45 results about "Quantum evolutionary algorithm" patented technology

The invention discloses a method for reconstructing and modeling the uncertainty of a distribution network in a demand response viewing angle, which comprises the following steps: 1) constructing a distribution network reconstruction model, which comprises a distributed power supply parameter and an electric automobile parameter; 2) dividing the system into corresponding periods according to a peak-valley time-of-use tariff method for reconstruction respectively; and 3) taking the minimum network loss as a target function for the reconstruction to obtain the desired value of the target function by probabilistic load flow computation and solve the distribution network reconstruction model by an improved quantum evolutionary algorithm. The reconstruction model provided by the invention performs reconstruction in different periods according to the influence of one of demand response forms (peak-valley time-of-use tariff) on load to better overcome the defect of a lot of operation on a switch of the real-time reconstruction. Meanwhile, the method reconstructs data of a section without taking the influence of demand response on load into account to overcome the defects of larger network loss of an obtained topological structure in other periods.

The invention relates to an inter-enterprise production scheduling optimization method under an ASP mode, which comprises the following steps: (1) an ASP platform enterprise issues a productive task to an ASP cooperation platform; (2) the parameters of the quantum evolutionary algorithm are set; (3) the encoding is performed; (4) an integer code group Q (t) is obtained during the decoding process, and then a working procedure sequence is obtained through a random code; (5) the fitness value of each chromosome in the Q (t) is calculated according to a fitness function; (6) the chromosome q best with minimum fitness value is got in the group Q (t), and a binary chromosome corresponding to the q best is an optimal individual T best in a group R (t), and a corresponding quantum chromosome is an optimal individual p best in a group P (t); (7) quantum crossover and quantum variation are performed on the group P (t) through contrasting T best with Ri (t); (8) the state is refreshed by utilizing a quantum rotating gate; (9) an optimal scheduling scheme is obtained. The inter-enterprise production scheduling optimization method effectively promotes the share of collaborative production among enterprise groups, increases the resource utilization ratio, has simple operation, and obtains the effective production scheduling result rapidly.

The invention relates to the technical field of electric power system configuration and discloses a substation capacity planning method based on the mixed quantum evolutionary algorithm. According to the technical scheme, the substation capacity planning method comprises steps of substation data collection, substation capacity configuration and result output. The substation capacity configuration comprises the steps that firstly, a system is initialized; secondly, the state of a population Q (t) is observed and an observation state population P (t) is produced; thirdly, local search is performed on individuals in the observation state population P (t); fourthly, decoding is performed, and a variable optimal solution is obtained; fifthly, fitness evaluation is performed on an objective function; sixthly, the optimal individual and relevant information are stored; seventhly, end conditions are judged; eighthly, the population is updated. According to the substation capacity planning method based on the mixed quantum evolutionary algorithm, the advantages of strong capacity in global optimization and a fast convergence rate of the quantum evolutionary algorithm and the advantage of strong capacity in local search of the tabu search algorithm are combined, therefore, an optimized capacity configuration scheme of a substation can be fast and accurately obtained, and an output result can be fast and accurately obtained.

The invention discloses a multi-scale direct load control method of an electric water heater group. The method comprises the following steps: generating single electric heater daily water data according to a family daily load curve, and setting multi-scale according to an electric power system daily load curve; and aggregating the electric water heater to form multiple water electric heater groups; and performing a quantum evolutionary algorithm on each scale of the water heater group to obtain an optimal control strategy. Through the adoption of the method disclosed by the invention, the peak-clipping and valley-filling can be effectively performed, and the method has important significance for the stability and the economy of the electrical power system.

The invention relates to a hyperspectral image waveband selection method based on a quantum evolution particle swarm optimization algorithm, and belongs to the field of image processing. The hyperspectral image waveband selection method comprises the following steps: inputting a hyperspectral image of a waveband to be selected, and setting the scale, dimension and maximum iteration frequency of apopulation; mapping the position occupied by each particle from the unit space to the solution space of the optimization problem, and selecting the combination of the inter-class separability and theoptimal index as a fitness function; and introducing the variation probability into a quantum evolutionary particle swarm algorithm, classifying the output optimal waveband combination image by adopting a maximum likelihood method, calculating the overall classification precision, and calculating the average correlation between waveband combination wavebands adopted by the correlation. The hyperspectral image waveband selection method combines the quantum evolution particle swarm optimization algorithm with the particle swarm optimization algorithm, and can overcome the defect that local optimization is likely to happen, and the quantum evolution particle swarm optimization algorithm has the higher convergence speed, so that the operation time of the algorithm is shortened, and when waveband selection is carried out, the algorithm is more stable, and the classification precision is high, and the application prospect is wide.

The invention discloses a hybrid quantum algorithm-based intelligent vehicle dispatching management system and a working method thereof. According to the system and the method, a hybrid quantum particle swarm optimization algorithm is disclosed through dividing a quantum particle swarm into two sub-phase particle swarms according to features of an optimization variable on the basis of using an improved quantum algorithm and an improved particle swarm algorithm; an elite quantum mean value and chaotic disturbance theory combined quantum evolution algorithm is designed on the basis of deeply researching advantages and boundedness of a tabu search algorithm in problem solution; and a simulated annealing algorithm and quantum algorithm combined hybrid quantum optimization algorithm is disclosed to solve demand-uncertain vehicle path problems; and a target function and a constraint condition of a dynamic vehicle path problem model are given. Simulated analysis results indicate that the method is capable of improving the convergence speed and convergence reliability, and is an effective method for solving demand-uncertain vehicle path problems.

The invention discloses a Jop-Shop scheduling method based on a QEA variable rotation angle distance. Quantum chromosome coding based on procedures is adopted for expressing a schedule, and by detecting the validity of the schedule, the searching efficiency of a solution space is increased; furthermore, a quantum evolution algorithm mode based on the QEA variable rotation angle is utilized for generating a filial generation, so that the diversity of solutions is effectively expanded, and the convergence to a local optimal solution is effectively prevented; in addition, the convergence speed is increased, and a global optimal solution is finally obtained with a minimal time cost (namely the optimal scheduling scheme is realized). According to the invention, the binary solution mode, the decimal solution mode, the procedure solution mode and the quantum evolution algorithm based on the quantum evolution algorithm are utilized, so that the efficiency of the method is better than the efficiency of other methods.

The invention discloses a rolling bearing fault feature extraction method based on an improved quantum evolution algorithm, comprising steps of S1, acquiring the vibration signal f of a rolling bearing; S2, establishing a Gabor atom library; S3, establishing a quantum population [psi]; S4, performing quantum encoding on Gabor atoms by using a quantum probability amplitude; S5, subjecting the rolling bearing vibration signal f to a sparse decomposition on the Gabor atom library after the quantum probability amplitude encoding to select the optimal encoded atom g[gamma]*(t), the optimal population individual [psi]* and the optimal quantum phase [theta]*; S6, evolving the quantum population; S7, mutating the quantum population; S8, calculating the kurtosis value of a sparse reconstruction signal; and S9, repeating the step S4 to the step S8 until the maximum kurtosis value of the sparse reconstruction signal, wherein the sparse reconstruction signal at the maximum kurtosis value is the extracted rolling bearing fault feature component. The fault feature component extracted by the method has obvious periodicity, and the noise contained therein is obviously reduced. The method has certain advantages in terms of rapidity and adaptability.

The present invention discloses a micro-grid and micro-source capacity optimization address distribution method based on islanding. The method comprises the following steps of: 1) inputting an initial parameter; 2) analyzing a typical day; 3) setting an initial parameter of a quantum evolution algorithm; 4) obtaining an optimization parameter by an inner layer optimization method; 5) calculating a fitness value of a particle; 6) updating a local optimal vector and a global optimal vector; 7) using a biological evolution rule to update a position value of the particle; 8) performing local search; 9) performing convergence checking; and 10) outputting a result. By introducing an islanding concept, the present invention proposes the micro-grid and micro-source capacity optimization address distribution method considering islanding.

The invention provides a partition method of a power distribution network island with an electric vehicle battery swapping station based on a hybrid algorithm. The method comprises the steps of (1) inputting a network initial parameter, (2) setting the variable of the hybrid algorithm, (3) initializing a local optimal vector and a global optical vector, (4) calculating particle fitness, (5) updating the local optimal vector and the global optical vector, (6) updating a particle position value, (7) carrying out convergence testing, and (8) outputting a result. According to the method, a quantum evolutionary algorithm and a JADE algorithm are combined, and the partition method of the power distribution network island with the electric vehicle battery swapping station is provided.

The invention relates to a quantum evolutionary algorithm with connectionist learning, which is composed of a plurality of calculation units, and each calculation unit comprises a quantum individual, a collapsing individual and an attractor; the steps are as follows: initializing quantum individuals in all calculation units; for the ith calculation unit, directly sampling the quantum individual and a concept guide combination operator, and obtaining the collapsing individual, and using an objective function to evaluate the collapsing individual to obtain an adaptive value; evaluating the attractor into a corresponding collapsing individual according to the collapsing individual, and finishing initialization of the calculation units; initializing an information metric matrix formed by information quantity of the quantum individual into a 0 matrix; using a collapsing state generation algorithm to generate the collapsing individual by the quantum individual, and generating a temporary probability vector by partial collapsing individuals, and directly sampling corresponding quantum individuals by other collapsing individuals; updating quantum individuals and attractors in all calculation units according to adaptive values of the attractors and adaptive values of the collapsing individuals; and when reaching preset maximum number of iterations, then the quantum evolution process is finished.

The invention discloses an optical thin film characterization method based on a cloud-model quantum evolutionary algorithm (CQEA). The method comprises the following steps that firstly, an initial parameter of the CQEA is input; secondly, a microstructure parameter of an optical thin film is subjected to quantum coding, and an initial quantum population is generated; thirdly, based on a fitting evaluation coefficient of grazing incidence x-ray reflection (GIXR) of the thin film, the adaptability for characterizing a quantum individual of an optical thin film structure is evaluated, and the optimal quantum individual is selected; fourthly, whether the optimal quantum individual meets an optimization criterion or not is judged, if the optimal quantum individual meets the optimization criterion, the optimal optical thin film structure parameter is output, the algorithm is stopped, and otherwise, the algorithm continues; fifthly, the quantum population is updated through one-dimensional cloud complementary mutation and cross; sixthly, the quantum population is further updated by using an elitism preservation strategy, and the third step is executed. The method is suitable for the microstructure characterization of single-layer and multi-layer optical thin films based on the GIXR, and has the advantages of being low in calculation complexity, quick in convergence rate, high in solving precision and the like.

The invention discloses a protein high polymer (HP) calculation method based on a variable angular distance quantum evolutionary algorithm (QEA) algorithm. A quantum evolutionary algorithm based on the variable angular distance is applied to prediction of a secondary structure of proteins, and a variable angular distance evolutionary strategy is imported based on the framework foundation of the quantum evolutionary algorithm framework. A flexible high-efficient directional solution form is adopted for the presentation of the HP configuration. A direction traction mechanism is imported for increasing diversity of the directional solution, and therefore the protein HP model calculation method based on the variable angular distance QEA algorithm is enabled to find the lowest energy configuration of the protein high-efficiently. The method adopts the directional solution to replace the original coordinate solution, facilitates detection and repair of invalid closed loop HP configuration, and therefore execution speed of the method is improved. The protein HP calculation method based on the variable angular distance QEA algorithm adopts the pattern of the directional solution, a rollback method, the direction traction strategy, the variable angular distance technology or strategy and the like, and is better than other methods in efficiency.

The invention discloses an optimal neighborhood picture group selection method for depth map calculation. The method is characterized by comprising the following steps: 1. extracting affine invariant feature points on a reference picture and other pictures, matching the detected feature points, and calculating the spatial positions of the feature points; 2. randomly selecting a given number of pictures from all pictures, except for the reference picture, to form a candidate neighborhood picture group, and calculating the consistency degree of the reference picture and the candidate neighborhood picture group; 3. carrying out iteration on the candidate neighborhood picture group by using a quantum evolutionary algorithm so as to continuously improve the consistency degree, wherein the picture group obtained when the iteration is over serves as an optimal neighborhood picture group. By utilizing the method provided by the invention, the optimal neighborhood picture group can be efficiently selected from a great amount of pictures, so that the purpose of obtaining a high-precision depth map on the reference picture can be achieved.

Provided is a protein conformation space optimization method based on quantum evolutionary algorithm. The protein conformation space optimization method comprises the following steps: based on a framework of quantum evolutionary algorithm, with Rosetta Score3 as the optimum objective function, based on an amino acid sequence coarse-grained expression model, converting an energy calculation model into a dihedral angle optimization space energy model; encoding a dihedral angle individual expression of the amino acid sequence by means of real phase encoding; improving prediction precision by implementing the operation of quantum mutation through fragment assembly; by adopting quantum rotation gate, quantum updating individual population to achieve the purpose of partial adjusting the angle; through iterative evolutionary process, the algorithm will produce protein conformation with lower energy and reasonable structure. The protein conformation space optimization method has the advantage of quick acquisition of conformation of high prediction precision in the application of protein structure prediction.

The invention discloses an evolutionary quantum neural network architecture searching method based on a quantum simulator. The evolutionary quantum neural network architecture searching method mainly solves the problems that a quantum neural network model designed in the prior art is low in precision and high in complexity. According to the implementation scheme, quantization coding is carried out on image data; designing a basic framework of the quantum neural network; using the image data after quantum coding to search optimal structure parameters under the basic framework of the quantum neural network by adopting a quantum evolutionary algorithm, in the quantum evolutionary algorithm, coding the quantum neural network into quantum chromosomes, and using quantum observation, quantum revolving door updating and full interference crossover operation to search the optimal structure parameters; and constructing an optimal quantum neural network based on the optimal structure parameters. The quantum neural network obtained by searching has higher model precision and lower complexity, can be deployed on a quantum simulator or a real quantum system, makes full use of the parallel advantage of quantum calculation, improves the reasoning speed of the model, and can be used for image classification.

The invention discloses a smart grid loss reduction method under the control of a super quantum evolution algorithm. A combined means of a genetic algorithm and a quantum algorithm is adopted, a state vector expression of quantum is introduced to genetic coding, the chromosome evolution is achieved by means of a quantum logic gate, and a better effect than that of the conventional genetic algorithm is realized; and with regards to the characteristics of relatively low capacity of a smart grid system, relatively low voltage level and relative large network loss in the system and the demands of high intelligence and rapid response of a smart grid, optimization processing is carried out, so that the algorithm can meet the requirements of the smart grid for intelligence, rapid response and high reliability. By the smart grid loss reduction method under the control of the super quantum evolution algorithm, the improved quantum evolution algorithm is successfully applied to the smart grid system, the network loss of the smart grid system is maintained to be lowest in real time by the algorithm, the electric energy quality of the smart grid system is improved, the system reliability is improved, a technical blank in the field of smart grid reconstruction calculation is filled, and actual significance is brought to energy saving and emission reduction of the smart gird and improvement on the reliability of the power system.

The invention relates to a fault test optimization method of an electric power metering system. The method comprises the following steps: S1, according to the structure of the to-be-tested electric power metering system, obtaining test sets; S2, building a test selection model on the basis of existence of false alarm and leakage detection; and S3, by taking the test selection model as an optimization model, screening the test sets by adopting a quantum evolutionary algorithm to obtain optimized test sets. When the test sets are optimized, the condition that the test is not reliable is fully considered, so that the test requirements are met to the maximum extent, and more comprehensive and effective optimization can be realized.

The invention discloses a distributed power supply optimal configuration method considering an active management mode. The method comprises the following steps: (1) carrying out uncertainty modeling on a wind driven generator, a photovoltaic generator and a micro gas turbine; (2) converting into a double-layer planning model according to a coordinated decomposition thought, planning an upper layeras a distribution planning problem of DG, taking minimum annual comprehensive cost as a target, taking a lower layer planning model as an optimization problem of DG active power output, and taking minimum active power output removal amount of DG as a target; (3) solving the model by using a method of combining a quantum evolutionary algorithm and a primal-dual interior point method, and samplingthe wind speed, the illumination intensity and the load by using a Monte Carlo simulation method based on Latin hypercube sampling, so that the method better reflects the characteristics of the powerdistribution network accessed by large-scale DG in the future, conforms to the development trend of the power grid in the future; after the active management mode is used, the DG of the type is bettercontrolled, the admitting ability of the system to renewable energy sources is improved, and the development of renewable energy source power generation is promoted.

The invention provides a novel micro grid island partition method based on a quantum evolutionary algorithm. The method comprises the steps of (1) inputting a network initial parameter, a load parameter and a micro-source parameter, (2) setting the initial parameter of the quantum evolutionary algorithm, (3) calculating the fitness value of each particle, (4) updating a local optimal vector and a global optical vector, (5) updating a particle position value by using a biological evolution rule, (6) carrying out local searching, (7) carrying out a convergence test, and (8) outputting an island partition result. According to the method, through introducing the quantum evolutionary algorithm, a micro grid island partition problem with the consideration of a micro-source frequency characteristic and a load level is solved.