37 results about "Harmony memory" patented technology

The invention discloses a resource allocation method with minimized cloud system cost based on expiration date drive. The resource allocation method comprises the following steps of collecting an available resource of each physical node in a cloud system by a cloud server; collecting a task request of a user; finally allocating a virtual resource in the cloud system by adopting a harmony search method, i.e. initializing parameters of the harmony search method by the cloud server, generating a new solution of the harmony search method by the cloud server, determining an objective function value of the new solution, updating a solution vector in a harmony memory library, determining a solution with minimized cost in the harmony memory library and a cloud system cost value corresponding to the explanation with the minimized cost, repeatedly iterating to maximum iteration times and outputting an optimal harmony solution vector. According to the resource allocation method disclosed by the invention, the available resources in the cloud system are fully excavated; the resources are dynamically allocated from CPU (Central Processing Unit) resources, magnetic disk read-write speed resources and network wideband resources in a plurality of dimensionalities by using a virtual machine diversification technology; the technical support is provided for efficiently utilizing the resources in the cloud system and guaranteeing that tasks are finished within expiration dates.

The invention discloses a charging station layout programming method based on a V-graph and an HS algorithm. The method comprises the steps of firstly, estimating the range of charging stations which are constructed in a programming area through anticipation of charging queuing waiting time; secondly, comprehensively considering multiple factors such as a charging requirement and a region characteristic, establishing a charging station layout programming object according to a charging station construction/operation cost, a charging on-the-way time consumption cost and an arrival-at-station queuing waiting time cost; and finally, randomly generating station address coordinates of the charging stations in the programming area, coding the station address coordinate for obtaining one-directional vectors, defining the service range of each charging station by means of a Voronoi-graph (the V-graph in short) and generating an initial harmony vector, calculating a solution by means of a harmony search (HS) algorithm and storing the solution in a harmony memory (HM), updating the harmony memory through studying the harmony memory and tone fine turning until a number of updating times of the harmony memory is reached, finding out a charging station layout programming objective value and determining an optimal charging station layout programming solution. The charging station layout programming method has advantages of effective integration of multiple factors and high calculating speed. Furthermore the charging station layout programming method can be used for finding out an optimal value.

Systems and methods for optimizing power flows using a harmony search, including decoupling phases in a multi-phase power generation system into individual phase agents in a multi-phase power flow model for separately controlling at least one of phase variables or parameters. One or more harmony segments from harmony memory are ranked and selected based on a utility value determined for each of the decoupled phases. A harmony search with gradient descent learning is performed to move the selected harmony segments to a better local neighborhood. A new utility value for each of the selected segments is determined based on historical performance, and the harmony memory is iteratively updated if one or more of the new utility values are higher than a utility value of a worst harmony segment stored in the harmony memory.

The invention relates to a self-adaptive dual-harmony optimization method which comprises the following steps of: initially optimizing a harmony memory base and putting a generated initial solution into the harmony memory base; then equally dividing the initial solution into two groups, i.e. a master harmony library and an auxiliary harmony library respectively and respectively determining the tone trimming probabilities and the tone trimming bandwidths of the master harmony library and the auxiliary harmony library; iteratively searching from the opposite direction under the situation that the algorithm convergence rules are not satisfied to obtain two groups of new solutions; and replacing a solution in the existing memory bank by using an optimal solution in the two groups of new solutions obtained by multiple iteration, thereby obtaining an optimal solution to finally achieve the wonderful harmony. The self-adaptive dual-harmony optimization method has the beneficial effects that tone trimming probability and tone trimming bandwidth factors are continuously adjusted to improve the dynamic adaptability of an algorithm and the coordination ability of local search and full search; two groups of master and auxiliary harmonies which are different in the search direction and are mutually coordinated are constructed, so that the search range is expanded, the iteration number is reduced, and the global optimization is more quickly realized; the problem of complicated function optimization is solved; and the full search ability and the convergence rate are good.

The invention discloses a traffic image segmentation method based on an improved multi-object harmony search algorithm, and mainly solves problems of a conventional traffic image segmentation technology that the evaluation index is single, the anti-noise performance is poor, the segmentation accuracy is not high, and the number of image segmentation types is required by be determined manually. The implementation steps mainly comprise reading a gray scale image and counting a gray scale histogram; initializing a harmony memory bank; generating a group of new explanations, wherein the size the new explanations is equal to the size the harmony memory bank; updating the harmony memory bank; determining whether a termination condition is met or not; selecting the optimal cluster center from the harmony memory bank according to a PBM evaluation index; and classifying pixels of the image according to the optimal cluster center to obtain a segmentation result. Compared with the conventional traffic image segmentation technology, the method provided by the invention is diversified in evaluation index, high in segmentation accuracy and high in anti-noise performance, can automatically determine the number of segmentation types of the image, and can be applied to the traffic image segmentation.

The invention discloses a hybrid intelligent scheduling optimization method of a manufacturing enterprise workshop. The method comprises the following steps of: initializing related parameters of an HS algorithm and an SA algorithm; according to different production tasks, inputting processing information relating to each task; using a coding mode based on working procedures to code questions, and then utilizing a random generation mode to generate harmony memory HM initial solutions; utilizing the SA algorithm to carry out neighborhood transformation on all the initial solutions, if the solutions after the transformation are better than the initial solutions, then receiving the solutions after the transformation; and if not, then receiving the solutions after the transformation with a probability which successively decreases with a temperature in the SA algorithm; utilizing three kinds of mechanism, such as harmony memory learning, variable fine tuning and new tone random generation, to generate new solutions; utilizing the SA algorithm to carry out neighborhood transformation on the new solutions and to determine whether to receive the new solutions; establishing a target optimization function, and updating the HM according to an optimization result; and if a maximum iteration number is reached, outputting an optimal harmony solution, and drawing a scheduling Gantt chart of the system. The hybrid intelligent scheduling optimization method has the advantages that the hardware requirements are low, and the optimal solution can be found easily.

The invention relates to a dynamic frequency spectrum distribution method of a cognitive heterogeneous network. A probability HMCR carrying out selection from a quantum harmony set is set and a quantum-harmony-based dynamic frequency spectrum method is initialized; a quantum tone of each quantum harmony is measured to obtain a harmony base x and a harmony memory base H, and fitness calculation is carried out on each harmony and the corresponding fitness values are respectively stored in a Fit and a Fit 1; if rand is less than HMCR, the quantum tone of the last-generation quantum harmony is inherited and a quantum rotating gate is started to generate a new solution; if the rand is larger than the HMCR, a tent pseudo chaos sequence is generated randomly to generate a new quantum harmony; the quantum tone of each quantum harmony is measured successively to obtain a corresponding harmony, and fitness calculation is carried out to replace the corresponding fitness value in the Fit 1; and a global optimum harmony in the harmony memory base H is outputted in a loop iteration mode and global optimum harmony mapping is carried out to obtain a frequency spectrum distribution matrix A that is the optimum frequency spectrum distribution scheme of the cognitive heterogeneous network.

The invention discloses a defense penetration path planning method of an underwater vehicle based on a harmony search algorithm. The method mainly comprises the following steps: (1) initializing parameters, and carrying out discretization on a space; (2) initializing a harmony memory bank; (3) generating a new path; (4) updating the harmony memory bank; (5) judging whether end conditions are met or not, if yes, ending, and outputting the optimal path, if not, returning to the step (3) to continue. According to the invention, collaborative evolutionary ideas are introduced into the harmony search (HS) algorithm, and then a collaborative harmony search (CHS) algorithm is put forward. Through a test of standard test functions, compared with the original algorithm, the CHS algorithm is greatly improved in convergence accuracy and convergence speed, furthermore, compared with simple genetic algorithm (SGA) and particle swarm optimizers (PSO) algorithm, the CHS algorithm can avoid the premature convergence problem to a great extent.

An embodiment of the invention provides a robot structure error compensation method and device which are applied to a robot comprising at least one joint. The method includes the steps: taking a builtinitial harmony memory as a current harmony memory and initializing HMCR (harmony memory considering rate), PAR (pitch adjusting rate) and BW (bandwidth); selecting a first target harmony from a preset/current harmony memory according to the relationship between a first random number and the HMCR; processing the first target harmony based on the BW according to the relationship between a second random number and the PAR; updating the current harmony memory according to the relationship among target function values of the processed harmony and harmonies of the current harmony memory; updatingthe PAR and the BW according to preset rules and returning to select the first target harmony if the updated harmony memory cannot meet preset conditions; replacing original joint variable values of joints by candidate joint variable values of the joints corresponding to the harmony with the minimum target function value in the updated harmony memory. When the robot is in any structures, structureerrors of the robot can be compensated.

The invention provides a harmony search algorithm for solving mixed loading of various large-batch cold-chain articles. The method comprises the following steps: firstly, acquiring various parametersof to-be-conveyed cold-chain articles and a used single-temperature-zone refrigerator car, establishing a mixed loading model when different cold-chain articles are assembled to the single-temperature-zone refrigerator car, then establishing an initial harmony memory bank, obtaining an initial solution by adopting a random search algorithm, and repairing the solution through a repairing operator until a required number of solution vectors are obtained; secondly, calculating a new solution according to the parameters and harmony search rules and repaired, and finally obtaining a cold-chain article mixed loading scheme meeting the conditions. Under the condition that the temperature constraint, the volume constraint and the weight constraint of the single-temperature-zone refrigerator car are met, a harmony search algorithm is adopted for automatic calculation, and an assembling scheme with the minimum humidity difference, the minimum shelf life difference and the minimum mixed loading type difference as targets is generated.

The invention relates to a maximum power point tracking method under a local shadow condition, which comprises the following steps of: 1) constructing a photovoltaic cell model, a booster circuit model and a controller model based on a harmony search algorithm by combining current-voltage characteristics of a photovoltaic array under the local shadow; 2) initializing parameters of a self-adaptive harmony search algorithm, initializing a harmony memory bank, taking an optimized initial voltage value as harmony, generating a new harmony vector, and further obtaining an updated voltage; 3) updating the harmony vector in the harmony memory bank; and 4) judging whether an algorithm termination standard is reached or not, if so, outputting the optimal voltage and tracking the global maximum power point, otherwise, continuing to generate a new harmony vector and updating the harmony memory bank until the algorithm termination standard is reached. Compared with the prior art, the method has the advantages of improving the tracking speed and precision, improving the solar energy utilization rate and the like.

The invention discloses a radiomics feature selection method based on momentum adaptive harmony search, and belongs to the technical field of radiomics. The method comprises the following steps of: 1, checking a region of interest (ROI) of the medical image; 2, adrenal tumor CT image data containing the ROI are read; 3, extracting original image features from the read image data; 4, defining an objective function of the method for minimizing the problem; 5, initializing a harmony memory bank; 6, initializing the maximum number of iterations, the HMCR and the PAR; 7, generating a new solution j; 8, updating the harmony memory bank; and 9, repeating the steps 7-8, and outputting an optimal feature subset. According to the method, the HMCR and the PAR are dynamically adjusted, so that sinking into a local optimal solution is avoided, and the robustness of the algorithm is enhanced; the concept of momentum gradient descent is fused, and convergence is accelerated; the fitness function is adjusted, and the essence of the feature search optimization problem is better conformed.

The invention provides a dynamic scheduling method and system of orbital automatic guided vehicles based on harmony search. The method comprises the steps of: setting initial state parameters, variousprocessing parameters and optimization parameters of various numerically-controlled machine tools; encoding the serial numbers of the numerically-controlled machine tools served by an RGV trolley forN times in the future as a harmony vector with a length N, constructing a plurality of harmony vectors according to a specified harmony vector length and an encoding scheme to form an initial harmonymemory vault, and calculating a fitness value of each harmony vector in the harmony memory vault; randomly taking values within a variable value taking range to form a new harmony, or selecting the harmony in HM and performing disturbance and fine tuning to calculate a new harmony, and calculating the fitness value of the new harmony; updating the harmony memory vault according to the fitness value of the new harmony; and judging whether the current number of iterations reaches the maximum number of iterations, and if so, selecting a harmony with the best quality from the harmony memory vaultfor decoding, and the using the decoding result as the process in which the RGV trolley sequentially provide services for the corresponding numerically-controlled machine tools according to the sequence of the serial numbers of the numerically-controlled machine tools in the harmony vector, or otherwise, returning to the step of forming the new harmony.

The invention relates to an energy efficient routing method based on harmony search, which comprises the following steps of: searching N paths which can be directly reached between a source node and adestination node; starting from a source node, generating a random number P1 between 0 and 1 randomly; if the random number P1 is smaller than the memory bank value probability HCMR, selecting a nexthop node corresponding to Ns from the generated HMS when the next hop node is selected, and after selection is completed, determining the position of the next hop node through a roulette method; calculating an objective function for measuring the energy consumption condition of the generation path in the whole network; and comparing the target function value of the newly generated path with theminimum target function value in the harmony memory bank, and if the generated new solution is smaller than the optimal solution in the harmony memory bank, updating the newly generated path to the harmony memory bank HM.