检索结果-内蒙古大学图书馆

Collaborative Optimization of multi-energy multi-Microgrid system a Hierarchical Trust-Region multi-Agent Reinforcement Learning Approach

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Xu, Xuesong Xu, Kai Zeng, Ziyang Tang, Jiale He, Yuanxing Shi, Guangze Zhang, Tao Hunan University Of Technology and Business Frontier Crossing Academy Hunan Changsha410205 China Xiangjiang Laboratory Hunan Changsha410205 China College of Systems Engineering National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Multi-energy System Intelligent Interconnection Technology Changsha410073 China

In the context of the expanding diversity of energy demands, an increasing number of heterogeneous multi-energy Microgrids (MEMGs) are engaging in the collaborative framework of the multi-energy multi-microgrid system (MEMMG). However, following this trend, the existing centralized Integrated energy Management system (IEMS) control strategy is unreliable for future energy systems, characterized by more complex optimization control and a flexible system structure. This paper introduces a hierarchical multi-agent Deep Reinforcement Learning (HMADRL) approach for distributed IEMS in MEMMG. Firstly, by employing a hierarchical approach, this method simplifies control complexity by segmenting the overarching control challenge into tasks of collaborative planning and action control, which are distributed across varied multi-agent scenes. Considering both macro and microeconomic factors, alongside carbon emissions, the optimal operation of MEMMG is realized through a bottom-up edge multi-agent control approach, in contrast to traditional top-down centralized methods. Secondly, in the phase of the inter-MEMG collaborative strategy, the Centralized Training Decentralized Execution (CTDE) framework is employed, enabling each heterogeneous MEMG to independently develop local strategies while ensuring its own privacy. Thirdly, within each MEMG, the Trust-Region (TR) model is introduced for multi-agent action control, adeptly addressing the effects of mutual exclusion in decision-making time series. Simultaneously, an initialized Hot Experience Pool (HEP) is implemented, efficiently reducing exploration in complex, high-dimensional spaces. Finally, the off-time agent model is integrated into the HMADRL environment and undergoes secondary training based on real interactions, thereby deriving the optimal energy management policy. The proposed method markedly reduces reliance on exact physical modeling systems. Comparative simulations validate the proposed control scheme's efficacy

关键词： energy management systems

Large-scale matrix optimization based multi microgrid topology design with a constrained differential evolution algorithm

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Wenhua Huang, Shengjun Zhang, Tao Wang, Rui Wang, Ling The College of Systems Engineering National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha410073 China The Department of Automation Tsinghua University Beijing100084 China

Binary matrix optimization commonly arise in the real world, e.g., multi-microgrid network structure design problem (MGNSDP), which is to minimize the total length of the power supply line under certain constraints. Finding the global optimal solution for these problems faces a great challenge since such problems could be large-scale, sparse and multimodal. Traditional linear programming is time-consuming and cannot solve nonlinear problems. To address this issue, a novel improved feasibility rule based differential evolution algorithm, termed LBMDE, is proposed. To be specific, a general heuristic solution initialization method is first proposed to generate high-quality solutions. Then, a binary-matrix-based DE operator is introduced to produce offspring. To deal with the constraints, we proposed an improved feasibility rule based environmental selection strategy. The performance and searching behaviors of LBMDE are examined by a set of benchmark problems. Copyright © 2022, The Authors. All rights reserved.

关键词： Constrained optimization

A Thompson Sampling-Based Sparse Evolutionary Operator for Sparse Large-Scale multi-Objective Optimization

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年

作者： Qi, Sheng Wang, Rui Zhang, Tao Huang, Weixiong Qing, Feng Hu, Tao Wang, Ling National University of Defense Technology College of Systems Engineering Changsha410073 China National University of Defense Technology College of Systems Engineering Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha410073 China Tsinghua University Department of Automation Beijing100084 China

Traditional multi-objective evolutionary algorithms (MOEAs) face challenges when addressing sparse large-scale multi-objective optimization problems (SLSMOPs) with many zero decision variables. The 'large-scale"refers to the high dimensionality of the decision space, making it difficult for traditional MOEAs to traverse vast expanses efficiently with limited computational resources. Furthermore, In sparse contexts, most variables in Pareto optimal solutions are zero. It is difficult for traditional MOEAs to identify non-zero variables' positions efficiently. In reinforcement learning, Thompson sampling employs a probability distribution to estimate each item's value or success probability. Drawing inspiration from this concept, we propose a Thompson sampling-based sparse evolutionary operator (TSSEO). TSSEO maintains a probability distribution for each variable and utilizes this distribution to recommend for the variable, assisting MOEAs in transitioning from high-dimensionality dense to sparse spaces. Experimental results show that when integrated with representative MOEAs, TSSEO performs competitively in three real-world problems and eight benchmark problems involving up to 10,041 decision variables, compared to algorithms designed explicitly for SLSMOPs. © 1997-2012 IEEE.

关键词： multiobjective optimization

Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Wei Wang, Rui Zhang, Tao Li, Kaiwen Li, Wenhua Ishibuchi, Hisao The College of System Engineering National University of Defense Technology Changsha410073 China The Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology HKLMSI2T Changsha410073 China Guangdong Provincial Key Laboratory of Braininspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades. This study seeks to solve MO-OPs through a problem-decomposition framework, that is, a MO-OP is decomposed into a multi-objective knapsack problem (MOKP) and a travelling salesman problem (TSP). The MOKP and TSP are then solved by a multi-objective evolutionary algorithm (MOEA) and a deep reinforcement learning (DRL) method, respectively. While the MOEA module is for selecting cities, the DRL module is for planning a Hamiltonian path for these cities. An iterative use of these two modules drives the population towards the Pareto front of MO-OPs. The effectiveness of the proposed method is compared against NSGA-II and NSGA-III on various types of MO-OP instances. Experimental results show that our method exhibits the best performance on almost all the test instances, and has shown strong generalization ability. Copyright © 2022, The Authors. All rights reserved.

关键词： multiobjective optimization

A New Encoding Mechanism Embedded Evolutionary Algorithm for UAV Route Planning

学校读者我要写书评

暂无评论

A New Encoding Mechanism Embedded Evolutionary Algorithm for...

Congress on Evolutionary Computation

作者： Nanjiang Dong Rui Wang Tao Zhang College of Systems Engineering National University of Defense Technology Changsha P.R.China Hunan Key Laboratory of Multi-Energy System Intelligent Inter-connection Technology (HKLMESI2T) Changsha P.R.China

Evolutionary algorithms (EAs) are often applied to deal with UAV route planning. The solution encoding is one of important factor in designing effective EAs. In a traditional encoding mechanism, each individual represents one route. The whole population then consists of a number of routes. We argue that such an encoding is less effective in route planning, and then proposed an alternative encoding mechanism in which one individual represents only one navigation point. The whole population then represents one route. This implicitly turns EAs into single-point based search with high exploitation ability. To further improve the exploration ability of algorithms using this new encoding, a slightly modified differential evolution operator is applied. Combining the modified DE operator and the new encoding mechanism, the performance of the derived algorithm is significantly improved, obtaining much better route planning results than DE with the traditional encoding mechanism.

关键词： Three-dimensional displays Navigation Heuristic algorithms Sociology Collaboration Evolutionary computation Encoding

Deep reinforcement learning for combinatorial optimization: Covering salesman problems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Kaiwen Zhang, Tao Wang, Rui Wang, Yuheng Han, Yi College of Systems Engineering National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology HKL-MSI2T Changsha410073 China Graduate College National University of Defense Technology Changsha410073 China Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha410073 China

This paper introduces a new deep learning approach to approximately solve the Covering Salesman Problem (CSP). In this approach, given the city locations of a CSP as input, a deep neural network model is designed to directly output the solution. It is trained using the deep reinforcement learning without supervision. Specifically, in the model, we apply the multi-head Attention to capture the structural patterns, and design a dynamic embedding to handle the dynamic patterns of the problem. Once the model is trained, it can generalize to various types of CSP tasks (different sizes and topologies) with no need of re-training. Through controlled experiments, the proposed approach shows desirable time complexity: it runs more than 20 times faster than the traditional heuristic solvers with a tiny gap of optimality. Moreover, it significantly outperforms the current state-of-the-art deep learning approaches for combinatorial optimization in the aspect of both training and inference. In comparison with traditional solvers, this approach is highly desirable for most of the challenging tasks in practice that are usually large-scale and require quick decisions. Copyright © 2021, The Authors. All rights reserved.

关键词： Combinatorial optimization

Obtaining diverse solutions for reliable multi-microgrid network design

学校读者我要写书评

暂无评论

energy Internet 2024年第0期

作者： Tao Zhang Xingyi Yao Wenhua Li Rui Wang College of Systems Engineering National University of Defense Technology Changsha China Hunan Key Laboratory of Multi-energy System Intelligent Interconnection Technology Changsha China

The multi-microgrid network structure optimisation problem (MNSDOP) aims to minimise the circuit lengths while maximising power transmission stability, a crucial aspect for system robustness enhancement. While existing literature primarily focuses on achieving Pareto optimal solutions there is an overlooked emphasis on solution diversity. In situations like MNSDOPs, several optimal solutions might possess identical or comparable objective values, classifying them under multimodal multi-objective optimisation roblems (MMOPs). Offering an array of optimal solutions equips decision-makers with a holistic understanding of the problem, aiding in the identification of preferred solutions. Motivated by this gap, we introduce a multimodal multi-objective evolutionary algorithm tailored for MNSDOPs, termed MMO-BM. We also propose a diversity evaluation metric specifically for binary optimisation problems, substantially amplifying the exploration capabilities of evolutionary algorithms. In addition, a novel matrix-oriented DE operator is proposed to accerate the convergence process. Experimental evaluations attest to our method's prowess in yielding diverse and high-quality solutions.

关键词： energy Internet Internet power control

Learning to Branch in Combinatorial Optimization with Graph Pointer Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Rui Zhou, Zhiming Zhang, Tao Wang, Ling Xu, Xin Liao, Xiangke Li, Kaiwen The College of Systems Engineering National University of Defense Technology Changsha410073 China The Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology HKLMSI2T Changsha410073 China Institute of Automation Chinese Academy of Sciences Beijing100190 China The College of Intelligence Science and Technology National University of Defense Technology Changsha410073 China Department of Automation Tsinghua University Beijing100084 China The College of Computer Science and Technology National University of Defense Technology Changsha410073 China

Branch-and-bound is a typical way to solve combinatorial optimization problems. This paper proposes a graph pointer network model for learning the variable selection policy in the branch-and-bound. We extract the graph features, global features and historical features to represent the solver state. The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions. The model is trained to imitate the classic strong branching expert rule by a designed top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. Our approach also outperforms the state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances. Copyright © 2023, The Authors. All rights reserved.

关键词： Combinatorial optimization

Robust transmission expansion planning model considering multiple uncertainties and active load

学校读者我要写书评

暂无评论

Global energy interconnection 2021年第5期4卷 476-484页

作者： Wensheng Li Long Zhao Yin Bo Weilun Wang Mingqiang Wang Shuai Liu Rui Liu Xian Wang Economic&Technology Research Institute State Grid Shandong Electric Power CompanyJinan 250021Shandong ProvinceP.R China Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong UniversityJinan 250061Shandong ProvinceP.R China Global Energy Interconnection Group Co. Ltd.Xicheng District100031BeijingP.R.China

Uncertainty must be well addressed in transmission expansion planning(TEP)problem,and it significantly affects the reliability and cost-effectiveness of power *** to the complex operating environment of power systems,it is crucial to consider different types of uncertainties during the planning *** this paper,a robust TEP model is proposed by considering multiple uncertainties and active ***,in this model,the uncertainties of wind power output and contingency probability are considered *** uncertainties are described by scenario and interval,and the Benders decomposition technique is applied to solve the *** feasibility and effectiveness of the proposed model are illustrated using the IEEE RTS and IEEE 118-node systems.

关键词： Benders decomposition Transmission expansion planning Robust optimization Uncertainty