The remote desktop is widely used in enterprise environments. To improve its security, Zero Trust is generally introduced to replace the traditional perimeter-based model with dynamic trust evaluation and continuous verification. However, for the remote desktop system, where access chain topology can be abstracted as a graph consists of users, terminals, VMs and connections between them, classical dynamic trust evaluation approaches rely simply on users’ features collected from user-terminal interactions. They ignore features from remained parts of graph, such as terminal itself (as access medium) and status of virtual machines (as access target). Recent graph neural network (GNN) models are dedicated to fusing features from multiple sources in graph structure; however, they are often designed for low-heterogeneity domains and are thus not well suited to the heterogeneous interactions in remote desktop access. To address these challenges, we propose a heterogeneous graph neural network (HGNN) framework for trust evaluation in remote desktop systems. In particular, we model users, terminals, and virtual machines as distinct node types and represent their interactions as a heterogeneous graph, upon which we apply HGNN to aggregating multi-type relational information. This enables comprehensive and adaptive trust estimation tailored to the characteristics of remote desktop environments. Experiments on real-world datasets demonstrate that our method consistently outperforms baselines in terms of accuracy, precision, recall, and F1-score in the trust-level prediction task, confirming the effectiveness of heterogeneous graph modeling and neural-based aggregation in improving trust evaluation performance.

As an extension of cloud computing, edge computing provides storage and computing services at the network edge. Due to resource limitation of edge nodes, collaborative data offloading is usually utilized to offload overloaded data in the current node to adjacent nodes to ensure quality of service. In this case, the reputation mechanism is a crucial tool to select a reliable one from adjacent nodes to provide data storage service. However, existing works usually adopt the single source-based evaluation method, which is vulnerable to malicious manipulation and lacks objectivity. Meanwhile, the reputation of malicious nodes can be rapidly recovered, leading to a reduction in evaluation accuracy. To address these issues, we propose a secure blockchain-based edge nodes reputation scheme, combined with subjective evaluation result and objective monitoring values to provide a credible reputation. Specifically, to increase the malicious attack cost and limit reputation recovery speed, we design an Amplifying-based Reputation Calculation (ARC) mechanism to amplify the impact of malicious behaviors on reputation. In addition, we propose a Dynamic Miner Selection (DMS) algorithm to resist bookkeeping right attack from malicious infrastructure providers. Detailed analysis proves the security of our scheme and experiment results testify the effectiveness and efficiency.

Federated learning decentralizes the learning process, yet it does not provide adequate privacy protection. Current countermeasures predominantly rely on Local Differential Privacy (LDP) techniques. While larger noise injection offers stronger privacy, it also leads to a degradation in model performance and necessitates additional training iterations. Existing methods struggle to strike a balance between user privacy, model usability, and training efficiency. To address this, we propose an adaptive noise scaling method grounded in mutual information. This method is designed to dynamically optimize the noise scale, thereby safeguarding user privacy, enhancing training efficiency, and ensuring model usability. Specifically, we first estimate the mutual information between user training data and gradient updates in each iteration using Mutual Information Neural Estimation (MINE). Subsequently, we propose to dynamically adjust the optimal noise scale in each round of federated learning’s local training, based on the estimated mutual information. Experimental results demonstrate that using mutual information to dynamically adjust the noise scale reduces the number of training iterations by over 50%, while maintaining the same level of user privacy and data model availability.

Mobile Edge Computing (MEC) has emerged as a distributed computing paradigm offering low-latency services to users. However, the distributed and intricate deployment inevitably makes it challenge to ensure the reliability of MEC services. Anomaly detection using the streaming data of MEC services is an essential way to address the challenge. In this paper, to improve the detection accuracy and efficiency, we propose an MTDF-Detection framework for MEC services, jointly extracting Multi-Timescale and Dimensional Feature (MTDF), including the long-term trend, periodic, short-term fluctuation and auxiliary parameters (e.g., system maintenance and offloading task). In this framework, to reduce the computing costs, we adopt a Bidirectional Simple Recurrent Unit (Bi-SRU) to obtain contextual feature; and we design an adaptive m-Sigma algorithm to determine the dynamic threshold with real-time streaming data. Extensive experiments are conducted on a real-world dataset, and the results demonstrate that the MTDF-Detection framework outperforms the state-of-the-art schemes in terms of accuracy and efficiency.

Federated learning (FL) exhibits vulnerabilities to poisoning attacks, where Byzantine FL clients send malicious model updates to hamper the accuracy of the global model. However, these efforts are being circumvented by some more advanced stealthy poisoning attacks. In this paper, we propose an Enclave-aided Byzantine-robust Federated Aggregation (EBFA) framework. In particular, at each FL epoch, we first evaluate the layer-wise cosine similarity between the guide model (learned from an extra validation dataset) and local models, and then, utilize the boxplot method to construct a region of outliers to find Byzantine clients. To avoid the interference to the robust federated aggregation caused by classical privacy-preserving method, such as differential privacy and homomorphic encryption, we further design an efficient privacy-preserving scheme for robust aggregation via Trusted Execution Environment (TEE); and, to improve the efficiency, we only deploy the privacy-sensitive aggregation operations within resource limited TEE (or enclave). Finally, we perform extensive experiments on different datasets, and demonstrate that our proposed EBFA outperforms the state-of-the-art Byzantine-robust schemes (e.g., FLTrust) under non-IID settings. Moreover, our proposed enclave-aided privacy-preserving scheme could significantly improve the efficiency (over 40% for Alexnet) in comparison with the TEE-only scheme.

Abstract As a distributed learning paradigm, federated learning is supposed to protect data privacy without exchanging users’ local data. Even so, the gradient inversion attack, in which the adversary can reconstruct the original data from shared training gradients, has been widely deemed as a severe threat. Nevertheless, most existing researches are confined to impractical assumptions and narrow range of applications. To mitigate these shortcomings, we propose a comprehensive framework for gradient inversion attack, with well-designed algorithms for image and label reconstruction. For image reconstruction, we fully utilize the generative image prior, which derives from wide-used generative models, to improve the reconstructed results, by additional means of iterative optimization on mixed spaces and gradient-free optimizer. For label reconstruction, we design an adaptive recovery algorithm regarding real data distribution, which can adjust previous attacks to more complex scenarios. Moreover, we incorporate a gradient approximation method to efficiently fit our attack for FedAvg scenario. We empirically verify our attack framework using benchmark datasets and ablation studies, considering loose assumptions and complicated circumstances. We hope this work can greatly reveal the necessity of privacy protection in federated learning, while urge more effective and robust defense mechanisms.

Abstract Unprotected gradient exchange in federated learning (FL) systems may lead to gradient leakage-related attacks. CKKS is a promising approximate homomorphic encryption scheme to protect gradients, owing to its unique capability of performing operations directly on ciphertexts. However, configuring CKKS security parameters involves a trade-off between correctness, efficiency, and security. An evaluation gap exists regarding how these parameters impact computational performance. Additionally, the maximum vector length that CKKS can once encrypt, recommended by Homomorphic Encryption Standardization, is 16384, hampers its widespread adoption in FL when encrypting layers with numerous neurons. To protect gradients’ privacy in FL systems while maintaining practical performance, we comprehensively analyze the influence of security parameters such as polynomial modulus degree and coefficient modulus on homomorphic operations. Derived from our evaluation findings, we provide a method for selecting the optimal multiplication depth while meeting operational requirements. Then, we introduce an adaptive segmented encryption method tailored for CKKS, circumventing its encryption length constraint and enhancing its processing ability to encrypt neural network models. Finally, we present FedSHE , a privacy-preserving and efficient Fed erated learning scheme with adaptive S egmented CKKS H omomorphic E ncryption. FedSHE is implemented on top of the federated averaging (FedAvg) algorithm and is available at https://github.com/yooopan/FedSHE . Our evaluation results affirm the correctness and effectiveness of our proposed method, demonstrating that FedSHE outperforms existing homomorphic encryption-based federated learning research efforts in terms of model accuracy, computational efficiency, communication cost, and security level.

The recent advances of deep learning in various mobile and Internet-of-Things applications, coupled with the emergence of edge computing, have led to a strong trend of performing deep learning inference on the edge servers located physically close to the end devices. This trend presents the challenge of how to meet the quality-of-service requirements of inference tasks at the resource-constrained network edge, especially under variable or even bursty inference workloads. Solutions to this challenge have not yet been reported in the related literature. In the present paper, we tackle this challenge by means of workload-adaptive inference request scheduling: in different workload states, via adaptive inference request scheduling policies, different models with diverse model sizes can play different roles to maintain high-quality inference services. To implement this idea, we propose a request scheduling framework for general-purpose edge inference serving systems. Theoretically, we prove that, in our framework, the problem of optimizing the inference request scheduling policies can be formulated as a Markov decision process (MDP). To tackle such an MDP, we use reinforcement learning and propose a policy optimization approach. Through extensive experiments, we empirically demonstrate the effectiveness of our framework in the challenging practical case where the MDP is partially observable.

We present NadGPT, a transformer-based semi-supervised framework for network anomaly detection. It is known that transformer models are good at modeling long sequence data such as network traffic; however, without sufficient ground-truth labels, transformer models tend to suffer from over-fitting thus leading to inferior performance. Inspired by the recent success of GPT models in natural language processing (NLP), we propose a new auxiliary self-supervised task plugged to the backbone transformer, which enables GPT-like auto-regressive training on network traffic sequence without using ground-truth labels. Experiments demonstrate the proposed method greatly reduces the requirements of labels in network anomaly detection. For example, on ISCX 2012 dataset, given only 0.05% training labels our semi-supervised approach obtains nontrivial 81.7% (2-class) and 64.9% (5-class) Fl-scores on the validation set, which is far better than the supervised counterparts using the same training data. We hope our research could inspire more label-efficient methods in network traffic analysis.

Federated learning enables distributed and collaborative learning among multiple participants while protecting their privacy. However, due to its distributed nature, federated learning is vulnerable to Byzantine attacks. These attacks can poison the data or directly modify the model parameters, making the global model performance degrade or even leaving a backdoor. Existing strategies for mitigating Byzantine attacks require a priori information about the number of attackers or require additional validation datasets. However, prior knowledge of the number of Byzantine clients or the collection of representative validation datasets is not always feasible in practice. Moreover, recent research has shown that well-designed attacks can make malicious updates indistinguishable from benign ones by making them highly similar, thus bypassing existing defense methods that rely on these metrics.To tackle these problems, we propose Dynamic Clustering based Federated Learning (DCFL), a novel Byzantine robust FL approach without any additional validation datasets. The main idea behind DCFL is to rigorously constrain the magnitude and direction of local updates through norms and signs. To achieve this, we propose a novel metric that can effectively distinguish malicious updates from benign updates in terms of direction, which can help the server eliminate malicious updates before final aggregation. Our experiments on three datasets demonstrate the effectiveness of DCFL in mitigating various popular Byzantine attacks. Remarkably, the accuracy of the global model learned in the adversarial setting is even close to that of FedAVG under no attack.

Federated Learning (FL) has recently drawn considerable attention, enabling multiple end devices to collaboratively learn global models without collecting device data. In reality, end devices can usually be distributed in non-correlated environments and generate non-IID data, which may lead to the Artificial Intelligence (AI) model weight divergence among devices and model accuracy degradation after aggregation. In this paper, to address the non-IID data problem for FL, we treat this problem among end devices as a distribution adaptation problem among multiple source domains and analyze the feasibility of feature augmentation, and then propose a novel method called Label-wisE Distribution Adaptive Federated Learning (LEDA-FL). First, to reduce the divergence in the label-wise feature space, we integrate the modified Conditional Variational AutoEncoder (CVAE) to align the label-wise feature distributions among clients. Second, we augment the label-wise features for FL clients to improve the FL performance (test accuracy and communication efficiency). Finally, we conduct an extensive experiment on five popular datasets, and the experimental results show that our proposed method improves the test accuracy of the global model (e.g.,6.2% test accuracy improvement on CIFAR100 compared to FedProx) and the communication efficiency of FL (e.g., about 60% reduction in communication cost on CIFAR100 compared to FedProx).

Telemetry data is an important resource to detect anomaly of satellites in orbit. In recent years, the telemetry data-driven satellite anomaly detection has drawn great attention from academia and industries. However, in prior arts, the time-or frequency-domain data feature is usually separately utilized; and, to reduce the compute complexity, a small portion of data dimensions are usually selected from the telemetry data manually, leading to reduction in detection accuracy. Motivated by this, we propose a novel satellite telemetry data anomaly detection approach using high-dimension telemetry data, and the Multiple Factors and Co-Attention based LSTM (MFCA-LSTM) model. Specifically, to achieve an accurate prediction of telemetry sequence, we first propose the MFCA-LSTM model, jointly considering the time- and frequency-domain data feature, and the auxiliary information, e.g., telecommand and mission planning. Then, by using the MFCA-LSTM model, we construct a two-level anomaly detection framework to efficiently detect full-dimension data; and, to improve the accuracy rate and reduce the false alarm rate, we further propose an adaptive Tukey test algorithm to determine the dynamic thresholds. Finally, we perform extensive experiments based on two real-world datasets, and the results testify the effectiveness of our proposed framework.

Mobile edge computing (MEC), extending computing services from cloud to edge, is recognized as one of key pillars to facilitate real-time services and tackle backhaul bottleneck. However, it is not economically efficient to attach intensive security appliances to every MEC node to defend application-level DDoS attacks and ensure the availability of services. Thus, we explore the elasticity of security defense among MEC nodes by proposing a COoperative DEfense (CODE) framework for MEC, referred to asCODE4MEC. CODE4MEC aims to adapt to traffic changes by coordinating container-carried defensive resources among cooperative MEC nodes in an automatic way. Towards this aim, we propose four control plane functions to enable a life-cycle management for CODE4MEC, namely, CODE triggering, scheduling, coordination and releasing. However, an effective CODE4MEC requires non-trivial algorithmic schemes, in particular for CODE scheduling and coordination functions. We thus design an online combinatorial auction mechanism for real-time CODE scheduling, and prove a tighter performance bound relative to prior arts. As for CODE coordination, a flow-based traffic and context information coordination scheme is proposed to enable classical defense schemes to work properly and efficiently. Finally, using a combination of real testbed and simulation evaluations, we validate the effectiveness of CODE4MEC.

Deep Neural Networks (DNNs) have been widely used in everyday life owing to their impressive performance in complex machine learning tasks. The performance however comes at the cost of high computational complexity, which hinders the application of many DNN models in resource-constrained Internet-of-Things (IoT) and mobile devices. Device-edge collaborative DNN inference (referred to as co-inference) is an effective way to address the issue. However, it requires non-trivial algorithmic design, since the compound performance indicators including the inference efficiency and accuracy, and the data privacy have to be jointly considered. In this paper, we extend the degree of flexibility of the classical co-inference schemes, and propose a joint model, partitioning point and privacy differential intensity adaptation framework for co-inference, which comprises of the offline and online phases. In the offline phase, we train the co-inference model set that consists of a series of sub-models with different complexities, and profile the necessary performance of the sub-models. On that basis, we design an efficient algorithm for the online phase to promptly choose the sub-model, partitioning point and privacy differential intensity to meet the latency constraint and achieve the optimal accuracy-privacy tradeoff. Finally, extensive evaluations are carried out to demonstrate the effectiveness of our proposed framework.

With the capability of trading accuracy for latency on-the-fly, the technique of adaptive early-exit inference has emerged as a promising line of research to accelerate the deep learning inference. However, studies in this line of research commonly use a group of thresholds to control the accuracy-latency trade-off, where a thorough and general methodology on how to determine these thresholds has not been conducted yet, especially with regard to the common requirements of average inference latency. To address this issue and enable latency-aware adaptive early-exit inference, in the present paper, we approximately formulate the threshold determination problem of finding the accuracy-maximum threshold setting that meets a given average latency requirement, and then propose a threshold determination method to tackle our formulated non-convex problem. Theoretically, we prove that, for certain parameter settings, our method finds an approximate stationary point of the formulated problem. Empirically, on top of various models across multiple datasets (CIFAR-10, CIFAR-100, ImageNet and two time-series datasets), we show that our method can well handle the average latency requirements, and consistently finds good threshold settings in negligible time.

As an essential part to intelligently fine-grained scheduling, planning and maintenance in smart grid and energy internet, short-term load forecasting makes great progress recently owing to the big data collected from smart meters and the leap forward in machine learning technologies. However, the centralized computing topology of classical electric information system, where individual electricity consumption data are frequently transmitted to the cloud center for load forecasting, tends to violate electric consumers' privacy as well as to increase the pressure on network bandwidth. To tackle the tricky issues, we propose a privacy-preserving framework based on the edge-fog-cloud continuum for smart grid. Specifically, 1) we gravitate the training of load forecasting models and forecasting workloads to distributed smart meters so that consumers' raw data are handled locally, and only the forecasting outputs that have been protected are reported to the cloud center via fog nodes; 2) we protect the local forecasting models that imply electricity features from model extraction attacks by model randomization; 3) we exploit a shuffle scheme among smart meters to protect the data ownership privacy, and utilize a re-encryption scheme to guarantee the forecasting data privacy. Finally, through comprehensive simulation and analysis, we validate our proposed privacy-preserving framework in terms of privacy protection, and computation and communication efficiency.

Bring-Your-Own-Device (BYOD) has been widely viewed as a definite trend among enterprises in which employees bring and use their personal smartphones for work. Despite the perceived opportunities of increasing productivity and reducing costs, BYOD raises severe security and privacy concerns: the corporate networks and data are directly exposed to malware apps running on the personal smartphones. This highlights the necessity for performing real-time mobile malware detection in BYOD environments. Deep learning seems to be a natural choice to handle such detection, due to its state-of-the-art detection effectiveness. However, deep learning inference is usually too computationally complex for resource-constrained smartphones, and the communication overhead of cloud-based inference may be unacceptable. As a result, it is hard to seek the tradeoff between the real-time demand and optimality of detection accuracy. In this paper, we tackle this issue by proposing an endedge coordinated inference approach that can support highlyaccurate and average latency guaranteed malware detection. Our proposed approach integrates the early-exit and model partitioning methods to allow fast, correct and smartphonelocalized inference to occur frequently. Extensive evaluations are carried out, demonstrating that our proposed approach offers a good compromise between detection accuracy and efficiency.

Inference based on deep learning models is usually implemented by exposing sensitive user data to the outside models, which of course gives rise to acute privacy concerns. To deal with these concerns, Donget al.recently proposed an approach, namely the dropping-activation-outputs (DAO) first layer. This approach was claimed to be a non-invertible transformation, such that the privacy of user data could not be compromised. However, In this paper, we prove that the DAO first layer, in fact, can generally be inverted, and hence fails to preserve privacy. We also provide a countermeasure against the privacy vulnerabilities that we examined.

Mobile edge computing (MEC), as an enabling paradigm allowing mobile services to be performed at the edge of mobile networks, has been commonly expected to facilitate real-time services and offload backhaul traffic. However, the security issues raised by innovations in networks always hesitate us to embrace their benefits, and so MEC does. DDoS attacks originating from massive mobile devices in 5G, especially the vulnerable internet-of-things devices, is an unavoidable threat for MEC services. Unfortunately, each MEC node is hard to maintain service availability in the wake of DDoS attacks, owing to its limited hardware resources for defense. Therefore, we are motivated to study the cooperative defense against DDoS attacks for MEC, where defense resources can be shared between MEC nodes. Specifically, we purpose a global orchestration (GO) mechanism to make full use of freedom degrees of cooperative defense with respect to the number of cooperative participants and the amount of cooperative resource. In the process of designing the GO mechanism, we formulate the optimization problem of GO, and exploit the bucket elimination algorithm to find the optimal solutions. To make the GO mechanism practically usable, we propose a scalable approximation algorithm based on the mini-bucket elimination algorithm. Extensive simulations are carried out to validate the effectiveness of GO.

Demand side management will be a key component of future smart grid that can help reduce peak load and adapt elastic demand to fluctuating generations. In this paper, we consider customers that operate different appliances and propose a demand response approach based on utility maximization. Each appliance provides a certain benefit depending on the pattern or volume of power it consumes. Each customer wishes to optimally schedule its power consumption so as to maximize its individual net benefit subject to various consumption and power flow constraints. We show that there exist time-varying prices that can align individual optimality with social optimality, i.e., under such prices, when the customers selfishly optimize their own benefits, they automatically also maximize the social welfare. The utility company can thus use dynamic pricing to coordinate demand responses to the benefit of the overall system. We propose a distributed algorithm for the utility company and the customers to jointly compute this optimal prices and demand schedules. Finally, we present simulation results that illustrate several interesting properties of the proposed scheme.

The paradigms of Fog and Edge Computing along with Internet of Things (IoT) promise to make everything, especially smart devices, as part of the Internet environment, where highly-centralized computing infrastructures are gradually decentralized into micro data centers deployed at the edges of each network. As a result, access latency has been reduced dramatically because of the decreases in geographical distance. So far, a great deal of research effort has been focused on how to satisfy the ever-increasing demand for Fog and Edge Computing resources. Correspondingly, the traditional centralized power supply system need to be decentralized among other computing and communications resources. However, how to design, operate and manage a fully distributed power supply system to support the same service agreement level as in cloud computing under fog and edge computing largely remains unknown. In this article, we propose and develop a new power supply system for Fog and Edge computing based on our previous work on digital energy systems. Experimental results based on a real-world case study of the proposed system are presented to validate the effectiveness and efficiency of the proposed power supply system.

5G mobile edge computing (MEC), which pushes mobile services to the edge, has been recognized as an effective solution to enhance mobile users' quality of service, as well as to tackle the backhaul bottleneck. Although its architecture and service related techniques have drawn sufficient attentions, solutions to the security defense are still open. Therefore, we are motivated to propose a cooperative defense (CODE) framework against DDoS attacks for MEC by leveraging network function virtualization and software-defined networking architectures; in the framework, MEC nodes owning spare defense resource are orchestrated to help MEC nodes whose incoming traffic overwhelms their self-defense capability. To explore the elasticity space of CODE among multiple MEC nodes and develop an online resource management method of such CODE, we formulate the multi-requester multi-provider resource management problem for CODE, jointly considering the defense resource usage efficiency and the fairness of CODE participants. To balance complexity and performance for the formulated problem, we are motivated by online combinatorial auctions, and propose an online algorithm that has a provable performance guarantee. Finally, extending the MEC simulation platform that is used in our previous work, we validate the effectiveness in terms of resilient defense capability, fairness and computation efficiency.

The cooperative Mobile Edge Computing (MEC) caching, where caches are distributed in 5G edge to cooperatively bring popular contents closer to mobile users, is concocted with high expectation on improving users' quality of experience. However, the system may suffer severely from the pollution attack. By frequently requesting unpopular contents, the adversaries in the pollution attack can break the patterns of content popularity. As a result, the cooperative content placement decision making, which relies on the popularity pattern, will be misguided to store unpopular contents instead of popular ones. In this paper, we explore the behaviors and threats of pollution attack in cooperative MEC caching. Starting with single-inject pollution where adversaries concentrate the attack on a single cache, we study the behaviors and diffusion features from both statistical experiments and theoretical analysis. Results show that the unpopular contents can fill into caches within 2 hops from attackers, and caches within 3 hops suffer from severe damage. Meanwhile, we also derive the upper boundary of the attack damage and present a boundary analysis. Furthermore, in multiple-inject pollution where the adversaries launch multiple single-inject pollution simultaneously, we evaluate the threat when attackers intelligently organize the attacks. It is found that the adversaries can cause 44% severer damage and cover 45% more area after intelligently organizing the attacks. Our work in this paper provides a fundamental basis for countermeasures designing.

Energy harvesting (EH)–enabled relaying has attracted considerable attention as an effective way to prolong the operation time of energy-constrained networks and extend coverage beside desired survivability and rate of transmission. In related literature, the Harvest-Store-Use (HSU) model is usually utilized to describe the energy flow behavior of the EH system. However, the half-duplex (HD) constraint of HSU that harvested energy can only be used after being temporally stored in energy buffer may reduce effective transmission time. Thus, we first construct the full-duplex (FD) energy flow behavior model of the EH system where the harvested energy can be tuned to power load and being stored simultaneously. The FD model is then proved to be equivalent with the HSU model when time interval is small enough. Considering some key physical variabilities, for example, the wireless channel and the amount of harvested energy, the transmission adaptation problem for multiple relays embedded with FD EH systems is formulated with the objective to improve the utilization of the harvested energy. We tackle the problem by using a centralized optimization algorithm by jointly tuning the factors, including power control for source and relay nodes, relay selection and dynamic switching among four relay transmission mode, namely HD amplify-and-forward (AF), HD decode-and-forward (DF), FD AF, and FD DF. The centralized optimization algorithm is proposed on the basis of dual decomposition and serves as a benchmark. To enable relays to individually make their own decisions, a distributed algorithm with relatively higher complexity is given by using consensus optimization in conjunction with the alternating direction method of multipliers, and a sub-optimal algorithm with low complexity is provided. The proposed algorithms are shown to have good performance via simulations for a range of different EH rates and prediction errors.

In this paper, we design a game theoretical framework for improving the Quality of Service (QoS) in cooperative RAN caching. Considering the cooperation under both single cell transmission and joint transmission, the QoS metric is uniformly quantified as the total content delivery time. Although the formulated cooperative content placement problem is proved NP-hard, noticing the local cooperative characteristics, we transform the problem into Local Altruistic Gaming where the Nash Equilibrium (NE) can be guaranteed and distributive algorithms such as Spatial Adaptive Play (SAP) are applicable. Then, two distributed learning algorithms are proposed, where the former overcomes the execution difficulties over tremendous action set in traditional SAP, and the latter further accelerate the convergence by reducing the number of additional suboptimal NEs brought by the former. To further improve the computation efficiency, an updating scheme is constructed to enable parallel updating in the proposed algorithms. Finally, based on a real-world LTE traffic dataset, the performance of the proposed algorithms and the updating scheme have been validated.

Compared with the traditional power grid, Energy Internet is motivated by the concept of intelligent energy sharing and coordination, achieving higher penetration of renewable energy and economic saving. In this paper, we propose a new framework for the time-slotted Peer-to-Peer (P2P) energy sharing and coordination in Energy Internet, which aims to achieve flexible and efficient distributed energy management and control. In this framework, users are equipped with distributed generators (DGs), distributed energy storage systems (DESs) and smart meters; the P2P energy sharing fashion is supported, where users can buy/sell electric from/to utility company and their neighboring users. The energy sharing and coordination problem is formulated as a convex optimization problem with the objective to minimize the economic cost of users. Then, a distributed algorithm is proposed, in combination with alternating direction method of multipliers (ADMM). On the basis of a real-world dataset of renewable energy and real-time electricity price, both analytical and numerical results show the effectiveness of the proposed framework and algorithm in terms of not only fast convergence in a time slot but also economic saving prominently for a long time application.

To achieve higher transmission efficiency and better quality of services for content accessing, we incorporate caches into half-duplex relaying networks. Specifically, to extend the RN-MU (Relay Node to Mobile User) transmission phases, an adaptive phase adjusting (APA) mechanism is designed, where the BS-RN (Base Station to Relay Node) phases adaptively shrink to only transmit the index of content if the requested content is cached in RN; otherwise, to reduce the transmission delay from mobile network and Internet, directly delivering content from the cache of the BS to the RN and then to MU is preferably adopted. This design depends mainly on what and how the caches store at their finite storage space. We thus further propose a cooperative content placement scheme. Since the corresponding problem is proved NP-hard, we transform it into an exact potential game, and design a Dynamic-picking Partially-updating Spatial Adaptive Play (DPSAP) algorithm and a parallel updating scheme. Numerical results based on a real-world traffic dataset have validated the performance of our proposed DPSAP, updating scheme, as well as the performance improvement of APA mechanism.

Energy harvesting (EH) enabled relaying has attracted lots of interests recently, as the network energy consumption can be reduced and the coverage range can be extended simultaneously. In most existing literatures, the Harvest-Store-Use (HSU) model is utilized to describe the energy flow behavior of the EH system. However, the half-duplex (HD) constraint of HSU that harvested energy can only be used for powering load after being temporally stored in energy storage unit may reduce the effective transmission time. Thus, we first model the full-duplex (FD) energy flow behavior of the EH system where harvested energy can be tuned to power load and being stored simultaneously, and then prove the FD model is equivalent to the HSU model when time interval is small enough. With consideration of some key physical variabilities, e.g., the wireless channel and the amount of harvested energy, and the energy consumption difference between FD and HD relaying protocols, we further model the transmission optimization problem to improve the utilization of harvested energy by optimizing the short-term throughput. Finally, to numerically obtain the optimized short-term throughput, we propose the joint power adaption, relay selection and transmission protocol switching algorithm. Results show that the performance of the proposed algorithm outperforms that of fixed relaying algorithms, e.g., the short-term throughput of the proposed algorithm is improved by about 40% comparing with fixed HD relaying algorithm, with 20 user equipments, and loop interference power and EH rate equal to 23 dB and 120 J/s, respectively.

Deploying caches in mobile networks, especially in the radio access network (RAN) is regarded as a promising way to improve mobile user experiences and alleviate the increasing pressure of traffic growth. However, the characteristics of mobile traffic and the performance of RAN caching still remains unclear. In this paper, we extensively analyze the traffic characteristics, the content popularity and the cache performance using a unique dataset collected from a commercial LTE network of China Mobile, from the perspective of mobile access network. The dataset spans nearly a week and consists of a collection of approximately 62.1 millions HTTP sessions, generated by more than 3200 users distributed across three base stations. Based on this realistic dataset, we observe that HTTP traffic can be reduced by 24.4% on average and the hit ratio can reach up to 42.2%, using 100GB cache size. The implications on some fundamental design issues of practical RAN caching systems, including reasonable size of RAN cache, suitable locations of cache deployment and potential benefits of collaborative RAN caching, are further presented. We believe our findings will shed light on practical RAN caching system design.

The radio access network (RAN) cache is recently proposed to improve quality of experience perceived by mobile users on Internet content access and reduce intense pressure on the backhaul network. However, because RAN caches (e.g., associated with base stations) are located below mobility management entities in mobile core network, the continuity of content service for the handover users with unfinished RANcache content transmission is destroyed. Thus motivated, we design the seamless RAN-cache handover framework based on mobility prediction algorithm (MPA), where the smart terminal with unfinished content service during mobility predicts the break and the target handover access node (such as the BS or the WiFi access point), and pre-triggers the source RAN cache to return the content service to CDN servers outside the core network (CN) or to notify the RAN cache associated with the target handover access node to prepare for serving the handover user. The framework incurs no change to cellular infrastructure including RAN and CN. Different from prior arts of assumption that users' mobility is pre-known, we design the parallel autoregressive (AR) based received signal strength (RSS) prediction approach to achieve mobility prediction, and mathematically define its false probability during different tolerant intervals. The simulation scenario deployment engine and the user movement engine are designed, considering practical issues. Through simulations, the the false probability of seamless RAN-cache handover pre-trigger through MPA is less than 1.36%, and it can be guaranteed less than 1% as the maximal RAN-cache handover processing time is increased by 8%.

The radio access network (RAN) cooperative caching, which explores the scale effect through cooperative content sharing and caching among multiple RAN caches, is considered as one effective way to fully benefit from the RAN cache. In this paper, we study the feasibility and self-organizing algorithm for RAN cooperative caching. Specifically, we first analyze the real-world dataset of daily content requests from 10 LTE Base Stations (BSs), and find that pursuing high hit rate does not guarantee the reduction of backhaul traffic. Besides, it is shown that content requests from different BSs feature strongly temporal and spatial correlations. To the best of our knowledge, this finding proves the feasibility of RAN cooperative caching for the first time. Then, based on our findings, we propose the self-organizing algorithm for RAN caches to individually decide on how to update their cached content objects, utilizing the defined utility with consideration of the link states among RAN caches, and the size and the request number of the missed and cached content objects. Finally, the performance of our proposed algorithm is validated based on real-world dataset. The results show that the proposed algorithm achieves significant improvement in reducing backhaul traffic. For instance, when cache capacity of each BS is 65% of the traffic generated by non-repeated content objects which are requested in one day over its coverage, the proposed algorithm with 8 defined cooperative caches (CoCas) reaches an average reduction of more than 60% of the backhaul traffic generated in one day over the BS's coverage.

Distributed caching in the radio access network (RAN) has been a common approach for improving QoE per- ceived by mobile users and reducing backhaul traffic load. In this paper, we focus on the problem of cooperative and online searching and routing for content objects cached according to their local popularity in small- cell networks (SCNs), considering practical issues of implementation complexity and content prefer- ence diversity, which is different from prior arts mainly focusing on global content caching optimization with pre-knowledge of content requests and/or mobility pattern of users. We propose an in-RAN caches orchestration strategy (named as iCacheOS), where cooperative content searching and sharing is achieved through content joint wireless and backhaul routing algorithm. Specifically, the in-RAN caches orchestration framework is designed under the software defined networking inspired system architecture consisting of the central orchestrator and in-RAN caches with the local routing function; the content joint wireless and backhaul routing problem is constructed with the objective to minimizing the SCN content transmission delay, which is proved to be a quadratic assignment problem (QAP); to assure high computation efficiency, a joint dimension reduction, Lagrangian relaxation and accelerated branch and bound algorithm is pro- posed. Numerical results reveal that iCacheOS can significantly reduce the content transmission delay and outgoing backhaul traffic load, and is more robust to content preference diversities, in comparison with other strategies.

Distributed and cooperative caches (DCCs) enabled small-cell network (SCN) has been a common approach for improving QoE perceived by mobile users (UEs) and reducing backhaul traffic load. In this paper, we propose a joint wireless and backhaul load balancing (JWBLB) framework for DCCs enabled SCNs with the objective to minimizing the system content transmission delay. The JWBLB is achieved through content-request UEs and small-cell base stations re-association, and back-haul links and cooperative caches selection, with the knowledge of the cached content distribution, jointly considering traffic load of wireless and backhaul links. Specifically, 1) a software defined networking (SDN) inspired load balancing control architecture, consisting of the coordinator and DCCs, is designed. 2) The optimal JWBLB problem is formulated with the objective to minimizing the system content transmission delay, which is proved to be a quadratic assignment problem (QAP). 3) A joint Lagrangian relaxation and decomposition, and accelerated branch and bound algorithm is proposed to efficiently find the optimal binary solutions of the considered QAP. Simulation results show that JWBLB achieves great reduction in the average transmission delay and outgoing backhaul traffic load. For instance, 65% average transmission delay can be reduced as only 50% UEs with potential re-association possibility, and 48.4% outgoing traffic load caused by content fetches from Internet is reduced as the Zipf distribution parameter equals 0.6.

The gap between the stable system resource supply and the traffic load (i.e, the demand) with temporal fluctuations and spatial disparities results in deficiency in the system resource (e.g, power and spectrum resources) utility in cellular networks. To bridge the variant gap, cell breathing schemes are adopted in prior arts, which mainly focus on the temporal variance. Therefore, there is every reason to further explore the improvement room in terms of efficiency in the system resource utilization of cell breathing, jointly considering temporal fluctuations and spatial disparities of the traffic load, especially under Ultra-Dense HetNets (UDHNs), the promising delivery of 5G networks. We propose the High-Resolution Cell Breathing (HiRCB) strategy for improving energy efficiency for UDHNs: 1) inspired by pixels in digital imaging, the UDHN coverage area is logically divided into Traffic Lattices (TLs), capturing spatial disparities of the traffic load; 2) the TL association problem with the objective of maximizing the accumulative energy efficiency utility is formulated; 3) to solve the formulated problem, the Parallel and Integer TL Association Algorithm (PITLAA) is proposed, featuring parallel computations and algorithmic conversions from multiple to single TL association. Numerical results show that HiRCB improves at least 50% energy efficiency.

Due to advantages in spectral efficiency and energy efficiency of its air-interface, the coordinated multi-point (CoMP) transmission has been adopted in 4G and beyond mobile communication systems, such as LTE-A, which enables the transmission cooperation among multiple remote radio units (RRUs). As the main component of a RRU, the power amplifier (PA) is always blamed for its low power efficiency, which is difficult to be further improved by today's hardware technology. To eliminate the on-grid power consumption caused by the low PA efficiency and the corresponding CO2emission, we propose a new CoMP transmission framework, in which all RRUs and associated PAs are powered by the solar power. Then, based on the proposed framework, we derive the optimal coordinated transmission scheduling algorithm for maximizing the throughput with considerations of fast fading channel, limited pre-knowledge about channel state information (CSI), random energy arrival and finite energy storage. Theoretical analyses of the proposed algorithm are given, and numerical results show that our algorithm can achieve a close performance to the optimal transmission scheduling algorithm with a priori knowledge about CSI.

To reduce the fossil energy consumption and the operational expenses, the hybrid energy powered cellular network (HybENet) with BSs powered by on-grid or renewable energy is studied. To minimize the total expenses of energy consumption (EEC) and guarantee the quality of service of HybENet, a liquid cell management algorithm, which adaptively and cooperatively adjusts the service coverage of BSs according to the actual load, is proposed. Specifically, the problem of minimizing the total EEC under constraints of the fluctuating arrivals of the renewable energy and the QoS is formulated as a combinatorial optimization problem. Then, we prove that the problem can be decomposed into two sub-problems: 1) the mean of per-link energy minimization problem, from which the closed expression of power allocation is derived; 2) the traffic block assignment problem, which is solved by ant colony optimization. Simulation results show that the total EEC can be effectively reduced.

There is a growing interest around the world in supplying the communication networks with green energy from natural resources, e.g., solar, wind, and hydro, to reduce carbon footprints. However, the green energy sources and the energy buffer have the limitation of unstable availability and capacity. It is challenging to ensure that the fluctuant energy supply meets the demands of dynamic traffic loads. In this paper, we study the problem of how to ensure the sustainability of green energy powered cellular networks (i.e., green cellular networks). We firstly construct a generalized model to describe the energy evolution process of green energy powered cells. Then, energy dynamics metrics, which are energy level transfer time and energy outage probability, are analyzed by adopting diffusion approximation. Based on the results obtained in the analysis, a liquid cell management scheme is proposed to ensure the sustainability of green energy powered cells by adjusting the cell radii. The scheme performs excellently in improving both the lifetime and green energy utilization of green HeNBs.

Besides energy-efficient technologies, increasing attention is paid on powering cellular networks with renewable energy sources, concerning climate change, fossil fuel prices and energy security. In this paper, we not only aim to reduce the absolute energy consumption of cellular networks, but also provide a guideline to utilize the renewable energy efficiently in cellular networks. The renewable energy sources have the limitation of unstable availability and capacity. It is thus challenging to improve renewable energy efficiency while maintaining the energy supply sustainability. The energy supply sustainability problem is modeled as an optimization problem aiming to maximize the network energy residue ratio (ERR), which is NP-hard. To solve the optimization problem in polynomial time, the network ERR maximization algorithm is proposed after analyzing the relation between energy efficiency and energy depleting rate (EDR). The algorithm maximizes link energy efficiency via power control at physical (PHY) layer and maximizes network ERR via access control at media access control (MAC) layer jointly in a cross-layer manner. The network ERR maximization algorithm performs excellently in improving both the lifetime and the number of users served by renewable energy.

In this paper, we study the energy efficiency in the multiple access points (AP) coherent cooperative transmission (CCT) system with frequency-selective fading. Supposing the per antenna power constraint is sufficient, we derive the achievable optimal energy efficiency by distributing the transmit power among subchanels and cooperative APs, aiming at minimizing the Joule consumed per transmission bit of the CCT system. Based on Dinkelbach's theory, we solve our main problem with the associated parametric programming problem, and prove that the problem for the CCT can be transformed into an equivalent problem for the single AP transmission (SAT), which is much easier to be solved. The analytical solution is derived, along with an optimal power allocation algorithm. Numerical results are given to verify our analysis, and demonstrate that with the proposed scheme, the CCT outperforms the SAT in terms of the energy efficiency.

Service continuity in two-tier Femtocell networks, especially impaired by the handover latency, remains as a problem to be solved. Motivated by this problems, a Layer 3 prediction handover scheme is proposed, which can be integrated into the user equipment (UE) part of industry-preferable mobile-assisted network-controlled handover (MANCH). The main contributions of the proposed scheme include: 1) based on time series analysis theory, the prediction model of Layer 3 (L3) filtered reference signal received power (RSRP) is constructed to activate L3 handover prior to Layer 2 (L2) handover procedure; 2) in order to improve the reliability and robustness of the L3 prediction model, a two-priority handover trigger event evaluation method is designed, where the classical and prediction handover trigger event evaluation parts co-exist, and the former is prior to the latter; 3) the relationship between defined prediction handover gain (PHG) and the probability of false handover prediction trigger is derived. In simulations, to evaluate the robustness of the proposed scheme, a module of UEs' movement pattern is designed, considering characteristics of the UE's movement pattern. Results of the performance evaluation show that handover latency of indoor handover UEs can be effectively reduced with high prediction accuracy.

The two-tier femtocell network is comprised of a central macrocell underlaid with shorter range femtocell hotspots. Due to the universal frequency reuse, this kind of new system architecture brings about urgent problems of the interference management and the resource allocation. Motivated by these problems, the following contributions are made in this paper: 1) a novel joint power and subchannel allocation problem for Orthogonal Frequency Division Multiple Access (OFDMA) downlink based femtocells is formulated on the premise of minimizing Femto BSs' radiating interference; 2) a pseudo-handover based scheduling information exchange method is proposed to avoid the collision interference; 3) an iterative scheme of subchannel allocation and power control is proposed to solve the formulated problem, which is an NP-complete problem. Through simulations and comparisons with three other schemes, the proposed scheme shows better performance in reducing interference and the Femto BS's transmit power, and improving the spectrum efficiency.