Reinforcement⁃Learning⁃Based Appointed⁃Time Prescribed Performance Attitude Control for Rigid Spacecraft

This paper addresses a geometric control algorithm for the attitude tracking problem of the rigid spacecraft modeled on SO(3).Considering the topological and geometric properties of SO(3),we introduced a smooth positive attitude error function to convert the attitude tracking issue on SO(3)into the stabilization counterpart on its Lie algebra.The error transformation technique was further utilized to ensure the assigned transient and steady state performance of the attitude tracking error with the aid of a well⁃designed assigned⁃time performance function.Then,using the actor⁃critic(AC)neural architecture,an adaptive reinforcement learning approximator was constructed,in which the actor neural network(NN)was utilized to approximate the unknown nonlinearity online.A critic function was introduced to tune the next phase of the actor neural network operation for performance improvement via supervising the system performance.A rigorous stability analysis was presented to show that the assigned system performance can be achieved.Finally,the effectiveness and feasibility of the constructed control strategy was verified by the numerical simulation.

Pareto-Based Complete Local Search and Combined Timetabling for Multi-objective Job Shop Scheduling Problem with No-Wait Constraint

Job shop scheduling has become the basis and core of advanced manufacturing technology. Various differences exist between academic research and practical production. The majority of previous researches on job shop scheduling problem (JSSP)describe the basic production environment, which have a single objective and limited constraints. However,a practical process of production is characterized by having multiple objectives,no-wait constraint,and limited storage. Thus this research focused on multiobjective,no-wait JSSP. To analyze the problem,it was further divided into two sub-problems, namely, sequencing and timetabling. Hybrid non-order strategy and modified complete local search with memory were used to solve each problem individually. A Pareto-based strategy for performing fitness assessment was presented in this study. Various experiments on benchmark problems proved the feasibility and effectiveness of the proposed algorithm.

Vision-Based Adaptive Prescribed-Time Control of UAV for Uncooperative Target Tracking with Performance Constraint

This paper discusses the uncooperative target tracking control problem for the unmanned aerial vehicle(UAV)under the performance constraint and scaled relative velocity constraint,in which the states of the uncooperative target can only be estimated through a vision sensor.Considering the limited detection range,a prescribed performance function is designed to ensure the transient and steady-state performances of the tracking system.Meanwhile,the scaled relative velocity constraint in the dynamic phase is taken into account,and a time-varying nonlinear transformation is used to solve the constraint problem,which not only overcomes the feasibility condition but also fails to violate the constraint boundaries.Finally,the practically prescribed-time stability technique is incorporated into the controller design procedure to guarantee that all signals within the closed-loop system are bounded.It is proved that the UAV can follow the uncooperative target at the desired relative position within a prescribed time,thereby improving the applicability of the vision-based tracking approach.Simulation results have been presented to prove the validity of the proposed control strategy.

A new energy landscape paving heuristic for satellite module layouts

This article describes a study of the satellite module layout problem （SMLP）, which is a three-dimensional （3D） layout optimization problem with performance constraints that has proved to be non-deterministic polynomial-time hard （NP-hard）. To deal with this problem, we convert it into an unconstrained optimization problem using a quasi-physical strategy and the penalty function method. The energy landscape paving （ELP） method is a class of Monte-Carlo-based global optimization algorithm that has been successfully applied to solve many optimization problems. ELP can search for low-energy layouts via a random walk in complex energy landscapes. However, when ELP falls into the narrow and deep valleys of an energy landscape, it is difficult to escape. By putting forward a new update mechanism of the histogram function in ELP, we obtain an improved ELP method which can overcome this drawback. By incorporating the gradient method with local search into the improved ELP method, a new global search optimization method, hELP, is proposed for SMLP. Two representative instances from the literature are tested. Computational results show that the proposed hELP algorithm is an effective method for solving SMLP with performance constraints.

Instance-Specific Algorithm Selection via Multi-Output Learning

Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential relations between different candidate algorithms for the algorithm selection. In this study, we propose an instancespecific algorithm selection method based on multi-output learning, which can manage these relations more directly.Three kinds of multi-output learning methods are used to predict the performances of the candidate algorithms：（1）multi-output regressor stacking;（2） multi-output extremely randomized trees; and（3） hybrid single-output and multioutput trees. The experimental results obtained using 11 SAT datasets and 5 Max SAT datasets indicate that our proposed methods can obtain a better performance over the state-of-the-art algorithm selection methods.

Dynamic Power Saving via Least-Square Self-Tuning Regulator in the Virtualized Computing Systems

In recent years,power saving problem has become more and more important in many fields and attracted a lot of research interests.In this paper,the authors consider the power saving problem in the virtualized computing system.Since there are multiple objectives in the system as well as many factors influencing the objectives,the problem is complex and hard.The authors will formulate the problem as an optimization problem of power consumption with a prior requirement on performance,which is taken as the response time in the paper.To solve the problem,the authors design the adaptive controller based on least-square self-tuning regulator to dynamically regulate the computing resource so as to track a given reasonable reference performance and then minimize the power consumption using the tracking result supplied by the controller at each time.Simulation is implemented based on the data collected from real machines and the time delay of turning on/off the machine is included in the process.The results show that this method based on adaptive control theory can save power consumption greatly with satisfying the performance requirement at the same time,thus it is suitable and effective to solve the problem.