{"title":"Sparse Bayesian Learning Based Off-Grid Estimation of OTFS Channels with Doppler Squint","authors":"Xuehan Wang;Xu Shi;Jintao Wang","doi":"10.26599/TST.2023.9010093","DOIUrl":"https://doi.org/10.26599/TST.2023.9010093","url":null,"abstract":"Orthogonal Time Frequency Space (OTFS) modulation has exhibited significant potential to further promote the performance of future wireless communication networks especially in high-mobility scenarios. In practical OTFS systems, the subcarrier-dependent Doppler shift which is referred to as the Doppler Squint Effect (DSE) plays an important role due to the assistance of time-frequency modulation. Unfortunately, most existing works on OTFS channel estimation ignore DSE, which leads to severe performance degradation. In this letter, OTFS systems taking DSE into consideration are investigated. Inspired by the input-output analysis with DSE and the embedded pilot pattern, the sparse Bayesian learning based parameter estimation scheme is adopted to recover the delay-Doppler channel. Simulation results verify the excellent performance of the proposed off-grid estimation approach considering DSE.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 6","pages":"1821-1828"},"PeriodicalIF":6.6,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10475894","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141435218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Offline Reinforcement Learning with Constrained Hybrid Action Implicit Representation Towards Wargaming Decision-Making","authors":"Liwei Dong;Ni Li;Guanghong Gong;Xin Lin","doi":"10.26599/TST.2023.9010100","DOIUrl":"https://doi.org/10.26599/TST.2023.9010100","url":null,"abstract":"Reinforcement Learning (RL) has emerged as a promising data-driven solution for wargaming decision-making. However, two domain challenges still exist: (1) dealing with discrete-continuous hybrid wargaming control and (2) accelerating RL deployment with rich offline data. Existing RL methods fail to handle these two issues simultaneously, thereby we propose a novel offline RL method targeting hybrid action space. A new constrained action representation technique is developed to build a bidirectional mapping between the original hybrid action space and a latent space in a semantically consistent way. This allows learning a continuous latent policy with offline RL with better exploration feasibility and scalability and reconstructing it back to a needed hybrid policy. Critically, a novel offline RL optimization objective with adaptively adjusted constraints is designed to balance the alleviation and generalization of out-of-distribution actions. Our method demonstrates superior performance and generality across different tasks, particularly in typical realistic wargaming scenarios.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 5","pages":"1422-1440"},"PeriodicalIF":6.6,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10460410","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MPformer: A Transformer-Based Model for Earthen Ruins Climate Prediction","authors":"Guodong Xu;Hai Wang;Shuo Ji;Yuhui Ma;Yi Feng","doi":"10.26599/TST.2024.9010035","DOIUrl":"https://doi.org/10.26599/TST.2024.9010035","url":null,"abstract":"Earthen ruins contain rich historical value. Affected by wind speed, temperature, and other factors, their survival conditions are not optimistic. Time series prediction provides more information for ruins protection. This work includes two challenges: (1) The ruin is located in an open environment, causing complex nonlinear temporal patterns. Furthermore, the usual wind speed monitoring requires the 10 meters observation height to reduce the influence of terrain. However, in order to monitor wind speed around the ruin, we have to set 4.5 meters observation height according to the ruin, resulting in a non-periodic and oscillating temporal pattern of wind speed; (2) The ruin is located in the arid and uninhabited region of northwest China, which results in accelerating aging of equipment and difficulty in maintenance. It significantly amplifies the device error rate, leading to duplication, missing, and outliers in datasets. To address these challenges, we designed a complete preprocessing and a Transformer-based multi-channel patch model. Experimental results on four datasets that we collected show that our model outperforms the others. Ruins climate prediction model can timely and effectively predict the abnormal state of the environment of the ruins. This provides effective data support and decision-making for ruins conservation, and exploring the relationship between the environmental conditions and the living state of the earthen ruins.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 6","pages":"1829-1838"},"PeriodicalIF":6.6,"publicationDate":"2024-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10520028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141435226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dispatch of a Coal Mine-Integrated Energy System: Optimization Model with Interval Variables and Lower Carbon Emission","authors":"Hejuan Hu;Xiaoyan Sun;Bo Zeng;Dunwei Gong;Yong Zhang;Patrick Nyonganyi;Henerica Tazvinga","doi":"10.26599/TST.2023.9010110","DOIUrl":"https://doi.org/10.26599/TST.2023.9010110","url":null,"abstract":"In the coal mining process, a large amount of Coal Mine-Associated energy (CMAE), such as coal mine methane and underground wastewater, is produced. Research on the modeling and optimization dispatching of a Coal Mine-Integrated Energy System (CMIES) with CMAE effectively saves energy and reduces carbon pollution. CMAE has great uncertainties owing to the affections of the hydrogeology conditions and mining schedules. In addition, thermal loads have high comfort requirements in mines, which brings great challenges to the optimization dispatching of CMIESs. Therefore, this paper studies the architecture and solution of CMIESs with a flexible thermal load and source-load uncertainty. First, to effectively improve the electric and thermal conversion efficiency, the architecture of CMIES, including a concentrating solar power station, is built. Second, for the scheduling model with bilateral uncertainty, the interval representation method with interval variables is proposed, and a multi-objective scheduling model based on the interval variables and flexible thermal load is constructed. Finally, we propose a solution method for the model with interval variables. A case study is conducted to demonstrate the performance of our model and method for lowering carbon emissions and cost.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 5","pages":"1441-1462"},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517925","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Effective Optimization Method for Integrated Scheduling of Multiple Automated Guided Vehicle Problems","authors":"Hongyan Sang;Zhongkai Li;M. Fatih Tasgetiren","doi":"10.26599/TST.2023.9010087","DOIUrl":"https://doi.org/10.26599/TST.2023.9010087","url":null,"abstract":"Automated Guided Vehicle (AGV) scheduling problem is an emerging research topic in the recent literature. This paper studies an integrated scheduling problem comprising task assignment and path planning for AGVs. To reduce the transportation cost of AGVs, this work also proposes an optimization method consisting of the total running distance, total delay time, and machine loss cost of AGVs. A mathematical model is formulated for the problem at hand, along with an improved Discrete Invasive Weed Optimization algorithm (DIWO). In the proposed DIWO algorithm, an insertion-based local search operator is developed to improve the local search ability of the algorithm. A staggered time departure heuristic is also proposed to reduce the number of AGV collisions in path planning. Comprehensive experiments are conducted, and 100 instances from actual factories have proven the effectiveness of the optimization method.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 5","pages":"1355-1367"},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517928","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tianyu Luo;Yong Heng;Lining Xing;Teng Ren;Qi Li;Hu Qin;Yizhi Hou;Kesheng Wang
{"title":"A Two-Stage Approach for Electric Vehicle Routing Problem with Time Windows and Heterogeneous Recharging Stations","authors":"Tianyu Luo;Yong Heng;Lining Xing;Teng Ren;Qi Li;Hu Qin;Yizhi Hou;Kesheng Wang","doi":"10.26599/TST.2023.9010101","DOIUrl":"https://doi.org/10.26599/TST.2023.9010101","url":null,"abstract":"An Electric Vehicle (EV) is an appropriate substitution for traditional transportation means for diminishing greenhouse gas emissions. However, decision-makers are beset by the limited driving range caused by the low battery capacity and the long recharging time. To resolve the former issue, several transportation companies increases the travel distance of the EV by establishing recharging stations in various locations. The proposed Electric Vehicle-Routing Problem with Time Windows (E-VRPTW) and recharging stations are constructed in this context; it augments the VRPTW by reinforcing battery capacity constraints. Meanwhile, super-recharging stations are gradually emerging in the surroundings. They can decrease the recharging time for an EV but consume more energy than regular stations. In this paper, we first extend the E-VRPRTW by adding the elements of super-recharging stations. We then apply a two-stage heuristic algorithm driven by a dynamic programming process to solve the new proposed problem to minimize the travel and total recharging costs. Subsequently, we compare the experimental results of this approach with other algorithms on several sets of benchmark instances. Furthermore, we analyze the impact of super-recharging stations on the total cost of the logistic plan.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 5","pages":"1300-1322"},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517978","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Focusing Ability Enhancement in Broadside Direction of Array: From UCA to UCCA","authors":"Zidong Wu;Linglong Dai","doi":"10.26599/TST.2023.9010127","DOIUrl":"https://doi.org/10.26599/TST.2023.9010127","url":null,"abstract":"To meet the ever-increasing demand for the data rates of wireless communications, extremely largescale antenna array (ELAA) has emerged as one of the candidate technologies for future 6G communications. The significantly increased number of antennas in ELAA gives rise to near-field communications, necessitating tailored beamforming techniques within the near-field regions to accommodate the spherical-wave propagation characteristics. Among various array geometries of ELAA, uniform circular array (UCA) has gained much attention for its distinct capability of maintaining uniform beam pattern across different azimuth angles. However, existing analysis of near-field UCA beamforming indicates that the near-field region severely declines in the broadside of UCA, where the system fails to benefit from near-field communications. To tackle this problem, the near-field beamforming technique of uniform concentric circular arrays (UCCAs) is investigated in this paper, which has the potential to enlarge the near-field region in the broadside direction. First, the analysis of beamforming gain in the 3D space with UCA and UCCA is provided. Then, the distinct beamforming characteristics that set UCCA apart from UCA are delineated, revealing the superiority of UCCA in extending the near-field region in broadside at the cost of slightly reduced near-field region in the coplane. Simulation results are provided to verify the effectiveness of the theoretical analysis of beamforming gain with UCCA and the enhanced focusing ability of UCCA in the broadside direction.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 5","pages":"1593-1603"},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517927","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Temporal Knowledge Graph Embedding Model Based on Variable Translation","authors":"Yadan Han;Guangquan Lu;Shichao Zhang;Liang Zhang;Cuifang Zou;Guoqiu Wen","doi":"10.26599/TST.2023.9010142","DOIUrl":"https://doi.org/10.26599/TST.2023.9010142","url":null,"abstract":"Knowledge representation learning (KRL) aims to encode entities and relationships in various knowledge graphs into low-dimensional continuous vectors. It is popularly used in knowledge graph completion (or link prediction) tasks. Translation-based knowledge representation learning methods perform well in knowledge graph completion (KGC). However, the translation principles adopted by these methods are too strict and cannot model complex entities and relationships (i.e., N-1, 1-N, and N-N) well. Besides, these traditional translation principles are primarily used in static knowledge graphs and overlook the temporal properties of triplet facts. Therefore, we propose a temporal knowledge graph embedding model based on variable translation (TKGE-VT). The model proposes a new variable translation principle, which enables flexible transformation between entities and relationship embedding. Meanwhile, this paper considers the temporal properties of both entities and relationships and applies the proposed principle of variable translation to temporal knowledge graphs. We conduct link prediction and triplet classification experiments on four benchmark datasets: WN11, WN18, FB13, and FB15K. Our model outperforms baseline models on multiple evaluation metrics according to the experimental results.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 5","pages":"1554-1565"},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517975","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xixing Li;Qingqing Zhao;Hongtao Tang;Xing Guo;Mengzhen Zhuang;Yibing Li;Xi Vincent Wang
{"title":"Flexible Job Shop Composite Dispatching Rule Mining Approach Based on an Improved Genetic Programming Algorithm","authors":"Xixing Li;Qingqing Zhao;Hongtao Tang;Xing Guo;Mengzhen Zhuang;Yibing Li;Xi Vincent Wang","doi":"10.26599/TST.2023.9010141","DOIUrl":"https://doi.org/10.26599/TST.2023.9010141","url":null,"abstract":"To obtain a suitable scheduling scheme in an effective time range, the minimum completion time is taken as the objective of Flexible Job Shop scheduling Problems (FJSP) with different scales, and Composite Dispatching Rules (CDRs) are applied to generate feasible solutions. Firstly, the binary tree coding method is adopted, and the constructed function set is normalized. Secondly, a CDR mining approach based on an Improved Genetic Programming Algorithm (IGPA) is designed. Two population initialization methods are introduced to enrich the initial population, and a superior and inferior population separation strategy is designed to improve the global search ability of the algorithm. At the same time, two individual mutation methods are introduced to improve the algorithm's local search ability, to achieve the balance between global search and local search. In addition, the effectiveness of the IGPA and the superiority of CDRs are verified through comparative analysis. Finally, Deep Reinforcement Learning (DRL) is employed to solve the FJSP by incorporating the CDRs as the action set, the selection times are counted to further verify the superiority of CDRs.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"29 5","pages":"1390-1408"},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517917","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}