78 results about "Shuffled frog leaping algorithm" patented technology

The invention discloses a multi-objective quantum Shuffled Frog Leaping Algorithm (SFLA) based water resource optimization and diversion method, comprising the following steps: firstly obtaining basic information data on water resources; establishing multi-objective optimization and diversion models for water resources; executing the shuffled Frog Leaping Algorithm (SFLA) to find the best solutions to Pareto of the multi-objective optimization and diversion of water resources; and finally according to a multi-objective decision theory, choosing the best theory to divert water resources by combining objective weights and subjective weights. According to the invention, optimization is achieved through an overall choosing process. Calculation efficiency is increased so as to meet the requirements for best multi-objective diversion programs in a water resource system.

The invention discloses a reservoir group adaptability scheduling method based on an RCP. The method comprises the steps that a soil and water assessment tool (SWCP) hydrological model is driven by meteorological data in the global climate mode under representative concentration pathways (RCP) to predict a future runoff process; the basic information of reservoirs is acquired to establish a reservoir group adaptive scheduling model; the predicted future runoff under the RCP is used as the input of the adaptive scheduling model; and a chaos shuffled frog leaping algorithm (CSFLA) is carried out to determine a reservoir group adaptive scheduling policy. According to the invention, future runoff prediction of a drainage basin can be realized based on the RCP; a reservoir group optimal scheduling model adapting to power generation, flood control, ecology and other targets under the RCP is constructed and solved; the reservoir group adaptive scheduling policy which copes with the climate change is provided; and the method can be widely used in the practice of reservoir group scheduling production.

A method and a system for scheduling parallel machines based on hybrid shuffled frog leaping algorithm and variable neighborhood search algorithm are provided to solve collaborative production and processing of jobs on a plurality of unrelated batch processing machines. The jobs are distributed to machines based on the normal processing time and deterioration situation of the jobs on different machines and are arranged. An effective multi-machine heuristic rule is designed according to the structural properties of an optimal solution for the single-machine problem, and the improved rule is applied to the improved shuffled frog leaping algorithm to solve this problem. The improvement strategy for the traditional shuffled frog leaping algorithm is to improve the local search procedure of the traditional frog leaping algorithm by introducing the variable neighborhood search algorithm. The convergence rate and optimization capacity of the original algorithm are thus improved.

The invention relates to a testing method for moisture states of an oil-immersed type bushing. Due to the influence to the oil-immersed type bushing by over-standard of drying production technology, sealing failure of outer insulation, insulation aging of oil paper and the like, the water in the insulation paper always maintains the nonuniform distribution state; the moisture state of the bushingis evaluated by the ground insulation resistance of a bushing tap, tangent value of dielectric loss angle, and electric capacitance; however, the previous testing process cannot obviously reflect thewater content in the insulation paper of the bushing, and the sensitivity is lower, so that the moisture state of the oil-immersed type bushing cannot be effectively evaluated. The testing method hasthe advantages that the hidden Markov model parameters of the bushing under different moisture states and at different temperatures can be obtained; according to the tested dielectric spectrum curve,the probability of different moisture states of the bushing is calculated by a shuffled frog leaping algorithm, so as to effectively test the moisture states of the oil-immersed type bushing.

The invention discloses a cognitive ratio power control method. The method improves a revenue function on the basis of a non-cooperative game power control algorithm proposed by D.Goodman, and provides a new power control algorithm based on non-cooperative game; and simultaneously, for improving the searching precision of the power control algorithm, the invention further provides an improved shuffled frog leaping algorithm. The cognitive radio power control method of the invention has higher calculation accuracy, implements effective control on transmitting power of users, and can improve system performance obviously.

The invention discloses a method for improving a standard shuffled frog leaping algorithm.The method comprises the steps of initializing parameters; calculating the adaptive value of each frog individual, and finding the adaptive value and position of the global optimum frog individual of a frog population; conducting optimum drawdown ranking on the frog population; conducting dividing for obtaining frog sub-populations; finding the positions of the optimum and the worst frog individual of each frog sub-population; conducting updating operation on the position of the worst frog individual of each frog sub-population; calculating the adaptive value of the frog individual with the position updated in each frog sub-population, and finding the global optimum adaptive value and the position of the frog population at this moment; implementing prediction of the global optimum adaptive value of the frog population obtained after iteration is completed next time, and furthermore adjusting the movement step-length variable coefficient dj and skip among steps; judging whether the ending conditions are met or not.By means of the method, the defects that at the later stage, the convergence rate of the standard shuffled frog leaping algorithm is severely lowered, convergence precision is insufficient, and the algorithm is prone to getting into local optimum are overcome.

The invention discloses a multi-target shuffled frog-leaping algorithm based on multilevel message feedback. The multi-target shuffled frog-leaping algorithm comprises the steps of optimizing a standard shuffled frog-leaping optimizing layer, a frog evolving and learning layer and an external file information exchanging layer, wherein the standard shuffled frog-leaping optimizing layer is used for obtaining new positions of the frog and comparing advantages and disadvantages of old positions with those of the new positions; entering the frog evolving and learning layer if the new positions are inferior to the old positions; obtaining Pareto domination solutions in the optimizing process and storing the Pareto domination solutions in an external file; extracting a certain number of non-domination solutions to conduct information exchange from the external file according to a preset strategy after every arriving ends so as to improve the qualities of the solutions in the file and provide a globally optimal solution for later frog optimizing and frog evolving and learning. The multi-target shuffled frog-leaping algorithm based on the multilevel message feedback has the advantages of being visual, simple, clear, universal and the like, making good use of complete information of the positions of the frog in the arriving process, and powerfully strengthening the frog ability of jumping out of the locally optimal solution.

An oil paper insulation dominant time constant calculation method based on an extended Debye equivalent circuit sequentially comprises the following steps: the step 1, performing preparation work comprising powering off a transformer to stop operation, enabling various phases of high- and low-voltage windings and a neutral point to be in short connection and be grounded, and then releasing residual charges; the step 2, obtaining data comprising setting a polarization voltage and a charging and discharging time ratio, performing wiring, and performing a recovery voltage test experiment on the transformer by utilizing an RVM5461; the step 3, selecting a shuffled frog leaping algorithm, and establishing an evaluation function to solve an equivalent circuit parameter; the step 4, calculating peak value measurement time through adoption of segmented Hermit interpolations for 3 times, and obtaining a continuous recovery voltage polarization spectrum according to a recovery voltage calculation formula; and the step 5, searching a peal value of the recovery voltage polarization spectrum to determine a dominant time constant. The problem of insufficient accuracy of a non-standard polarization spectrum dominant time constant in actual measurement and the problem of long consumed time in the actual measurement are overcome, and accuracy of diagnosing a moisture content of an insulation system by utilizing the dominant time constant is improved.

The invention discloses a construction method of a concrete dam deformation safety monitoring model, specifically, on the basis that by using the historical data of dam deformation observation, a stepwise regression model is established, a shuffled frog leaping algorithm (SFLA) with local optimization performance and global optimization performance is adopted to determine a weight coefficient of each sub-model, an inversion analysis method of dam prototype data is utilized to determine physical and mechanical parameters of a dam, a frog leaping hybrid model is established, and then a concretedam deformation safety monitoring model is obtained. According to the method, the residual error is analyzed and predicted by using the chaos theory, and the residual error prediction item is added tothe leapfrog prediction hybrid model, so that the problem that the fitting effect is good and the prediction result is poor due to the fact that the influence of the fitting residual error is not considered in a conventional dam displacement monitoring model is effectively solved.

The invention discloses a distribution network operation optimization method integrating reactive power optimization and network reconstruction. According to the method, coordination and cooperation of a reactive power optimization technology and a network reconstruction technology in distribution network operation optimization are fully considered. An optimization model employing annual comprehensive cost as a target function is firstly defined; a new coding strategy and an identification method of a solution are provided; and finally the best comprehensive optimization scheme is determined by a shuffled frog leaping algorithm. By the distribution network operation optimization method, the potential economic value existing in cooperation of the reactive power optimization technology and the network reconstruction technology can be fully explored; and the distribution network operation optimization method has certain practical reference value.

The present invention discloses a control method for a flexible direct-current power transmission system. The flexible direct-current power transmission system is composed of an alternating current system, an electric reactor, a current rectifier, a capacitor, a direct current power transmission circuit, an inverter and a load, wherein both the current rectifier and the inverter use three-phase bridge-type circuits. The current rectifier adopts the control method, based on shuffled frog leaping algorithm (SFLA) optimized active disturbance rejection controller (ADRC) provided by the present invention, the method adopts dual close-loop vector control, and an outer voltage loop adopts SFLA optimized ADRC control so as to stabilize direct current voltage while an inner loop adopts current decoupling control to realize decoupling of active power and reactive power. According to the method, ADRC parameter adjustment can be performed on line according to system operation states, the self-adaption adjustment capability is good, and the anti-jamming capability of the system is raised.

A power big data oriented microgrid short-period load prediction method is used for improving prediction precision for a microgrid short-period load. The power big data oriented microgrid short-period load prediction method is characterized by comprising the steps of firstly establishing a microgrid short-period load prediction model based on a kernelized extreme learning machine (KELM); then optimizing a combined parameter (C,sigma) of the kernelized extreme learning machine by means of an improved shuffled frog leaping algorithm (ISFLA), and obtaining an ISFLA-KELM prediction model; and finally predicating the microgrid short-period load by means of the ISFLA-KELM prediction model. According to the power big data oriented microgrid short-period load prediction method, the ISFLA-KELM prediction model is utilized for predicating the microgrid short-period load. An experiment represents a fact that the KELM has relatively high regression forcasting capability. Furthermroe the ISFLA algorithm has high optimization capability and the parameter of the KELM can be optimized, thereby greatly improving prediction precision for the microgrid short-period load.

The invention belongs to the technical field of carbon emission prediction, and in particular relates to a carbon dioxide emission prediction method comprising the steps of collecting data including the historical CO2 emission, population, GDP per capita, urbanization rate, secondary industry added value proportion, energy consumption structure, energy strength, overall coal consumption, carbon emission strength and total export-import volume; performing non-dimensionalization on the data, computing a gray association degree between each piece of data and the CO2 emission, and screening CO2 emission influence factor indexes input by the model according to the gray association degrees to achieve feature dimension reduction; using a gray prediction model GM(1,1) to predict the screened CO2 emission influence factor index; and using predicted values of the CO2 emission influence factors to serve as model inputs, and then using an improved shuffled frog leaping algorithm to optimize a least square support vector machine model for predicting the CO2 emission. The method provide by the invention has efficient computing performance and excellent global searching ability.

Disclosed are a network dynamic topology control system and a network dynamic topology control method, which belong to the technical field of network. The dynamic topology control system provided by the present invention comprises a link information collection module, a flow prediction module, an intelligent decision-making module and a topology update module. The system firstly collects link flow information and topology change information through the link information collection module, then carries out flow prediction and time prediction, and sends the prediction information and the topology change information to the intelligent decision-making module. The system carries out dormancy awakening decision in combination with a path feedback mechanism and the shuffled frog leaping algorithm (SFLA), in order to select best dormant links and routers, and accordingly deal with the topology. The dynamic topology control system can manage dynamic changes in network topology, the network is normally operated, and energy-saving effects are achieved.

The invention relates to a quadrotor unmanned aerial vehicle parameter distinguishing method based on an improved shuffled frog leaping algorithm. The shuffled frog leaping algorithm is taken as a basis, a frog leaping rule in the algorithm is improved, the global convergence rate of the shuffled frog leaping algorithm is improved, a fitness function is designed according to quadrotor unmanned aerial vehicle parameters, the computation complexity of the algorithm is reduced, and quadrotor unmanned aerial vehicle parameter distinguishing efficiency is improved. The method exhibits certain universality, and parameter distinguishing for the majority of nonlinear systems with a high coupling degree can be realized.

The invention relates to the technical field of flexible DC networks, in particular to a collaborative optimization configuration method for current limiting reactors and fault current limiters in a flexible DC network. A multi-objective optimization configuration mathematical model is established by comprehensively considering the performance of a system and the cost of current limiting equipmentand taking the current limiting effect, the total inductance value of the current limiting reactors and the quantity of the fault current limiters as objective functions and breaking current of DC circuit breakers, overcurrent protection of converter valves and the current limiting reactors as constraint conditions; the multi-objective optimization configuration mathematical model is solved by adopting a multi-objective shuffled frog-leaping algorithm to obtain an optimal solution set; and a proper configuration scheme is selected from the optimal solution set by combining the actual situation. According to the method, optimization configuration is carried out on the current limiting reactors and the fault current limiters in the flexible DC network, so that the global optimization objectives of the best current limiting effect, the minimum total inductance value of the current limiting reactors and the minimum installation number of the fault current limiters are achieved and continuous and stable operation of a health part of the flexible DC network in a fault can be ensured.

The invention discloses a modified shuffled frog-leaping algorithm enhanced self-adaption band-pass filtering method for fault diagnosis of a screw compressor. The method includes: 1) performing EEMDprocessing on a collected vibrating signal, calculating the relative kurtosis value of each IMF component, picking the maximum and sub-maximum components of the relative kurtosis value and performingsignal reconstruction; 2) performing modified SFLA-based self-adaption band-pass filtering processing on the reconstructed signal, and precisely cutting-out a high-frequency band signal being rich infault information; 3) performing Hilbert envelope demodulation analysis on the filtered signal, performing spectral analysis on the demodulated signal, and finally diagnosing the fault of the screw compressor. In the invention, firstly, by means of the relative kurtosis value, IMF component reconstruction is carried out to obtain new signals, so that the fault information is maintained as most aspossible and influence on feature extraction due to noise and false component is avoided; secondly, by means of a self-adaption band-pass filter enhanced by the modified SFLA, the reconstructed signalis subjected to the self-adaption band-pass filtering, so that central frequency and bandwidth of band-pass filtering are optimized, and precision of the fault diagnosis is increased.

The invention relates to a dynamic regional backlight dimming method based on an improved shuffled frog-leaping algorithm. On the basis of a image-brightness-based typical feature value, a dynamic regional backlight dimming problem is transformed into an optimization problem and an improved shuffled frog-leaping algorithm is used for solving the problem, so that one solution is found out among all partition brightness distribution solutions and thus an image after regional diming has the highest display quality under the circumstance that the certain energy consumption is not exceeded. One group of initial backlight brightness values is determined by using an image-brightness-based feature parameter statistic method; and optimum backlight brightness values of all divided regions are calculated by using an improved shuffled frog-leaping algorithm to obtain an optimal divided-region backlight brightness distribution solution. With the determined regional backlight brightness distribution solution, distortion of an image after dimming is reduced and thus the image display quality is ensured; the energy consumption is reduced to the great extent; and the mutual restriction relationship between the image display quality and the energy consumption is balanced.

The invention relates to a software and hardware division technology in system software and hardware collaborative design and provides an improved software and hardware division method applied to software and hardware collaborative design. The method is improved mainly for solving the problems that when a shuffled frog-leaping algorithm is applied to software and hardware division, convergence speed is low, and the algorithm is possibly trapped into local optimum, and therefore a software and hardware division algorithm with better performance than an original frog-leaping algorithm is proposed. According to the technical scheme, the software and hardware division method based on the improved shuffled frog-leaping algorithm comprises the steps that (1) a frog population is initialized; (2) G equidistant center coordinates are determined according to a frog group number G and a task node number N; (3) iterative updating is started; (4) the distance from the position coordinate of each frog to each center coordinate is calculated in sequence according to a made order; and (5) the position coordinate of the optimal frog is output to serve as an optimal software and hardware division scheme. The method is mainly applied to a software and hardware division occasion in software and hardware collaborative design.

The invention discloses a method for concrete temperature monitoring and simulation back analysis based on a thermal imager, which comprises: observing the distribution of a concrete surface temperature field by using a thermal imager, so as to obtain typical measuring point temperature data and an infrared thermogram; inverting concrete thermodynamic parameters by a shuffled frog leaping algorithm based on the temperature data observed by the thermal imager; simulating a concrete temperature field and stress field based on the inverted concrete thermodynamic parameters; and comprehensively analyzing the concrete cracking condition by using the temperature data observed by the thermal imager and the simulated temperature field and stress field. According to the invention, the correctness of the calculation results and the feasibility of the temperature control scheme are examined by comparing the infrared thermogram with the concrete surface temperature field and stress field in a corresponding simulation model, which overcomes various deficiencies in current large-size concrete temperature detection methods.

The invention relates to an information quality quantification method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring data of a substation secondary system in a preset time period; performing clustering analysis on the data by adopting a clustering method based on a shuffled frog leaping algorithm to obtain a plurality of data sets; performing quantitative analysis on each data set according to at least two preset evaluation indexes to obtain data proportion of each data set under each evaluation index; and according to the data proportion of each data set under each evaluation index and the target weight of each evaluation index, obtaining the quality quantized value of each data set. By adopting the method, the accuracy and efficiency of information quality quantification can be improved.

The invention discloses a multi-relay cooperative self-adaptive relay selection and power distribution method. A shuffled frog leaping algorithm is introduced into an AF multi-relay cooperative system, path loss is fully considered under the condition that total power is subjected to certain constraint, the maximum average signal to noise ratio of a destination node serves as a target, and the searching advantages of the shuffled frog leaping algorithm are utilized to achieve power distribution of the AF multi-relay cooperative communication system and reduce BER performance of the system.

The invention discloses a strip steel thickness prediction method employing a shuffled frog leaping feedback extreme learning machine. The strip steel thickness prediction method comprises the following steps: 1) analyzing acquired steel plate data signals; 2) performing feature extraction; 3) introducing a Kalman filtering idea into the extreme learning machine, and feeding back a difference value between the actual output and the expected output of the network to an input layer to form a feedback extreme learning machine algorithm, optimizing random parameters of the feedback extreme learning machine algorithm by applying a shuffled frog leaping algorithm, and constructing a shuffled frog leaping feedback extreme learning machine prediction model; and 4) applying the shuffled frog leaping feedback extreme learning machine obtained in the step 3) to prediction of the strip steel outlet thickness, and performing result comparison with a traditional extreme learning machine and a shuffled frog leaping extreme learning machine to verify the effectiveness of the method. Through the steps, the prediction method is small in prediction error, high in prediction precision and good in robustness.

The invention discloses a constant modulus blind equalization processing method based on the optimization of a DNA shuffled frog leaping algorithm (DNA-SFLA-CMA) in a communication system. The invention takes full advantage of the great optimizing capability of an SFLA and the higher convergence precision of a DNA genetic algorithm, combines the two algorithms to obtain the DNA-SFLA, and utilizes the DNA-SFLA to optimize a constant modulus blind equalization weight vector. The optimization steps comprise: 1) initializing a frog population; 2) calculating the fitness value of a frog individual in the frog population, sorting position vectors of frog individuals from smallest to largest according to fitness values, and performing interlace operation on the position vectors of frog individuals, and mutation operation on DNA sequence position vectors after DNA coding of the frog individuals so as to select the position vectors of an optimal frog individual; and 3) employing the position vectors of an optimal frog individual as the initial weight vector of a constant modulus blind equalization method. The constant modulus blind equalization processing method has the advantages of fast convergence speed and small mean square error.

The invention discloses a goods allocation distribution model establishment method in bidirectional layout mode, and the method enables each piece of goods to be reasonably allocated to a storable goods allocation according to the goods warehouse-out / warehouse-in frequency, the center of gravity of a goods shelf and the goods aggregation degree as evaluation standards, thereby achieving the purposes that the operation time of a stacking machine for executing a warehouse-in task is short, the overall center of gravity of the goods shelf is low, and the associated cargo are placed in an approaching mode. Meanwhile, in a follow-up optimization algorithm, an improved shuffled frog leaping algorithm is provided to carry out simulation optimization on the model, meanwhile, when the algorithm is adopted, a new local updating strategy is designed, a self-adaptive dynamic synchronization factor is introduced, and good performance is achieved in any stage of optimization solution. The automatic selection of the stocker to the warehouse-out / warehouse-in platform is realized, and the actual working condition requirement of'two-way type 'can be met.

The invention relates to a DG (DataGuard) optimal configuration application method based on a shuffled frog-leaping particle swarm. The method comprises the following steps that: firstly, on the basis of considering a traditional distributed power optimal configuration target, bringing the environment cost of a distributed power into an evaluation index, wherein established optimal configuration model target functions comprise the investment cost, the operation cost, the network loss cost, the electricity purchasing cost and the environment cost of the distributed power; and then, utilizing an improved particle swarm algorithm based on shuffled frog-leaping to carry out model optimization, putting forward a method that the local search strategy of an artificial bee colony is fused into a standard particle swarm algorithm to search a new solution for the first time, then, utilizing the shuffled frog-leaping algorithm to update worst particles in a population, and finally, solving an optimal solution condition which meets DG grid connection. By use of the method, the defects that the standard particle swarm algorithm is likely to fall in local optimization and convergence speed is low are effectively solved.

Disclosed is a shuffled frog leaping algorithm based internet of things node reputation evaluation method. The shuffled frog leaping algorithm based internet of things node reputation evaluation method includes analyzing local features of nodes in the internet of things, calculating importance of the nodes in internet of things autonomous domains, using the calculated node importance as a basis for node screen, using a shuffled frog leaping algorithm for clustering the nodes, selecting a kind of nodes with higher importance as neighbor nodes of reputation evaluation, using the neighbor nodes to perform reputation evaluation on nodes to be evaluated according to a reputation evaluation algorithm, calculating a more accurate node reputation value according to current reputation and history reputation of the nodes, setting a threshold value, comparing the node reputation value with the threshold value to judge whether the nodes are credible, judging the nodes are incredible nodes when the reputation value is lower than the set threshold hold, and otherwise, judging the nodes are credible nodes. According to the shuffled frog leaping algorithm based internet of things node reputation evaluation method, the problem that incredible nodes interfere evaluation results in traditional reputation evaluation systems can be effectively avoided.

The invention discloses a hydrological data anomaly detection method based on spatio-temporal information. The method comprises the following steps: dividing associated sites; dividing a water level time sequence; obtaining a model output result by using the trained convolutional neural network (CNN) model, carrying out residual prediction on the model output result by using a Markov chain (MC), and judging an abnormal station according to the model output result and the predicted residual; obtaining abnormal conditions of the to-be-detected station and all associated stations; and performingresult fusion by adopting a dynamic distribution DS evidence theory (DADS) algorithm to obtain a hydrological data exception prediction result. According to the method, the influence of rainstorm seasons on hydrological data is fully considered, the detection precision is improved, a shuffled frog leaping algorithm (SFLA) is introduced to improve convolutional network parameters, an MC algorithm is added to carry out residual prediction, and the accuracy of prediction data is improved; and finally, through a dynamic distribution D-S evidence theory, fully considering spatial factors, and fusing multi-associated site prediction results, so the false alarm frequency is effectively reduced.

An embodiment of the invention discloses a distributed power generation investment and distribution network planning optimization method in a deregulated environment. The method includes model construction and an improved multi-objective shuffled frog leaping algorithm. The model construction includes an objective function, a constraint condition and uncertainty processing. The improved multi-objective shuffled frog leaping algorithm includes a shuffled frog leaping algorithm mechanism and steps. According to the method, joint optimization of distributed power generation investment and distribution network construction planning is studied, and a profit distribution coefficient is introduced in constructing an objective function process to achieve a win-win goal. According to the method, DNO can encourage investment and planning of various distributed power generation technologies more effectively, and uncertainties of various parameters in the future are also considered, which can helpplanners to make plans more accurately.

The invention discloses a traveling salesman route planning method based on a novel shuffled frog leaping algorithm, and the method comprises the steps: (1) reading problem information which comprisesthe coordinates of all visited cities and the scale of a problem; (2) initializing algorithm parameters; (3) generating an initial candidate population, and calculating fitness; (4) selecting an evolutionary population by adopting a reverse roulette strategy; (5) establishing an independent optimal subgroup, and dividing the subgroups according to individual fitness; (6) allocating an exclusive global optimal solution to each subgroup, and performing local search on each subgroup; (7) shuffling each subgroup, enhancing local search, putting the subgroups back to the candidate population, andre-selecting an iterative population to participate in the next iteration; and (8) judging whether the number of iterations reaches a maximum value or not, if so, terminating the iteration, and outputting an individual with optimal fitness, wherein the individual is the order of accessing the city by the traveling salesman. The method has the advantages of being high in search speed, high in search capacity and short in planned route.