Machine Learning for 5G and Beyond:From ModelBased to Data-Driven Mobile Wireless Networks

During the past few decades,mobile wireless communications have experienced four generations of technological revolution,namely from 1 G to 4 G,and the deployment of the latest 5 G networks is expected to take place in 2019.One fundamental question is how we can push forward the development of mobile wireless communications while it has become an extremely complex and sophisticated system.We believe that the answer lies in the huge volumes of data produced by the network itself,and machine learning may become a key to exploit such information.In this paper,we elaborate why the conventional model-based paradigm,which has been widely proved useful in pre-5 G networks,can be less efficient or even less practical in the future 5 G and beyond mobile networks.Then,we explain how the data-driven paradigm,using state-of-the-art machine learning techniques,can become a promising solution.At last,we provide a typical use case of the data-driven paradigm,i.e.,proactive load balancing,in which online learning is utilized to adjust cell configurations in advance to avoid burst congestion caused by rapid traffic changes.

e-Learning环境学习测量研究进展与趋势——基于眼动应用视角

"日益关注学习测量"已成为教育变革的重要趋势,e-Learning环境学习测量的研究正日益突显多维整体、真实境脉、实时连续的特征。该文通过眼动应用视角透析e-Learning环境学习测量研究的进展与趋势。基于信息加工论、"直接假说"和"眼脑假说",阐释眼动在信息提取、加工、整合以及意义建构中的重要作用。此外,围绕多媒体界面有效性、多媒体学习效果、数字阅读、信息加工过程和学习分析五个方面,对研究内容、研究结果和发展趋势进行梳理与分析。研究认为眼动技术有助于获取具备"大数量、全样本、实时性、微观指向"特性的学习数据,可以深入评估多媒体学习效果和阅读过程,量化注意力、认知过程和学习结果之间的关系,为拓展教育技术的研究手段和应用领域提供了方向指引。

Vision for energy material design:A roadmap for integrated data-driven modeling

The application scope and future development directions of machine learning models(supervised learning, transfer learning, and unsupervised learning) that have driven energy material design are discussed.

Domain-Oriented Data-Driven Data Mining Based on Rough Sets

Data mining (also known as Knowledge Discovery in Databases - KDD) is defined as the nontrivial extraction of implicit, previously unknown, and potentially useful information from data. The aims and objectives of data mining are to discover knowledge of interest to user needs.Data mining is really a useful tool in many domains such as marketing, decision making, etc. However, some basic issues of data mining are ignored. What is data mining? What is the product of a data mining process? What are we doing in a data mining process? Is there any rule we should obey in a data mining process? In order to discover patterns and knowledge really interesting and actionable to the real world Zhang et al proposed a domain-driven human-machine-cooperated data mining process.Zhao and Yao proposed an interactive user-driven classification method using the granule network. In our work, we find that data mining is a kind of knowledge transforming process to transform knowledge from data format into symbol format. Thus, no new knowledge could be generated (born) in a data mining process. In a data mining process, knowledge is just transformed from data format, which is not understandable for human, into symbol format,which is understandable for human and easy to be used.It is similar to the process of translating a book from Chinese into English.In this translating process,the knowledge itself in the book should remain unchanged. What will be changed is the format of the knowledge only. That is, the knowledge in the English book should be kept the same as the knowledge in the Chinese one.Otherwise, there must be some mistakes in the translating proces, that is, we are transforming knowledge from one format into another format while not producing new knowledge in a data mining process. The knowledge is originally stored in data (data is a representation format of knowledge). Unfortunately, we can not read, understand, or use it, since we can not understand data. With this understanding of data mining, we proposed a data-driven knowledge acquisition method based on rough sets. It also improved the performance of classical knowledge acquisition methods. In fact, we also find that the domain-driven data mining and user-driven data mining do not conflict with our data-driven data mining. They could be integrated into domain-oriented data-driven data mining. It is just like the views of data base. Users with different views could look at different partial data of a data base. Thus, users with different tasks or objectives wish, or could discover different knowledge (partial knowledge) from the same data base. However, all these partial knowledge should be originally existed in the data base. So, a domain-oriented data-driven data mining method would help us to extract the knowledge which is really existed in a data base, and really interesting and actionable to the real world.

Data-driven simulation in fluids animation: A survey

The field of fluid simulation is developing rapidly,and data-driven methods provide many frameworks and techniques for fluid simulation.This paper presents a survey of data-driven methods used in fluid simulation in computer graphics in recent years.First,we provide a brief introduction of physical based fluid simulation methods based on their spatial discretization,including Lagrangian,Eulerian,and hybrid methods.The characteristics of these underlying structures and their inherent connection with data driven methodologies are then analyzed.Subsequently,we review studies pertaining to a wide range of applications,including data-driven solvers,detail enhancement,animation synthesis,fluid control,and differentiable simulation.Finally,we discuss some related issues and potential directions in data-driven fluid simulation.We conclude that the fluid simulation combined with data-driven methods has some advantages,such as higher simulation efficiency,rich details and different pattern styles,compared with traditional methods under the same parameters.It can be seen that the data-driven fluid simulation is feasible and has broad prospects.

电磁目标表征:知识-数据联合驱动新范式

电磁目标表征是电磁空间态势感知中的一项共性基础性问题。早期目标表征基于专家经验知识,需要设计者具有较强的专业背景与先验知识,其在复杂信号环境下的性能不佳。近年来发展起来的深度学习为复杂电磁环境下的目标信号表征提供了新的途径,它通过模拟人脑的深层结构建立机器学习模型,以端到端的方式自动表征和处理目标数据,在电磁目标检测、分类、识别、参数估计、行为认知等感知任务中显示出良好的性能。然而,深度学习严重依赖海量高质量标注数据,在现实电磁环境中存在一定局限。将知识融入智能系统一直是人工智能的研究方向,结合知识与数据进行电磁目标表征,将有望提升目标感知精度与泛化能力,正在成为电磁目标表征中新的方向。本文回顾了电磁目标表征技术的发展过程,对新的知识-数据联合驱动的电磁目标感知范式进行了展望。

融合K-means聚类和序列分解的实车锂电池剩余使用寿命预测

电动汽车锂离子动力电池健康状态(SOH)衰退过程受使用工况影响存在较多波动,导致模型预测精度下降,在锂电池剩余使用寿命(RUL)短期预测时,SOH波动情况不可忽略,为了准确预测SOH短期内波动情况,须从实车上传的锂电池运行数据中提取有效的健康因子。本文建立一种联合分布特征输入和序列分解融合的锂电池RUL预测方法,使用K-means聚类方法构建车辆锂电池运行过程的联合分布特征,并通过S-G滤波器对SOH衰退曲线进行序列分解,分别使用长短时记忆神经网络(LSTM)和多层感知机(MLP)对趋势部分和波动部分进行预测,融合得到最终预测结果。理论分析和实车采集数据验证表明,融合模型可以在预测车辆锂电池RUL短期衰退趋势的同时预测SOH的波动情况,有较高的短期预测精度。

Blockchain-Based Cognitive Computing Model for Data Security on a Cloud Platform

Cloud storage is widely used by large companies to store vast amounts of data and files,offering flexibility,financial savings,and security.However,information shoplifting poses significant threats,potentially leading to poor performance and privacy breaches.Blockchain-based cognitive computing can help protect and maintain information security and privacy in cloud platforms,ensuring businesses can focus on business development.To ensure data security in cloud platforms,this research proposed a blockchain-based Hybridized Data Driven Cognitive Computing(HD2C)model.However,the proposed HD2C framework addresses breaches of the privacy information of mixed participants of the Internet of Things(IoT)in the cloud.HD2C is developed by combining Federated Learning(FL)with a Blockchain consensus algorithm to connect smart contracts with Proof of Authority.The“Data Island”problem can be solved by FL’s emphasis on privacy and lightning-fast processing,while Blockchain provides a decentralized incentive structure that is impervious to poisoning.FL with Blockchain allows quick consensus through smart member selection and verification.The HD2C paradigm significantly improves the computational processing efficiency of intelligent manufacturing.Extensive analysis results derived from IIoT datasets confirm HD2C superiority.When compared to other consensus algorithms,the Blockchain PoA’s foundational cost is significant.The accuracy and memory utilization evaluation results predict the total benefits of the system.In comparison to the values 0.004 and 0.04,the value of 0.4 achieves good accuracy.According to the experiment results,the number of transactions per second has minimal impact on memory requirements.The findings of this study resulted in the development of a brand-new IIoT framework based on blockchain technology.

面向新型电力系统运行的数据-物理融合建模综述

构建新型电力系统是我国实现碳达峰、碳中和目标的关键,将给电力工业带来深刻变革与挑战。数据-物理融合建模(简称融合建模)是一类新兴的建模技术,能够同时发挥物理机理与数据的价值,有望成为新型电力系统重要的分析工具。为此,该文首先梳理融合建模的相关概念与应用场景,讨论近年来国内外的研究趋势与热点。进而从技术特征和融合模式两方面,提出针对融合模型的分析框架。同时,聚焦于新型电力系统运行领域,全方位总结整理融合建模在应对现有技术挑战方面的潜在优势及不足,并展望未来研究与工程实践的重点发展领域。

一种风向监督双流神经网络--以一维Burgers方程求解为例

针对一维Burgers方程下单一建模方式难以充分考虑不同阶段风向对系数的影响比重,无法有效获得各节点间的关联信息的问题,本文提出了一种风向监督双流神经网络分别预测上下风向的有限差分系数。同时设计了一种风向判断模块,实现了对预测得到有限差分系数的权重融合。通过风向监督双流神经网络,并结合先验知识对学得的系数分配一定的权重,以突出上下风向对预测结果的不同影响,可以有效实现对不同风向上的点分别进行预测,使得空间结构特征信息挖掘更加充分,从而提高差分系数预测的精度。在比传统数值求解方法网格分辨率粗4~8倍的同时,提高了谷歌团队工作的精度,以此提高了计算的速度。

基于数据-知识驱动的高精度海底地形绘制:以南海为例

海底地形具有非常重要的商业、工程、军事和科学研究价值。目前,常用重力场数据反演海底地形,如自由空气重力异常和垂直重力梯度。然而,由于现有方法反演海底地形具有较强的多解性,仍然无法准确获取高精度的海底地形。该文提出了重力-密度法与随机森林结合的数据-知识驱动新方法,以重建准确的海底地形。该方法在中国南海海域进行了测试,并与重力-密度法、随机森林以及现有的SIO模型进行了对比分析。反演结果显示,数据-知识驱动提供了更好的反演性能,随机森林和重力-密度法次之,SIO模型最差。相比于重力-密度法,数据-知识驱动的平均绝对误差、平均相对误差和均方根误差分别降低了21%、25%和7%;而相比于随机森林,它们分别也降低了20%、20%和20%。此外,数据-知识驱动模型与船载测深数据具有较高的一致性,其差值大约有72%分布在±10 m范围内,占比高于其他三种模型。该结果证明了数据-知识驱动方法在海底地形反演中的可行性和有效性,有助于加快高精度海底地形的绘制。

IRF-RL的混合流水车间动态调度方法研究

为适应混合流水车间生产需求,提出了一种基于机器学习的两阶段动态调度方法。在离线挖掘阶段,以历史数据为基础,采用改进随机森林算法建立一个由制造系统生产状态到最优调度规则的知识映射网络,挖掘出有价值的调度规则用于在线决策,跳过预热阶段提高调度效率进而优化调度方案;在线调度阶段,采用强化学习算法对车间状态的实时数据进行分析和训练,根据系统状态的动态变化优化策略选择,以实现对扰动事件的自适应和快速响应能力;仿真实验结果验证了结合数据挖掘和强化学习的两阶段动态调度方法具有可行性和有效性,可充分利用制造数据并在线调度制造执行过程。

基于E-Seq2Seq技术的数据驱动型机组组合智能决策方法

在能源技术变革日新月异、人工智能技术与电力系统深度融合的背景下,研究具有高适应性、高精度的机组组合智能决策方法具有重要意义。该文结合门限循环神经网络(gated recurrent unit,GRU)提出一种基于E-Seq2Seq(expand sequence to sequence,E-Seq2Seq)技术的数据驱动型机组组合智能决策方法。首先研究并梳理机组组合模型输入输出序列的类型与结构,形成机组组合弹性多序列映射型样本;然后研究提出一种适用于弹性多序列映射型样本的E-Seq2Seq技术;在此基础上,以GRU为神经元构建机组组合深度学习模型,并最终提出一种基于E-Seq2Seq技术的数据驱动型机组组合智能决策方法。基于IEEE118节点系统、Python环境的算例验证该文方法的正确性和有效性。

数据使能教学决策的发展--从数据教育应用到多模态学习分析支持教学决策

大量研究表明,数据驱动的教学决策能有效增强教师教学和学生学习的效果。当前研究多聚焦于数据驱动的教学决策模型及实践案例,较少关注支持教师教学决策的数据组织、收集和分析的过程。文章运用文献研究法和案例分析法,阐明基于数据教育应用原理的教学决策过程,并对其中的数据收集和分析过程进行解构,基于多模态学习分析的发展和过程优势,建构多模态学习分析支持的教学决策过程模型,找寻多模态学习分析支持教学决策的多模态数据收集和处理的过程与方法,并从实践角度分析两种多模态学习支持的教学决策的典型案例的过程和实践,希冀为国内中小学开展基于数据的有效教学决策研究和实践提供指引。

基于Bi-LSTM循环神经网络的风储系统控制策略

“双碳”背景下风电的渗透率不断提高,将对电力系统的形态和运行机制产生深刻影响。本文提出了一种基于双向长短期记忆Bi-LSTM(bidirectional long short-term memory)循环神经网络的风储系统控制策略。采用双向长短时循环神经网络提取控制结果与风电场实际出力以及储能状态间的时序信息,通过构建基于双向长短时记忆循环神经网络的控制模型,使得风电场在多种运行工况下能够快速、准确地得到储能系统调节结果。基于实际风电场数据仿真结果表明,本文所提控制策略能够保证在一定经济效益的前提下,将风储系统控制误差保持在0.50%~1.37%。

Knowledge-guided machine learning reveals pivotal drivers for gasto-particle conversion of atmospheric nitrate

Particulate nitrate,a key component of fine particles,forms through the intricate gas-to-particle conversion process.This process is regulated by the gas-to-particle conversion coefficient of nitrate(ε(NO_(3)^(-))).The mechanism betweenε(NO_(3)^(-))and its drivers is highly complex and nonlinear,and can be characterized by machine learning methods.However,conventional machine learning often yields results that lack clear physical meaning and may even contradict established physical/chemical mechanisms due to the influence of ambient factors.It urgently needs an alternative approach that possesses transparent physical interpretations and provides deeper insights into the impact ofε(NO_(3)^(-)).Here we introduce a supervised machine learning approachdthe multilevel nested random forest guided by theory approaches.Our approach robustly identifies NH4 t,SO_(4)^(2-),and temperature as pivotal drivers forε(NO_(3)^(-)).Notably,substantial disparities exist between the outcomes of traditional random forest analysis and the anticipated actual results.Furthermore,our approach underscores the significance of NH4 t during both daytime(30%)and nighttime(40%)periods,while appropriately downplaying the influence of some less relevant drivers in comparison to conventional random forest analysis.This research underscores the transformative potential of integrating domain knowledge with machine learning in atmospheric studies.

物理-数据-知识混合驱动的人机混合增强智能系统管控方法

当代系统认知、管理与控制的核心理论、方法与技术已经转移到大数据和人工智能技术上,这导致当前人工智能技术条件局限与复杂系统认知、管理、控制的需求之间形成了一道鸿沟。因此,现实的需求催生了人工智能的一种新型形态——人机混合增强智能形态,即人类智能与机器智能协同贯穿于系统认知、管理、控制等过程的始终,人类的认知和机器智能认知互相混合,形成增强型的智能形态,这种形态是人工智能或机器智能可行的、重要的成长模式。提出了一种物理-数据-知识混合驱动的人机混合增强智能系统管控方法。从可信分布式数据、计算和算法,物理深度学习,融合系统运行规则的混合型深度强化学习,因果分析,可解释性AI与数字人5个方面详细阐述了所提方法。最后,以电力系统调控为背景,以3个应用为例分析了所提方法的应用方式和技术路径。

An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids

With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data.

Data-driven Surrogate-assisted Method for High-dimensional Multi-area Combined Economic/Emission Dispatch

Multi-area combined economic/emission dispatch(MACEED)problems are generally studied using analytical functions.However,as the scale of power systems increases,ex isting solutions become time-consuming and may not meet oper ational constraints.To overcome excessive computational ex pense in high-dimensional MACEED problems,a novel data-driven surrogate-assisted method is proposed.First,a cosine-similarity-based deep belief network combined with a back-propagation(DBN+BP)neural network is utilized to replace cost and emission functions.Second,transfer learning is applied with a pretraining and fine-tuning method to improve DBN+BP regression surrogate models,thus realizing fast con struction of surrogate models between different regional power systems.Third,a multi-objective antlion optimizer with a novel general single-dimension retention bi-objective optimization poli cy is proposed to execute MACEED optimization to obtain scheduling decisions.The proposed method not only ensures the convergence,uniformity,and extensibility of the Pareto front,but also greatly reduces the computational time.Finally,a 4-ar ea 40-unit test system with different constraints is employed to demonstrate the effectiveness of the proposed method.

考虑信息时移的分布式光伏机理-数据混合驱动短期功率预测

分布式光伏短期功率预测缺乏同时空气象数据。传统方法直接借助邻近集中式光伏站点数据进行功率预测,忽略了地理位置偏移带来的气象信息时移,难以满足预测精度要求。文中提出了一种考虑气象信息时移的混合预测方法。在机理驱动模型中,采用最优时移对气象数据进行偏移修正;在数据驱动模型中,引入时间模式注意力机制削弱气象数据偏移的影响。然后,通过Stacking集成学习框架将两种方法进行融合,形成机理-数据混合驱动模型,进一步提高预测稳定性及准确率。基于分布式光伏和公共气象站点实际数据进行的案例分析表明,所提方法能够有效利用偏移地理位置的气象数据,实现更高精度的分布式光伏发电功率预测。