CN104102956A - Distribution network expansion planning method based on strategy adaption differential evolution - Google Patents

Abstract

The invention discloses a distribution network expansion planning method based on strategy adaption differential evolution. A capital time value is considered, calculation is carried out according to equal amount installment payment capital recovery, a model is established by taking least annual investment and operation maintenance cost as a target, a differential evolution algorithm based on strategy adaption on the basis of the model is proposed, an optimal solution obtained by the algorithm is decoded, a planning line is drawn on an electric power GIS (geographic information system) platform according to a line number obtained by decoding to carry out structure repair to an individual, and the individual is enabled to satisfy a radiative network structure. An adaption evolutionary strategy is continuously updated in an iteration process to prevent the algorithm from being trapped in local optimum, and a planning process of a distribution network line is enabled to exhibit better interactivity, more intuitive planning result and flexibility in planning scheme regulation by a GIS.

Description

A kind of distribution network planning method of evolving based on tactful adaptive differential

Technical field

The present invention relates to the Expansion Planning of distribution network in a kind of electric system, in particular, a kind of distribution network planning method of evolving based on tactful adaptive differential.

Background technology

Distribution network planning refers on the basis of present situation electrical network analysis and following load forecast of distribution, from possible transformer station position and capacity, Connection Mode, feeder line number, path and model, find out an optimum or suboptimal design as expansion modification scheme, make investment, operation, maintenance, network loss and reliability failure costs sum minimum.

According to the different disposal method to economy and reliability index, that the mathematical model of distribution network planning can be divided into is economical, reliable and comprehensive 3 classes.

The objective function of economical model is only considered economic index, and fail-safe analysis is conventionally only as posteriority n-1 verification.According to the difference of economic index, can be further divided into transportation model and least cost model.The former think all load squares comprehensively hour mode of connection is the shortest, take line power as control variable; It is objective function that the latter be take investment recovery cost, equipment amortization expense and electric energy loss expense sum, and this model more meets the requirement of economy in engineering compared with the former.

Reliable model is the economic level based on certain, the plan model that the reliability of take is target.

Comprehensive model is with certain conversion regime, and the reliability cost that reliability index is converted to reliability benefit integrated economics model forms objective function.

In above three kinds of models, economy model has certain economy and is worth, but reliability is generally poor.Reliability model can embody the relation of improvement and the fund input of reliability index, but practicality is poor, plans for general for local expansion.Comprehensive model is sought to average out between reliability cost and reliability benefit, thereby makes distribution network planning reach global optimum, has higher comprehensive social benefit.

Summary of the invention

For distribution network planning, when using evolution algorithm to solve, be easily absorbed in local optimum, computation process and easily produce the problems such as a large amount of infeasible solutions, the present invention proposes a kind of effectively avoid being absorbed in local optimum, the good distribution network planning method of evolving based on tactful adaptive differential of reliability.

The technical solution adopted for the present invention to solve the technical problems is:

A distribution network planning method of evolving based on tactful adaptive differential, described distribution network planning method comprises the following steps:

A1, the result according to substation locating and sizing with following load forecast of distribution create load point, transformer station and branch road to be selected, built branch road element information, and set up the topology rule of corresponding point-point, point-line, line-face on electric power GIS platform;

A2, the element information creating is carried out to pre-service: load point and transformer station are sequentially numbered to branch road to be selected and built branch road serial number, and start of record peripheral node numbering; For geographic barrier, generate buffer zone, carry out buffer zone analysis, find out the circuit corridor that is not suitable for the construction of line;

A3, consider the time value of fund, pay separately capital recovery calculate by single-candidate, take year investment and operation and maintenance cost minimum is target, and objective function is suc as formula (1):

$\min F=\underset{i\∈S_1}{\mathrm{\Σ}}(\mathrm{\ω}+\mathrm{\λ})l_{i}f\left(D_i\right)X_i+\underset{i\∈S_2}{\mathrm{\Σ}}{\mathrm{\λl}}_{i}f\left(D_i\right)+\underset{i\∈S}{\mathrm{\Σ}}{l}_{i}g\left(D_i\right)\frac{P_i^2}{U_N^2}{\mathrm{\τ}}_{\max }d---\left(1\right)$

In formula: S ₁, S ₂, S is respectively newly-built sets of lines, built sets of lines and total line collection; ω is a year equivalent recovery coefficient, and λ is the number percent keeping in repair, depreciation accounts for investment cost; l _ithe length of circuit i, f (D _i) for wire diameter be D _ithe cost of circuit unit length, X _ibe the decision variable of i bar circuit, select this circuit as feeder line branch road, X _iget 1, otherwise get 0; g(D _i) for wire diameter be D _ithe resistivity of circuit; P _ifor the power that passes through of circuit i, U _nfor rated voltage; τ _maxthe maximum loss time in year, d is unit electricity price;

In differential evolution algorithm, dimension D is branch road quantity N to be selected _line, population quantity NP=10*D, mutation operator F is the random string of binary characters producing, and crossover operator CR gets 0.1, and end condition is that the optimum individual obtaining after tabu search algorithm is identical with the optimum individual fitness that switching enters before tabu search algorithm; The switching condition that enters tabu search algorithm is that iteration surpasses some generations and optimum individual continuous some generations do not change; The condition that exits tabu search algorithm is that step-length surpasses some steps and optimum individual continuous some generations do not change;

A4, read element information, generating algorithm initial population, evaluates initial population, and make first of population individual for global optimum individual;

A5, judge whether to reach end condition, if so, evolve and stop, using optimum individual as separating output, go to step A10; If not, continue algorithm, enter steps A 6;

A6, judge whether to need update strategy to select probability, if so, upgrade probability;

A7, according to the selection probability of Different Strategies is random, select a kind of strategy to make a variation and interlace operation, and carry out structural constraint verification, if individuality does not meet constraint, proceed to steps A 11; If meet constraint, enter steps A 8;

A8, select operation, if the new physical efficiency after variation intersects is replaced old individuality, enter the next generation, corresponding strategy is when cumulative 1 time of former generation number of success, otherwise cumulative 1 time of the frequency of failure;

A9, travel through current population, find out optimum individual, judge whether current optimum individual is better than global optimum's individuality, if replace, otherwise retain, enter afterwards steps A 5;

A10, the optimum solution that algorithm is obtained are decoded, and planning circuit is drawn out in the circuit number obtaining according to decoding on electric power GIS platform;

A11, individuality is carried out to structure repair, make it meet Radial network structure, reparation completes, and proceeds to steps A 8.

Further, in described steps A 4, read the positional information of load point and payload, the positional information of transformer station, branch road to be selected, built branch road.Random generation length is N _linestring of binary characters, and guarantee that the quantity of " 1 " in character string is N _node(number of nodes), the function of applying mechanically (1) formula calculates each individual target function value.

Further again, in described steps A 6, it is 10 that statistical algebra LP is set, upgrading algebraically is 15, and every experience 15 generation iteration, just adds up and work as former generation G failed, the number of success of each strategy in 10 generations of backstepping forward, and calculate the selection probability of corresponding strategy, suc as formula (2), (3), wherein S _k,Grepresent tactful k G for time the probability of success; Ns _k,g, nf _k,grepresent that respectively tactful k g is for successful, failed number of times; ε is 0.01, in order to prevent that the tactful probability of success from being 0; p _k,Grepresent the tactful k G selection probability in generation;

$S_{k,G}=\frac{{\mathrm{\Σ}}_{g=G-\mathrm{LP}}^{G-1}{\mathrm{ns}}_{k,g}}{{\mathrm{\Σ}}_{g=G-\mathrm{LP}}^{G-1}{\mathrm{ns}}_{k,g}+{\mathrm{\Σ}}_{g=G-\mathrm{LP}}^{G-1}{\mathrm{nf}}_{k,g}}+\mathrm{\ϵ}---\left(1\right)$

$p_{k,G}=\frac{S_{k,G}}{{\mathrm{\Σ}}_{k=1}^K{S}_{k,G}}---\left(2\right)$

Further, in described steps A 7, (4), (5), (6) 3 kinds of Mutation Strategies are set.

v _i,j＝x _r1,j+F·(x _r2,j-x _r3,j) (3)

v _i,j＝x _i,j+F·(x _best,j-x _i,j)+F·(x _r1,j-x _r2,j)+F·(x _r3,j-x _r4,j) (4)

v _i,j＝x _i,j+F·(x _r2,j-x _r3,j)+F·(x _r4,j-x _r5,j) (5)

Mutation operation is to each target individual X _i,G, i=1,2 ..., NP, produces variation individuality according to probability selection strategy.Wherein, the random sequence number r selecting in strategy ₁, r ₂, r ₃, r ₄, r ₅different, and r ₁, r ₂, r ₃, r ₄, r ₅i is also different from target individual sequence number; X in strategy (5) _{best, j}for optimum individual.In three kinds of strategies, arithmetic operator is logical operator, " " presentation logic or, " " presentation logic XOR, "+" presentation logic with.

Then according to formula (7), (8), (9), carry out interlace operation, wherein randb (j) is random j the estimated value generating between [0,1], and rnbr (i) is a random sequence of selecting.

U _i,G+1＝(U _1i,G+1,U _2i,G+1,L,U _Di,G+1) (6)

$U_{\mathrm{ji},G+1}=\left\{\begin{array}{cccc}{V}_{\mathrm{ji},G+1}& \mathrm{if}(\mathrm{randb}\left(j\right)\≤\mathrm{CR})& \mathrm{or}& j=\mathrm{rnbr}\left(i\right)\\ X_{\mathrm{ji},G+1}& \mathrm{if}(\mathrm{randb}\left(j\right)>\mathrm{CR})& \mathrm{and}& j\≠\mathrm{rnbr}\left(i\right)\end{array}\right.---\left(7\right)$

(i＝1,2,L,NP,j＝1,2,L,D) (8)

Individuality is carried out to connectedness, radiativity structural constraint verification, if do not meet constraint, do not proceed to steps A 11 and carry out structure repair.

In described steps A 13, first to not meeting the individuality of radiativity structure, carry out number of branches reparation, make N _branch=N _node-1; Then degree of depth traversal is individual sets, and recording individual isolates part, if individuality exists closed loop, records closed loop branch road; After having traveled through, interrupt at random a branch road in closed loop, and the isolated part of individuality is coupled together.

Beneficial effect of the present invention is mainly manifested in: the present invention's application strategy self-adaptation when carrying out distribution network planning has avoided solution procedure to be absorbed in local optimum, and in conjunction with the network analysis of GIS, buffering analysis optimization algorithmic procedure, make planning process more directly perceived, conveniently manually result is adjusted.

Accompanying drawing explanation

Fig. 1 is the process flow diagram of the distribution network planning method based on tactful adaptive differential evolution.

Tu2Shi transformer station position and load point distribute.

Fig. 3 is initial distribution network.

Fig. 4 is the optimization distribution line obtaining after execution algorithm.

Embodiment

Below in conjunction with accompanying drawing, the invention will be further described.

With reference to Fig. 1～Fig. 4, a kind of distribution network planning method of evolving based on tactful adaptive differential, as shown in Figure 1, wherein comprises following steps:

A1, according to substation locating and sizing and following load forecast of distribution result, at electric power GIS platform, create relevant factor information;

A2, the element information creating is carried out to pre-service;

A3, determine objective function, the specific strategy that algorithm is controlled accordingly parameter and adopted is set;

A4, read element information, generating algorithm initial population, evaluates initial population, and make first of population individual for global optimum individual;

A5, judge whether to reach end condition, if so, evolve and stop, using optimum individual as separating output, go to step A10; If not, continue algorithm, enter steps A 6;

A6, judge whether to need update strategy to select probability, if so, upgrade probability;

A7, according to the selection probability of Different Strategies is random, select a kind of strategy to make a variation and interlace operation, and carry out structural constraint verification, if individuality does not meet constraint, proceed to steps A 11; If meet constraint, enter steps A 8;

A8, select operation, if the new physical efficiency after variation intersects is replaced old individuality, enter the next generation, corresponding strategy is when cumulative 1 time of former generation number of success, otherwise cumulative 1 time of the frequency of failure;

A9, travel through current population, find out optimum individual, judge whether current optimum individual is better than global optimum's individuality, if replace, otherwise retain, enter afterwards steps A 5;

A10, the optimum solution that algorithm is obtained are decoded, and planning circuit is drawn out in the circuit number obtaining according to decoding on electric power GIS platform.

A11, individuality is carried out to structure repair, make it meet Radial network structure, reparation completes, and proceeds to steps A 8;

Wherein, DE algorithm adopts binary coding, character string on each " 1 " represent that the branch road of corresponding numbering is selected, " 0 " represents that the branch road of corresponding numbering do not choose.

Described method, wherein in steps A 1, result according to substation locating and sizing with following load forecast of distribution creates load point, transformer station and branch road to be selected, built branch road element information, and sets up the topology rule of corresponding point-point, point-line, line-face on electric power GIS platform.

Described method, wherein in steps A 2, by all nodes (comprising load point and transformer station) serial number, all branch roads (comprising branch road to be selected and built branch road) serial number, and start of record peripheral node numbering; For geographic barrier, generate buffer zone, carry out buffer zone analysis, find out the circuit corridor that is not suitable for the construction of line, reduce algorithm dimension space, reduce blind search.

Described method, wherein in steps A 3, Optimized model is considered the time value of fund, pays separately capital recovery calculate by single-candidate, and take year investment and operation and maintenance cost minimum is target, and objective function is suc as formula (6).

$\min F=\underset{i\∈S_1}{\mathrm{\Σ}}(\mathrm{\ω}+\mathrm{\λ})l_{i}f\left(D_i\right)X_i+\underset{i\∈S_2}{\mathrm{\Σ}}{\mathrm{\λl}}_{i}f\left(D_i\right)+\underset{i\∈S}{\mathrm{\Σ}}{l}_{i}g\left(D_i\right)\frac{P_i^2}{U_N^2}{\mathrm{\τ}}_{\max }d---\left(6\right)$

In formula: S ₁, S ₂, S is respectively newly-built sets of lines, built sets of lines and total line collection; ω is a year equivalent recovery coefficient, and λ is the number percent keeping in repair, depreciation accounts for investment cost; l _ithe length of circuit i, f (D _i) for wire diameter be D _ithe cost of circuit unit length, X _ithe decision variable that is i bar circuit (selects this circuit as feeder line branch road, X _iget 1, otherwise get 0); g(D _i) for wire diameter be D _ithe resistivity of circuit; P _ifor the power that passes through of circuit i, U _nfor rated voltage; τ _maxthe maximum loss time in year, d is unit electricity price.In DE (Differential Evolution, differential evolution) algorithm, dimension D is branch road quantity N to be selected _line, population quantity NP=10*D, mutation operator F is the random string of binary characters producing, and crossover operator CR gets 0.1, and end condition is that iteration reached for 200 generations;

Described method, wherein in steps A 4, reads the positional information of load point and payload, the positional information of transformer station, branch road to be selected, built branch road.Random generation length is N _linestring of binary characters, and guarantee that the quantity of " 1 " in character string is N _node(number of nodes), the function of applying mechanically (1) formula calculates each individual target function value.

In described steps A 6, it is 10 that statistical algebra LP is set, and upgrading algebraically is 15, be every experience 15 generation iteration, just statistics is worked as former generation G failed, the number of success of each strategy in 10 generations of backstepping forward, and calculates the selection probability of corresponding strategy, suc as formula (10), (11), wherein S _k,Grepresent tactful k G for time the probability of success; Ns _k,g, nf _k,grepresent that respectively tactful k g is for successful, failed number of times; ε is 0.01, in order to prevent that the tactful probability of success from being 0; p _k,Grepresent the tactful k G selection probability in generation;

$S_{k,G}=\frac{{\mathrm{\Σ}}_{g=G-\mathrm{LP}}^{G-1}{\mathrm{ns}}_{k,g}}{{\mathrm{\Σ}}_{g=G-\mathrm{LP}}^{G-1}{\mathrm{ns}}_{k,g}+{\mathrm{\Σ}}_{g=G-\mathrm{LP}}^{G-1}{\mathrm{nf}}_{k,g}}+\mathrm{\ϵ}---\left(9\right)$

$p_{k,G}=\frac{S_{k,G}}{{\mathrm{\Σ}}_{k=1}^K{S}_{k,G}}---\left(10\right)$

In described steps A 7, (12), (13), (14) 3 kinds of Mutation Strategies are set.

v _i,j＝x _r1,j+F·(x _r2,j-x _r3,j) (11)

v _i,j＝x _i,j+F·(x _best,j-x _i,j)+F·(x _r1,j-x _r2,j)+F·(x _r3,j-x _r4,j) (12)

v _i,j＝x _i,j+F·(x _r2,j-x _r3,j)+F·(x _r4,j-x _r5,j) (13)

Mutation operation is to each target individual X _i,G, i=1,2 ..., NP, produces variation individuality according to probability selection strategy.Wherein, the random sequence number r selecting in strategy ₁, r ₂, r ₃, r ₄, r ₅different, and r ₁, r ₂, r ₃, r ₄, r ₅i is also different from target individual sequence number; ; X in strategy (13) _{best, j}for optimum individual.In three kinds of strategies, arithmetic operator is logical operator, " " presentation logic or, " " presentation logic XOR, "+" presentation logic with.

Then according to formula (15), (16), (17), carry out interlace operation, wherein randb (j) is random j the estimated value generating between [0,1], and rnbr (i) is a random sequence of selecting.

U _i,G+1＝(U _1i,G+1,U _2i,G+1,L,U _Di,G+1) (14)

$U_{\mathrm{ji},G+1}=\left\{\begin{array}{cccc}{V}_{\mathrm{ji},G+1}& \mathrm{if}(\mathrm{randb}\left(j\right)\≤\mathrm{CR})& \mathrm{or}& j=\mathrm{rnbr}\left(i\right)\\ X_{\mathrm{ji},G+1}& \mathrm{if}(\mathrm{randb}\left(j\right)>\mathrm{CR})& \mathrm{and}& j\≠\mathrm{rnbr}\left(i\right)\end{array}\right.---\left(15\right)$

(i＝1,2,L,NP,j＝1,2,L,D) (16)

Individuality is carried out to connectedness, radiativity structural constraint verification, if do not meet constraint, do not proceed to steps A 11 and carry out structure repair.

In described steps A 13, first to not meeting the individuality of radiativity structure, carry out number of branches reparation, make N _branch=N _node-1; Then degree of depth traversal is individual sets, and recording individual isolates part, if individuality exists closed loop, records closed loop branch road; After having traveled through, interrupt at random a branch road in closed loop, and the isolated part of individuality is coupled together.

Embodiment

The present embodiment is one and has 25 nodes and 42 real systems that can extend the 10kv power distribution network of branch road, and electric power GIS platform adopts line of electric force management GIS infosystem, and ground drops on probationly this system in Yantai, Shandong etc., and operation reflection is good.

Node data is as shown in table 1, capacity 0 be transformer station; Prop up circuit-switched data as shown in table 2.Voltage-drop constraint is set to 5%, ω and gets 0.105, λ and get 0.05, τ _maxget 10000h, d gets 0.5.

On line of electric force management GIS information system platform, create node key element as Fig. 2, solid dot is load, and hollow dots is transformer station, creates circuit key element as Fig. 3.Application algorithm carries out after computing, obtains as the distribution line cabling scenario of Fig. 4.Table 1 is node data, table 2 feeder line data.

Table 1

Branch road number	Starting point	Terminal	Resistance (Ω)	Reactance (Ω)	Cost (unit)	Capacity (A)	Length (km)
								1	1	2	2.52	0.84	106500	90	2.1
2	1	3	1.98	0.66	99750	90	1.65

3	1	42	2.64	0.88	10800	90	2.2
								4	2	5	4.2	0.8	30000	125	2
5	2	6	3.15	0.6	22500	125	1.5
								6	3	6	3.68	0.7	26250	125	1.75
7	3	7	3.68	0.7	26250	125	1.75
								8	4	7	3.68	0.7	26250	125	1.75
9	4	8	2.1	0.4	15000	125	1
								10	4	12	2.1	0.4	15000	125	1
11	5	9	2.63	0.5	18750	125	1.25
								12	6	9	3.15	0.6	22500	125	1.5
13	6	10	3.68	0.7	26250	125	1.75
								14	7	10	4.2	0.8	30000	125	2
15	7	11	4.2	0.8	30000	125	2
								16	7	8	3.68	0.7	26250	125	1.75
17	9	15	2.63	0.5	18750	125	1.25
								18	9	10	3.68	0.7	26250	125	1.75
19	10	14	3.68	0.7	26250	125	1.75
								20	10	13	5.78	1.1	41250	125	2.75
21	11	13	3.68	0.7	26250	125	1.75
								22	1	16	1.8	0.6	97500	90	1.5
23	2	16	2.21	0.42	15750	125	1.05
								24	16	17	1.58	0.3	11250	125	0.75
25	2	17	2.21	0.42	15750	125	1.05
								26	5	17	2.1	0.4	15000	125	1
27	17	18	3.15	0.6	22500	125	1.5
								28	5	18	1.58	0.3	11250	125	0.75
29	15	18	2.63	0.5	18750	125	1.25
								30	1	19	1.86	0.62	98250	90	1.55
31	4	19	2.1	0.4	15000	125	1
								32	19	20	1.58	0.3	11250	125	0.75
33	12	20	1.58	0.3	11250	125	0.75
								34	12	21	1.05	0.2	7500	125	0.5
35	21	22	1.05	0.2	7500	125	0.5
								36	8	23	2.21	0.42	15750	125	1.05
37	11	23	1.05	0.2	7500	125	0.5
								38	8	22	1.37	0.26	9750	125	0.65
39	3	24	1.58	0.3	11250	125	0.75
								40	9	25	0.95	0.18	6750	125	0.45
41	14	25	1.05	0.2	7500	125	0.5
								42	4	24	0.84	0.16	6000	125	0.4

Table 2

From wiring result, can find out, all there is the service area of clear and non-overlapping copies on every loop line road, and the load capacity that every loop line road articulates also meets the restriction of circuit max cap., consequently rational as seen, and meets engineering reality.The present embodiment shows that method of the present invention is under certain calculating scale, comparatively effectively to calculate a feasible cabling scenario, and on electric power GIS platform, reflects intuitively result, thereby raising planning personnel work efficiency.

Claims (5)

1. a distribution network planning method of evolving based on tactful adaptive differential, is characterized in that: described distribution network planning method comprises the following steps:

A1, the result according to substation locating and sizing with following load forecast of distribution create load point, transformer station and branch road to be selected, built branch road element information, and set up the topology rule of corresponding point-point, point-line, line-face on electric power GIS platform;

A2, the element information creating is carried out to pre-service: load point and transformer station are sequentially numbered to branch road to be selected and built branch road serial number, and start of record peripheral node numbering; For geographic barrier, generate buffer zone, carry out buffer zone analysis, find out the circuit corridor that is not suitable for the construction of line;

A3, consider the time value of fund, pay separately capital recovery calculate by single-candidate, take year investment and operation and maintenance cost minimum is target, and objective function is suc as formula (1):

In formula: S ₁, S ₂, S is respectively newly-built sets of lines, built sets of lines and total line collection; ω is a year equivalent recovery coefficient, and λ is the number percent keeping in repair, depreciation accounts for investment cost; l _ithe length of circuit i, f (D _i) for wire diameter be D _ithe cost of circuit unit length, X _ibe the decision variable of i bar circuit, select this circuit as feeder line branch road, X _iget 1, otherwise get 0; g(D _i) for wire diameter be D _ithe resistivity of circuit; P _ifor the power that passes through of circuit i, U _nfor rated voltage; τ _maxthe maximum loss time in year, d is unit electricity price;

In differential evolution algorithm, dimension D is branch road quantity N to be selected _line, population quantity NP=10*D, mutation operator F is the random string of binary characters producing, and crossover operator CR gets 0.1, and end condition is that the optimum individual obtaining after tabu search algorithm is identical with the optimum individual fitness that switching enters before tabu search algorithm; The switching condition that enters tabu search algorithm is that iteration surpasses some generations and optimum individual continuous some generations do not change; The condition that exits tabu search algorithm is that step-length surpasses some steps and optimum individual continuous some generations do not change;

A4, read element information, generating algorithm initial population, evaluates initial population, and make first of population individual for global optimum individual;

A5, judge whether to reach end condition, if so, evolve and stop, using optimum individual as separating output, go to step A10; If not, continue algorithm, enter steps A 6;

A6, judge whether to need update strategy to select probability, if so, upgrade probability;

A7, according to the selection probability of Different Strategies is random, select a kind of strategy to make a variation and interlace operation, and carry out structural constraint verification, if individuality does not meet constraint, proceed to steps A 11; If meet constraint, enter steps A 8;

A8, select operation, if the new physical efficiency after variation intersects is replaced old individuality, enter the next generation, corresponding strategy is when cumulative 1 time of former generation number of success, otherwise cumulative 1 time of the frequency of failure;

A9, travel through current population, find out optimum individual, judge whether current optimum individual is better than global optimum's individuality, if replace, otherwise retain, enter afterwards steps A 5;

A10, the optimum solution that algorithm is obtained are decoded, and planning circuit is drawn out in the circuit number obtaining according to decoding on electric power GIS platform;

A11, individuality is carried out to structure repair, make it meet Radial network structure, reparation completes, and proceeds to steps A 8.

2. a kind of distribution network planning method of evolving based on tactful adaptive differential as claimed in claim 1, it is characterized in that: in described steps A 4, read the positional information of load point and payload, the positional information of transformer station, branch road to be selected, built branch road, generating at random length is N _linestring of binary characters, and guarantee that the quantity of " 1 " in character string is N _node, the function of applying mechanically (1) formula calculates each individual target function value.

3. a kind of distribution network planning method of evolving based on tactful adaptive differential as claimed in claim 1 or 2, it is characterized in that: in described steps A 6, it is 10 that statistical algebra LP is set, upgrading algebraically is 15, be every experience 15 generation iteration, just statistics is worked as former generation G failed, the number of success of each strategy in 10 generations of backstepping forward, and calculates the selection probability of corresponding strategy, suc as formula (2), (3), wherein S _k,Grepresent tactful k G for time the probability of success; Ns _k,g, nf _k,grepresent that respectively tactful k g is for successful, failed number of times; ε is 0.01, in order to prevent that the tactful probability of success from being 0; p _k,Grepresent the tactful k G selection probability in generation;

。

4. a kind of distribution network planning method of evolving based on tactful adaptive differential as claimed in claim 1 or 2, is characterized in that: in described steps A 7, (4), (5), (6) 3 kinds of Mutation Strategies are set,

v _i,j＝x _r1,j+F·(x _r2,j-x _r3,j) (3)

v _i,j＝x _i,j+F·(x _best,j-x _i,j)+F·(x _r1,j-x _r2,j)+F·(x _r3,j-x _r4,j) (4)

v _i,j＝x _i,j+F·(x _r2,j-x _r3,j)+F·(x _r4,j-x _r5,j) (5)

Mutation operation is to each target individual X _i,G, i=1,2 ..., NP, produces variation individuality according to probability selection strategy, wherein, and the random sequence number r selecting in strategy ₁, r ₂, r ₃, r ₄, r ₅different, and r ₁, r ₂, r ₃, r ₄, r ₅i is also different from target individual sequence number; X in strategy (5) _{best, j}for optimum individual, in three kinds of strategies, arithmetic operator is logical operator, " " presentation logic or, " " presentation logic XOR, "+" presentation logic with;

Then according to formula (7), (8), (9), carry out interlace operation, wherein randb (j) is random j the estimated value generating between [0,1], and rnbr (i) is a random sequence of selecting

U _i,G+1＝(U _1i,G+1,U _2i,G+1,L,U _Di,G+1) (6)

(i＝1,2,L,NP,j＝1,2,L,D) (8)

Individuality is carried out to connectedness, radiativity structural constraint verification, if do not meet constraint, do not proceed to steps A 11 and carry out structure repair.

5. a kind of distribution network planning method of evolving based on tactful adaptive differential as claimed in claim 1 or 2, is characterized in that: in described steps A 11, first to not meeting the individuality of radiativity structure, carry out number of branches reparation, make N _branch=N _node-1; Then degree of depth traversal is individual sets, and recording individual isolates part, if individuality exists closed loop, records closed loop branch road; After having traveled through, interrupt at random a branch road in closed loop, and the isolated part of individuality is coupled together.