CN115829170B - Driving scheme optimization method, driving scheme optimization system and storage medium - Google Patents
Driving scheme optimization method, driving scheme optimization system and storage medium Download PDFInfo
- Publication number
- CN115829170B CN115829170B CN202310127795.1A CN202310127795A CN115829170B CN 115829170 B CN115829170 B CN 115829170B CN 202310127795 A CN202310127795 A CN 202310127795A CN 115829170 B CN115829170 B CN 115829170B
- Authority
- CN
- China
- Prior art keywords
- chromosomes
- chromosome
- target
- travel
- sub
- 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.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Navigation (AREA)
Abstract
The application provides a driving scheme optimization method, a driving scheme optimization system and a storage medium, wherein the driving scheme optimization method comprises the following steps: determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server; and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm by taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions. The technical scheme provided by the application can effectively combine the genetic algorithm with big data information, accurately and efficiently provide a more energy-saving driving scheme, and thus can better solve the problem of energy conservation and emission reduction of the commercial vehicle industry.
Description
Technical Field
The present disclosure relates to an information processing method based on a specific computing model, and more particularly, to a driving scheme optimization method, system, and storage medium.
Background
In recent years, the transportation industry of China is vigorously developed. In the transportation of persons and goods by means of vehicles, passenger or freight system operators and passenger or freight car drivers often desire to obtain a driving scheme with the lowest energy consumption of the vehicle on the transportation line in case of meeting the requirements of the passenger or freight time limit. In the after market field of commercial vehicles, there are currently already proposals for improving driving level by driving behavior evaluation guidance technology to promote vehicle fuel economy. However, in a large background of energy saving and emission reduction, improving the economic driving effect of a vehicle by merely evaluating the driving behavior to improve the driving level has not satisfied the demands of current social development. The market has higher requirements for new generation driving scheme optimization technical schemes.
Disclosure of Invention
The application provides a driving scheme optimization method, which comprises the following steps: determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server; and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm by taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions.
According to an embodiment of the present application, before determining a vehicle speed interval of each section of travel of the target vehicle on the target road, the driving scheme optimization method further includes: and dividing the target line into a plurality of sections of strokes based on the high-speed service area information and a preset mileage threshold.
According to an embodiment of the present application, dividing the target line into multiple routes based on the high-speed service area information and a preset mileage threshold includes: dividing the target line into a plurality of sections of first strokes by using a high-speed service area as a segmentation point; and dividing the first travel into a plurality of sections of second travel in response to any one of the plurality of sections of first travel being greater than a preset mileage threshold upper limit.
According to an embodiment of the present application, dividing the first pass into multiple segments of the second pass includes: dividing the first journey into a plurality of sections of sub-journey according to the ascending slope, the flat road and the descending slope; sequentially judging whether the divided sub-strokes are smaller than a preset mileage threshold lower limit according to the stroke sequence, and sequentially merging the sub-strokes into the subsequent sub-strokes in response to the fact that the divided sub-strokes are smaller than the preset mileage threshold lower limit until each merged sub-stroke is larger than or equal to the preset mileage threshold lower limit; wherein the last sub-trip is merged into the previous sub-trip in response to the last sub-trip being less than a preset mileage threshold lower limit.
According to an embodiment of the present application, determining, by a genetic algorithm, a most energy-efficient driving scheme for the target vehicle to complete the target route includes: randomly setting an initial vehicle speed for each section of travel in a vehicle speed section of each section of travel on the target road; selecting a combination of initial vehicle speeds of the sections of strokes, the total duration of which is smaller than the maximum time limit, of which the target vehicle completes the target line, as a combination of a set of initial vehicle speeds in an initial vehicle speed set, wherein the initial vehicle speed set comprises a combination of M sets of initial vehicle speeds; setting binary code values of initial vehicle speeds of all sections of strokes in each group of initial vehicle speed combinations in the initial vehicle speed setting set as all sections of gene values of one chromosome, thereby obtaining M first-generation chromosomes; determining the fitness of each chromosome based on the total energy consumption value corresponding to each chromosome in the M first-generation chromosomes; sequentially selecting M chromosomes to be crossed from M chromosomes of the current generation through a roulette selection algorithm, wherein each chromosome in the M chromosomes can be repeatedly selected; randomly crossing the M chromosomes to be crossed to generate M crossed chromosomes; performing mutation operation on the M crossed chromosomes to generate M second-generation chromosomes; carrying out the roulette selection operation, the crossover operation and the mutation operation on the M second-generation chromosomes until M Nth-generation chromosomes are generated; selecting one chromosome with highest fitness from the first generation chromosome to the Nth generation chromosome; and decoding each segment of gene of one chromosome with the highest selected fitness into the target vehicle speed of each segment of journey.
According to an embodiment of the present application, randomly setting an initial vehicle speed for each of the runs in a vehicle speed section of each of the runs on the target road includes: and randomly setting an initial vehicle speed for each section of travel in a vehicle speed section of each section of travel on the target line through a quasi-random Sobol sequence.
According to an embodiment of the present application, determining the fitness of each chromosome based on the total energy consumption value corresponding to each chromosome in the M first-generation chromosomes includes: determining the total oil consumption Qi of the target vehicle for completing the target line based on each segment of genes of the ith chromosome in the M first-generation chromosomes; according to
And determining the fitness Ai of the ith chromosome.
According to an embodiment of the present application, sequentially selecting M chromosomes to be crossed from M chromosomes of a current generation by a roulette selection algorithm includes: determining the selected normalized probability of each chromosome based on the fitness of each chromosome in the M chromosomes of the current generation; selecting M chromosomes based on the normalized probability of each chromosome being selected; the selected M chromosomes are sequentially listed as the M chromosomes to be crossed, wherein each of the M chromosomes of the current generation can be repeatedly selected.
According to an embodiment of the present application, performing random crossover operation on the M chromosomes to be crossed, and generating M crossed chromosomes includes: pairing the chromosomes to be crossed of the M times in pairs according to the selected sequence; determining whether to cross paired chromosomes according to the adaptive cross probability function; in response to determining to cross the paired chromosomes, performing random cross operations on the paired chromosomes to form crossed chromosomes; in response to determining that the paired chromosomes are not crossed, directly determining the paired chromosomes as the crossed chromosomes; wherein the adaptive cross probability function P c The method comprises the following steps:
P c1 and P c2 As an empirical parameter, f' is the fitness of a chromosome with greater fitness among the two paired chromosomes, f max Fitness for the most adaptable chromosome among the M chromosomes of the current generation, f avg Is the average fitness of the M chromosomes of the current generation.
According to an embodiment of the present application, performing a mutation operation on the M crossed chromosomes, and generating M second-generation chromosomes includes: determining whether to mutate the chromosome according to the adaptive mutation probability function; generating a mutated chromosome by randomly flipping binary codes of one or more genes of the chromosome in response to determining to mutate the chromosome; sound box Directly determining the chromosome as the mutated chromosome in response to determining that the chromosome is not mutated; wherein the adaptive variation probability function P m The method comprises the following steps:
P m1 and P m2 As an empirical parameter, f is the fitness of the chromosome to be mutated.
According to an embodiment of the present application, P c1 =0.85，P c2 =0.55，P m1 =0.1，P m2 =0.002。
According to an embodiment of the present application, the driving scheme optimization method further includes: after mutation operation is carried out on M crossed chromosomes of each generation, carrying out gene optimization on K chromosomes with highest fitness in M mutated chromosomes of the current generation by a simulated annealing method, and taking the K chromosomes as initial chromosomes of next roulette selection operation, crossover operation and mutation operation.
The application also provides a driving scheme optimizing system, which comprises: a memory storing executable instructions; and one or more processors in communication with the memory to execute the executable instructions to: determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server; and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm by taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions.
The present application also provides a computer-readable storage medium for driving scheme optimization, characterized in that the computer-readable storage medium stores executable instructions executable by one or more processors to perform operations comprising: determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server; and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm by taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions.
The technical scheme provided by the application can effectively combine the genetic algorithm with big data information, accurately and efficiently provide a more energy-saving driving scheme, and thus can better solve the problem of energy conservation and emission reduction of the commercial vehicle industry.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings, in which:
Fig. 1 is a schematic diagram of a driving scheme optimization method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a specific process for optimizing a driving scheme using genetic algorithms according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a roulette selection algorithm according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a crossover algorithm according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a mutation algorithm according to an embodiment of the present application; and
fig. 6 is a schematic structural diagram of a driving scheme optimizing system according to an embodiment of the present application.
Description of the embodiments
For a better understanding of the present application, a more detailed description of the technical solution of the present application will be made with reference to the accompanying drawings. It should be understood that the detailed description is merely illustrative of exemplary embodiments of the application and is not intended to limit the scope of the application in any way. Like reference numerals refer to like elements throughout the specification. The expression "and/or" includes any or all combinations of one or more of the associated listed items.
In the drawings, the size, proportion, and shape of the drawings have been slightly adjusted for convenience of explanation. The figures are merely examples and are not drawn to scale. As used herein, the terms "about," "approximately," and similar terms are used as terms of a table approximation, not as terms of a table degree, and are intended to account for inherent deviations in measured or calculated values that will be recognized by one of ordinary skill in the art.
It will be further understood that terms such as "comprises," "comprising," "includes," "including," "having," "contains," and/or "containing" are open-ended, rather than closed-ended, terms that specify the presence of the stated features, elements, and/or components, but do not preclude the presence or addition of one or more other features, elements, components, and/or groups thereof. Furthermore, when a statement such as "at least one of the list of features" appears after the list of features, it modifies the entire list of features rather than just a single feature in the list. Furthermore, when describing embodiments of the present application, use of "may" means "one or more embodiments of the present application. Also, the term "exemplary" is intended to refer to an example or illustration.
Unless otherwise defined, all terms (including engineering and technical terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
In addition, features in the embodiments and examples of the present application may be combined with each other without conflict. In addition, unless explicitly defined or contradicted by context, the particular steps included in the methods described herein are not necessarily limited to the order described, but may be performed in any order or in parallel. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic diagram of a driving scheme optimization method according to an embodiment of the present application.
Referring to fig. 1, a driving scheme optimization method 1000 is provided. According to the embodiment of the application, the driving scheme optimizing method comprises the following steps of.
In step S1010, a vehicle speed section of each trip of the target vehicle on the target road is determined based on the operation data of the vehicles of the same type as the target vehicle retrieved from the big data cluster server. The vehicle operation data may be the same type of vehicle operation data including vehicle identification, vehicle operation time, longitude, latitude, direction, altitude, vehicle speed, rotation speed, torque, accelerator opening, brake, load, and the like. The vehicle operation data can be obtained from the big data cluster server through a big data extraction technology, and the big data extraction method is not limited in the application. The vehicle speed section of each trip may be vehicle speed section information calculated by the central server or the vehicle-mounted computer based on load information, power information, gradient information of each trip of the target line and vehicle speed data of the same type of vehicles retrieved from the big data cluster server, and generally includes a lower vehicle speed limit and an upper vehicle speed limit of the trip. According to the method and the device, the vehicle speed interval of each travel can be determined after some interference data in the vehicle operation data are removed. The operation data of the vehicles with the same type as the target vehicle needs to be retrieved from the big data cluster server in order to avoid setting vehicle speed suggestions without reference value for the target vehicle in the driving scheme optimization process. For example, for a steep uphill road section or a mountain road section with more curves, if a road section condition is ignored, a vehicle speed advice is set for the target vehicle, such a vehicle speed advice may exceed the traveling capability of the target vehicle. Therefore, referring to the running data of the vehicle of the same type as the target vehicle, it is possible to avoid deviation of the finally set vehicle speed advice from the actual road condition.
In step S1020, a vehicle speed interval of each travel of the target vehicle on the target line and a maximum time limit of the target vehicle for completing the target line are taken as constraint conditions, and a most energy-saving driving scheme of the target vehicle for completing the target line is determined through a genetic algorithm. The maximum time limit for a target line is typically determined by the mission time limit requirements of passenger or freight transport. The genetic algorithm is adopted as a calculation model as a whole, the input quantity of the genetic algorithm can be a vehicle speed interval of each section of travel of the target vehicle on the target line, the longest time limit of the target vehicle for completing the target line, and the output quantity of the genetic algorithm is the longest energy-saving vehicle speed value of each section of travel of the target vehicle for completing the target line. The genetic algorithm is an algorithm for globally searching for an optimal solution for simulating the win or lose of individuals in a natural population. Which may seek an optimal solution through multiple iterations (i.e., "evolutions") under defined conditions. The technical scheme provided by the application can effectively combine the genetic algorithm with big data information, accurately and efficiently provide a more energy-saving driving scheme, and thus can better solve the problem of energy conservation and emission reduction of the commercial vehicle industry.
As described above, in order to avoid deviation of the finally set vehicle speed proposal from the actual road condition, the technical scheme provided by the application refers to the running data of the vehicles with the same type as the target vehicle, so as to determine the vehicle speed section of each section of travel of the target vehicle on the target road. In order to provide more accurate reference information and give consideration to calculation efficiency, the application proposes dividing the target line into multiple sections of strokes based on high-speed service area information and a preset mileage threshold.
More specifically, according to the present application, the target line may be first divided into multiple strokes in advance using the high-speed service area as a preliminary segmentation point. Such travel division, while convenient and quick, lacks some accuracy. This is because the distance between the high-speed service areas may have a large difference, the spacing between part of the high-speed service areas may be only tens of kilometers, and the spacing between part of the high-speed service areas may reach hundreds of kilometers. Thus, according to an improved solution of the present application, if any one of the first strokes is greater than a preset mileage threshold upper limit (for example, 100 km), the first stroke is divided into a plurality of sections of second strokes. This division may be performed as follows.
First, the first journey exceeding the upper limit of the preset mileage threshold is divided into a plurality of sub-journeys according to the gradient. For example, such sub-trips may be an uphill section, a flat section, a downhill section, a flat section, an uphill section, in that order.
And then, judging whether the divided sub-strokes are smaller than a preset mileage threshold lower limit according to the stroke sequence. For example, if a first segment of sub-strokes, i.e., less than a preset mileage threshold lower limit, the segment of sub-strokes is merged with the next segment of sub-strokes. If the combined sub-stroke is still smaller than the preset mileage threshold lower limit, the combined sub-stroke is continuously combined with the next sub-stroke until the combined sub-stroke is larger than or equal to the preset mileage threshold lower limit.
And continuing the sub-travel combining process according to the travel sequence until each combined sub-travel is greater than or equal to the preset mileage threshold lower limit.
However, in some partitioning processes, it is possible that the last sub-trip is still eventually less than the preset mileage threshold lower limit because it has no subsequent sub-trips. In this case it may be combined with the previous sub-stroke.
The difference in distance between the strokes divided according to the above rule is greatly reduced, so that the referential property of determining the target vehicle speed section based on the operation data retrieved from the big data cluster server is also greatly improved.
Fig. 2 is a schematic diagram of a specific process of optimizing a driving scheme using a genetic algorithm according to an embodiment of the present application.
Referring to FIG. 2, the present application proposes a genetic algorithm 2000 that optimizes an automobile operating scheme. According to an embodiment of the present application, a genetic algorithm for optimizing an automotive operating regime includes the following steps.
In step S2010, an initial vehicle speed is randomly set for each of the runs in a vehicle speed section of each of the runs on the target road.
For example, the initial vehicle speed may be randomly set for each trip in a vehicle speed section of each trip on the target line by a quasi-random Sobol sequence. The quasi-random Sobol sequence is a low degree of variability sequence in exchange for an improvement in individual uniformity at the expense of individual randomness. In this application, a pseudo-random Sobol sequence is used to generate a random number Qn, where Qn e [0,1]. The initial vehicle speed Vn of each section of travel is determined by combining the random number Qn with the vehicle speed interval of each section of travel as follows:
Vn=Vmin+Qn×(Vmax-Vmin)。
in step S2020, a combination of initial vehicle speeds for each of the runs for which the total length of time the target vehicle completes the target route is less than the maximum time limit is selected as a combination of one set of initial vehicle speeds in an initialization vehicle speed set including a combination of M sets of initial vehicle speeds.
After the above pseudo-random Sobol sequence is adopted to generate the random number Qn and the initial vehicle speed Vn, it is also necessary to check whether the combination of such initial vehicle speeds Vn can meet the total duration requirement of the target line, and if the combination of initial vehicle speeds Vn meets the vehicle speed interval requirement of each section of travel, the combination of the initial vehicle speeds Vn is not satisfactory if the target vehicle cannot complete the target line within the longest time limit according to the combination of such initial vehicle speeds Vn. Finally, a combination of M groups of initial vehicle speeds can be selected from the combination of initial vehicle speeds Vn meeting the maximum time limit requirement as the basis of the subsequent genetic algorithm 'evolution'. M is also referred to as the number of individuals in a population, or as the population size. According to the present application, M may be set to an even number between 50 and 70 in order to achieve both accuracy and computational efficiency.
In step S2030, binary coded values of the initial vehicle speeds of the respective segments of the trips in the combination of each set of initial vehicle speeds in the initial vehicle speed setting set are set as the segment gene values of one chromosome, thereby obtaining M first-generation chromosomes.
Through the binary code, the driving scheme can be digitized, so that the driving scheme optimization method is converted into a mathematical problem for solving the optimal solution. Assuming that the highest vehicle speed that the target vehicle can reach is 100km/h, binary encoding of the initial vehicle speed requires 7-bit binary numbers. If the target line has P strokes in total, the length of one chromosome is 7×P. Through the transformation, the initial vehicle speed is transformed into a gene in biology, and the problem of solving the optimal vehicle speed combination can be transformed into the problem of solving the optimal chromosome by utilizing a genetic algorithm.
In step S2040, fitness of each of the M first-generation chromosomes is determined based on the total energy consumption value corresponding to each of the chromosomes.
Fitness functions are functions used in genetic algorithms to evaluate the "quality" of chromosomes (or "population individuals"). Higher fitness means higher chromosome quality, the mathematical solution represented by the chromosome is closer to the optimal solution. In the driving scheme optimization problem, the total energy consumption value of the target vehicle for completing the target line is an important evaluation factor of the driving scheme. It is therefore a reasonable solution to determine the fitness function based on the total energy consumption value that the target vehicle needs to consume to complete the target line.
In the following, a fuel vehicle is used as an example to show how the fitness function is determined.
The present application shows, by way of example, the calculation formula of the total fuel consumption Q:
wherein: q is the total fuel consumption value of the target line completed by the target vehicle, and the unit is L; q (Q) j The fuel consumption value of a small path (a mathematical trace) of a target line is completed for a target vehicle, and the unit is L; pj is the operating power of the target vehicle during the short journey, in kW; ge is specific fuel consumption, namely the weight of fuel required by unit energy consumption, and the unit is g/kWh; t is the time of the target vehicle to complete the short distance in seconds(s); ρ is the fuel density in g/ml.
The above formula for Pj is:
where Vj is the speed of the target vehicle at time j in units ofkm/h。F Driving of The function of the vehicle speed Vj may be approximately converted based on the parameter information of the target vehicle. Thus, the total fuel consumption Q may be estimated based on the vehicle speed value for each stroke.
The fitness of each chromosome can be determined according to the following formula:
wherein: ai is the fitness of the ith chromosome;Qithe total oil consumption of the target line is completed by the target vehicle according to the combination of the vehicle speeds determined by the ith chromosome.
In step S2050, after the fitness of each chromosome is determined, M chromosomes to be crossed may be sequentially selected from M chromosomes of the current generation by the roulette selection algorithm. Wherein each of the M chromosomes of the current generation can be repeatedly selected.
Referring to the schematic diagram of roulette wheel in the roulette selection algorithm shown in fig. 3, the normalized probability of each chromosome being selected can be determined according to the fitness Ai of each chromosome in the M chromosomes of the current generation. The larger the fitness Ai of the chromosome, the larger the normalized probability, and the larger the area occupied in the wheel. Then, a pointer is set somewhere on the wheel. In this case, each time the wheel is turned, the pointer points to a particular chromosome, e.g. E1, E2, ei or E M . Each of the M chromosomes may be selected repeatedly. Thus, after M roulette rotations, M chromosome to be crossed can be selected.
In step S2060, random crossover operations are performed on M chromosomes to be crossed, and M crossed chromosomes are generated.
After selecting M chromosomes to be crossed, the chromosomes can be paired according to the selected order. For example, chromosome E1 selected for the first time is paired with chromosome E2 selected for the second time; pairing the chromosome E3 selected for the third time with the chromosome E4 selected for the fourth time; chromosome E selected at M-1 th time M-1 Dyeing selected from M th timeBody E M Pairing. Then, referring to FIG. 4, one or more pairs of genes of paired chromosomes are crossed. For example, the 1 st gene of chromosome E1 and the 1 st gene of chromosome E2 are interchanged with each other; for another example, the 1 st gene and the 4 th gene of chromosome E1 are interchanged with the 1 st gene and the 4 th gene of chromosome E2, respectively. The chromosomes E1 'and E2' obtained after the exchange are crossed chromosomes.
According to another embodiment of the present application, verification of the chromosome is also required after crossing. Specifically, after the intersection, it is necessary to determine whether the target vehicle can complete the target route within the maximum time limit according to the speed per hour of each segment of the journey corresponding to the chromosome after the intersection. If not, randomly crossing again the corresponding paired chromosomes until crossed chromosomes are obtained that meet the maximum time limit.
According to another embodiment of the present application, it is also determined first whether to cross paired chromosomes before crossing paired chromosomes. In particular, it may be determined whether to cross paired chromosomes according to an adaptive crossover probability function. If it is finally determined that the paired chromosomes are crossed, performing a random crossing operation on the paired chromosomes as described above with reference to fig. 4, forming crossed chromosomes; if it is finally determined that the paired chromosomes are not crossed, the paired chromosomes are directly determined as the crossed chromosomes.
The specific form of the adaptive crossover probability function is as follows:
wherein P is c1 And P c2 Is an empirical parameter, e.g. P c1 =0.85，P c2 =0.55. f' is the fitness of the chromosome with larger fitness of the two paired chromosomes, f max Fitness for the most adaptable chromosome among the M chromosomes of the current generation, f avg Is the average fitness of the M chromosomes of the current generation.
In step S2070, mutation operation is performed on M crossed chromosomes to generate M second-generation chromosomes.
The mutation operation is an operation of rewriting a gene value of one or more genes of a chromosome. The operation is to break the constraint of the original gene combination, so that not only the local optimal solution but also the global optimal solution can be found.
Referring to fig. 5, a mutation operation may be performed on each of M crossed chromosomes. During the mutation operation, one or more genes of the chromosome may be randomly selected for mutation. For example, in the example shown in fig. 5, mutation operation is performed on the first gene G1 of one chromosome after crossover. During the mutation operation, each gene value (i.e., binary code value of the velocity) of the gene G1 is inverted by "0" and "1", thereby obtaining a mutated gene G1'. The mutated chromosome is consistent with the genes before mutation except the 1 st gene G1; the 1 st gene G1' of the mutated chromosome has a gene value opposite to the original gene G1.
According to another embodiment of the present application, verification of the mutated chromosome is also required after mutation. Specifically, after mutation, it is necessary to determine whether or not the target vehicle can complete the target route within the maximum time limit according to the time rate of each stroke corresponding to the mutated chromosome. If not, the random mutation operation is carried out on the corresponding chromosome again until a mutated chromosome which can meet the longest time limit is obtained.
According to another embodiment of the present application, it is also determined whether a mutation operation is performed on a chromosome before the mutation operation is performed. Specifically, whether to mutate the chromosome may be determined according to an adaptive mutation probability function. If it is finally determined to mutate the chromosome, generating a mutated chromosome by randomly flipping binary codes of one or more genes of the chromosome by the method described with reference to fig. 5; if it is finally determined that the chromosome is not mutated, the chromosome is directly determined as the mutated chromosome.
The adaptive variation probability function Pm is:
P m1 and P m2 Is an empirical parameter, e.g. P m1 =0.1，P m2 =0.002. f is the fitness of the chromosome to be mutated.
In step S2080, the roulette selection, crossover and mutation operations described above are performed on the M second-generation chromosomes until M N-th-generation chromosomes are produced. Through multi-generation evolution, the global optimal solution can be gradually approximated. According to the application, N may be a natural number between 400 and 500 for both accuracy and computational efficiency.
In step S2090, one chromosome having the highest fitness is selected from the first-generation chromosomes to the nth-generation chromosomes.
In each evolution, M evolved chromosomes (i.e., crossing and mutated chromosomes) are obtained. After evolution of the N generations, mxn chromosomes can be obtained. Therefore, one chromosome having the highest fitness can be selected from the m×n chromosomes.
In step S2100, each segment of the gene of one chromosome having the highest fitness selected is decoded into the target vehicle speed for each segment of the route. Due to the negative correlation between the fitness and the energy consumption, after each segment of gene of one chromosome with the highest fitness is decoded into the target vehicle speed of each segment of journey, the vehicle speed combination scheme with the lowest energy consumption of the target vehicle for completing the target line can be obtained.
According to another embodiment of the present application, after mutation operation is performed on M crossed chromosomes of each generation, gene optimization may be performed on K chromosomes with the highest fitness among M mutated chromosomes of the current generation by a simulated annealing method, so as to serve as initial chromosomes of the next roulette selection operation, the crossover operation and the mutation operation.
The simulated annealing method is a random optimizing algorithm based on Monte-Carlo iterative solving strategy, is a probability solving algorithm, and has the advantages of higher calculation efficiency and stronger local searching capability. The algorithm is added in the evolution of the genetic algorithm, so that the efficiency and the quality of the genetic algorithm can be effectively improved, and the iteration times of the genetic algorithm are reduced. According to the method, parameters such as initial temperature Tb, final temperature Tc, cooling speed Vr and the like in the simulated annealing algorithm can be adjusted to carry out gene optimization on K chromosomes with highest fitness in each generation of chromosomes.
The application also provides a driving scheme optimizing system which can be realized in the forms of a mobile terminal, a Personal Computer (PC), a tablet personal computer, a server and the like. Referring now to FIG. 6, a schematic diagram of a driving scheme optimization system suitable for use in implementing embodiments of the present application is shown.
As shown in fig. 6, the computer system includes one or more processors, communication sections, etc., such as: one or more Central Processing Units (CPUs) 601, and/or one or more image processors (GPUs) 613, etc., the processors may perform various suitable actions and processes according to executable instructions stored in a read-only memory (ROM) 602 or loaded from a storage 608 into a Random Access Memory (RAM) 603. The communication portion 612 may include, but is not limited to, a network card, which may include, but is not limited to, a IB (Infiniband) network card.
The processor may communicate with the ROM 602 and/or the RAM 603 to execute the executable instructions, and is connected to the communication portion 612 through the bus 604, and communicates with other target devices through the communication portion 612, so as to perform operations corresponding to any of the methods set forth in the embodiments of the present application, for example: determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server; and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm by taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions.
In addition, in the RAM 603, various programs and data necessary for device operation can also be stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. In the case of RAM 603, ROM 602 is an optional module. The RAM 603 stores executable instructions that cause the CPU 601 to execute operations corresponding to the above-described driving scenario optimization method, or write executable instructions into the ROM 602 at the time of execution. An input/output interface (I/O interface) 605 is also connected to the bus 604. The communication unit 612 may be integrally provided or may be provided with a plurality of sub-modules (e.g., a plurality of IB network cards) and be connected to a bus link.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage unit 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, and the like, is mounted on the drive 610 as needed.
It should be noted that the architecture shown in fig. 6 is only an alternative implementation, and in a specific practical process, the number and types of components in fig. 6 may be selected, deleted, added or replaced according to actual needs; in the setting of different functional components, implementation manners such as separation setting or integration setting may be adopted, for example, the GPU and the CPU may be separately set or the GPU may be integrated on the CPU, the communication portion 612 may be separately set, may be integrally set on the CPU or the GPU, and the like. Such alternative embodiments fall within the scope of the present disclosure.
In particular, the process described with reference to fig. 1 may be implemented as a computer program product according to the present application. For example, the present application proposes a computer program product comprising computer readable instructions which, when executed by a processor, implement the operations of: determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server; and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm by taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions.
In such embodiments, the computer program product may be downloaded and installed from a network via the communication portion 609 and/or read and installed from the removable medium 611. When being executed by the CPU 601, performs the above-described functions defined in the methods of the present application.
The technical solutions of the present application may be implemented in many ways. For example, the techniques of this application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The order of steps used to describe the method is provided only for the purpose of more clearly describing the technical solution. The method steps of the present application are not limited to the order specifically described above unless specifically limited. Furthermore, in some embodiments, the present application may also be implemented as a storage medium storing a computer program product.
The above description is merely illustrative of the implementations of the application and of the principles of the technology applied. It should be understood by those skilled in the art that the scope of protection referred to in this application is not limited to the specific combination of the above technical features, but also encompasses other technical solutions formed by any combination of the above technical features or their equivalents without departing from the technical concept. Such as the above-described features and technical features having similar functions (but not limited to) disclosed in the present application are replaced with each other.
Claims (11)
1. The driving scheme optimizing method is characterized by comprising the following steps of:
dividing a target line into a plurality of sections of first strokes by using the high-speed service area as a segmentation point;
dividing the first travel into a plurality of sections of second travel in response to any one of the plurality of sections of first travel being greater than a preset mileage threshold upper limit;
determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server;
taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions, and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm;
wherein dividing the first stroke into a plurality of segments of second strokes comprises:
dividing the first journey into a plurality of sections of sub-journey according to the ascending slope, the flat road and the descending slope;
sequentially judging whether the divided sub-strokes are smaller than a preset mileage threshold lower limit according to the stroke sequence, and sequentially merging the sub-strokes into the subsequent sub-strokes in response to the fact that the divided sub-strokes are smaller than the preset mileage threshold lower limit until each merged sub-stroke is larger than or equal to the preset mileage threshold lower limit;
Wherein the last sub-trip is merged into the previous sub-trip in response to the last sub-trip being less than a preset mileage threshold lower limit.
2. The driving scheme optimizing method according to claim 1, wherein determining, by a genetic algorithm, a most energy-efficient driving scheme for the target vehicle to complete the target route includes:
randomly setting an initial vehicle speed for each section of travel in a vehicle speed section of each section of travel on the target road;
selecting a combination of initial vehicle speeds of the sections of strokes, the total duration of which is smaller than the maximum time limit, of which the target vehicle completes the target line, as a combination of a set of initial vehicle speeds in an initial vehicle speed set, wherein the initial vehicle speed set comprises a combination of M sets of initial vehicle speeds;
setting binary code values of initial vehicle speeds of all sections of strokes in each group of initial vehicle speed combinations in the initial vehicle speed setting set as all sections of gene values of one chromosome, thereby obtaining M first-generation chromosomes;
determining the fitness of each chromosome based on the total energy consumption value corresponding to each chromosome in the M first-generation chromosomes;
sequentially selecting M chromosomes to be crossed from M chromosomes of the current generation through a roulette selection algorithm, wherein each chromosome in the M chromosomes can be repeatedly selected;
Randomly crossing the M chromosomes to be crossed to generate M crossed chromosomes;
performing mutation operation on the M crossed chromosomes to generate M second-generation chromosomes;
carrying out the roulette selection operation, the crossover operation and the mutation operation on the M second-generation chromosomes until M Nth-generation chromosomes are generated;
selecting one chromosome with highest fitness from the first generation chromosome to the Nth generation chromosome;
and decoding each segment of gene of one chromosome with the highest selected fitness into the target vehicle speed of each segment of journey.
3. The driving scheme optimizing method according to claim 2, wherein randomly setting an initial vehicle speed for each of the runs in a vehicle speed section of each of the runs on the target road includes:
and randomly setting an initial vehicle speed for each section of travel in a vehicle speed section of each section of travel on the target line through a quasi-random Sobol sequence.
4. The driving scheme optimization method according to claim 2, wherein determining fitness of each chromosome based on the total energy consumption value corresponding to each chromosome in the M first-generation chromosomes comprises:
Determining the total oil consumption Qi of the target vehicle for completing the target line based on each segment of genes of the ith chromosome in the M first-generation chromosomes;
according to
And determining the fitness Ai of the ith chromosome.
5. The driving scheme optimization method according to claim 2, wherein sequentially selecting M chromosomes to be crossed from M chromosomes of a current generation by a roulette selection algorithm comprises:
determining the selected normalized probability of each chromosome based on the fitness of each chromosome in the M chromosomes of the current generation;
selecting M chromosomes based on the normalized probability of each chromosome being selected;
the selected M chromosomes are sequentially listed as the M chromosomes to be crossed, wherein each of the M chromosomes of the current generation can be repeatedly selected.
6. The driving scheme optimizing method according to claim 5, wherein performing random crossover operation on the M chromosomes to be crossed, generating M crossed chromosomes includes:
pairing the chromosomes to be crossed of the M times in pairs according to the selected sequence;
determining whether to cross paired chromosomes according to the adaptive cross probability function;
In response to determining to cross the paired chromosomes, performing random cross operations on the paired chromosomes to form crossed chromosomes;
in response to determining that the paired chromosomes are not crossed, directly determining the paired chromosomes as the crossed chromosomes;
wherein the adaptive cross probability function P c The method comprises the following steps:
P c1 and P c2 As an empirical parameter, f' is the fitness of a chromosome with greater fitness among the two paired chromosomes, f max Fitness for the most adaptable chromosome among the M chromosomes of the current generation, f avg Is the average fitness of the M chromosomes of the current generation.
7. The driving scheme optimization method according to claim 6, wherein the performing mutation operation on the M crossed chromosomes to generate M second-generation chromosomes includes:
determining whether to mutate the chromosome according to the adaptive mutation probability function;
generating a mutated chromosome by randomly flipping binary codes of one or more genes of the chromosome in response to determining to mutate the chromosome;
in response to determining that the chromosome is not mutated, directly determining the chromosome as the mutated chromosome;
Wherein the adaptive variation probability function P m The method comprises the following steps:
P m1 and P m2 As an empirical parameter, f is the fitness of the chromosome to be mutated.
8. The driving scheme optimizing method according to claim 7, characterized in that P c1 ＝0.85，P c2 ＝0.55，P m1 ＝0.1，P m2 ＝0.002。
9. The driving scheme optimizing method according to claim 2, characterized in that the driving scheme optimizing method further comprises:
after mutation operation is carried out on M crossed chromosomes of each generation, carrying out gene optimization on K chromosomes with highest fitness in M mutated chromosomes of the current generation by a simulated annealing method, and taking the K chromosomes as initial chromosomes of next roulette selection operation, crossover operation and mutation operation.
10. A driving scheme optimization system, characterized in that the driving scheme optimization system comprises:
a memory storing executable instructions; and
one or more processors in communication with the memory to execute the executable instructions to:
dividing a target line into a plurality of sections of first strokes by using the high-speed service area as a segmentation point;
dividing the first travel into a plurality of sections of second travel in response to any one of the plurality of sections of first travel being greater than a preset mileage threshold upper limit;
Determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server;
taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions, and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm;
wherein dividing the first stroke into a plurality of segments of second strokes comprises:
dividing the first journey into a plurality of sections of sub-journey according to the ascending slope, the flat road and the descending slope;
sequentially judging whether the divided sub-strokes are smaller than a preset mileage threshold lower limit according to the stroke sequence, and sequentially merging the sub-strokes into the subsequent sub-strokes in response to the fact that the divided sub-strokes are smaller than the preset mileage threshold lower limit until each merged sub-stroke is larger than or equal to the preset mileage threshold lower limit;
wherein the last sub-trip is merged into the previous sub-trip in response to the last sub-trip being less than a preset mileage threshold lower limit.
11. A computer-readable storage medium for driving scheme optimization, the computer-readable storage medium storing executable instructions executable by one or more processors to perform operations comprising:
Dividing a target line into a plurality of sections of first strokes by using the high-speed service area as a segmentation point;
dividing the first travel into a plurality of sections of second travel in response to any one of the plurality of sections of first travel being greater than a preset mileage threshold upper limit;
determining a vehicle speed section of each travel of the target vehicle on a target road based on the operation data of the vehicles with the same type as the target vehicle retrieved from the big data cluster server;
taking a vehicle speed interval of each section of travel of the target vehicle on the target line and the longest time limit of the target vehicle for completing the target line as constraint conditions, and determining the most energy-saving driving scheme of the target vehicle for completing the target line through a genetic algorithm;
wherein dividing the first stroke into a plurality of segments of second strokes comprises:
dividing the first journey into a plurality of sections of sub-journey according to the ascending slope, the flat road and the descending slope;
sequentially judging whether the divided sub-strokes are smaller than a preset mileage threshold lower limit according to the stroke sequence, and sequentially merging the sub-strokes into the subsequent sub-strokes in response to the fact that the divided sub-strokes are smaller than the preset mileage threshold lower limit until each merged sub-stroke is larger than or equal to the preset mileage threshold lower limit;
Wherein the last sub-trip is merged into the previous sub-trip in response to the last sub-trip being less than a preset mileage threshold lower limit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310127795.1A CN115829170B (en) | 2023-02-17 | 2023-02-17 | Driving scheme optimization method, driving scheme optimization system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310127795.1A CN115829170B (en) | 2023-02-17 | 2023-02-17 | Driving scheme optimization method, driving scheme optimization system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115829170A CN115829170A (en) | 2023-03-21 |
| CN115829170B true CN115829170B (en) | 2023-05-12 |
Family
ID=85521744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310127795.1A Active CN115829170B (en) | 2023-02-17 | 2023-02-17 | Driving scheme optimization method, driving scheme optimization system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115829170B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8452509B2 (en) * | 2010-12-23 | 2013-05-28 | Cummins Intellectual Property, Inc. | System and method of vehicle speed-based operational cost optimization |
| CN106503804A (en) * | 2016-10-11 | 2017-03-15 | 南京理工大学 | A kind of train timing energy-saving operation method based on Pareto multi-objective genetic algorithms |
| CN110893853B (en) * | 2018-08-23 | 2021-07-30 | 厦门雅迅网络股份有限公司 | Vehicle control method and system based on front gradient information |
| CN111191813A (en) * | 2019-10-14 | 2020-05-22 | 重庆邮电大学 | Vehicle distribution path optimization method based on cargo load and soft time window limitation |
| CN111145068B (en) * | 2019-12-09 | 2023-09-26 | 南京航空航天大学 | Long-distance high-timeliness economical cruising vehicle speed planning method |
| KR102194962B1 (en) * | 2020-05-20 | 2020-12-24 | 주식회사 네이처모빌리티 | System for providing bigdata based artificial intelligence automatic allocation matching service using assignmanet problem and simulated annealing |
| CN114444843A (en) * | 2021-11-30 | 2022-05-06 | 上海海洋大学 | Agricultural product green logistics distribution vehicle scheduling method and system based on large-scale variable neighborhood search strategy |
-
2023
- 2023-02-17 CN CN202310127795.1A patent/CN115829170B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115829170A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Battery electric vehicle energy consumption prediction for a trip based on route information | |
| TWI638320B (en) | Systems, methods and non-transitory computer-readable storage mediums for recommending an estimated time of arrival | |
| Letnik et al. | Dynamic management of loading bays for energy efficient urban freight deliveries | |
| CN110059875B (en) | Public bicycle demand prediction method based on distributed whale optimization algorithm | |
| JP2014019433A (en) | Hybrid vehicle fuel efficiency improvement using inverse reinforcement learning | |
| CN115953104B (en) | Hybrid fleet scheduling method based on dung beetle optimization algorithm | |
| CN106651213A (en) | Processing method and device for service orders | |
| CN108573600B (en) | Driver behavior induction and local traffic flow optimization method | |
| Tang et al. | Energy-optimal routing for electric vehicles using deep reinforcement learning with transformer | |
| CN116432448B (en) | Variable speed limit optimization method based on intelligent network coupling and driver compliance | |
| Feng et al. | Statistical analysis and prediction of parking behavior | |
| CN115759462A (en) | Charging behavior prediction method and device for electric vehicle user and electronic equipment | |
| CN115422747A (en) | Method and device for calculating discharge amount of pollutants in tail gas of motor vehicle | |
| CN114187489B (en) | Method and device for detecting abnormal driving risk of vehicle, electronic equipment and storage medium | |
| Xiong et al. | Energy management strategy of intelligent plug-in split hybrid electric vehicle based on deep reinforcement learning with optimized path planning algorithm | |
| Lo et al. | A fuel-efficient route plan method based on game theory | |
| CN115829170B (en) | Driving scheme optimization method, driving scheme optimization system and storage medium | |
| CN110766237A (en) | Bus passenger flow prediction method and system based on SPGAPSO-SVM algorithm | |
| Lu et al. | A bi-level distribution mixture framework for unsupervised driving performance evaluation from naturalistic truck driving data | |
| Liu et al. | An improved path planning algorithm based on fuel consumption | |
| Yuan et al. | Study of driving cycle of city tour bus based on coupled GA-K-means and HMM algorithms: a case study in Beijing | |
| CN112766533A (en) | Shared bicycle demand prediction method based on multi-strategy improved GWO _ BP neural network | |
| Kang | Data and Algorithmic Modeling Approaches in Crash Analysis | |
| Hong et al. | Personalized Energy Consumption Prediction of CAEVs With Personal Driving Cycle Selection | |
| Li et al. | Construction of Driving Cycle Based on SOM Clustering Algorithm for Emission Prediction |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |