Research on Location Selection Model of Base Station based on Improved Genetic Algorithm
0
Citation
0
Reference
10
Related Paper
Abstract:
With the increase in the number of users accessing the 5G network in the future, how to choose the location of 5G base stations to ensure effective network coverage of the service area, so as to provide reliable communication and transmission services, is a key issue to be considered. By establishing an improved genetic algorithm model, the site planning problem is solved. According to the circular coverage area of the base station, the coverage requirement and the minimum cost optimization goal are completed. First, denoising according to business volume, and finally get 35,915 weak coverage points. The sum of the cost of setting up macro base stations and micro base stations is the optimization goal, and the coverage rate of the weak coverage point is more than 90%, is set as the constraint condition. At the same time, the lethal factor is set in the selection process, and the individuals who do not meet the threshold conditions of the original base station are deleted. The improved operator is adopted in the crossover link and mutation link, which speeds up the running speed of the algorithm and ensures the population diversity and the accuracy of the results. Finally, 689 macro base stations and 269 micro base stations are established, with a coverage rate of 93.51% and an optimal cost solution of 7159. By visualizing the results on the coordinate map, it can be clearly seen that most of the weak coverage points have been covered, which shows that the improved genetic algorithm shows fast convergence speed and good optimal value, and verifies the effectiveness of the model.Keywords:
Base (topology)
Selection algorithm
The genetic algorithm with competitive selection between adjacent two generations changes the selection method of the simple genetic algorithm, and improves search efficiency. But the two generation competitive genetic algorithm is ease to become premature, and partial the best search ability can't be improved. Improvement genetic algorithm has been proposed about these problems, thought the adaptive adjustment of the mutation probability, and the position of crossover and mutation in chromosomes, the proposed method can improve the property of the genetic algorithm with competitive selection between adjacent two generations. It's been identifying in experiment that the improved algorithm can efficiently overcome premature problem and increase the ability of the partial best search.
Position (finance)
Cite
Citations (0)
Genetic algorithm is a well-known heuristic search algorithm, typically used to generate valuable solutions to optimization and search problems. The most important operation in a genetic algorithm is crossover, as it has the greatest effect on its convergence rate. Therefore, in order to achieve the most optimal results in a reasonable time, one has to decide on the crossover type, as well as make a selection of a crossover point. In order to explore the effect of the crossover point selection methods on the convergence rate, we conducted experiments based on different crossover point selection criteria, whereby the results indicate the high importance of controlling the randomization of the crossover point selection range.
Cite
Citations (0)
The problem of automatic selection and configuration of base station sites in the dynamic scenario is investigated. We propose a intelligent approach based on Genetic Algorithm used to adjust the level of the antenna power and select the base stations’ site from the candidate sites. According to the users’ density the base stations adjust their antenna radiated power automatically. Results are given that most of base stations are powered off when the density becomes very low, and show that it will save lots of energy resources. Since this algorithm can adjust the status of base stations intelligently and automatically, it can be used in SON.
Base (topology)
Selection algorithm
Cite
Citations (1)
To resolve the design of radar orthogonal signal problem,this paper proposed a new algorithm based on genetic algorithm and simulated algorithm.The algorithm used genetic algorithm for global search,while simulated algorithm for local search.It improved genetic algorithm strategy,and introduced the adaptive probability changes to the crossover and mutation,and adaptive to preserve the best individual,and the genetic algorithm results were selectively simulated operation,which resolved the problem of premature and time.The experiment results show that the proposed algorithm is effective and feasible,which the performance is better than traditional genetic algorithm and simulated algorithm.
Cite
Citations (1)
In order to address the problem that current genetic algorithm used in service composition selection cannot get optimization,a genetic algorithm improved is proposed. The improved methods include self-adaptive crossover,self-adaptive mutation and stochastic uniform selection. The simulation shows,the fitness value can be improved seven percent from the aspect of optimization. And with the increase of the number of abstract services,the advantage is more significant,so it's especially fit for large number of abstract services.
Fitness proportionate selection
Value (mathematics)
Cite
Citations (0)
Spatial Feature Aware Genetic Algorithm of Network Base Station Configuration for Internet of Things
Network configurations, which maximize the accessed number of the sensor devices in IoT subjected to limited active base stations is an important topic. The weakness of traditional genetic algorithms mainly lies in that the spatial feature, i.e., the geometry distribution of base stations, is not considered. A novel genetic algorithm, in which the spatial feature of base stations is taken into account, to obtain the optimal subset of base stations in IoT is proposed. The crossover operation and the mutation operation are designated based on the spatial characteristic. Experiments have been conducted to prove the proposed algorithm for the network configuration.
Base (topology)
Feature (linguistics)
Cite
Citations (5)
The space allocation problem particularly in academic institutions is well known as a complex, difficult and time consuming task. This paper investigates the optimum genetic operators’ selection method in genetic algorithm in handling combinatorial optimisation problems. The discussed space allocation problem focuses on the distribution of timetable among available lecture halls and rooms in the university. We investigate the optimum selection method to select parents during the reproduction and crossover genetic operations. The investigated selection methods are random, deterministic and roulette wheel selection.
Fitness proportionate selection
Roulette
Truncation selection
Genetic operator
Cite
Citations (0)
This paper introduces a new selection scheme inspired by sexual selection and some new methods based on combination of crossovers, concept of sexual selection and lifetime for chromosomes. A bi-linear allocation lifetime approach is used to label the chromosomes based on their fitness value. After selecting a label for each chromosome, using fuzzy rules and selecting a suitable crossover method, initially prepared for recombination in the genetic algorithm (GA). Computational experiments are conducted to compare the performance of this new technique with some commonly used crossover mechanisms found in a standard GA in order to solving some numerical functions from the literature.
Key words: Genetic algorithm, selection, sexual selection, fuzzy, crossover.
Truncation selection
Cite
Citations (1)
In order to effectively enhance its competitiveness in the domestic and foreign aviation markets, it is possible to directly reduce the cost of the airlines by configuring the aircraft types of airlines. This paper takes actual problems as constraints and establishes a model configuration model by setting multiple constraints. The genetic algorithm is used to solve it, and its optimal solution is obtained by means of selection, crossover and mutation. Comparing it with the optimal solution obtained by mixed integer linear programming, it is found that as the number of iterations increases, it can be clearly found that the cost of the optimal solution gradually decreases. It proves the effectiveness of genetic algorithm in optimizing aircraft configuration of airlines.
Cite
Citations (1)
The logistics distribution path planning is important for improving the efficiency of logistics distribution and saving logistics costs.The optimization of logistics distribution path length is converted to a classic Traveling Salesman Problem(TSP) optimization problem.The mathematical model is established.An improved genetic algorithm is put forward based on the mathematical model.Then,sequence-based selection operator,minimum cost tree-based crossover operator and random length control-based mutation operator are proposed for the selection,crossover and mutation of the genetic algorithm,respectively.The simulation results based on comparison between the improved genetic algorithm and the simple genetic algorithm show that the improved genetic algorithm has better global searching ability,fast convergence.As a result,it is an effective method to solve the logistics distribution path optimization problem.
Genetic operator
Operator (biology)
Cite
Citations (5)