检索结果-内蒙古大学图书馆

Machine Learning-Driven Dynamic Traffic Steering in 6G: A Novel Path Selection Scheme

BIG DATA AND COGNITIVE COMPUTING 2024年第12期8卷 172-172页

作者： Ng, Hibatul Azizi Hisyam Mahmoodi, Toktam Kings Coll London Dept Engn London WC2R 2LS England

Machine learning is taking on a significant role in materializing a new vision of 6G. 6G aspires to provide more use cases, handle high-complexity tasks, and improvise the current 5G and beyond 5G infrastructure. Artificial Intelligence (AI) and machine learning (ML) are the optimal candidates to support and deliver these aspirations. Traffic steering functions encompass many opportunities to help enable new use cases and improve overall performance. The emergence and advancement of the non-terrestrial network is another driving factor for creating an intelligence selection scheme to have a dynamic traffic steering function. With service-based architecture, 5G and 6G are data-driven architectures that use massive transactional data to emerge a new approach to handling highly complex processes. A highly complex process, a massive volume of data, and a short timeframe require a scheme using machine learning techniques to resolve the challenges. In this paper, the study creates a scheme to use the massive historical data and provide a decision scheme that enables dynamic traffic steering functions addressing the future emergence of the heterogeneous transport network and aligns with the Open Radio Access Network (O-RAN). The proposed scheme in this paper gives an inference to be programmed in the telecommunication nodes. It provides a novel scheme to enable dynamic traffic steering functions for the 6G transport network. The study shows an appropriate data size to create a high-performance multi-output classification model that produces more than 90% accuracy for traffic steering functions.

关键词： machine learning Open Radio Access Network non-terrestrial network QoS flow identifier mixed integer linear programming optimization solver service function chaining Virtual Network Function multi-output classification random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Marginal fixed premium for clean hydrogen portfolio standard (CHPS) considering techno-economic analysis of clean hydrogen production based on hydropower plants

引用

ENERGY REPORTS 2023年 10卷 1356-1368页

作者： Son, Yeong Geon Kwag, Hyung Geun Lee, Sung Hun Kim, Sung Yul Keimyung Univ Daegu South Korea Korea Power Exchange Naju South Korea Korea Water Resources Corp Daejeon South Korea

As the hydrogen economy recently gains momentum, the Korean government is actively encouraging Independent Power Producers (IPPs) to leverage hydrogen energy. The surging uncertainties in the power market, precipitated by the rapid increase in renewable energy sources (RES), necessitates IPPs to formulate a new benefit structure that utilizes green hydrogen. However, the current economic challenges associated with the operation of RES linked to water electrolysis result in diminished participation from IPPs. In response, the Korean government is planning to implement the Clean Hydrogen Portfolio Standard (CHPS), which requires clean hydrogen power generation and offers corresponding Fixed Premium (FP) subsidies. In this paper, we incrementally increase the FP for RES linked to electrolyzers (ELZ) and derive a marginal fixed premium (FPmar). This method initiates a shift towards higher economic feasibility compared to the traditional benefit structure of power tradingbased RES. We suggest a green hydrogen-based business model (BM) that synergizes hydropower with water electrolysis and calculate a suitable CHPS subsidy to ensure the economic feasibility of this BM. In conclusion, this paper equips IPPs operating hydropower with the capability to evaluate the adequacy of the government-provided FP for the economical operation of a hydropower plant linked to water electrolysis. Furthermore, it provides policymakers with the framework to make informed decisions regarding the necessary FPmar to stimulate IPPs' participation.& COPY;2023 The Authors. Published by Elsevier *** is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Clean hydrogen portfolio standard Fixed premium Hydrogen energy Hydropower mixed integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Optimization and analysis of a hydrogen supply chain in terms of cost, CO2 emissions, and risk: the case of Turkey

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2023年第60期48卷 22752-22765页

作者： Erdogan, Ahmet Guler, Mehmet Guray Yildiz Tech Univ Fac Mech Engn Dept Ind Engn Istanbul Turkiye

The transportation sector, which is largely dependent on oil, is faced with many problems such as the danger of depletion of fossil fuels that are harmful to the environment. Moreover, the situations such as epidemics and war cause excessive fluctuations in oil prices. Therefore, there is a need for new solutions based on alternative energy sources for a sustainable transportation sector. Hydrogen fuel cell electric vehicles (HFCEV) are one of the significant alternatives for an efficient, zero emissions and sustainable transportation system. Considering the potential investment in HFCEV technology, the need for a cost effective, green, and low risk Hydrogen Supply Chain (HSC) network infrastructure is inevitable. In this study, the HSC design of the Turkish transportation sector over a 25-year period (2026-2050) is investigated. The problem is modeled using a multi-period mixed integer linear programming (MIP) model. Three objectives are addresses: cost, carbon dioxide (CO2) emissions and safety risk. In order to consider the uncertainty in the hydrogen demand, five different scenarios are analyzed using fuzzy concept. There are four main results. First, unit hydrogen cost is found to be very high due to low demand and high capital cost in the initial period (2026-2031). Second, HSC network is established in a decentralized setting in all scenario solutions. The level of decentralization gets stronger over time and with increasing demand. Third, short-distance road transport is generally preferred for hydrogen transport. Fourth, since the aim is to minimize cost, CO2 emissions, and risk level, a mixed production strategy based on cost-oriented SMR and zeroemissions-oriented Electrolysis (ELE) is observed in all scenarios.& COPY;2023 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

关键词： Hydrogen supply chain network Multi-objective optimization mixed integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Decentralized Weapon-Target Assignment Under Asynchronous Communications

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2023年第2期46卷 312-324页

作者： Hendrickson, Katherine Ganesh, Prashant Volle, Kyle Buzaud, Paul Brink, Kevin Hale, Matthew Univ Florida Dept Mech & Aerosp Engn Gainesville FL 32611 USA Univ Florida Dept Mech & Aerosp Engn Shalimar FL 32579 USA Air Force Res Lab Nav Control Branch Weap Dynam Eglin AFB FL 32542 USA

The weapon-target assignment problem is a classic task assignment problem in combinatorial optimization, and its goal is to assign some number of workers (the weapons) to some number of tasks (the targets). Classical approaches for this problem typically use a centralized planner leading to a single point of failure and often preventing real-time replanning as conditions change. This paper introduces a new approach for distributed, autonomous assignment planning executed by the weapons where each weapon is responsible for optimizing over distinct subsets of the decision variables. A continuous, convex relaxation of the associated cost function and constraints is introduced, and a distributed primal-dual optimization algorithm is developed that will be shown to have guaranteed bounds on its convergence rate, even with asynchronous computations and communications. This approach has several advantages in practice due to its robustness to asynchrony and resilience to time-varying scenarios, and these advantages are exhibited in experiments with simulated and physical commercial off-the-shelf ground robots as weapon surrogates that are shown to successfully compute their assignments under intermittent communications and unexpected attrition (loss) of weapons.

关键词： Weapon Target Assignment Asynchronous Communications Robots Optimization Algorithm COTS mixed integer linear programming Fire and Forget Histograms Computing Evolutionary Algorithm

来源：评论

学校读者我要写书评

暂无评论

SAND-2: An optimized implementation of lightweight block cipher

引用

INTEGRATION-THE VLSI JOURNAL 2023年 91卷 23-34页

作者： Chen, Wen Li, Lang Guo, Ying Huang, Ying Hengyang Normal Univ Coll Comp Sci & Technol Hengyang 421002 Peoples R China Hengyang Normal Univ Hunan Prov Key Lab Intelligent Informat Proc & App Hengyang 421002 Peoples R China

The development of ARX-based lightweight block ciphers has been plagued by the difficulty of theoretical se-curity analysis. SAND solves this problem better by obtaining an equivalent representation based on a synthetic S-box. This paper analyzed SAND in terms of diffusivity and found that it can be optimized. SAND has the issue of slow diffusion after the initial plaintext and key are all 0. On the other hand, it takes at least 11 rounds for SAND to reach full diffusion without AddRoundKey. Thus, this paper proposes a high-diffusion architecture SAND-2 to address the above issues. Firstly, issue 1 is solved by replacing the AND operation with a NAND operation and calling the round function dynamically. Then, in order to solve issue 2, P1 and P2 permutations are introduced into G0 and G1, respectively. The full diffusion speed of SAND-2 is 63.7% increased compared to SAND. In addition, the comparison results of hardware indicators show that the hardware resources of SAND-2 are slightly lower, and the throughput is 10% higher than SAND. Finally, the security analysis shows that SAND-2 reaches the upper bound of the resisting differential analysis in fewer rounds.

关键词： SAND ARX-Based lightweight block cipher High -diffusion architecture mixed integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Continuous-Thrust Reachable Set for linear Relative Motion Near Elliptical Orbits

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2023年第6期59卷 9117-9127页

作者： Lin, Xin Zhang, Gang Harbin Inst Technol Res Ctr Satellite Technol Harbin 150080 Peoples R China

Continuous-thrust relative reachable set is presented for the spacecraft linear relative motion near elliptical orbits. Two cases with different constraints are considered: the energy-constrained case and the fuel-constrained case. Based on the distance-fields-over-grids method, the envelopes of the relative reachable sets for both cases are approximated by a number of grid points on it, and these grid points are obtained from a series of optimization problems. Based on the continuous-thrust analytical state propagation, the original optimization problems for both cases are converted into the nonlinear programming problems. Furthermore, for the energy-constrained case, the analytical solution is obtained by using the Lagrange multiplier method;whereas for the fuel-constrained case, the problem is converted into a mixed-integer linear programming problem to rapidly obtain solutions. Several numerical examples are provided to verify that the developed methods for solving the spacecraft relative reachable sets are feasible and computationally efficient.

关键词： Space vehicles Optimization Fuels Planetary orbits Performance analysis Indexes mixed integer linear programming Continuous thrust energy constraint fuel constraint mixed-integer linear programming (MILP) relative reachable set (RRS)

来源：评论

学校读者我要写书评

暂无评论

Simultaneous sizing and scheduling optimization for PV-wind-battery hybrid systems with a modified battery lifetime model: A high-resolution analysis in China

引用

APPLIED ENERGY 2024年 360卷

作者： Zhao, Yi-Bo Dong, Xiao-Jian Shen, Jia-Ni He, Yi-Jun Shanghai Jiao Tong Univ Shanghai Electrochem Energy Devices Res Ctr Dept Chem Engn Shanghai 200240 Peoples R China

Battery lifetime is a key factor in the optimal design of hybrid renewable energy systems (HRESs). However, the integration of both battery calendar and cycle lifetimes into HRES design optimization poses challenges in achieving high computational efficiency and ensuring global optimality. In this work, a battery lifetime model considering both calendar and cycle lifetimes is adopted for the simultaneous sizing and scheduling optimization of photovoltaics-wind-battery systems. To reduce computational complexity, the nonlinear term originated from the minimum function, which determines the actual battery lifetime as the earlier -reached one of calendar and cycle lifetimes, is reformulated into a mixed integer linear programming framework. This modified model is then applied to conduct HRES design optimization in China, utilizing climate and load data with 0.5(degrees) x 0.5(degrees) spatial resolution. High -resolution results not only validate the wide applicability and satisfactory computational efficiency of the proposed model, but also underline the economic importance of incorporating both calendar and cycle lifetimes in system design. It is found that lifecycle costs of stand-alone and grid -connected HRESs could be reduced by 5000k CNY and 22,600k CNY in over 50% of the resource -abundant areas in China, respectively. Moreover, it is discovered that costs of HRESs might apparently increase when local maximum consecutive rainy days (MCRD) exceeds 3, suggesting that MCRD could be a useful indicator to assess system feasibility in diverse locations. This work provides efficient tools and valuable insights that could be generalized worldwide to assist investors and governments in the system siting, evaluation and design processes.

关键词： Hybrid renewable energy systems Sizing Calendar lifetime Cycle lifetime mixed integer linear programming High resolution

来源：评论

学校读者我要写书评

暂无评论

Learning From Images: Proactive Caching With Parallel Convolutional Neural Networks

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2023年第12期22卷 7234-7248页

作者： Wang, Yantong Hu, Ye Yang, Zhaohui Saad, Walid Wong, Kai-Kit Friderikos, Vasilis Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China Columbia Univ Dept Elect Engn New York NY 24061 USA Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Virginia Tech Bradley Dept Elect & Comp Engn WirelessVT Arlington VA 22203 USA UCL Dept Elect & Elect Engn London WC1E 6BT England Kings Coll London Ctr Telecommun Res Dept Engn London WC2R 2LS England

With the continuous trend of data explosion, delivering packets from data servers to end users causes increased stress on both the fronthaul and backhaul traffic of mobile networks. To mitigate this problem, caching popular content closer to the end-users has emerged as an effective method for reducing network congestion and improving user experience. To find the optimal locations for content caching, many conventional approaches construct various mixed integer linear programming (MILP) models. However, such methods may fail to support online decision making due to the inherent curse of dimensionality. In this paper, a novel framework for proactive caching is proposed. This framework merges model-based optimization with data-driven techniques by transforming an optimization problem into a grayscale image. For parallel training and simple design purposes, the proposed MILP model is first decomposed into a number of sub-problems and, then, Convolutional Neural Networks (CNNs) are trained to predict content caching locations of these sub-problems. Furthermore, since the MILP model decomposition neglects the network resources (such as caching space and link bandwidth) competition among sub-problems, the CNNs' outputs have the risk to be infeasible solutions. Therefore, two algorithms are provided: the first uses predictions from CNNs as an extra constraint to reduce the number of decision variables;the second employs CNNs' outputs to accelerate local search. Numerical results show that the proposed scheme can reduce 71.6% computation time, whose computation time reaches around 28.9ms, with only 0.8% additional performance cost compared to the MILP solution, which provides high quality decision making in pseudo real-time.

关键词： Costs Convolutional neural networks Training Optimization Gray-scale Prediction algorithms Base stations grayscale image mixed integer linear programming proactive caching

来源：评论

学校读者我要写书评

暂无评论

A generic parallel optimization framework for solving hard problems in optical networks

引用

COMPUTER COMMUNICATIONS 2023年第1期199卷 177-185页

作者： Li, Longfei Li, Yongcheng Bose, Sanjay K. Shen, Gangxiang Soochow Univ Jiangsu New Opt Fiber Technol & Commun Network Eng Sch Elect & Informat Engn Suzhou 215006 Jiangsu Peoples R China Soochow Univ Sch Elect & Informat Engn Suzhou Key Lab Adv Opt Commun Network Technol Suzhou 215006 Jiangsu Peoples R China Soochow Univ Inst Broadband Res & Innovat IBRI Sch Elect & Informat Engn Suzhou 215006 Jiangsu Peoples R China Plaksha Univ Mohali India

Many optimization problems in optical networks are either NP-hard or take a long time to solve. In this paper, we develop a generic parallel computing framework which either solves these problems completely or at least improves the quality of the solution. To verify the effectiveness of the proposed framework, we build a miniaturized parallel computing system and test our approach based on different heuristic and meta-heuristic algorithms for the bin-packing problems, mixed integer linear programming (MILP) models, and distributed machine learning. Experimental studies show that the proposed parallel computing framework based on the miniaturized parallel computing system is effective in so far as it either significantly reduces the computing time or improves the quality of the solution as compared to when only a single machine is used.

关键词： Optimization problems Parallel optimization Heuristic Meta-heuristic mixed integer linear programming Machine learning Bin-packing problem Optical networks

来源：评论

学校读者我要写书评

暂无评论

A two-objective optimization of ship itineraries for a cruise company

引用

4OR-A QUARTERLY JOURNAL OF OPERATIONS RESEARCH 2023年第4期21卷 683-709页

作者： Di Pillo, Gianni Fabiano, Marcello Lucidi, Stefano Roma, Massimo SAPIENZA Univ Rome ACTOR SRL Start Up Via Nizza 45 I-00198 Rome Italy SAPIENZA Univ Rome Dept Comp Control & Management Engn A Ruberti Via Ariosto 25 I-00185 Rome Italy

This paper deals with the problem of cruise itinerary planning which plays a central role in worldwide cruise ship tourism. In particular, the Day-by-day Cruise Itinerary Optimization (DCIO) problem is considered. Assuming that a cruise has been planned in terms of homeports and journey duration, the DCIO problem consists in determining the daily schedule of each itinerary so that some Key Performance Indicators are optimized. The schedule of an itinerary, i.e. the sequence of visited ports, the arrival and departure time at each port, greatly affect cruise operative costs and attractiveness. We propose a mixed integer linear programming (MILP) formulation of the problem with the objective of minimizing the itinerary cost due to fuel and port costs, while maximizing an itinerary attractiveness index. This latter is strongly related to the ports visited as well as to the overall schedule of the itinerary. Therefore the problem turns out to be a bi-objective optimization problem. We provide its solution in terms of Pareto optimal solution points. Each single objective MILP problem which arises is solved by using an exact algorithm, implemented in a commercial solver. We consider the day-by-day itineraries of a major luxury cruise company in many geographical areas all over the world. Here we report, as illustrative examples, the results obtained on some of these real instances.

关键词： Cruise shipping Cruise itinerary optimization Itinerary cost and attractiveness mixed integer linear programming Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：