54 results about "Criss-cross algorithm" patented technology

The invention relates to a short-term load predicting method of a power grid. The method comprises the steps: step 1, acquiring historical data and pre-treating the data; step2, decomposing the historical load sample data into a plurality of different-frequency sub-sequences by using wavelet decomposition; step 3, performing single-branch reconstruction to each sub-sequence; step 4, dynamically choosing training samples and establishing a neural network predicting model optimized by a vertical and horizontal intersection algorithm; step 5, predicting each sub-sequence 24 hours in advance by using the optimal neural network predicting model; and step 6, superposing the predicted value of each sub-sequence to obtain a whole prediction result. The inherent defects of the neutral network can be overcome by optimizing BP neutral network parameters by a brand-new swarm intelligence algorithm, that is, the vertical and horizontal intersection algorithm instead of the traditional algorithm; the burr problem caused by the impact load processing is solved by the wavelet decomposition, the precision declining resulting from the removal of the effective load in the burr pre-treatment is solved and the predicted value of the hybrid algorithm is more approximate to the actual measured load value.

The invention discloses an electric system economic dispatching optimization method based on a criss-cross algorithm. The criss-cross algorithm is a brand new swarm intelligence optimization algorithm and mainly comprises a horizontal cross operator and a longitudinal cross operator, wherein a multi-dimensional optimizing space is divided into hypercubes with half of the population size through horizontal cross, and each pair of paired parent particles searches for filial generations in its hypercube subspace and the periphery of the hypercube subspace; arithmetic cross search is executed on different dimensions in the population with a certain probability through longitudinal cross; a domination solution obtained from a moderate solution generated through two kinds of cross through a competition operator will rapidly spread into the whole population in a chain reaction mode, so that the evolution speed is greatly increased. The electric system economic dispatching optimization method based on the criss-cross algorithm has the advantages of being high in global searching ability and high in convergence rate through the criss-cross algorithm, applicable to optimizing a non-linear high-dimensional function and also applicable to achieving large-scale complex optimization in practical engineering.

Embodiments of the invention disclose a short-term wind power prediction method, device and system. the method comprises the following steps of: obtaining wind power history data, and preprocessing the wind power history data to obtain training sample data and test sample data; predicting the test sample data by adoption of a pre-established extreme learning machine optimization model so as to obtain a wind power prediction result, wherein the extreme learning machine optimization model is established through adding the training sample data into an extreme learning machine; and optimizing parameters of the extreme learning machine by adoption of a chaotic crisscross algorithm-combined particle swarm algorithm so as to obtain a trained extreme learning machine optimization model, wherein the parameters comprise an input weight and hidden layer offset. According to the method, device and system, the local search ability and global convergence precision of the extreme learning machine optimization model are improved, and the optimized extreme learning machine optimization model is adopted to predict the test sample data, so that the obtained prediction result is more accurate.

The invention discloses a pedestrian indoor positioning method based on particle filter. RSS measurement, an MEMS acceleration meter and a fused frame model of map information and a particle filtering device are integrated in the method, the MEMS acceleration meter and the map information are additionally arranged in a positioning system, walking distance is estimated based on a movement model of a zero crossing algorithm, the particle filtering device is used for integrating nonlinear information form the MEMS acceleration meter and a building map, accumulated errors caused by noise of sensors are avoided, compared with Kalman filter, the fusing algorithm gets improvement when the average value and standard deviation of the errors are estimated, and robustness is achieved relative to a wrong estimation result of walking distance. Simulation experiments and actual testing results show that compared with Kalman filter, the method gets remarkable improvement when the average value and the standard deviation of the errors are estimated.

The invention relates to a transformer fault diagnosis method, which comprises the following steps of S1, obtaining the concentration of dissolved gas in transformer oil and sample data correspondingto a fault conclusion, performing preprocessing, and generating a training sample set and a test sample set; s2, establishing a kernel extreme learning machine prediction model by adopting the generated training sample set; s3, optimizing kernel function parameters and penalty coefficients of the kernel extreme learning machine by adopting a crisscross algorithm in the model training process; andS4, inputting the test sample into a trained kernel extreme learning machine for prediction to obtain a transformer fault diagnosis result. According to the transformer fault diagnosis method, the problem that transformer fault data encoding and kernel extreme learning machine parameter selection are difficult is effectively solved; meanwhile, the local optimization problem of a traditional BP neural network is avoided, the method can be applied to scientific research and engineering application in the related fields of transformers, the recognition speed is high, the recognition rate is high,and the diagnosis precision of transformer faults is greatly improved.

The invention discloses a transmission line inspection path optimization method based on a differential crisscross optimization algorithm. The algorithm is a hybrid optimization algorithm composed of a differential evolution algorithm and a crisscross optimization algorithm. The crisscross optimization algorithm (DE-CSO) fuses the strong global search ability of the crisscross optimization algorithm and the local search ability of the differential evolution algorithm. The transmission line inspection path optimization method disclosed by the invention has the beneficial effects that the DE-CSO method disclosed by the invention is used for solving the multi-target transmission line inspection path problem in which a tower risk probability and the shortest path are considered at the same time, meanwhile the DE-CSO method has good global approximation ability and fast convergence performance, and thus having important practical significance of improving the line inspection planning level and improving the inspection efficiency.

The invention discloses a load prediction method and apparatus for a power system. Historical load data of a power system are obtained; decomposition and single-branch reconstruction are carried out on the historical load data by wavelet transform, thereby obtaining wavelet decomposition data of loads with different frequencies; a BP neural network model is established; wavelet decomposition data are trained by using the BP neural network model and a network parameter is optimized by using a crisscross optimization algorithm with an elitism selection strategy, and an optimal network parameter is determined; with the optimized BP neural network, load components obtained by single-branch reconstruction in the wavelet decomposition data are predicted; and prediction values of all load components are superposed and a practical prediction result is determined. According to the method and apparatus provided by the invention, on the basis of the wavelet transform and the crisscross optimization algorithm, the load prediction model of the neural network is optimized; and the neural network parameter is optimized by using the crisscross optimization algorithm. Therefore, defects that the BP neural network is vulnerable to local optimum and poor generalization can be overcome, so that the prediction precision of a region having lots of impact loads can be improved effectively.

This software enables a financial institution acting as a clearing agent to offer a liquidity pool where their clients can anonymously submit orders for a financial instrument. Many financial markets suffer from reduced liquidity, the causes for which include: 1) fragmentation across multiple markets, 2) fragmentation across a large instrument universe and 3) attempting to trade an illiquid instrument. The software has been developed to uniquely improve available liquidity using crossing algorithms that intelligently identify orders for similar instruments as relevant execution opportunities, and applies a quantitative scoring of their propensity to trade on which clients can anonymously negotiate and execute. As crossing algorithms are not constrained by the conventional restriction that orders must be for identical instruments, the system is able to increase liquidity by identifying execution opportunities that existing markets cannot, while employing an anonymous negotiation process that minimizes information leakage to mitigate disruption to market prices.

The invention discloses a multi-region dynamic economy scheduling method and system. The method comprises that a target function of a multi-region economic scheduling problem is established; an initial population is generated by initialization, the fitness of the initial population is calculated, and the initial population serves as a parent population; an NW small world network model is used to obtain an adjacent matrix; the parent population is updated according to the adjacent matrix to obtain a filial population, and the fitness of particles in the filial population is calculated by utilizing a fitness function; the particle fitness in neighborhoods divided by corresponding adjacent matrixes in parent and filial populations is compared by utilizing a competition operator, and particles of high fitness are reserves and serve as a parent population in next iteration; and when a preset maximal iteration frequency is reached, a result of the multi-region economic scheduling problem is output. The NW small world network improved differential crisscross algorithm is used to overcome the defect of population diversity loss in the optimization searching process of basic differential evolution algorithm and crisscross algorithm.

The invention discloses a short period electricity price prediction method, apparatus and system. The method includes acquiring the pre-processed electricity price historical data; adopting a variational mode decomposition method to decompose the electricity price historical data to obtain a plurality of discrete mode components; adopting a pre-established neural network optimization model to predict and process each discrete mode to obtain the predicted value corresponding to each discrete mode component; superposing each predicted value to obtain the electricity price prediction result, wherein the establishment process of the neural network optimization model is to add the training sample data to the neural network; and adopting a crosswise algorithm to optimize the parameters of the neural network to obtain the trained neural network optimization model. In the process of using, the influence of nonstationarity and nonlinearity of the electricity price series on the prediction results is reduced, and the global convergence accuracy and prediction accuracy are improved.

The present invention discloses an improved crisscross optimization algorithm-based multi-objective reactive power optimization method and system. The method comprises the steps of calculating target values of each particle in an initial population, wherein the target values at least comprise target values of an active power network loss, a voltage offset and a voltage stability margin; performing horizontal cross and vertical cross on the initial population so as to generate sub-generation W and sub-generation R; screening the sub-generation R to obtain an excellent particle population; and combining the initial population, the sub-generation W and the excellent particle population so as to generate a population pool, selecting a new generation of population by using non-dominated sorting and crowding distance, and outputting a final result when an iteration number of times is greater than a preset threshold. In the method, the active power network loss, voltage offset and voltage stability margin are all considered in reactive power optimization of the system, and the system is optimized by using the improved crisscross optimization algorithm, so that multi-objective reaction power optimization is realized, and the algorithm is less likely to optimize locally.

The invention discloses a heat and power cogeneration dynamic economical scheduling method and a device thereof. The method comprises the steps of creating an initial population of a crisscross optimization algorithm according to a preset constrained condition; calculating a fitness function and using the initial population as a parent population; performing a cross operation on the parent population; performing a longitudinal operation on the parent population after the cross operation; calculating the fitness function on the parent population after crisscross updating; and if the number of iterations which correspond with the parent population reaches a preset number, outputting the optimal fitness function which corresponds with the parent population and a scheduling solution that corresponds with the optimal fitness function. According to the method and the device, the crisscross optimization algorithm is applied in heat and power cogeneration dynamic economical scheduling, and a strong constraining optimization problem is settled through the crisscross optimization algorithm, thereby realizing a scheduling effect with relatively high economical performance, and improving solving efficiency and accuracy. Furthermore through using a rotation standby requirement in a preset constrained condition, an error and an accidental electric load offset in maximal power generation output are compensated.

The embodiment of the invention discloses a reversible information hiding method, device and equipment for carrying out multi-histogram point selection based on a crisscross algorithm and a computer readable storage medium. The method comprises the steps of acquiring local features of each image block of a carrier image, wherein the local features of each image block comprise the sum of longitudinal pixel differences and the sum of transverse pixel differences; setting a category label for each image block; calculating a prediction error of a central pixel point of each image block, and generating a prediction error histogram for each category; determining an embedded point combination from the plurality of prediction error histograms by using a crisscross algorithm; and based on the embedding point combination, carrying out watermark embedding on the carrier image by using a histogram translation method to generate a secret-carrying image. On the premise of guaranteeing the high fidelity of the secret-loaded image, the optimal embedding point combination is quickly found, the calculation complexity is greatly reduced, the time cost of watermark embedding is reduced, and the practicability is high.

The invention discloses a direct-current microgrid power optimization configuration and operation method based on wave power generation. A storage battery adopts variable power control for dividing aworking state of a wave power generation direct-current microgrid system into multiple working states, and based on a power difference of the wave power generation capacity and the load consumption, the directions and values of charging and discharging power in the storage battery are controlled, so that the wave power generation direct-current microgrid system is switched in the multiple states.The power optimization of the wave power generation direct-current microgrid system is divided into MPPT control and limited power control: when the wave power generation direct-current microgrid system works in the MPPT control, the wave power generation direct-current microgrid system tracks a maximum output power point of a wave power generation device in combination with a criss-cross algorithm; and when the wave power generation direct-current microgrid system is in the limited power control, the wave power generation direct-current microgrid system is used for controlling output power ofthe wave power generation device in combination with the criss-cross algorithm. According to the method, the output power can maintain stable operation of the wave power generation direct-current microgrid system.

The invention discloses an engineering parameter optimizing method. The engineering parameter optimizing method comprises the steps of constructing a target function corresponding to a preset engineering problem beforehand; utilizing a novel grey wolf algorithm to solve the target function on the premise that a constraint condition of the target function is satisfied, wherein the process of utilizing the novel grey wolf algorithm to solve the target function specifically comprises the steps of presetting a wolf pack; conducting iteration and renewal on the wolf pack for S times to obtain a renewed wolf pack; screening out a global optimum individual from the renewed wolf pack, and determining the dimension corresponding to the global optimum individual as an optimum engineering parameter, and the iteration and renewal process comprises the steps of renewing the wolf pack, conducting fitness calculation, and utilizing lengthways interlace operation to correct the renewing direction. According to the engineering parameter optimizing method, a competition strategy is added, the lengthways interlace operation in a crisscrossed algorithm is further utilized, and thus the probability that the wolf pack is involved into local optimum is avoided. Besides, the invention further discloses an engineering parameter optimizing system.

A method for predict short-term wind speed the parameters of neural network are optimized by crossover algorithm, By means of iterative longitudinal and transverse cross-calculations of wind velocityparticles, the most suitable particles were screened out, Fitness reflects the difference between the target output and the actual output, the higher the fitness, the stronger the prediction ability of neural network, the particles with the highest fitness can embody the optimal solution of the whole training wind speed group, The particle with the highest fitness can not only find the optimal solution for the whole, It avoids the defect of the local optimization of the neural network, and can improve the generalization ability of the neural network by adjusting the parameters of the neural network with the highest fitness, the network parameters are better, the prediction accuracy can be greatly improved, and then the utilization of wind energy can be improved. The invention also discloses a short-term wind speed prediction device, a device, a system and a readable storage medium, which have the beneficial effects.

The invention discloses a power grid optimal power flow problem solving method based on a distributed crisscross algorithm, and the method employs a local area network computer group system as a distributed computing environment of the crisscross algorithm, and aims at realizing high parallelism of population crisscross operation and fitness calculation by using the advantages of parallel computing of the crisscross algorithm and the interactivity and mobility of a multi-agent system . According to each evolution of the original crisscross algorithm population, a new population is generated through alternation of transverse crossover and longitudinal crossover, and then the current optimal value of an individual is reserved according to a greedy principle, so that reduction of communication overhead is facilitated, the calculation efficiency is improved, and meanwhile, the possibility is provided for enhancing the flexibility of distributed parallel calculation of the crisscross algorithm. The multi-agent parallel computing platform based on the crisscross algorithm is developed by combining the characteristics of non-global control of the crisscross algorithm and the advantage ofmulti-agent system distribution.

The invention discloses a failure recovery method of a direct-current power distribution network. The failure recovery method comprises the steps that firstly, after failure is cut off, the network issubjected to dynamic island dividing according to output power prediction of a distributed power source and demand prediction of loads; secondly, a network reconstruction model of the direct-currentpower distribution network is established, a suitable objective function is selected, and a binary crisscross optimization algorithm is adopted for solving under the premise of meeting the constraintcondition; and finally, if a power grid still cannot meet the constrain condition, part of the loads are cut off according to the importance degree grade of the loads till the power grid recovers to be in a qualified state. An island is divided firstly, then the network is optimized through global reconstruction, island dividing and global reconstruction are conducted once again at intervals of Ton the time scale, the optimal failure recovery strategy is realized, and power supplying can be removed more effectively.

The invention discloses a two-stage scheduling model optimization method for an integrated energy system. The method comprises the following steps: S1, constructing a day-ahead economic scheduling model according to the operation cost of system equipment; S2, correcting the operation state of each micro-unit based on the day-ahead economic scheduling model, and constructing a real-time optimization scheduling model; S3, based on the real-time optimization scheduling model, improving a population variation mode by mapping a chaotic crisscross algorithm so as to ensure population diversity and all information of excellent individuals; and S4, constructing a two-stage scheduling optimization solving process based on a CCSO-BOS algorithm. According to the method, a day-ahead scheduling optimization model and a real-time scheduling optimization model of the comprehensive energy system are established on the basis of load prediction and renewable energy processing prediction data. The proposed multi-objective nonlinear optimization problem can be solved, so that renewable energy can be consumed and utilized to the maximum extent. The operation cost of the system is effectively reduced.

The invention relates to an energy consumption management method of a data center and discloses an energy-saving scheduling method of the data center. The energy-saving scheduling method comprises the following specific steps: scheduling method generation: randomly generating a plurality of virtual machine scheduling methods, wherein the virtual machine scheduling methods refer to corresponding relationships between virtual machines and a server; scheduling optimization: adjusting the virtual machine scheduling methods through a cross algorithm and a mutation algorithm to obtain a final scheduling result, and executing the final scheduling result, wherein the cross algorithm comprises the step of selecting a higher-fitness virtual machine scheduling method to conduct cross operation; the mutation algorithm comprises the step of selecting a lower-fitness virtual machine scheduling method for conduct cross operation. The energy-saving scheduling method of the data center has the advantages that the problem of difficult energy consumption optimization of the data center is solved, the accuracy is high, the energy-saving effect is good, the calculation steps are fewer and online real-time calculation can be supported.

The invention provides a battery fault diagnosis method based on a crisscrossing optimizing fuzzy BP neural network. The battery fault diagnosis method includes the steps that firstly, fuzzification is conducted on a sample, information of inaccuracy or indeterminacy and the like in fault diagnosis are processed, and thus atraining sample of the neural network is more accurate; and next, various weights and threshold valves of the neural network are optimized by using a crisscrossing algorithm, thus a convergence speed of the neural network is accelerated, local optimum cannot be trapped, a fuzzy theory is combined with optimizing of crisscrossing to the neural network, and thus diagnosis to a battery fault is more accurate. The battery fault diagnosis method based on the crisscrossing optimizing fuzzy BP neural network is applied to a series of common batteries of lithium batteries, lead batteries, other fuel batteries and the like, the battery fault can be diagnosed in real time either a standing state or a using state, and compared with other existing battery fault diagnosing methods, the method is higher in accuracy and smaller in error.

The invention provides a cooperative control system for double-winding permanent magnet synchronous motors. The cooperative control system comprises two sets of controllers which are the same in structure and are used for controlling two double-winding permanent magnet synchronous motors. In the hardware structure aspect, a complete electrical dual-redundancy structure is employed, a redundancy backup strategy is achieved in parts, the reliability of which are required to be high, such as a communication part, a resolver signal resolving part and the like, and the working reliability of the control system is improved. In the software control aspect, DSP modules of the two sets of controllers communicate with each other through SPI, the two sets of controller supervise each other under normal working condition, and the fault can be isolated quickly when the fault occurs. With respect to the cooperative control system, a system feedback cross algorithm is employed, the problem that during the operation process, the electromagnetic torque between the two motors is not balanced, and therefore the power of the motors is increased is solved, and the system performance is further improved.

The invention provides a transverse microstructure generation method of a unidirectional long fiber reinforced composite material. In the target area where the RVE model needs to be generated, the initial parameters of the RVE model are determined, the regularly distributed fiber position is taken as the initial fiber position, combined with the intersection algorithm between adjacent rows or columns, under the condition that the periodicity of the fiber at the boundary is ensured, a random perturbation method is utilized to generate the RVE with periodic repetitive fiber random distribution.Based on the obtained random fiber position coordinates, the initial position of the micro-pores is determined, and the size and shape of the pores are determined randomly. Finally, the transverse microscopic model of the composites considering the random distribution of the fiber and the micro-pores is established by random perturbation of the position of the pores. The invention considers the reconstruction technology of the transverse microstructure of the unidirectional long fiber composite material, adopts the random perturbation method for the random distribution of the fibers and the pores, and can effectively and efficiently establish the transverse RVE model considering the random distribution of the fibers and the pores.

The invention discloses a maximum power tracking control method for a photovoltaic system under partial shading. The method mainly comprises the steps of an initialization strategy, a constraint mechanism, fitness calculation, horizontal crisscross, vertical crisscross, global optimization saving and the like. A vertical and horizontal crisscross algorithm adopted by the method is a current novelintelligent optimization algorithm, and compared with particle swarm optimization (PSO), a genetic algorithm (GA) and other intelligent optimization algorithms, the vertical and horizontal crisscrossalgorithm achieves the high-dimensional non-convex multi-peak optimization purpose and has the advantages of high solution precision, high convergence speed and the like. The algorithm achieves the optimization iteration process of a population through the horizontal crisscross, the vertical crisscross and a competition operator, and finally the optimal solution is obtained.

The invention relates to the field of design automation, in particular to a circuit parameter optimization method based on a differential optimization algorithm, which is applied to reference voltagesource design and comprises the following steps: S1, describing device parameters in a circuit structure by using a parameter vector, and selecting a plurality of device parameters as parameter vectors; S2, judging whether the parameter vector meets an optimization termination condition or not, and if so, ending optimization; if not, executing the step S3; S3, obtaining variation vectors in one-to-one correspondence with the parameter vectors by using a variation algorithm according to the parameter vectors; S4, performing cross processing on the parameter vectors and the corresponding variation vectors by using a cross algorithm to obtain cross vectors; and S5, calculating performance indexes corresponding to the parameter vector, the variation vector and the cross vector respectively, selecting a vector which enables the performance indexes to be optimal as a new parameter vector by using a selection algorithm, and executing the step S2. According to the optimization method disclosedby the invention, parameter optimization can be quickly executed on the reference voltage source circuit.

The invention discloses a method for determining wave power generation device parameters. Initial parameters of a wave power generation device can be pre-determined, then multi-time iterative optimization is conducted on the parameters, the parameters are calculated in iteration process each time through a differential mutation algorithm, a longitudinal crossing algorithm and a transverse crossingalgorithm, the adaptability of the parameters is determined through a preset adaptability target function, thus parameters with higher adaptability are screened out, and finally optimal parameters are obtained through multi-time iteration. It is visible that the method integrates the differential mutation algorithm, the longitudinal crossing algorithm and the transverse crossing algorithm, and the optical parameters of the wave power generation device are finally obtained. Experiments show that the method is higher in convergence rate and stronger in local search capability. In addition, theinvention also provides an apparatus and device for determining wave power generation device parameters and a computer readable storage medium. The effects of the apparatus and the device correspond to the effect of the method.

The invention aims to provide a method for quickly finding an optimal solution or an approximate optimal solution of a uniform graph dyeing problem. The invention discloses a method for solving a uniform dyeing problem based on a cultural gene algorithm. The algorithm comprises the following steps: generating a population containing p elite solutions, designing a crossover operator, carrying out local optimization on offspring solutions, and judging whether a newly generated solution is suitable for being added into the population or not. The problem of uniform graph dyeing is solved, that is,the minimum positive integer k value corresponding to a uniform legal k-dyed solution of an undirected graph G = (V, E) is found. A cultural gene algorithm search framework is adopted, and a corresponding cross algorithm, a local search algorithm and a mating pool upgrading algorithm are designed according to a uniform graph dyeing problem. The method is faster and more convenient, and is suitable for solving the load balance problem in the real world.

The invention relates to the technical field of wind power prediction, in particular to an ultra-short-term wind power prediction method based on a DCCSO optimization deep learning model. The method comprises the following steps: collecting original wind power data, preprocessing the original wind power data, and establishing a time sequence attention-gating cycle unit deep learning prediction model; then optimizing an initial weight and a threshold value of the sequential attention-gated loop unit deep learning prediction model based on an improved crisscross algorithm, so that the convergence speed and the generalization performance of the sequential attention-gated loop unit deep learning prediction model can be effectively improved, wherein in the time sequence attention-gated loop unit deep learning prediction model, the time sequence attention can improve the sensitivity of the model to the input time, and the gated loop unit can further mine the hidden time correlation in the input time sequence; besides, the combination of the time sequence attention and the gating circulation unit is of great significance for improving the wind power prediction precision.

In a data processing system for determining intersections between geometric objects, the work is split between a CPU and a stream processor. The intersection determination is controlled by the CPU. Data processing intensive parts of intersection algorithms, such as checking possible overlap of objects, checking overlap of normal fields of objects, approximating the extent of an object, approximating the normal fields of an object, or making conjectures for intersection topology and / or geometry between objects, are run on the stream processor. The results of the algorithmic parts run on the stream processor are used by the part of the algorithms run on the CPU. In cases where conjectures for the computational result are processed on the stream processor, the conjectures are checked for correctness by algorithms run on the CPU. If the correctness check shows that the result found is incomplete or wrong, additional parts of the algorithm are run on the CPU and possibly on the stream processor.