Considering a multi-stage stochastic task, in which a multi-static radar system (MSRS) is applied to assist with missile interception, the authors study an optimisation problem of radar resource management. Specifical...
详细信息
Considering a multi-stage stochastic task, in which a multi-static radar system (MSRS) is applied to assist with missile interception, the authors study an optimisation problem of radar resource management. Specifically, under restriction of a fixed energy budget, the authors devote to minimise the loss, which is caused by the unsuccessfully intercepted missiles, through optimal power allocation (OPA) of MSRS within multiple stages. The design of OPA can be translated into a sequential decision-making problem. The authors formulate the problem through variable definition and modelling the missile interception procedure. As the authors need to consider the randomness of multiple coupled stages and jointly allocation power between multiple radar nodes, to solve the proposed problem is of huge computational load. The authors propose a solution that combines with reinforcement learning and particle swarm optimisation. Comparing with the uniform power allocation scheme, the simulation results demonstrate that the OPA scheme designed by the proposed method is capable to achieve preferable and more stable performance for the whole missile interception. The authors' contributions include a novel optimisation resource management model for a multi-stage stochastic task and an effective solution for the optimal resource management scheme.
Air Traffic Flow Management (ATFM) is a complex sequential decision-making problem that involves dynamically matching flights with sectors under changing environmental conditions. Finding an optimal solution for ATFM ...
详细信息
Air Traffic Flow Management (ATFM) is a complex sequential decision-making problem that involves dynamically matching flights with sectors under changing environmental conditions. Finding an optimal solution for ATFM is challenging due to its dynamic nature and operational constraints. Reinforcement learning is a well-suited approach for sequential decision-making problems. However, ATFM poses three potential challenges: 1) large state space, 2) combinatorial action space, and 3) variational feasible action set, resulting from numerous agents with tightly-coupled constraints. These challenges can hinder the effectiveness of direct application of reinforcement learning methods. While prescriptive analytics can readily handle hard constraints via a mathematical optimization model, but it is computationally intractable for online sequential decision-making problems under changing environments. To address these challenges, we propose a novel framework, Reinforcement-Learning-Informed Prescriptive Analytics (RLIPA), in which an "informing" scheme is devised to integrate reinforcement learning and prescriptive analytics and leverage their strengths in predicting future reward and coping with hard constraints respectively. RLIPA is a general framework that can be adapted to other problems beyond ATFM, which typically involves many agents with tightly-coupled hard constraints. We demonstrate the usage and performance of RLIPA using numerical results and a real case study in comparison to two baseline *** to Practitioners-To improve Air Traffic Flow Management (ATFM) and reduce flight congestion, we propose a new method called reinforcement-learning-informed prescriptive analytics (RLIPA). RLIPA is a general framework that facilitates online sequential decision-making problems with multiple agents coupled with hard constraints. The approach consists of two stages: first, estimating future potential rewards for each agent via reinforcement learning, and second, in
Stochastic programming is a powerful analytical method in order to solve sequential decision-making problems under uncertainty. We describe an approach to build such stochastic linear programming models. We show that ...
详细信息
Stochastic programming is a powerful analytical method in order to solve sequential decision-making problems under uncertainty. We describe an approach to build such stochastic linear programming models. We show that algebraic modeling languages make it possible for non-specialist users to formulate complex problems and have solved them by powerful commercial solvers. We illustrate our point in the case of option contracts in supply chain management and propose a numerical analysis of performance. We propose easy-to-implement discretization procedures of the stochastic process in order to limit the size of the event tree in a multi-period environment. (C) 2003 Elsevier Ltd. All rights reserved.
Urban-planning authorities continually face the problem of optimising the allocation of green space over time in developing urban environments. The problem is essentially a sequentialdecision-making task involving se...
详细信息
Urban-planning authorities continually face the problem of optimising the allocation of green space over time in developing urban environments. The problem is essentially a sequentialdecision-making task involving several interconnected and non-linear uncertainties, and requires time-intensive computation to evaluate the potential consequences of individual decisions. We explore the application of two very distinct frameworks incorporating evolutionary algorithm approaches for this problem: (i) an offline' approach, in which a candidate solution encodes a complete set of decisions, which is then evaluated by full simulation and (ii) an online' approach which involves a sequential series of optimisations, each making only a single decision, and starting its simulations from the endpoint of the previous run. We study the outcomes, in each case, in the context of a simulated urban development model, and compare their performance in terms of speed and quality. Our results show that the online version is considerably faster than the offline counterpart, without significant loss in performance.
With recent developments in the airline industry worldwide, the competition among the industry has increased largely with many key players in the market. In order to generate profits, the industry has paid much attent...
详细信息
With recent developments in the airline industry worldwide, the competition among the industry has increased largely with many key players in the market. In order to generate profits, the industry has paid much attention to generate optimal routes that are maintenance feasible. The main aim of operational aircraft maintenance routing problem (OAMRP) is to generate these optimal routes for each aircraft that are maintenance feasible and follow the constraints defined by the Federal Aviation Administration (FAA). In this paper, the OAMRP is studied with two main objectives. First, to propose a formulation of a network flow-based Integer Linear Programming (ILP) framework for the OAMRP that considers three main maintenance constraints simultaneously: maximum flyinghour, limit on the number of take-offs between two consecutive maintenance checks and the work-force capacity. Second, to develop a new reinforcement learning-based algorithm which can be used to solve the problem, quickly and efficiently, as compared to commonly available optimization software. Finally, the evaluation of the proposed algorithm on real case datasets obtained from a major airline located in the Middle East verifies that the algorithm generates high-quality solutions quickly for both medium and large-scale flight schedule dataset.
暂无评论