A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learning

Federated Edge Learning(FEL),an emerging distributed Machine Learning(ML)paradigm,enables model training in a distributed environment while ensuring user privacy by using physical separation for each user’s data.However,with the development of complex application scenarios such as the Internet of Things(IoT)and Smart Earth,the conventional resource allocation schemes can no longer effectively support these growing computational and communication demands.Therefore,joint resource optimization may be the key solution to the scaling problem.This paper simultaneously addresses the multifaceted challenges of computation and communication,with the growing multiple resource demands.We systematically review the joint allocation strategies for different resources(computation,data,communication,and network topology)in FEL,and summarize the advantages in improving system efficiency,reducing latency,enhancing resource utilization,and enhancing robustness.In addition,we present the potential ability of joint optimization to enhance privacy preservation by reducing communication requirements,indirectly.This work not only provides theoretical support for resource management in federated learning(FL)systems,but also provides ideas for potential optimal deployment in multiple real-world scenarios.By thoroughly discussing the current challenges and future research directions,it also provides some important insights into multi-resource optimization in complex application environments.

Resource management at the network edge for federated learning

Federated learning has been explored as a promising solution for training machine learning models at the network edge,without sharing private user data.With limited resources at the edge,new solutions must be developed to leverage the software and hardware resources as the existing solutions did not focus on resource management for network edge,specially for federated learning.In this paper,we describe the recent work on resource manage-ment at the edge and explore the challenges and future directions to allow the execution of federated learning at the edge.Problems such as the discovery of resources,deployment,load balancing,migration,and energy effi-ciency are discussed in the paper.

Learning-based user association and dynamic resource allocation in multi-connectivity enabled unmanned aerial vehicle networks

Unmanned Aerial Vehicles(UAvs)as aerial base stations to provide communication services for ground users is a flexible and cost-effective paradigm in B5G.Besides,dynamic resource allocation and multi-connectivity can be adopted to further harness the potentials of UAVs in improving communication capacity,in such situations such that the interference among users becomes a pivotal disincentive requiring effective solutions.To this end,we investigate the Joint UAV-User Association,Channel Allocation,and transmission Power Control(J-UACAPC)problem in a multi-connectivity-enabled UAV network with constrained backhaul links,where each UAV can determine the reusable channels and transmission power to serve the selected ground users.The goal was to mitigate co-channel interference while maximizing long-term system utility.The problem was modeled as a cooperative stochastic game with hybrid discrete-continuous action space.A Multi-Agent Hybrid Deep Reinforcement Learning(MAHDRL)algorithm was proposed to address this problem.Extensive simulation results demonstrated the effectiveness of the proposed algorithm and showed that it has a higher system utility than the baseline methods.

Resource Allocation for Cognitive Network Slicing in PD-SCMA System Based on Two-Way Deep Reinforcement Learning

In this paper,we propose the Two-way Deep Reinforcement Learning(DRL)-Based resource allocation algorithm,which solves the problem of resource allocation in the cognitive downlink network based on the underlay mode.Secondary users(SUs)in the cognitive network are multiplexed by a new Power Domain Sparse Code Multiple Access(PD-SCMA)scheme,and the physical resources of the cognitive base station are virtualized into two types of slices:enhanced mobile broadband(eMBB)slice and ultrareliable low latency communication(URLLC)slice.We design the Double Deep Q Network(DDQN)network output the optimal codebook assignment scheme and simultaneously use the Deep Deterministic Policy Gradient(DDPG)network output the optimal power allocation scheme.The objective is to jointly optimize the spectral efficiency of the system and the Quality of Service(QoS)of SUs.Simulation results show that the proposed algorithm outperforms the CNDDQN algorithm and modified JEERA algorithm in terms of spectral efficiency and QoS satisfaction.Additionally,compared with the Power Domain Non-orthogonal Multiple Access(PD-NOMA)slices and the Sparse Code Multiple Access(SCMA)slices,the PD-SCMA slices can dramatically enhance spectral efficiency and increase the number of accessible users.

Deep-Ensemble Learning Method for Solar Resource Assessment of Complex Terrain Landscapes

As the global demand for renewable energy grows,solar energy is gaining attention as a clean,sustainable energy source.Accurate assessment of solar energy resources is crucial for the siting and design of photovoltaic power plants.This study proposes an integrated deep learning-based photovoltaic resource assessment method.Ensemble learning and deep learning methods are fused for photovoltaic resource assessment for the first time.The proposed method combines the random forest,gated recurrent unit,and long short-term memory to effectively improve the accuracy and reliability of photovoltaic resource assessment.The proposed method has strong adaptability and high accuracy even in the photovoltaic resource assessment of complex terrain and landscape.The experimental results show that the proposed method outperforms the comparison algorithm in all evaluation indexes,indicating that the proposed method has higher accuracy and reliability in photovoltaic resource assessment with improved generalization performance traditional single algorithm.

Development of Inquiry-Based Learning Tourism Products in Binzhou from the Perspective of Tourism Resources

Under the macro-background of “all-for-one” tourism,this study analyzes the related concepts and characteristics of inquiry-based learning tourism to understand the significance and role of developing inquiry-based learning tourism in China.With Binzhou as the object of study,this study also explores the development of inquiry-based learning tourism products from the aspects of the product development idea,level,framework and marketing,with a view to providing references for implementing inquiry-based learning tourism activities in other regions.

The Construction and Application of Digital Resources in Rural Primary School English Teaching and Learning

To arouse rural primary school students’ English learning interest, broaden their horizon and promote their critical thinking, we construct a series of dig-ital education resources which include not only language points of phonetics, vocabulary, language skills of English teaching and learning but western and Chinese cultures. The results show teachers and students’ roles and discourse power changed by using the digital education resources in the process of rural primary school English teaching and learning.

Using the Technology Acceptance Model to Analyze the Learning Outcome of Open Education Resources

Along with the development of information and communications technology,open educational resources were widely applied in training usage.The use of these resources facilitates the access to knowledge by enabling learners to transcend time and space.In this way,learners are able to obtain new knowledge more actively and efficiently than before.Using Technology Acceptance Model(TAM)as the theoretical foundation,this study aims to explore the learning outcome of using open educational resources with the perceived convenience as the external variable.In this study,the open educational resources were defined as online courses on the Open Course Ware(OCW)and Massive Open Online Courses(MOOCs),on which the learners choose courses themselves and study without the impact from people,matters,time,space,and things with the help of the Internet.To achieve the objectives of the study,the researchers conducted a survey with the participants who had already used the open educational resources.In total,124 valid samples were collected.The Partial Least Squares(PLS)statistical method was used to carry out the analysis.Overall,the model of this study has good prediction and explanatory power.After the data analysis,the study found that the perceived convenience exerts a positive impact on the use of the open educational resources.In addition,among the four TAM variables,the perceived usefulness does not exert a significant impact on the behavioral intention to use,but the other three TAM variables all have a significant impact on the behavioral intention.

Human Rights and Social Justice through Open Educational Resources and Lifelong Learning

A landmark in the realization of UNESCO’s Sustainability Goals,Education for All(SDG4),was passed when the organization’s Recommendation of Open Educational Resources(OER)was uniformly adopted in 2019.Now it is time to transfer from the consciousness of OER to their mainstream realization at all levels,micro,meso,and macro,including all stakeholders,such as governments,institutions,academics,teachers,administrators,librarians,students,learners,and the civil service.The OER Recommendation includes five areas:building capacity and utilizing OER;developing supportive policies;ensuring effectiveness;promoting the creation of sustainable OER models;promoting and facilitating international collaboration;monitoring and evaluation.OER are valued as a catalyst for innovation and the achievement of UNESCO’s SDG 4,education for all,lifelong learning,social justice,and human rights.The OER Recommendation will be a catalyst for the realization of several other SDGs.Because access to quality OER concerns human rights and social justice,this Recommendation is vital.In 2020,the effects of the worldwide COVID-19 pandemic clearly demonstrated the importance of opening up education and the access to internationally recognized,qualified learning resources.This article describes and discusses how the promise of resilient,sustainable quality open education can be fulfilled in the new normal and the next normal.

Study on Optimization of English Learning in Higher Vocational Schools under Network Resources

The information sharing and learning platform under network resources has not only facilitated the study of English,but has also changed the traditional learning model.There are many influencing factors for students to learn English using network technology.This article mainly analyzes non-English majors in higher vocational schools.Students learn independently about the unfavorable factors in English and propose corresponding optimization strategies to improve the learning efficiency.

MET as Program Resources for College English Teaching and Learning：Application and Implications

This paper investigates the current situation of Modern Educational Technology （MET） as program resources for college English teaching, exploring the effectiveness of the integration of MET and language teaching and learning. The case study in this paper illustrates that MET does benefit college English teaching but there are many problems of its application. Pedagogical implications are then provided to enhance the effective integration of MET and language teaching and learning： （1） it is wise for the teachers and learners to reconcile what is desirable with what is acceptable and possible in MET application; （2） teachers should optimize other existing resources to solve the problems caused by inequality and unavailability of MET; （3） teachers should have a clear conception of the relationship of MET and pedagogy to design and apply courseware appropriately; （4） students have beliefs in the benefits of MET, resulting in enhancing their individual language learning and efficiency.

Ontology and metadata for online learning resource repository management based on semantic web

An ontology and metadata for online learning resource repository management is constructed. First, based on the analysis of the use-case diagram, the upper ontology is illustrated which includes resource library ontology and user ontology, and evaluated from its function and implementation; then the corresponding class diagram, resource description framework （RDF） schema and extensible markup language （XML） schema are given. Secondly, the metadata for online learning resource repository management is proposed based on the Dublin Core Metadata Initiative and the IEEE Learning Technologies Standards Committee Learning Object Metadata Working Group. Finally, the inference instance is shown, which proves the validity of ontology and metadata in online learning resource repository management.

Adjustment to affective factors in English learning by using Internet English Curriculum Resource

The new curriculum standard points out that affection is one of the most important goals of fundamental education. The non-target language environment is easier to cause the affective change of middle school students who are changeable in their affective state. Based on the affective filter hypothesis, this paper deals with the adjustment to affective factors in English learning by using Internet English Curriculum Resource, such as attitude and motivation, anxiety and inhibition, self-esteem and self-confidence. At last, some suggestions are offered to judge Internet English Curriculum Resource.

Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

A Machine-Learning Based Time Constrained Resource Allocation Scheme for Vehicular Fog Computing

Through integrating advanced communication and data processing technologies into smart vehicles and roadside infrastructures,the Intelligent Transportation System(ITS)has evolved as a promising paradigm for improving safety,efficiency of the transportation system.However,the strict delay requirement of the safety-related applications is still a great challenge for the ITS,especially in dense traffic environment.In this paper,we introduce the metric called Perception-Reaction Time(PRT),which reflects the time consumption of safety-related applications and is closely related to road efficiency and security.With the integration of the incorporating information-centric networking technology and the fog virtualization approach,we propose a novel fog resource scheduling mechanism to minimize the PRT.Furthermore,we adopt a deep reinforcement learning approach to design an on-line optimal resource allocation scheme.Numerical results demonstrate that our proposed schemes is able to reduce about 70%of the RPT compared with the traditional approach.

Machine Learning Based Resource Allocation of Cloud Computing in Auction

Resource allocation in auctions is a challenging problem for cloud computing.However,the resource allocation problem is NP-hard and cannot be solved in polynomial time.The existing studies mainly use approximate algorithms such as PTAS or heuristic algorithms to determine a feasible solution;however,these algorithms have the disadvantages of low computational efficiency or low allocate accuracy.In this paper,we use the classification of machine learning to model and analyze the multi-dimensional cloud resource allocation problem and propose two resource allocation prediction algorithms based on linear and logistic regressions.By learning a small-scale training set,the prediction model can guarantee that the social welfare,allocation accuracy,and resource utilization in the feasible solution are very close to those of the optimal allocation solution.The experimental results show that the proposed scheme has good effect on resource allocation in cloud computing.

A New Solution to Intrusion Detection Systems Based on Improved Federated-Learning Chain

In the context of enterprise systems,intrusion detection(ID)emerges as a critical element driving the digital transformation of enterprises.With systems spanning various sectors of enterprises geographically dispersed,the necessity for seamless information exchange has surged significantly.The existing cross-domain solutions are challenged by such issues as insufficient security,high communication overhead,and a lack of effective update mechanisms,rendering them less feasible for prolonged application on resource-limited devices.This study proposes a new cross-domain collaboration scheme based on federated chains to streamline the server-side workload.Within this framework,individual nodes solely engage in training local data and subsequently amalgamate the final model employing a federated learning algorithm to uphold enterprise systems with efficiency and security.To curtail the resource utilization of blockchains and deter malicious nodes,a node administration module predicated on the workload paradigm is introduced,enabling the release of surplus resources in response to variations in a node’s contribution metric.Upon encountering an intrusion,the system triggers an alert and logs the characteristics of the breach,facilitating a comprehensive global update across all nodes for collective defense.Experimental results across multiple scenarios have verified the security and effectiveness of the proposed solution,with no loss of its recognition accuracy.

Deep Reinforcement Learning Based Joint Partial Computation Offloading and Resource Allocation in Mobility-Aware MEC System

Mobile edge computing(MEC)emerges as a paradigm to free mobile devices(MDs)from increasingly dense computing workloads in 6G networks.The quality of computing experience can be greatly improved by offloading computing tasks from MDs to MEC servers.Renewable energy harvested by energy harvesting equipments(EHQs)is considered as a promising power supply for users to process and offload tasks.In this paper,we apply the uniform mobility model of MDs to derive a more realistic wireless channel model in a multi-user MEC system with batteries as EHQs to harvest and storage energy.We investigate an optimization problem of the weighted sum of delay cost and energy cost of MDs in the MEC system.We propose an effective joint partial computation offloading and resource allocation(CORA)algorithm which is based on deep reinforcement learning(DRL)to obtain the optimal scheduling without prior knowledge of task arrival,renewable energy arrival as well as channel condition.The simulation results verify the efficiency of the proposed algorithm,which undoubtedly minimizes the cost of MDs compared with other benchmarks.

Stochastic Gradient Compression for Federated Learning over Wireless Network

As a mature distributed machine learning paradigm,federated learning enables wireless edge devices to collaboratively train a shared AI-model by stochastic gradient descent(SGD).However,devices need to upload high-dimensional stochastic gradients to edge server in training,which cause severe communication bottleneck.To address this problem,we compress the communication by sparsifying and quantizing the stochastic gradients of edge devices.We first derive a closed form of the communication compression in terms of sparsification and quantization factors.Then,the convergence rate of this communicationcompressed system is analyzed and several insights are obtained.Finally,we formulate and deal with the quantization resource allocation problem for the goal of minimizing the convergence upper bound,under the constraint of multiple-access channel capacity.Simulations show that the proposed scheme outperforms the benchmarks.