Edge Servers Research Articles

Task offloading for Industrial Internet of Things based on evolutionary multiobjective multitasking optimization

In mobile edge computing(MEC) scenarios, offloading computation-intensive and delay-critical tasks to nearby mobile edge servers with abundant computing resources can reduce the time delay(TD) of tasks and energy consumption(EC) of terminal devices, thus improving application performance and user experience. In order to reduce the TD of tasks and the EC of factory terminal devices(FTDs), MEC is introduced into the Industrial Internet of Things(IIoT). Because TD and EC are conflicting objectives, most existing research models the task offloading problem(TOP) as a multiobjective optimization problem to optimize both TD and EC. However, as the number of FTDs and tasks in the MEC network increases, the scale and computational cost of the TOP increases, and it is very challenging to obtain the optimal task offloading scheme through multiobjective optimization. Multitasking optimization can make use of knowledge transfer between related tasks to promote the solving efficiency of each task. Based on this, we model the TOP in IIoT as a multiobjective TOP (MTOP). A cheap task that is highly similar to MTOP is constructed, and a novel evolutionary multiobjective multitasking framework is developed, which uses the positive knowledge transfer between tasks to optimize TD and EC in the network. Then, an effective evolutionary multiobjective multitasking algorithm is proposed, which includes multi-functional knowledge transfer strategy(MFKT) and adaptive cheap task update strategy(ACTU). MFKT uses decision variables with different functions in the cheap tasks for positive knowledge transfer, so as to improve the performance of MTOP. ACTU dynamically updates the cheap task to maintain knowledge transfer between tasks. In different test instances, the proposed algorithm is compared with the existing multiobjective and multitasking algorithms. The experimental results show that the proposed algorithm is more competitive in terms of TD and EC, it can guarantee the service quality of the IIoT system and has strong robustness and scalability.

Software-Based Security Framework for Edge andMobile IoT

With the proliferation of Internet of Things (IoT) devices, ensuring secure communications has become imperative. Due to their low cost and embedded nature, many of these devices operate with computational and energy constraints, neglecting the potential security vulnerabilities that they may bring. This work-in-progress is focused on designing secure communication among remote servers and embedded IoT devices to balance security robustness and energy efficiency. The proposed approach uses lightweight cryptography, optimizing device performance and security without overburdening their limited resources. Our architecture stands out for integrating Edge servers and a central Name Server, allowing secure and decentralized authentication and efficient connection transitions between different Edge servers. This architecture enhances the scalability of the IoT network and reduces the load on each server, distributing the responsibility for authentication and key management.

An edge server placement based on graph clustering in mobile edge computing

With the exponential growth of mobile devices and data traffic, mobile edge computing has become a promising technology, and the placement of edge servers plays a key role in providing efficient and low-latency services. In this paper, we investigate the issue of edge server placement and user allocation to reduce transmission delay between base stations and servers, and balance the workload of individual servers. To this end, we propose a graph clustering-based edge server placement model by fully considering the constraints such as the distance, coverage area and number of channels of base stations. The model mainly consists of a two-layer graph convolutional network (GCN) component and a differentiable version of K-means clustering component, which transforms the server placement problem into an end-to-end learning optimization problem on a graph. It trains the GCN network to achieve the best clustering results with the expectation of average delay and load balancing as the loss function to obtain the edge server placement and user assignment scheme. We conducted experiments based on the Shanghai Telecom dataset, and the results show the effectiveness of our approach in both latency reduction and load balancing.

Optimizing proactive content caching with mobility aware deep reinforcement & asynchronous federate learning in VEC

Edge caching in the Internet of Vehicles (IoV) can reduce backhaul strain and content access delay. However, due to the constant changes in vehicle requests, offloading applications to edge servers is crucial for efficiently anticipating and caching popular content. Additionally, conventional data-sharing techniques are inadequate for this task due to their inability to preserve the privacy of vehicular users (VU). To overcome these issues, we propose a cooperative proactive content caching system incorporating Asynchronous federated learning and Deep reinforcement learning named PCAD that leverages the strengths of Dueling Deep Q-Networks and Prioritized Experience Replay in vehicular edge computing. PCAD lowers the latency of content access by prefetching contents that are popular beforehand caching them on edge nodes and cutting the waiting time for every vehicle to complete training as well as uploading local models before updating the global model. Additionally, we investigate intelligent caching decisions based on content prediction. Comprehensive experimental evaluations indicate that our proposed approach significantly outperforms existing benchmark caching techniques. More specifically, our suggested approach works better than DDQN, c-ϵ-greedy, and PCAD without DRL methods and the cache hit rate improves by approximately 4.25%, 11.23%, and 25.82%, respectively, as the cache capacity hits 400 MB.

Efficient, Scalable, and Sustainable DNN Training on SoC-Clustered Edge Servers

Efficient, Scalable, and Sustainable DNN Training on SoC-Clustered Edge Servers

Distributed Recommendation Systems: Survey and Research Directions

With the explosive growth of online information, recommendation systems have become essential tools for alleviating information overload. In recent years, researchers have increasingly focused on centralized recommendation systems, capitalizing on the powerful computing capabilities of cloud servers and the rich historical data they store. However, the rapid development of edge computing and mobile devices in recent years has provided new alternatives for building recommendation systems. These alternatives offer advantages such as privacy protection and low-latency recommendations. To leverage the advantages of different computing nodes, including cloud servers, edge servers, and terminal devices, researchers have proposed recommendation systems that involve the collaboration of these nodes, known as distributed recommendation systems. This survey provides a systematic review of distributed recommendation systems. Specifically, we design a taxonomy for these systems from four perspectives and comprehensively summarize each study by category. In particular, we conduct a detailed analysis of the collaboration mechanisms of distributed recommendation systems. Finally, we discuss potential future research directions in this field.

Offloading Strategy for Forest Monitoring Network Based on Improved Beetle Optimization Algorithm

In forest monitoring networks, the computational capabilities of sensors cannot meet the latency requirements for complex tasks, and the limited battery capacity of these sensors hinders the long-term execution of monitoring tasks. Mobile edge computing (MEC) acts as an effective solution for this issue by offloading tasks to edge servers, significantly reducing both task latency and energy consumption. However, the computational capacity of MEC servers and the bandwidth in the system are limited, and the communication environment in forested areas is complex. To simulate the complexity of the forest communication environment, we incorporate empirical path loss and multipath fading into the calculation of signal transmission rates. The computational offloading problem is then converted into a minimum-cost optimization problem with multiple constraints related to energy consumption and latency, which we formulate as an NP-hard problem. We propose a dung beetle optimization (DBO) strategy for computational offloading, enhancing it with an improved circle chaotic mapping, a dimension decomposition strategy, and Cauchy disturbance. This algorithm has the beauty of symmetry in the search range, and the symmetrical features can comprehensively search for existing solutions. Experimental results demonstrate that the improved dung beetle optimization algorithm (IDBO) achieves better convergence, lower complexity, and superior optimization outcomes compared to local offloading strategies and other metaheuristic algorithms, confirming the effectiveness of the proposed algorithm and ensuring the service quality of the forest monitoring network.

Workload-based adaptive decision-making for edge server layout with deep reinforcement learning

Mobile edge computing (MEC) is crucial in applications such as intelligent transportation, innovative healthcare, and smart cities. By deploying servers with computing and storage capabilities at the network edge, MEC enables low-latency services close to end users. However, the configuration of edge servers needs to meet the low-latency requirements and effectively balance the servers’ workloads. This paper proposes an adaptive layout and dynamic optimization method, modeling the edge server layout problem as a Markov decision process. It introduces a workload-based server placement rule that adjusts the locations of edge servers according to the load of base stations, enabling the learning of low-latency and load-balanced server layout strategies. Experimental validation on a real dataset from Shanghai Telecom shows that the proposed algorithm improves average latency performance by about 40% compared to existing technologies, and enhances workload balancing performance by about 17%.

End-to-End Latency Optimization for Resilient Distributed Convolutional Neural Network Inference in Resource-Constrained Unmanned Aerial Vehicle Swarms

An unmanned aerial vehicle (UAV) swarm has emerged as a powerful tool for mission execution in a variety of applications supported by deep neural networks (DNNs). In the context of UAV swarms, conventional methods for efficient data processing involve transmitting data to cloud and edge servers. However, these methods often face limitations in adapting to real-time applications due to the low latency of cloud-based approaches and weak mobility of edge-based approaches. In this paper, a new system called deep reinforcement learning-based resilient layer distribution (DRL-RLD) for distributed inference is designed to minimize end-to-end latency in UAV swarm, considering the resource constraints of UAVs. The proposed system dynamically allocates CNN layers based on UAV-to-UAV and UAV-to-ground communication links to minimize end-to-end latency. It can also enhance resilience to maintain mission continuity by reallocating layers when inoperable UAVs occur. The performance of the proposed system was verified through simulations in terms of latency compared to the comparison baselines, and its robustness was demonstrated in the presence of inoperable UAVs.

A Secure IIoT Environment That Integrates AI-Driven Real-Time Short-Term Active and Reactive Load Forecasting with Anomaly Detection: A Real-World Application

The Industrial Internet of Things (IIoT) revolutionizes both industrial and residential operations by integrating AI (artificial intelligence)-driven analytics with real-time monitoring, optimizing energy usage, and significantly enhancing energy efficiency. This study proposes a secure IIoT framework that simultaneously predicts both active and reactive loads while also incorporating anomaly detection. The system is optimized for real-time deployment on an edge server, such as a single-board computer (SBC), as well as on a cloud or centralized server. It ensures secure and reliable industrial operations by integrating smart data acquisition systems with real-time monitoring, control, and protective measures. We propose a Temporal Convolutional Networks-Gated Recurrent Unit-Attention (TCN-GRU-Attention) model to predict both active and reactive loads, which demonstrates superior performance compared to other conventional models. The performance metrics for active load forecasting are 0.0183 Mean Squared Error (MSE), 0.1022 Mean Absolute Error (MAE), and 0.1354 Root Mean Squared Error (RMSE), while for reactive load forecasting, the metrics are 0.0202 (MSE), 0.1077 (MAE), and 0.1422 (RMSE). Furthermore, we introduce an optimized Isolation Forest model for anomaly detection that considers the transient conditions of appliances when identifying irregular behavior. The model demonstrates very promising performance, with the average performance metrics for all appliances using this Isolation Forest model being 95% for Precision, 98% for Recall, 96% for F1 Score, and nearly 100% for Accuracy. To secure the entire system, Transport Layer Security (TLS) and Secure Sockets Layer (SSL) security protocols are employed, along with hash-encoded encrypted credentials for enhanced protection.

Efficient slicing scheme and cache optimization strategy for structured dependent tasks in intelligent transportation scenarios

The challenges posed by structured large-scale tasks to resource-sensitive intelligent transportation systems have been acknowledged, particularly regarding the need to reduce delay and energy consumption during the caching and offloading processes. To address these challenges and improve the quality of service for vehicular users, a cloud–edge-end collaboration caching strategy (CACCSC) based on structured task content awareness was proposed in this paper. The dependencies among task fragments were modeled through fuzzy judgment criteria. In addition, a system delay model, an energy consumption model, and an edge server load balancing model were developed, along with a multi-objective optimization model that integrates system delay, energy consumption, and edge server load balancing variance. To solve this multi-objective optimization problem, an adaptive multi-objective optimization algorithm (MDE-NSGA-III) was developed, which combines an enhanced version of the Differential Evolution algorithm with improvements to the NSGA-III algorithm. Finally, it has been demonstrated through simulation experiments that when the number of users in the system reaches 35, the system delay, energy consumption, and load balancing variance of the MDE-NSGA-III optimization scheme proposed in this paper are 6.1%, 6.6%, and 25% lower than those of the NSGA-III scheme, 15.8%, 10%, and 41.7% lower than those of the NSGA-II scheme, and 62.7%, 20.7%, and 8.3% lower than those of the PeEA scheme.

Service migration with edge collaboration: Multi-agent deep reinforcement learning approach combined with user preference adaptation

Multi-access edge computing provides proximate intelligent services for distributed users. Due to the user’s mobility and highly dynamic network, edge servers with limited coverage cannot ensure continuity of running services and maintain high-level Quality of Service. To tackle this issue, an effective service migration strategy is of paramount importance. However, the current approach ignores the cooperation between multiple edge servers and independent users. In this article, we study service migration with edge collaboration to realize lightweight migration by layer-sharing framework of containers, saving redundant transmissions of migration. Then, we formalize the migration decision problem as maximizing the migration utility problem. To obtain efficient online decisions, we proposed a dynamic service migration strategy (MA-DSM) based on multi-agent proximal policy optimization (MAPPO) algorithm, which leverages a flexible multi-policy framework to achieve user preference adaptation. Specifically, we improve the basic MAPPO by devising a context-aware grouping method to cluster agents with user’s mobility patterns and service preferences. Parameter sharing is introduced into the actor–critic network to learn customized policies for different clusters, facilitating cooperation among users in the same cluster. Extensive experiments demonstrate that our proposed approach outperforms baselines in terms of convergence, latency and migration utility.

Quantum-inspired gravitational search algorithm-based low-price binary task offloading for multi-users in unmanned aerial vehicle-assisted edge computing systems

Unmanned aerial vehicles (UAVs)-assisted edge computing (EC) brings computing resources closer to smart mobile devices (SMDs). Users of SMDs with limited resources can experience the flavour of computation and data-intensive applications. Users conserve energy by offloading resource-intensive tasks to edge servers (ESs) or UAVs. While offloading may introduce communication delays, leveraging ample wireless bandwidth can mitigate this issue by facilitating faster data transmission rates. However, mobile service providers (MSPs), facilitating offloading infrastructure, impose charges on users for bandwidth usage. Efficient utilization of limited computation units (CUs) is crucial. This paper introduces a binary task offloading (BTO) model for multi-user in multi-UAV-assisted EC systems using a quantum-inspired gravitational search algorithm (QGSA). Quantum encoding and decoding of the agents are provided. The decoding phase uses a novel hashing. The fitness function considers energy, delay, price, and resource utilization. Two penalties are incorporated with the fitness to discard the decoded agent that violates the constraints of the BTO model. The proposed QGSA ensures polynomial time execution. The proposed work is extensively simulated in multiple scenarios and compared with existing approaches. It is observed that the QGSA outperformed other algorithms in terms of delay, energy, resource utilization, and price. Analyses of convergence and statistics are performed.

Federated Learning‐Based Mobile Traffic Prediction in Satellite‐Terrestrial Integrated Networks

ABSTRACTIntroductionWith the development and integration of satellite and terrestrial networks, mobile traffic prediction has become more important than before, which is the basis for service provision and resource scheduling when supporting various vertical applications. However, existing traffic prediction methods, especially deep learning‐based methods, require massive data for model training. Due to data privacy concerns, mobile traffic data are not easily shared among different parties, making it difficult to obtain a precise prediction model.MethodsTo mitigate the data leakage risk, a federated learning framework is proposed in this study for mobile traffic prediction in satellite‐terrestrial integrated networks to achieve a tradeoff between data privacy and prediction accuracy. In the proposed framework, local models are trained in base stations on the ground, and a global model is aggregated in the satellite edge server in space.ResultsA deep learning‐based prediction model with an adaptive graph convolutional network (AGCN) and long short‐term memory (LSTM) modules is proposed and validated in numerical experiments, which achieves the lowest prediction error with a real‐world traffic dataset when compared with other graph neural network (GNN) variants in the federated learning setting.ConclusionNumerical experiments with a real‐world mobile traffic dataset demonstrate the effectiveness of the proposed approach, which outperforms other GNN variants with lower prediction errors.

Task offloading for multi-server edge computing in industrial Internet with joint load balance and fuzzy security

The industrial Internet revolutionizes traditional manufacturing through the incorporation of technologies such as real-time production optimization, big data analysis, etc. Computing resource-constrained industrial terminals struggle to effectively execute latency-sensitive and computation-intensive tasks triggered by these technologies. Edge computing (EC) emerges as a promising paradigm for offloading tasks from terminals to the adjacent edge servers, offering the potentiality to augment the computational capacities for industrial terminals. However, the development of accurate offloading strategies poses a prominent challenge for EC in the industrial Internet. Incorrect offloading strategies will misguide the task offloading procedure, resulting in adverse consequences. In this paper, we study the latency-aware multi-server partial EC task offloading problem in the industrial Internet with the consideration of joining load balancing and security protection to provide accurate strategies. Firstly, we establish a task offloading model that supports partial offloading, facilitating latency reduction, task offloading across multiple edge servers with load balance, and accommodation of fuzzy task risks. We quantify the established model as a constrained optimization formulation and prove its NP-hardness. Secondly, to solve the composite offloading strategy comprising both the offloading location and offloading ratio derived from our model, we propose a bi-layer offloading algorithm with joint load balance and fuzzy security, which is based on the adaptive genetic algorithm and simulated annealing particle swarm optimization. Based on extensive experimental results, we find that the established model is effective in reducing the objective value, with a respective decrease of 27% and 46% compared to full execution in edge servers and local execution in industrial terminals. Furthermore, the proposed offloading algorithm exhibits superior performance in terms of solution accuracy compared to existing algorithms.

A Dynamic Edge Server Placement Scheme Using the Improved Snake Optimization Algorithm

In the paradigm of mobile edge computing (MEC), providing low-latency and high-reliability services for users is garnering increasing attention. Appropriate edge-server placement is the crucial first step to realizing such services, as it can meet computation requirements and enhance resource utilization. This study delves into efficient and intelligent dynamic edge-server placement by taking into account time-varying network scenarios and deployment costs. Firstly, edge servers are classified into static and dynamic ones. Subsequently, an improved snake optimization algorithm is proposed to determine the number and placement locations of dynamic servers while adhering to delay requirements. Finally, a minimum placement-cost algorithm is put forward to further reduce the service cost. Experimental results demonstrate that compared to classic algorithms, the proposed algorithms can achieve a reduction in latency of 5% to 12%. And compared to the state-of-the-art methods, they can reduce service costs by 20% to 43%. This research offers an effective solution for dynamic edge-server placement and holds great theoretical and practical significance.

SecDS: A security-aware DAG task scheduling strategy for edge computing

Edge computing typically handles applications as multiple dependent sub-tasks presented with Directed Acyclic Graphs (DAGs) and offloads them to multiple edge servers to reduce network bandwidth pressure thereby improving task execution efficiency. However, security risk may be increased due to the involvement of many edge servers in a DAG-based task execution. For instance, execution may fail if any involved edge server is attacked. Nonetheless, security management mechanisms have not been adequately explored.To address the issue, this paper proposes a security-aware DAG task scheduling strategy, termed SecDS, which improves task execution efficiency while ensuring task execution security. The core idea is to adaptively select from various security algorithms for task offloading in light of security estimation. Specifically, a security-trust model is first proposed to define the security risk level between user devices and edge servers. Then, a novel security mechanism is designed to indicate a suitable security algorithm for the task offloading at each security risk level. Furthermore, to offset the cost of the security mechanism, a novel task scheduler is proposed to minimize completion time while satisfying security requirements. Finally, extensive experiments with heterogeneous DAG task flows (generated by an open-source generator, DAGGEN) have been conducted to demonstrate the effectiveness of SecDS.

Green Computation Offloading With DRL in Multi‐Access Edge Computing

ABSTRACTIn multi‐access edge computing (MEC), computational task offloading of mobile terminals (MT) is expected to provide the green applications with the restriction of energy consumption and service latency. Nevertheless, the diverse statuses of a range of edge servers and mobile terminals, along with the fluctuating offloading routes, present a challenge in the realm of computational task offloading. In order to bolster green applications, we present an innovative computational task offloading model as our initial approach. In particular, the nascent model is constrained by energy consumption and service latency considerations: (1) Smart mobile terminals with computational capabilities could serve as carriers; (2) The diverse computational and communication capacities of edge servers have the potential to enhance the offloading process; (3) The unpredictable routing paths of mobile terminals and edge servers could result in varied information transmissions. We then propose an improved deep reinforcement learning (DRL) algorithm named PS‐DDPG with the prioritized experience replay (PER) and the stochastic weight averaging (SWA) mechanisms based on deep deterministic policy gradients (DDPG) to seek an optimal offloading mode, saving energy consumption. Next, we introduce an enhanced deep reinforcement learning (DRL) algorithm named PS‐DDPG, incorporating the prioritized experience replay (PER) and stochastic weight averaging (SWA) techniques rooted in deep deterministic policy gradients (DDPG). This approach aims to identify an efficient offloading strategy, thereby reducing energy consumption. Fortunately, algorithm is proposed for each MT, which is responsible for making decisions regarding task partition, channel allocation, and power transmission control. Our developed approach achieves the ultimate estimation of observed values and enhances memory via write operations. The replay buffer holds data from previous time slots to upgrade both the actor and critic networks, followed by a buffer reset. Comprehensive experiments validate the superior performance, including stability and convergence, of our algorithm when juxtaposed with prior studies.

NVM-Enhanced Machine Learning Inference in 6G Edge Computing

With the increasing popularization of smart terminals and real-time interactive applications, fast growing technical requirements push both academia and industry to look beyond 5G and conceptualize the sixth generation (6G) mobile network. Artificial intelligence (AI) with machine learning capacities at the edge is one crucial component of a 6G mobile network which makes various time-sensitive and high-stake services possible, e.g., smart security, virtual reality, self-driving vehicles. However, resource constraints, especially the memory limitation of edge servers, become major obstacles to deploying machine learning services at the edge. Fortunately, the new generation of non-volatile memory (NVM) provides new affordable memory resources that can be easily attached to existing edge servers. In this paper, we propose a novel machine learning application placement scheme using the NVM technology at the edge to reduce the end-to-end latency. Specifically, the proposed NVM-enhanced placement scheme takes into consideration the latency of various machine learning applications over NVM devices and the network. The corresponding optimization problem is exceedingly challenging, i.e., NP-hard. Therefore, we developed a novel approximation algorithm with both low computational complexity and theoretical guarantees. Experiments and extensive simulations using real-world applications highlight that our scheme provides significantly lower end-to-end latency compared with existing baselines.

Edge Computing-driven Smart Transportation: Analysis and Prediction of Urban Traffic Flow

Abstract With the continuous development of artificial intelligence, the research and application of automated connected driving is receiving more and more attention. The combination of mobile edge computing and Telematics provides crucial technical support. In this paper, we propose a rasterization method for mobile edge computing scenario. We establish a grid classification model based on K-means to facilitate targeted and distributed optimization of computing resources. Meanwhile, we dynamically adjust the allocation of computational resources and the location of edge servers in advance deployment by predicting vehicle traffic. The experimental results demonstrate that the K-means-based grid classification model can accurately classify the grids and differentiate the traffic patterns of the grids, such as remote suburban areas, suburban areas, residential living areas, production industrial areas, and commercial center areas. The Backpropagation (BP) neural network-based grid traffic flow prediction model can simulate the overall changes of the grid traffic flow throughout a day to the maximum extent. Finally, we plan optimization scheme in urban mobile edge scenarios based on the results obtained from our analysis and prediction, and through our results, we can make edge computing resources be utilized efficiently.