Abstract
For the single-phase ground fault, which has the highest probability of occurrence in a 10 kV distribution network, the ant colony algorithm is combined with a neural network for fault line ...selection, and the algorithm is optimized. The study builds a 10 kV distribution network model in MATLAB and simulates the neutral ground fault. It compares the results of the optimized line selection algorithm, and the traditional line selection algorithm proves that the accuracy of the method in identifying faulty lines is significantly better than that of the traditional method.
Wireless Sensor Networks (WSN) became a key technology for a ubiquitous living and remains an active research due to the wide range of applications. The design of energy efficient WSN is still a ...greater research challenge. Clustering techniques have been widely used to reduce the energy consumption and prolong the network lifetime. This paper introduces an algorithm named Fuzzy logic based Unequal clustering, and Ant Colony Optimization (ACO) based Routing, Hybrid protocol for WSN to eliminate hot spot problem and extend the network lifetime. This protocol comprises of Cluster Head (CH) selection, inter-cluster routing and cluster maintenance. Fuzzy logic selects CHs efficiently and divides the network into unequal clusters based on residual energy, distance to Base Station (BS), distance to its neighbors, node degree and node centrality. It uses ACO based routing technique for efficient and reliable inter-cluster routing from CHs to BS. Moreover, this protocol transmits data in a hybrid manner, i.e. both proactive and reactive manner. A threshold concept is employed to transmit/intimate sudden changes in the environment in addition to periodic data transmission. For proper load balancing, a new routing strategy is also employed where threshold based data transmission takes place in shortest path and the periodic data transmission takes place in unused paths. Cross-layer cluster maintenance phase is also used for uniform load distribution. The proposed method is intensively experimented and compared with existing protocols namely LEACH, TEEN, DEEC and EAUCF. The simulation results show that the proposed method attains maximum lifetime, eliminates hot spot problem and balances the energy consumption among all nodes efficiently.
In this paper we present an extension of ant colony optimization (ACO) to continuous domains. We show how ACO, which was initially developed to be a metaheuristic for combinatorial optimization, can ...be adapted to continuous optimization without any major conceptual change to its structure. We present the general idea, implementation, and results obtained. We compare the results with those reported in the literature for other continuous optimization methods: other ant-related approaches and other metaheuristics initially developed for combinatorial optimization and later adapted to handle the continuous case. We discuss how our extended ACO compares to those algorithms, and we present some analysis of its efficiency and robustness.
The application of swarm intelligence algorithms to wireless sensor networks (WSNs) deployment has been the focus of research community for past few years. One such algorithm is ant colony ...optimization (ACO), whose application in reducing the cost of WSNs in terms of deployed sensor nodes has recently attracted attention of the researchers. In this letter, we propose an ACO-based framework for WSN deployment in a realistic 3-D environment, by making modifications to the standard ACO algorithm. The simulation results lead to the conclusion that the proposed framework achieves better performance compared with the state-of-the-art ACO-based algorithms in terms of size of the solution for node deployment. In addition, in a 3-D environment, time overhead problem arises in standard ACO-based algorithms since they require a large number of iterations to achieve better solutions. In contrast, the performance of the proposed approach does not degrade with reduction in number of iterations, which enables the algorithm to achieve quick convergence.
Microwave microfluidic sensors have been employed for dielectric characterization of different liquids. Intuitively, the microfluidic channel plays a vital role in determining the sensor performance. ...In this article, for the first time, numerical optimization design of microfluidic channel route is carried out with the aim of improving the sensor sensitivity. Two swarm intelligence algorithms, i.e., particle-ant colony optimization algorithm and wolf colony algorithm, are implemented for the route optimization. Through the developed optimization procedure, the sensor sensitivity of the original design can be increased significantly. Several prototypes of optimized sensors are fabricated and tested, and they exhibit good capability in retrieving the liquid properties. In comparison with original complementary split-ring resonator-based sensor with a sensitivity of 0.308% for water measurement, the optimized sensor achieves a high sensitivity value of 0.55%, i.e., the sensor sensitivity is increased by 78.6% after optimization. The developed methodology can also be used in other designs, such as series LC -based sensor, whose sensitivity can be improved by about 50%. It is demonstrated that the developed methodology possesses good automatic optimization ability and universality for the optimal design of microwave microfluidic sensors.
In this paper, we present a multi-objective vehicle routing problem with flexible time windows (MOVRPFlexTW). In this problem, a fleet of vehicles can service a set of customers earlier and later ...than the required time with a given tolerance. This flexibility enables a logistics company to save distribution costs at the expense of customer satisfaction. This paper uses a direct interpretation of the vehicle routing problem with flexible time windows (VRPFlexTW) as a multi-objective problem, where the total distribution costs (including travel costs and fixed vehicle costs) are minimized and the overall customer satisfaction is maximized. We propose a solution strategy based on ant colony optimization and three mutation operators, which incorporates the concept of Pareto optimality for multi-objective optimization. The performance of the proposed approach was evaluated using the well-known benchmark Solomon’s problems. Our experimental results show that the suggested approach is effective, because it provides solutions that are comparative to the best known results in the literatures. Finally, we not only highlight the advantages of MOVRPFlexTW when compared with the single objective VRPFlexTW, but also illustrate its applicability and validation by analyzing a real case.
Load Balancing (LB) is one of the most important tasks required to maximize network performance, scalability and robustness. Nowadays, with the emergence of Software-Defined Networking (SDN), LB for ...SDN has become a very important issue. SDN decouples the control plane from the data forwarding plane to implement centralized control of the whole network. LB assigns the network traffic to the resources in such a way that no one resource is overloaded and therefore the overall performance is maximized. The Ant Colony Optimization (ACO) algorithm has been recognized to be effective for LB of SDN among several existing optimization algorithms. The convergence latency and searching optimal solution are the key criteria of ACO. In this paper, a novel dynamic LB scheme that integrates genetic algorithm (GA) with ACO for further enhancing the performance of SDN is proposed. It capitalizes the merit of fast global search of GA and efficient search of an optimal solution of ACO. Computer simulation results show that the proposed scheme substantially improves the Round Robin and ACO algorithm in terms of the rate of searching optimal path, round trip time, and packet loss rate.
In this article, an improved multiobjective ant colony optimization (ACO) algorithm is proposed to design the weighting factors (WFs) in the model predictive control of power converters. First, the ...principle of the multiobjective ACO algorithm is introduced. Then, the WF design process based on the multiobjective ACO algorithm is given in both the single-function mode and the Pareto mode. Finally, improvement measures are proposed for the multiobjective ACO algorithm to reduce the calculation and accelerate the convergence. Simulations and experiments are carried out on a parallel three-level dc-dc converter. The results show that the proposed method is faster and less-computational than the traditional ACO algorithm, and is more accurate than the particle swarm optimization algorithm. With the proposed method, higher solution diversity and smaller control error can be achieved. In addition, the proposed method can also be used for WF online tuning, which will bring more benefits when the converter parameters are mismatched.
With the purpose of finding a satisfactory pipe path between the starting point and target point, pipe routing design (PRD) has been applied in many industry fields. The research of two-dimensional ...PRD is the foundation of solving complex RPD problems, and has widely applications in factory layout, facilities installation, and so on. The ant colony optimization (ACO) algorithm is one of the most widely used approaches to solve PRD. However, the traditional ACO has drawbacks such as slow convergence speed, easy to fall into local optimum and low efficiency. In this study, an improved dynamic adaptive ACO (IDAACO) is proposed. The IDAACO includes four novel mechanisms which are the heuristic strategy with direction information, adaptive pseudorandom transfer strategy, improved local pheromone updating mechanism and improved global pheromone updating mechanism. Then, a series of experiments are carried out to verify the effectiveness of the four proposed mechanisms included by IDAACO. Subsequently, the IDAACO is compared with several existing approaches for solving PRD, and the experimental results confirm the advantages of IDAACO in terms of the practicality and high-efficiency. Finally, the IDAACO is used to solve the PRD problem for semi-submersible production platform in oil and gas industry.
•A mathematical model of 2D pipe routing design (PRD) problem is established.•A novel heuristic approach for solving PRD is proposed and named IDAACO.•The proposed IDAACO includes four novel mechanisms.•Compared with several existing approaches, experimental results show the advantage of IDAACO.•The IDAACO is utilized to solve the problem of PRD for semi-submersible production platform.
The aim of this study was to develop a fast and robust methodology to analyse the biogas production process. The Anaerobic Digestion Model No.1 was used to simulate the co-digestion of agricultural ...substrates. Neural network models were used to predict the biogas flow rate. With the help of the ant colony optimisation algorithm, the significant process variables were identified. Thus the model dimension was reduced and the model performance was improved. The achieved results showed that the approach gave a reliable way to analyse the biogas production process with respect to the significant process variables. This methodology could be further implemented to control the biogas production process and to manage the substrate composition.
•Simulation of the co-digestion of two agricultural substrates was performed.•To predict the biogas flow rate the neural logic was employed.•The optimisation was done with the help of metaheuristics, based on variable selection approach.
PDF
