library construction method, characterized in that: Comprising, Based on the distribution network center database, write factual statements, build fact library files; Develop distribution network case problem discrimination rules and distribution network homologous problem discrimination rules, build distribution network planning problem discrimination rule library files, and write using forward reasoning logic; Based on Pyke, combined with the distribution network planning problem discrimination rule library and the distribution network fact library, build a distribution network planning problem discrimination rule engine; And, Develop a distribution network planning problem library template, call the rule engine, add the generated distribution network planning problem to the fact library, and based on the distribution network planning problem library template, organize the distribution network planning problem library, and manually check the distribution network planning problem library; The distribution network case problem refers to the problem of a single device, such as distribution transformer overload, low voltage problem; Distribution network homologous problems are divided into three cases: multiple problems belong to the same device, multiple devices with the same problem are connected to the same superior device, and multiple same problems occur in the same area; The case problem discrimination rule is formulated according to the specific distribution network planning technical guidelines, which is a discrimination of whether a certain feature of the device meets the requirements, and the case problem discrimination rule can be expressed according to the rule expression specification of the rule engine Pyke; The homologous problem discrimination rule is divided into three categories and is written according to the rule expression specification of the rule engine Pyke; Each distribution network planning problem discrimination rule of the distribution network planning problem discrimination rule library includes a mode part and an action part; The mode part is used to match facts and determine whether there is a problem, and the action part is the operation after the rule and fact match is successful, which collects the problem and puts it into the fact library working memory; Based on Pyke, combined with the distribution network planning problem discrimination rule library and the distribution network fact library, build a distribution network planning problem discrimination rule engine, which includes: First, load the distribution network fact library file and read the data of the distribution network fact library into the working memory; Second, use the pyke compilation function to compile the distribution network planning problem discrimination rule library file to get the corresponding distribution network planning problem discrimination rule library file; Finally, write the rule engine driver file to prepare for subsequent rule engine calls; The pattern matcher of the rule engine compares the facts and the mode part of the rule; If the match is successful, the corresponding rule is triggered, the engine is executed, and the distribution network planning problem is generated as new facts and added to the fact library; If multiple rules and facts match at the same time, they are triggered in order of priority, and the action of the triggered rule may generate new facts, which are also added to the working memory; Based on the distribution network planning problem library template, use the pandas library of python to organize the distribution network planning problems in the fact library into a standardized problem library.

2. The rule engine driven power distribution network planning problem library construction method of claim 1, wherein: The distribution network center database is collected by distribution network planning personnel, including substation, medium voltage feeder, and distribution transformer information.

3. The rule engine driven power distribution network planning problem library construction method of claim 1 or 2, wherein: The fact statement needs to follow the expression specification of fact statement of the rule engine Pyke, and each device is taken as a fact statement, and the basic conditions of the substation, medium voltage feeder and distribution transformer are written respectively. The expression specification of fact statement is fact type identifier.

4. The rule engine driven power distribution network planning problem library construction method of claim 1, wherein: The rule expression specification of the rule engine Pyke is as follows: foreach Condition assert Action. The homologous problem discrimination rules are divided into three categories, and are also written according to the rule expression specification of the rule engine Pyke.

5. The rule engine driven power distribution network planning problem library construction method of claim 1 or 4, wherein: The order of the rules in the distribution network planning problem discrimination rule library is as follows: The discrimination rules of multiple problems belonging to the same device; The discrimination rules of multiple devices with the same problem accessing the same superior device; The discrimination rules of multiple same problems appearing in the same area; The discrimination rules of individual case problems.

6. The rule engine driven power distribution network planning problem library construction method of claim 1, wherein: The artificial checking of the distribution network planning problem library includes: Checking whether the data is missing, whether the problem is repeatedly written into the individual case problem library and the homologous problem library, and whether the data is filled in the correct position; If the check is qualified, the distribution network planning problem library is successfully constructed, the distribution network planning problem library is output, and the process is ended; If the check is unqualified, the distribution network planning problem discrimination rule library is modified according to the feedback opinions until the check is qualified.

Images