Satellite observation scheduling plays a significant role in improving the efficiency of Earth observation systems. To solve the large-scale multisatellite observation scheduling problem, this article proposes an ensemble of metaheuristic and exact algorithms based on a divide-And-conquer framework (EHE-DCF), including a task allocation phase and a task scheduling phase. In the task allocation phase, each task is allocated to a proper orbit based on a metaheuristic incorporated with a probabilistic selection and a tabu mechanism derived from ant colony optimization and tabu search, respectively. In the task scheduling phase, we construct a task scheduling model for every single orbit and solve the model by using an exact method (i.e., branch and bound, B&B). The task allocation and task scheduling phases are performed iteratively to obtain a promising solution. To validate the performance of the EHE-DCF, we compare it with B&B, three divide-And-conquer-based metaheuristics, and a state-of-The-Art metaheuristic. Experimental results show that the EHE-DCF can obtain higher scheduling profits and complete more tasks compared with existing algorithms. The EHE-DCF is especially efficient for large-scale satellite observation scheduling problems.@en

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.@en

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.@en

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.@en

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.@en

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.@en

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.@en

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.@en

Architectural design is a process that considers many objectives to satisfy. In general, these objectives are conflicting with each other. On the other hand, many design parameters are associated with these conflicting objectives, too. Therefore, architectural design is described as a complex task. To handle the complexity, computational optimization methods can be employed to investigate architectural design process in detail. This paper focuses on investigating Pareto-front solutions for theatre hall design using multi-objective evolutionary algorithms. To formulate the theatre hall acoustic design problem, we consider three objectives. Two objectives are minimization of both reverberation time, and total initial cost whereas the third objective is the maximization of seating capacity. In addition, several designs and acoustical performance constraints are defined. To tackle this problem, a multi-objective self-adaptive differential evolution algorithm (JDEMO) is proposed and compared with a well-known non-dominated sorting genetic algorithm-II (NSGA-II) from the literature. Computational results show that the proposed JDEMO algorithm achieves competitive results when compared to the NSGA-II.@en

The aim of the research is to find a feasible set of theatre hall design alternatives for two objectives, which are the total cost and the reverberation time, subject to several constraints. We formulate the problem as a multi-objective realparameter constrained optimization problem. To handle this problem, we investigated two different optimization algorithms, namely, a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and a multi-objective Harmony Search algorithm (MOHS) in order to gather Pareto front approximation with a set of non-dominated solutions. We demonstrate that the MOHS yields slightly better results than the NSGA-II algorithm.@en

The aim of the research is to find a feasible set of theatre hall design alternatives for two objectives, which are the total cost and the reverberation time, subject to several constraints. We formulate the problem as a multi-objective realparameter constrained optimization problem. To handle this problem, we investigated two different optimization algorithms, namely, a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and a multi-objective Harmony Search algorithm (MOHS) in order to gather Pareto front approximation with a set of non-dominated solutions. We demonstrate that the MOHS yields slightly better results than the NSGA-II algorithm.@en

The aim of the research is to find a feasible set of theatre hall design alternatives for two objectives, which are the total cost and the reverberation time, subject to several constraints. We formulate the problem as a multi-objective realparameter constrained optimization problem. To handle this problem, we investigated two different optimization algorithms, namely, a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and a multi-objective Harmony Search algorithm (MOHS) in order to gather Pareto front approximation with a set of non-dominated solutions. We demonstrate that the MOHS yields slightly better results than the NSGA-II algorithm.@en

The aim of the research is to find a feasible set of theatre hall design alternatives for two objectives, which are the total cost and the reverberation time, subject to several constraints. We formulate the problem as a multi-objective realparameter constrained optimization problem. To handle this problem, we investigated two different optimization algorithms, namely, a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and a multi-objective Harmony Search algorithm (MOHS) in order to gather Pareto front approximation with a set of non-dominated solutions. We demonstrate that the MOHS yields slightly better results than the NSGA-II algorithm.@en

The aim of the research is to find a feasible set of theatre hall design alternatives for two objectives, which are the total cost and the reverberation time, subject to several constraints. We formulate the problem as a multi-objective realparameter constrained optimization problem. To handle this problem, we investigated two different optimization algorithms, namely, a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and a multi-objective Harmony Search algorithm (MOHS) in order to gather Pareto front approximation with a set of non-dominated solutions. We demonstrate that the MOHS yields slightly better results than the NSGA-II algorithm.@en