基于粒子群算法的水稻用水的优化配置

本文旨在实现水稻用水资源的优化配置.早稻、一季稻和晚稻等不同类型水稻的用水,以及同一类型的水稻在不同的生长阶段,均存在着用水优化配置的问题.粒子群优化算法比较容易操作,在计算方面具有效率和精度高的优点,可以应用于水稻用水的优化配置模型的求解.以衡阳县高炉村的水稻用水优化配置为具体算例,验证了算法的可行性.     

软件可靠性指标分配的故障树分析法

首先对目前已有的各种分配技术与方法的特点进行了探讨,介绍了如何采用故障树技术求得导致系统失效的功能模块的最小割集,首次提出将故障树技术运用到可靠性的分配中,创建了可靠性分配的故障树快速分配模型并具体分析了其在软件可靠性指标分配中的应用． 最后,分析了这种技术的不足,并对该方法可能的改进进行了一些探讨．     

Chance-constrained activity analysis

The methods of activity analysis (Koopmans [6,7]) are re-examined in the presence of technological uncertainty. In particular, such uncertainty arises when new emerging technologies are employed in the production process and/or when new product designs are being developed. Both input coefficients and output coefficients may be uncertain. If activity levels are to be determined and fixed a priori, one may not be able to require in advance that total output suffice to cover total demand. (Indeed, demand itself may also be uncertain.) Instead, the requirement is written as a chance-constraint, to hold on some predetermined probability level only.The purpose of the present note is to discuss the economic properties of the resulting optimal solution. The certainty equivalent of the chance-constrained program and the corresponding Kuhn-Tucker conditions are written down. At the point of optimum, each producer will hold some inventories of finished goods as a contingency against variation in the output coefficients and in demand. Equilibrium prices will suffice to provide each activity some expected positive profit (an explicit formula for the calculation of the magnitude of this profit is provided).In choosing between several risky activities, each producer may attempt to establish an optimal portfolio of activities, providing a trade-off between expected cost and risk. The nature of an emerging theory of activity portfolios, developed along the lines of standard concepts in financial portfolio analysis, is indicated.     

Research on Joint Resource Allocation for Multibeam Satellite Based on Metaheuristic Algorithms

With the rapid growth of satellite communication demand and the continuous development of high-throughput satellite systems, the satellite resource allocation problem—also called the dynamic resources management (DRM) problem—has become increasingly complex in recent years. The use of metaheuristic algorithms to obtain acceptable optimal solutions has become a hot topic in research and has the potential to be explored further. In particular, the treatment of invalid solutions is the key to algorithm performance. At present, the unused bandwidth allocation (UBA) method is commonly used to address the bandwidth constraint in the DRM problem. However, this method reduces the algorithm’s flexibility in the solution space, diminishes the quality of the optimized solution, and increases the computational complexity. In this paper, we propose a bandwidth constraint handling approach based on the non-dominated beam coding (NDBC) method, which can eliminate the bandwidth overlap constraint in the algorithm’s population evolution and achieve complete bandwidth flexibility in order to increase the quality of the optimal solution while decreasing the computational complexity. We develop a generic application architecture for metaheuristic algorithms using the NDBC method and successfully apply it to four typical algorithms. The results indicate that NDBC can enhance the quality of the optimized solution by 9–33% while simultaneously reducing computational complexity by 9–21%.     

An efficient task allocation framework for scheduled data in edge based Internet of Things using hybrid optimization algorithm approach

Allocation of tasks in IoT is an integral and critical approach to finding a perfect match between scheduled tasks of a particular application and Edge-based processing devices for instant response and efficient utilization of resources to make them renewable. We need a protocol to help optimize the problem of allocating processing devices to the tasks, as task allocation is considered an NP-hard problem to prevent problems with energy consumption and response time problems. For this, a hybrid bio-inspired Swarm-based approach will improve the solution to optimize the matching of a task to a particular device. This paper proposed a Meta-heuristic algorithm to optimize Energy and Time-delay for allocating tasks to the edge-based Processing device in IoT. The proposed algorithm called the Hybrid Artificial Bee Colony whales Optimization algorithm (HAWO) is formulated by integrating Artificial Bee Colony with the Whales Optimization algorithm to overcome the search process of an Artificial Bee Colony, which converges too soon due to the local search of Employee Bee phase and Onlooker Bee phase causing the problem of looping. From the simulation results conducted in Matlab, it is observed that the integrated HAWO method shows promising results in terms of Energy and Time Delay when compared with Artificial Bee Colony and Whales Optimization algorithms separately. Also, proposed method when compared with the benchmark work shows significant improvements of 50%, 25% and 60% in terms of Energy, Time Delay and Best cost, respectively.     

On data reduction for dynamic vector bin packing

We study a dynamic vector bin packing (DVBP) problem. We show hardness for shrinking arbitrary DVBP instances to size polynomial in the number of request types or in the maximal number of requests overlapping in time. We also present a simple polynomial-time data reduction algorithm that allows to recover $(1+\epsilon )$-approximate solutions for arbitrary $\epsilon >0$. It shrinks instances from Microsoft Azure and Huawei Cloud by an order of magnitude for $\epsilon =0.02$.