We present a complete system to optimize traffic lights green phases and temporal offsets based on a combination of microscopic simulation and black box, evolutionary algorithms. We also report the outcome of an AI ve...
详细信息
ISBN:
(纸本)9789897583742
We present a complete system to optimize traffic lights green phases and temporal offsets based on a combination of microscopic simulation and black box, evolutionary algorithms. We also report the outcome of an AI versus experts comparison workshop conducted with our algorithm and seasoned experts from a specialized traffic engineering office. Experimental results indicate that the proposed algorithmic scheme significantly outperforms expert efforts. Our system entails a memetic (genetic+gradient) calibration module to adapt the Origin/Destination (O/D) matrix to current traffic conditions, an inoculation procedure to incorporate existing traffic light programs, genetic multi-objective optimization capabilities and sound metrics. Experiments are conducted over several real world datasets of operational sizes from the Paris outskirts and various other French urban areas. Our experimental outcome is threefold. First, we report the success of the memetic calibration module in adjusting the simulator's O/D matrix to a point with variation levels corresponding to recorded sensor data. Second, we confirm the ability of the system to obtain significant gains on that sound basis: gains ranging from 15% to 35% are consistently reached on both traffic jams reduction and pollutant emissions. Most importantly, we report the outcome of the comparison workshop: a formalized methodology followed by experts to manually optimize traffic lights, iterative experimental logs tracing the application of that methodology to two real world cases and comparable results obtained by the algorithm on the same cases. Results indicate that the AI module performs significantly better than experts in both speed and final solution quality.
This paper addresses nonlinear time series modelling and prediction problem using a type of wavelet neural networks. The basic building block of the neural network models is a ridge type function. The training of such...
详细信息
ISBN:
(纸本)9783030205218;9783030205201
This paper addresses nonlinear time series modelling and prediction problem using a type of wavelet neural networks. The basic building block of the neural network models is a ridge type function. The training of such a network is a nonlinear optimization problem. evolutionary algorithms (EAs), including genetic algorithm (GA) and particle swarm optimization (PSO), together with a new gradient-free algorithm (called coordinate dictionary search optimization - CDSO), are used to train network models. An example for real speed wind data modelling and prediction is provided to show the performance of the proposed networks trained by these three optimization algorithms.
Present article investigates a novel method of pattern synthesis in planar array using restricted search Evolution algorithms. Multiple objectives of Side Lobe Level and beamwidth control have been transformed in sing...
详细信息
ISBN:
(纸本)9781728135175
Present article investigates a novel method of pattern synthesis in planar array using restricted search Evolution algorithms. Multiple objectives of Side Lobe Level and beamwidth control have been transformed in single objective using weighted sum technique. In said optimization process excitation amplitude weights along with uniform inter-element spacing respectively have been considered as optimization parameters. Effectiveness of the proposed method has been illustrated through design and validation of 9x9 planar array configuration.
Ocean exploration has always attracted research interest. One of the most significant advances in the area of underwater navigation is an unmanned, self-propelled vehicle, namely the Autonomous Underwater Vehicle (AUV...
详细信息
ISBN:
(纸本)9781728155845
Ocean exploration has always attracted research interest. One of the most significant advances in the area of underwater navigation is an unmanned, self-propelled vehicle, namely the Autonomous Underwater Vehicle (AUV). Since the level of autonomy is crucial for AUVs, path planning is identified as one of the core components to improve AUV persistence. This study examines the optimization problem of underwater rendezvous through a cluttered and variable operating field. An improved Particle Swarm Optimization (PSO) algorithm is introduced for underwater path planning and assessed against the classic PSO with respect to optimal solution quality and energy efficiency. Our results based on extended Monte Carlo simulations demonstrate robustness and efficiency of the proposed planners for optimal and collision free path planning. Finally, we set the scene for further enhancement in the area of evolutionary algorithms.
The traveling salesman problem is a well-known combinatorial optimization problem with permutation-based variables, which has been proven to be an NP-complete problem. Over the last few decades, many evolutionary algo...
详细信息
ISBN:
(纸本)9789897583841
The traveling salesman problem is a well-known combinatorial optimization problem with permutation-based variables, which has been proven to be an NP-complete problem. Over the last few decades, many evolutionary algorithms have been developed for solving it. In this study, a new design that uses the k-means clustering method, is proposed to be used as a repairing method for the individuals in the initial population. In addition, a new crossover operator is introduced to improve the evolving process of an evolutionary algorithm and hence its performance. To investigate the performance of the proposed mechanism, two popular evolutionary algorithms (genetic algorithm and differential evolution) have been implemented for solving 18 instances of traveling salesman problems and the results have been compared with those obtained from standard versions of GA and DE, and 3 other state-of-the-art algorithms. Results show that the proposed components can significantly improve the performance of EAs while solving TSPs with small, medium and large-sized problems.
The subject of the study is an application of evolutionary algorithms to optical node optimization in dense wavelength division multiplexing optical networks. The wider context of the presented research is in essence ...
详细信息
ISBN:
(纸本)9781510630666
The subject of the study is an application of evolutionary algorithms to optical node optimization in dense wavelength division multiplexing optical networks. The wider context of the presented research is in essence an improvement of service flexibility and achieving savings in capital expenditures in DWDM networks. Thus, the main objective of the optimization is to minimize capital expenditure, which includes the costs of optical node resources, such as transponders and filters used in new generation of reconfigurable optical add drop multiplexers, etc. For this purpose a model based on integer programming is proposed. The efficiency of the integer programming based software is compared with that of evolutionary algorithms. The results obtained show that there is a large advantage in using evolutionary algorithms for optimizing large optical networks when compared with integer programming and mixed integer programming, whereby the two latter algorithms fail to find the optimal solution within reasonable computational time. The numerical experiments were carried out for realistic networks of different dimensions and traffic demand sets.
Event Takeover Values (ETV) measure the impact of each individual in the population dynamics of evolutionary algorithms (EA). Previous studies argue that ETV distribution of panmictic EAs fit power laws with exponent ...
详细信息
ISBN:
(纸本)9781450367486
Event Takeover Values (ETV) measure the impact of each individual in the population dynamics of evolutionary algorithms (EA). Previous studies argue that ETV distribution of panmictic EAs fit power laws with exponent between 2.2 and 2.5 and that this property is insensitive to fitness landscapes and design choices of the EAs. One exception is cellular EAs, for which there are deviations of the power law for large values. In this paper, ETVs for structured and panmictic EAs with different population size and mutation probability on several fitness landscapes were computed. Although the ETVs distribution of pamictic EAs is heavy-tailed, the log-log plot of the complementary cumulative distributed function shows no linearity. Furthermore, Vuong's tests on the distributions generated by several instances of the problems conclude that power law models cannot be favored over log-normal models. On the other hand, the tests confirm that cEAs impose significant deviations to the distribution tail.
An experimental comparison of evolutionary algorithms and random search algorithms for the optimal control problem is carried out. The problem is solved separately by several representatives of each type of algorithms...
详细信息
An experimental comparison of evolutionary algorithms and random search algorithms for the optimal control problem is carried out. The problem is solved separately by several representatives of each type of algorithms. The simulation is performed on a mobile robot model. The results of each algorithm performance are compared according to the best found value of the fitness function, the mean value and the standard deviation. (C) 2019 The Authors. Published by Elsevier B.V.
Service organizations such as telecom or utility companies require uninterrupted availability of spare parts to maintain their service. It is very important for them to have right spares available at the right time at...
详细信息
ISBN:
(纸本)9781728124858
Service organizations such as telecom or utility companies require uninterrupted availability of spare parts to maintain their service. It is very important for them to have right spares available at the right time at the right place. Spare parts are normally kept in a warehouse and it is crucial that the warehouses are also located in the right place, where they can provide maximum value to the business. Warehouses are increasingly getting smaller and mobile in their nature, which can be quickly deployed and redeployed to different locations in a very short time. Finding the optimal deployment locations of the warehouses quickly can be challenging, especially when there are a large number of storages involved. In this work, we present an evolutionary algorithm based approach to deploy a large number of mobile warehouses. The resulting tool can be periodically utilized to relocate them to different locations according to changing business requirements, at the same time providing a significantly better quality of design in comparison to a typical traditional manual mechanism. The presented solution is incorporated into a system called Intuit Strategic Planner that is operational at a major UK telecom and has contributed to a significant cost saving for the business.
With' the continuous application of evolutionary algorithms in various combinatorial optimization problems, the traditional evolutionary algorithms are prone to premature convergence and fall into local optimizati...
详细信息
ISBN:
(纸本)9781450362948
With' the continuous application of evolutionary algorithms in various combinatorial optimization problems, the traditional evolutionary algorithms are prone to premature convergence and fall into local optimization solutions as the complexity of the problems increases. To solve this problem, this paper proposes a hybrid algorithm combining the Generative adversarial nets (GAN) and Genetic Algorithm (GA). The algorithm is based on Genetic Algorithm and introducted the GAN sample as another sample to the generated model. The algorithm expected more abundant sample information through GAN mining, got the advantage of sample training GAN through the GA. It makes GAN learn from the edge of sample information, which can generate more advantages of samples. The generated sample is injected into the evolution of the next generation, increasing the diversity of samples and increasing the opportunity to find the optimal solution. In this paper, the hybrid algorithm is used to solve the Permutation Flow Shop Problem to verify the algorithm's solution ability. Experimental results show that the hybrid algorithm can avoid premature local optimal solution compared with the traditional evolutionary algorithm.
暂无评论