A Hardware Architecture of Particle Swarm Optimization
نویسندگان
چکیده
Particle Swarm Optimization (PSO) is a useful algorithm to deal with non-linear problems such as route economic management optimization, vehicle routing optimization and so on. Several different kinds of improved PSO algorithms is provided to further increase its searching performance, which means PSO can deal with various kinds of situation through these improved algorithms. Moreover, Multi-Swarm strategy of PSO (MSPSO) is introduced to avoid premature and reach the optimal solution with less iteration time. However, software implementation of MSPSO is too time-consuming to be employed into real-time application when particles number and iterations time are huge, even on high-speed computer. Moreover, the synchronous hardware architecture of MSPSO is ineffective since it cannot achieve the maximum performance of each module during the calculation. In order to accelerate the processing speed of MSPSO, an asynchronous architecture of MSPSO based on Field-Programmable Gate Array (FPGA) is proposed in this research. The asynchronous architecture can improve the efficiency by executing the function of each module independently with maximum performance. In addition, Asynchronous Wrapper (AW) with handshaking protocol is adopted to connect core modules and peripheral modules, which can greatly enhance the stability of data exchange. The experimental results confirm that the asynchronous approach can drastically reduce the calculation time compared with synchronous approach.
منابع مشابه
Particle Swarm Optimization: A Hardware Implementation
Particle Swarm Optimization (PSO) is a popular population-based optimization algorithm. While PSO has been shown to perform well in a large variety of problems, PSO is typically implemented in software. Population-based optimization algorithms such as PSO are well suited for execution in parallel stages. This allows PSO to be implemented directly in hardware and achieve much faster execution ti...
متن کاملEfficient block-based motion estimation architecture using particle swarm optimization
High speed video transmission is the key to achieve high quality live or through offline streaming. Block Matching Motion Estimation (ME) is adopted in video coding standards to improve the performance in terms of speed and at the same time, the power consumption should be minimal. The paper proposes an efficient block-based ME architecture, in which the motion vectors are obtained by searching...
متن کاملA particle swarm optimization method for periodic vehicle routing problem with pickup and delivery in transportation
In this article, multiple-product PVRP with pickup and delivery that is used widely in goods distribution or other service companies, especially by railways, was introduced. A mathematical formulation was provided for this problem. Each product had a set of vehicles which could carry the product and pickup and delivery could simultaneously occur. To solve the problem, two meta-heuristic methods...
متن کاملAn approach to Improve Particle Swarm Optimization Algorithm Using CUDA
The time consumption in solving computationally heavy problems has always been a concern for computer programmers. Due to simplicity of its implementation, the PSO (Particle Swarm Optimization) is a suitable meta-heuristic algorithm for solving computationally heavy problems. However, despite the simplicity, the algorithm is inefficient for solving real computationally heavy problems but the pr...
متن کاملImplementation of Digital Circuits Using Neuro - Swarm Based on FPGA
This paper constructs fully parallel NN hardware realization of Artificial Neural Network (ANN) depends on the efficient execution of single neuron. Field Programmable Gate Array (FPGA) reconfigurable computing architecture is appropriated for hardware achievement of ANN. Numerous implementation of ANNs have been reported in scientific documents, trying to reduce Neural Networks NNs hardware ci...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- JCP
دوره 12 شماره
صفحات -
تاریخ انتشار 2017