The paper deals with economic optimization of the installed capacity of residential battery storage, as well as the day-ahead scheduling of energy storage to minimize the prosumer's price and volume risk at the ba...
详细信息
This paper proposes a model estimation method in offline Bayesian model-based reinforcement learning (MBRL). Learning a Bayes-adaptive Markov decision process (BAMDP) model using standard variational inference often s...
详细信息
This paper proposes a model estimation method in offline Bayesian model-based reinforcement learning (MBRL). Learning a Bayes-adaptive Markov decision process (BAMDP) model using standard variational inference often suffers from poor predictive performance due to covariate shift between offline data and future data distributions. To tackle this problem, this paper applies an importance-weighting technique for covariate shift to variational inference learning of a BAMDP model. Consequently, this paper uses a unified objective function to optimize both model and policy. The unified objective function can be seen as an importance-weighted variational objective function for model training. The unified objective function is also considered as the expected return for policy planning penalized by the model's error, which is a standard objective function in MBRL. This paper proposes an algorithm optimizing the unified objective function. The proposed algorithm performs better than algorithms using standard variational inference without importance-weighting. Numerical experiments demonstrate the effectiveness of the proposed algorithm.
Introduction: The control of Renewable Energy Communities (REC) with controllable assets (e.g., batteries) can be formalised as an optimal control problem. This paper proposes a generic formulation for such a problem ...
详细信息
Introduction: The control of Renewable Energy Communities (REC) with controllable assets (e.g., batteries) can be formalised as an optimal control problem. This paper proposes a generic formulation for such a problem whereby the electricity generated by the community members is redistributed using repartition keys. These keys represent the fraction of the surplus of local electricity production (i.e., electricity generated within the community but not consumed by any community member) to be allocated to each community member. This formalisation enables us to jointly optimise the controllable assets and the repartition keys, minimising the combined total value of the electricity bills of the ***: To perform this optimisation, we propose two algorithms aimed at solving an optimal open-loop control problem in a receding horizon fashion. Moreover, we also propose another approximated algorithm which only optimises the controllable assets (as opposed to optimising both controllable assets and repartition keys). We test these algorithms on Renewable Energy Communities control problems constructed from synthetic data, inspired from a real-life case of ***: Our results show that the combined total value of the electricity bills of the members is greatly reduced when simultaneously optimising the controllable assets and the repartition keys (i.e., the first two algorithms proposed).Discussion: These findings strongly advocate the need for algorithms that adopt a more holistic standpoint when it comes to controlling energy systems such as renewable energy communities, co-optimising or jointly optimising them from both a traditional (very granular) control standpoint and a larger economic perspective.
A novel isogeometric collocation method is proposed for the static limit analysis of axially-symmetric masonry domes subject to their self-weight. A shell-based static formulation is employed, alongside Heyman's a...
详细信息
A novel isogeometric collocation method is proposed for the static limit analysis of axially-symmetric masonry domes subject to their self-weight. A shell-based static formulation is employed, alongside Heyman's assumptions on masonry, to characterize the equilibrated and statically admissible stress states in the dome. As a distinctive feature of the approach, a vector stress function is introduced, generating point-wise self-equilibrated shell stress resultants in the dome. Accordingly, the classical minimum-thrust problem is formulated in terms of the unknown vector stress function, and the static admissibility conditions are enforced as the only optimization constraint. NURBS-based isogeometric analysis is adopted to accomplish the need for an accurate geometric description of the dome and a high-order continuous interpolation of the vector stress function. A discrete minimum-thrust problem is derived as a linear programming problem, with the static admissibility conditions checked at suitable collocation points. Instrumental to its solution is the computation of a particular solution of the equilibrium equations, which is obtained by an isogeometric collocation method. By a mechanical interpretation of the dual optimization problem, the settlement mechanism of the dome corresponding to its minimum-thrust state is also computed. Numerical results, dealing with a thorough convergence analysis, parametric analyses on spherical and ogival domes with parameterized geometry, and the real case of the Taj Mahal central dome are presented to prove the computational merit of the proposed approach. & COPY;2023 Elsevier B.V. All rights reserved.
The past decade has witnessed the rapid development of deep learning techniques, especially for large-scale and complex datasets. However, it is still a noteworthy problem in dealing with unsupervised hyperspectral im...
详细信息
The past decade has witnessed the rapid development of deep learning techniques, especially for large-scale and complex datasets. However, it is still a noteworthy problem in dealing with unsupervised hyperspectral image (HSI) segmentation since inefficiency and misleading result from the absence of supervised information. Generally, spectral clustering (SC) is one of the most powerful clustering algorithms, as it often outperforms other methods for image segmentation. Unfortunately, the poor scalability and generalization severely limit the use of SC, especially for large-scale and high-dimensional HSIs processing. The major motivation of this work is to solve this problem, and we designed a novel algorithm, termed deep SC with regularized linear embedding (DSCRLE), to benefit from both spectral graph theory and deep learning techniques. The brief procedure is first to construct a fully connected neural network to extract latent feature representations, and then normalize the feature representations by the spectral orthonormal constraint. Lastly, by introducing low-dimensional embedding, we refined the final outputs of all given unlabeled hyperspectral pixels. Extensive experiments have demonstrated that the competitiveness of the proposed method, and it outperforms the state-of-the-art clustering approaches in the task of HSI segmentation.
Two algorithms for solving misalignment issues in penalized PET/CT reconstruction using anatomical priors are proposed. Both approaches are based on a recently published joint motion estimation and image reconstructio...
详细信息
Two algorithms for solving misalignment issues in penalized PET/CT reconstruction using anatomical priors are proposed. Both approaches are based on a recently published joint motion estimation and image reconstruction method. The first approach deforms the anatomical image to align it with the functional one while the second approach deforms both images to align them with the measured data. Our current implementation alternates between alignment estimation and image reconstruction. We have chosen parallel level sets (PLSs) as a representative anatomical penalty, incorporating a spatially variant penalty strength. The performance was evaluated using simulated nontime-of-flight data generated with an XCAT phantom in the thorax region. We used the attenuation map in the anatomical prior. The results demonstrated that both methods can estimate the misalignment and deform the anatomical image accordingly. However, the performance of the first approach depends highly on the workflow of the alternating process. The second approach shows a faster convergence rate to the correct alignment and is less sensitive to the workflow. The presence of anatomical information improves the convergence rate of misalignment estimation for the second approach but slow it down for the first approach. Both approaches show improved performance in misalignment estimation as the data noise level decreases.
Ising Models, defined by quadratic objective functions (or Hamiltonians), enable to use quantum annealers to search for optimal or near-optimal solutions of satisfiability problems. However, current quantum annealers ...
详细信息
Ising Models, defined by quadratic objective functions (or Hamiltonians), enable to use quantum annealers to search for optimal or near-optimal solutions of satisfiability problems. However, current quantum annealers have limited resolution, meaning that small or closely-valued coefficients in the Hamiltonian may be obscured by flux noise, leading to a degradation in the performance of quantum annealing. In this paper, we propose a novel design methodology for encoding satisfiability problems into Ising models via Integer linear programming. Experimental results show that our method can effectively reduce the resolution requirements for quantum annealers.
One of the biggest problems in education, particularly in e-learning, is the high dropout rate that occurs in courses, so this paper presents a mathematical optimization model to maximize the completion efficiency of ...
详细信息
This paper proposes a new multiattribute decision making (MADM) method based on the proposed score function of connection numbers (CNs) and the set pair analysis (SPA) theory in the interval-valued intuitionist fuzzy ...
详细信息
This paper proposes a new multiattribute decision making (MADM) method based on the proposed score function of connection numbers (CNs) and the set pair analysis (SPA) theory in the interval-valued intuitionist fuzzy (IVIF) context. Firstly, we develop a score function for ranking CNs. The various notable characteristics of the proposed score function of CNs are also presented. Then, we propose a new MADM method based on interval-valued intuitionist fuzzy values (IVIFVs), the proposed score function of CNs and the SPA theory, where we convert IVIFVs into CNs and the optimal weights of attributes are calculated from the IVIF weights of attributes. Finally, the proposed MADM method is applied for MADM in the IVIF context, where the preference orders (POs) of the alternatives obtained by the proposed MADM method are compared with the ones obtained by the existing MADM methods. The proposed MADM method can overcome the drawbacks of the existing MADM methods. (C) 2020 Elsevier Inc. All rights reserved.
Recently, few-shot scene classification has become an important task in the remote sensing (RS) field, mainly solving how to obtain better classification performance when there are insufficient labeled samples. The fe...
详细信息
Recently, few-shot scene classification has become an important task in the remote sensing (RS) field, mainly solving how to obtain better classification performance when there are insufficient labeled samples. The few-shot scene classification task includes the pretrain stage and meta-test stage. There is no category intersection between these two stages. Thus, the sample distribution of the training set and meta-test set is different, leading to the training model's weak generalization or portability. To solve this problem, we propose a class-centralized dictionary learning (CCDL) method for the few-shot RS scene classification (FSRSSC). Specifically, in the pretraining stage, we adopt the model pretrained on a large natural images dataset and then fine-tune the network by the RS dataset. Using the pretrained model helps improve the model's generalization ability. In the meta-test stage, we propose a CCDL classifier, which guarantees the sparse representations of different categories more distant and the same more concentrated. We experiment on several benchmark datasets and achieve superior performance, demonstrating the proposed method's effectiveness.
暂无评论