Route planning algorithms, as a core technology of intelligent and connected vehicles (ICVs), significantly enhance road safety and traffic efficiency. Fusing traffic data and edge server information into route planning algorithms enables ICVs to avoid road accidents and enhances their access to low-latency computational resources. However, developing a route planning approach for ICVs faces two major challenges: (i) learning anomaly distributions from traffic data is complicated due to the scarcity of anomaly datasets, and (ii) the large-scale of routes complicates the evaluation of computational resources. In this article, we propose a route planning approach with traffic data and edge server (RP-TDES) to address these above challenges. Specifically, the anomaly detection module of the RP-TDES approach integrates a generator that mines spatiotemporal features and a discriminator based on similarity measures. Both components are optimized through adversarial training to address the scarcity of anomalous events. In addition, to address the challenge of evaluating the computational resources for a entire route, we propose an evaluation method that considers the vehicle's mobility characteristics. Finally, we validate the effectiveness of our approach on both real-world and synthetic road networks, and the experiment results show that our approach outperforms the baseline in route planning in terms of vehicle travel time and edge service capability. Meanwhile, experiment results demonstrate that our anomaly detection model also outperforms baseline methods for accident detection.

Microservice is a popular architecture to construct applications from a set of small independent services in cloud environment, leading to high cohesion, high availability, low coupling, and decent scalability. Due to large number of independent services in a microservice system, system faults generated from a single service would propagate to multiple services, eventually degraded the overall system performance and Quality of Service (QoS). Thus, it is crucial to efficiently and autonomously diagnose the runtime system fault. However, the complexity and dynamism of microservice systems and cloud environment pose unique challenges to precisely and robustly identify the faults and localize the root causes. In this paper, we propose an Autonomous Model Selection-Ensemble-Stacking (AMSES) framework for microservice system fault identification. The proposed framework can automatically select, ensemble, and stack optimal models from candidate unsupervised detection models for identifying different fault types robustly. In addition, AMSES can adaptively localize the fault services using autoselected root cause localization model. Moreover, by exploiting the fault degree and causal inferring score, we can diagnose the detected system fault precisely and interpretably. To evaluate the effectiveness, we empirically compare AMSES with state-of-the-art models on three kinds of faults on two microservice benchmarks: Sock-Shop and Train-Ticket. The experimental results show that AMSES can achieve$\mathbf{8 7. 1 \%}$and$\mathbf{9 1. 4 \%}$macroF1 average for fault type identification on Sock-Shop and TrainTicket, respectively. Meanwhile, AMSES could outperform its competitors for root cause localization with an average Avg@5 of 0.856 on Sock-Shop and 0.633 on Train-Ticket.

The rapid evolution of vehicular edge computing (VEC) poses critical challenges in distributed caching resource management, particularly in reducing content retrieval latency and improving cache utilization efficiency. We propose a community-aware caching framework tailored for VEC scenarios, comprising two main components: a Dynamic Thematic-Community Clustering (DTCC) algorithm based on Collapsed Gibbs sampling and a Potential Game-based Caching Optimization (GCO) strategy. The DTCC algorithm captures the temporal evolution of vehicular social networks, facilitating dynamic community partitioning and topic distribution extraction. Meanwhile, GCO formulates the caching decisions of vehicles and base stations as a non-cooperative game, whose community-aware utility function design guarantees both the existence and convergence of a Nash equilibrium. Extensive experiments on real-world datasets demonstrate that GCO consistently outperforms state-of-the-art baselines across diverse performance metrics, further validating its efficacy compared with existing caching solutions.

Multiaccess edge computing (MEC) is a novel service paradigm located at the network’s edge, where servers with computation and storage capabilities are placed in proximity to network endpoints to meet the high-speed computation and low-latency requirements of these endpoints. MEC faces numerous security challenges, with Distributed Denial of Service (DDoS) attacks being one of the primary threats. On one hand, the edge server layer (ESL) encounters a greater number of attack sources and has relatively fewer defense resources, making traditional defense techniques less applicable. On the other hand, the ESL can integrate with new technologies for earlier detection and interception of attack traffic, achieving more real-time attack mitigation. To provide comprehensive insights into the latest research developments and inspire new DDoS defense solutions, this article conducts an extensive survey and synthesis. This article begins with a summary of the basic concepts, application scenarios, and security vulnerabilities of MEC networks. It then introduces the types and principles of DDoS attacks faced by MEC networks. Subsequently, various security solutions for DDoS attacks in MEC were detailed and extensively compared, followed by an introduction to current application cases of DDoS defense deployment in practical MEC scenarios. Finally, open issues and future research directions are listed for further exploration.

As massive data is generated by Internet of Things (IoT) devices, user-end devices are required to implement computation-intensive functionalities, including multi-sensory data processing and analysis, sophisticated system control schemes, and artificial intelligence. Mobile Edge Computing (MEC) is a significant technology that has the potential to extend the computation and storage capacities of user-end devices by the decentralization of required resources and contents near users and at the edge. A crucial challenge in this direction is the development of a smart mechanism to effectively cache contents upon Edge Servers (ESs) near users for high effectiveness and low latency of content delivery with the constraints on computational and storage capacities of ESs. This study employs a queuing model for analyzing total request delay and interprets the content caching problem as an adversarial semi-bandits problem. We propose an Online Self-feedback Adversarial Semi-bandits Learning (OSAL) algorithm that incorporates a dual-layer learning architecture for dynamically generating caching strategies and maximizes the long-term reward. Experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art methods across various performance metrics in a real-world multi mobile-user content caching case.

Mobile edge computing (MEC) is an evolving paradigm for rendering services through network-accessible resources deployed over Internet of Things (IoT) nodes at the edge. Nevertheless, an MEC environment usually employs thousands of physical machines connected via hundreds of switches/routers that communicate and coordinate to deliver computing service. In such complicated systems, faults caused by software, human errors, and hardware are often unavoidable. The edge of network presents a dynamic environment with great quantities of terminals, high mobility of mobile devices, heterogeneous applications, and intermittent traffic. In such an environment, MEC can suffer from unbalanced resource provisioning and interruptions of faults occurring at different levels, which further causes task faults and affects service quality. To address this challenge, this work proposes a novel fault-tolerant offloading method for handling faults by leveraging a reinforcement-learning-based service offloading decision model. The model synthesizes a Dueling Deep Q Network (DQN)-based algorithm for deciding user offloading behaviors and an adaptive checkpointing method for improving task execution reliability. For the purpose of model validation and comparison, extensive simulations are conducted. Numerical results clearly demonstrate that the proposed method is highly effective and outperforms existing methods.

Detecting urban anomalies helps city managers solve traffic problems in a timely manner, prevent safety hazards, and make more scientific and rational urban development plans. However, most existing urban anomaly detection methods focus on single time slots and overlook the impact of anomalous events on traffic flow patterns. To this end, we propose a novel urban traffic flow pattern anomaly detection method in this paper, referred to as UTFP-AD. Our approach constructs traffic flow over a period of time as a temporal probability distribution and uses traffic flow dynamics to detect anomalous patterns. Specifically, we construct temporal probability distributions to represent regional traffic flow patterns and calculate the traffic flow dynamics to reflect traffic flow changes. Independent and correlated feature vectors are then input into the proposed Multi-One-Class Support Vector Machine to identify the final anomalous regions. For validation, we conducted experiments using both synthetic and real-world data, comparing our method with six existing methods. The experimental results demonstrate that UTFP-AD significantly outperforms the existing methods in terms of Recall, F1Score and hit rate.

The prerequisite for implementing incentive mechanisms and reliable participant selection schemes in federated learning is to obtain the contribution of each participant. Available evaluation methods for participant contributions require the server to possess a test dataset, often impractical. Additionally, the excessively high complexity of these works is unacceptable when training complex models in large-scale federated learning system. To address these issues, we propose a lightweight contribution evaluation method for federated learning participants, named LCEFL, based on model projection theory, which does not require the server to provide a test dataset. In addition, a model compression method is designed to be used in LCEFL to reduce the computational complexity. Furthermore, a trusted aggregation method based on LCEFL is proposed, where the weight of each participant's local model is determined by its trust level, which can be calculated using its contribution evaluation result. Experimental results show that LCEFL can achieve nearly the same accuracy as schemes based on Shapley Value, while significantly reducing computational overhead by more than 50%. Compared to available aggregation methods, the proposed trusted aggregation scheme is able to accelerate the convergence speed of the global model and improve its accuracy by 2% to 45%.

As a novel promising computational paradigm, wireless powered mobile edge computing (WPMEC) has been proposed to offer real-time energy and computing services for Internet of Things (IoT) devices. However, time-varying limited resources such as communication quality and residual energy pose great challenges in devising suitable real-time task offloading and resource allocation strategies to meet users' requirements for low latency and energy consumption. Existing studies either employ raw data offloading methods with significant communication overhead, or utilize ordinary data compression methods that result in poor compression effects. To cope with the challenges, this paper considers introducing the state-of-the-art lossless data compression technology into WPMEC and study the online joint optimization problem of task offloading decision, charging time allocation, and compression proportion allocation with the goal of optimizing task completion time. To tackle this problem, we propose an Intelligent Compression Offloading and adaptive resource Allocation algorithm called ICOA. We first put forward a well-devised framework based on deep reinforcement learning to generate a offloading decision vector set in real-time. Then we standardize the resource allocation problem as a linear programming problem and solve it using the simplex method. The experimental results on a real dataset show that, compared with the benchmark algorithms, the proposed algorithm can effectively reduce the task accomplishing time and energy consumption, and achieve the best approximate ratio. Moreover, ICOA requires low runtime, and can satisfy the real-time and effectiveness requirements very well.

Incentive plays an important role in mobile crowdsensing (MCS), as it impels mobile users to participate in sensing tasks and provide high-quality sensing data. However, considering the privacy (including identity privacy, sensing data privacy, and reputation value privacy) and practicality (including reliability, quality awareness, and efficiency) issues in practice, it is a challenge to design such an effective incentive scheme for MCS applications. Existing studies either fail to provide adequate privacy-preserving capabilities or have low practicality. To address these issues, we propose a scheme called BRRV in MCS which relies on two rounds of range reliability assessment to guarantee the reliability of data while achieving privacy preservation. In addition, we also present a lightweight scheme called LRRV in MCS which relies on a single round of range reliability assessment to guarantee the reliability of data while achieving lightweight and privacy preservation. Moreover, to fairly stimulate participants, constrain participants' malicious behavior, and improve the probability of high-quality data, we design a quality-aware reputation-based reward and penalty strategy to achieve dual incentives (including money incentives and reputation incentives) for participants. Furthermore, comprehensive theoretical analysis and experimental evaluation demonstrate that our proposed schemes are significantly superior to the existing schemes in several aspects.

Platoon refers to a group of vehicles traveling in a train-like strategy with a lean inter-vehicle gap, which can increase road capacity and reduce energy consumption. A platoon is composed of several member vehicles and one leader vehicle which determines the driving pattern of the platoon. Therefore, it is crucial to select a vehicle with the highest reputation value as the leader vehicle in a platoon. Reputation value is a private parameter of each vehicle, and how to preserve its privacy is also an issue worth paying attention to. Therefore, in this paper, a reputation-based and privacy-preserving platoon management (RPPM) scheme in vehicular networks is proposed. Specifically, we design a secure comparison protocol (SCP) to select a leader vehicle for each platoon. The SCP protocol not only reduces the involvement of trust authority but also preserves the privacy of vehicles’ reputation values. Furthermore, the cloud server aggregates reputation ciphertexts and feedback scores of the member vehicles based on the homomorphism characteristic of Paillier ciphertexts, and the reputation value privacy of member vehicles is preserved without affecting the aggregation results. The theoretical analysis indicates that the RPPM scheme is privacy-preserving and secure enough to resist several common attacks in vehicular networks. Simulations are conducted to demonstrate the performance of the RPPM scheme, and the results show that the RPPM scheme significantly outperforms the existing schemes in computation and communication overheads.

Mobile edge computing (MEC) is a forward-looking technology that provides services through resources to meet the needs of cloud-edge Internet of Things (IoT) devices. It provides computing and storage data facilities for IoT users and further renders services through resources in vicinity to fulfill the needs from IoT devices at the cloud edge. However, a major difficulty in guaranteeing reliable resource provisioning is mobility, which brings in chances of service migrations among difference distributed edge nodes and thus causes potential risks of service failures or disruptions. Existing solutions in this direction can be ineffective since they tend to consider that stability of inter-edge-node data transmission to be irrelevant to user mobility and are thus in lack of a comprehensive model for estimating effectiveness of migration paths selected. In this article, instead, we consider that the effectiveness of migrations paths to be selected are highly dependent on user mobility as well as inter-edge-node stability propose a novel predictive and mobile track-aware approach to fault-tolerant service migration path selection in MEC (PTSM). It is capable of exploiting uses trajectories for accurate predictions of future tracks and selecting target servers as well as migration paths with guaranteed migration reliability and performance in terms of multiple metrics. We demonstrate with extensive simulations and numerical results that our proposed method outperforms its peers in terms of migration reliability and performance.

Mobile edge computing (MEC) is a prospective technology to render services through resources to fulfill the requirements of IoT (Internet of Things) devices at the cloud edge. The highly dynamic and heterogeneous characteristics of IoT devices bring both opportunities and challenges, i.e., a higher-than-usual occurrence rate of failures. Such failures occur at all architectural levels of the IoT applications: IoT sensor and actuator nodes can be missed, network links between IoT nodes can be down, and processing and storage IoT components can fail. In this work, for optimizing service offloading efficiency, energy consumption, and system reliability, a semi-online fault-tolerant offloading method (UDQF) was proposed for countering MEC failures by adopting a semi-online-learning-based service offloading strategy. The proposed strategy leverages a Dueling Deep Q network-based algorithm to determine user offloading behavior and utilizes an adaptive checkpointing mechanism (periodically storing the system state and restarting the system at the last checkpointing) to improve the task reliability. To valid and compare the model, the simulated results indicate that the proposed method outperforms other counterparts in multiple metrics.

With the proliferation of novel Internet of Things (IoT) mobile applications and advanced communication technologies, nowadays we are surrounded by ubiquitous sensors and smart devices. These smart IoT devices generate a large volume of data day and night at the edge of the network, create a huge demand for edge computing resources, and thus, promote the emergence of the multiaccess edge computing (MEC) paradigm. In MEC environments, IoT devices or mobile users are allowed to offload their computational tasks to nearby edge servers to overcome the limitation of local computing resources. Though edge servers could provide low-latency service with high-responsible computing capabilities, they are still facing many challenges posed by the limited hardware resources and diverse offloading requests. However, traditional approaches are usually based on the centralized architecture and batch-processing scheduling mode, which might lead to low efficiency and high communication overhead. Besides, they also lack the consideration of task diversity and priorities, which are crucial in real-world application scenarios. Thus, smart task scheduling and resource provision strategies with a high real-time property are urgently needed for better user experience and higher resource utilization. In this article, we target the online edge IoT task scheduling and resource allocation problem and propose a decentralized approach (DoSRA). The experiments based on real-world edge environments have demonstrated that the proposed approach could achieve at most a 35.34% reduction on the average weighted offloading response time.

For achieving the goal of two-way communication and power flows, smart grids are integrated with much state-of-the-art hardware and software. However, these newly added components also introduce a lot of vulnerabilities into the power systems, which results in that malicious users can launch various cyber–physical attacks to steal electricity. The existing electricity theft detection techniques suffer from an implicit assumption that malicious users tamper with smart meter readings to values much less than their actual electricity consumptions. These are called large-amount electricity theft (LET) attacks. Nevertheless, in the real world, some malicious users may be cautious enough to deliberately launch small-amount electricity theft (SET) attacks, where smart meter readings are manipulated to numbers slightly lower than the actual values, mainly to escape detection. To address this limitation, we propose a detector that is able to deal with both LET and SET attacks effectively. This detector applies a cumulative sum (CUSUM) control chart and a Shewhart control chart together to analyze users’ reported readings and measurements of a central observer meter. It consists of an electricity theft detection phase, which aims to detect the existence of LET/SET attacks timely and a malicious user identification phase, which aims to identify malicious users exactly. Extensive experiments are conducted to evaluate the proposed detector, and the results show that it has good performance in terms of several metrics.

Chinese dialects discrimination is a challenging natural language processing task due to scarce annotation resource. In this article, we develop a novel Chinese dialects discrimination framework with transfer learning and data augmentation (CDDTLDA) in order to overcome the shortage of resources. To be more specific, we first use a relatively larger Chinese dialects corpus to train a source-side automatic speech recognition (ASR) model. Then, we adopt a simple but effective data augmentation method (i.e., speed, pitch, and noise disturbance) to augment the target-side low-resource Chinese dialects, and fine-tune another target ASR model based on the previous source-side ASR model. Meanwhile, the potential common semantic features between source-side and target-side ASR models can be captured by using self-attention mechanism. Finally, we extract the hidden semantic representation in the target ASR model to conduct Chinese dialects discrimination. Our extensive experimental results demonstrate that our model significantly outperforms state-of-the-art methods on two benchmark Chinese dialects corpora.

A mobile edge computing (MEC) paradgim is evolving as an increasingly popular means for developing and deploying smart-city-oriented applications. MEC servers can receive a great deal of requests from devices of mobile users, especially in crowded scenes, e.g., a city’s central business district and school areas. It thus remains a great challenge for appropriate scheduling and managing strategies to avoid hotspots, guarantee load-fairness among MEC servers, and maintain high resource utilization at the same time. To address this challenge, we propose a coalitional-game-based and location-aware approach to MEC service migration for mobile user reallocation in crowded scenes. Our proposed method includes: 1) dividing MEC servers into multiple coalitions according to their inter-Euclidean distance by using a modified$k$-means clustering method; 2) discovering hotspots in every coalition area and scheduling services based on their corresponding cooperations; and 3) migrating services to appropriate edge servers to achieve high utilization and load-fairness among coalition members. Experimental results based on a real-world mobile trajectory dataset for crowded scenes, and an urban-edge-server-position dataset demonstrate that our method outperforms existing ones in terms of load fairness, number of migrations, and utilization rate of edge servers.

Abstract The integration of conventional clothes with flexible electronics is a promising solution as a future‐generation computing platform. However, the problem of user authentication on this novel platform is still underexplored. This work uses flexible sensors to track human posture and achieves the goal of user authentication. We capture human movement pattern by four stretch sensors around the shoulder and one on the elbow. We introduce the long short‐term memory fully convolutional network (LSTM‐FCN), which directly takes noisy and sparse sensor data as input and verifies its consistency with the user's predefined movement patterns. The method can identify a user by matching movement patterns even if there are large intrapersonal variations. The authentication accuracy of LSTM‐FCN reaches 98.0%, which is 10.7% and 6.5% higher than that of dynamic time warping and dynamic time warping dependent.

Capturing 3D foot models is important for applications such as manufacturing customized shoes and creating clubfoot orthotics. In this paper, we propose a novel prototype, Sensock, to offer a fully wearable solution for the task of 3D foot reconstruction. The prototype consists of four soft stretchable sensors, made from silk fibroin yarn. We identify four characteristic foot girths based on the existing knowledge of foot anatomy, and measure their lengths with the resistance value of the stretchable sensors. A learning-based model is trained offline and maps the foot girths to the corresponding 3D foot shapes. We compare our method with existing solutions using red-green-blue (RGB) or RGBD (RGB-depth) cameras, and show the advantages of our method in terms of both efficiency and accuracy. In the user experiment, we find that the relative error of Sensock is lower than 0.55%. It performs consistently across different trials and is considered comfortable and suitable for long-term wearing.

The self-parking system is an important component of self-driving vehicles. Such a system needs to detect and locate the parking-slots from surround-view images, and then guide the vehicle to the designated parking-slot. In the real world, the appearances and environmental conditions of parking-slots can be rich and varied. Thus, to train the parking-slot detection model, it is necessary to collect and label a huge quantity of surround-view images covering as many real cases as possible. Such a process is cumbersome and costly, and will be repeated whenever encountering an unseen parking condition that is quite different from the ones covered by existing training set. To this end, in this paper we propose an extensible pipeline, namely FakePS, to assist parking-slot detection model training by making use of synthetic data. Specifically, with FakePS, we can first build various simulated parking scenes and collect labeled surround-view images automatically. Besides, we resort to pixel-level domain adaptation strategies to enhance the realism of the synthetic images using unlabeled real images while preserving their label information. The efficacy of FakePS has been corroborated by experimental results.

A typical surround-view system consists of four fisheye cameras. By performing an offline calibration that determines both the intrinsics and extrinsics of the system, surround-view images can be synthesized at runtime. However, poses of calibrated cameras sometimes may change. In such a case, if cameras' extrinsics are not updated accordingly, observable geometric misalignment will appear in surround-views. Most existing solutions to this problem resort to re-calibration, which is quite cumbersome. Thus, how to correct cameras' extrinsics in an online manner without using re-calibration is still an open issue. In this paper, we attempt to propose a novel solution to this problem and the proposed solution is referred to as “Online Extrinsics Correction for the Surround-view system OECS for short. We first design a Bi-Camera error model, measuring the photometric discrepancy between two corresponding pixels on images captured by two adjacent cameras. Then, by minimizing the system's overall BiCamera error, cameras' extrinsics can be optimized and the optimization is conducted within a sparse direct framework. The efficacy and efficiency of OECS are validated by experiments. Data and source code used in this work are publicly available at https://z619850002.github.io/OECage/.

Underexposed images often suffer from serious quality degradation such as poor visibility and latent noise in the dark. Most previous methods for underexposed images restoration ignore the noise and amplify it during stretching contrast. We predict the noise explicitly to achieve the goal of denoising while restoring the underexposed image. Specifically, a novel three-branch convolution neural network, namely RRDNet (short for Robust Retinex Decomposition Network), is proposed to decompose the input image into three components, illumination, reflectance and noise. As an image-specific network, RRDNet doesn't need any prior image examples or prior training. Instead, the weights of RRDNet will be updated by a zero-shot scheme of iteratively minimizing a specially designed loss function. Such a loss function is devised to evaluate the current decomposition of the test image and guide noise estimation. Experiments demonstrate that RRDNet can achieve robust correction with overall naturalness and pleasing visual quality. To make the results reproducible, the source code has been made publicly available at https://aaaaangel.github.io/RRDNet-Homepage.

Edge computing is a promising paradigm that can boost the performance of novel mobile applications and energize the real-time governance of Internet-of-Things (IoT) big data. In edge computing, mobile application vendors are allowed to employ edge resources to speed up end-users' applications in an elastic and on-demand manner. However, due to the complex geographical distribution of edge servers and users, how to decide the most appropriate destination edge server to hire and how to decide the corresponding user-server allocation plan with as-low-as-possible monetary cost are the key problems for application vendors. Instead of assuming a simultaneous-batch-arrival pattern of incoming users and considering static optimization of the Edge User Allocation (EUA) problem by most existing studies, in this paper, we consider an online EUA problem where users' arrival and departure follow a general pattern. We take the long-term edge user allocation rate and edge server leasing cost as scheduling targets and propose a decentralized collaborative and fuzzy-control-based approach to yielding real-time user-edge-server allocation schedules. In this approach, edge users are allowed to independently make their own allocation decision only based on local information (i.e., the status of nearby edge servers). Experiments on real-world edge datasets demonstrate our approach outperforms state-of-the-art approaches in terms of long-term allocation rate and system cost.

Recently, mobile edge computing (MEC) is widely believed to be a promising and powerful paradigm for bringing enterprise applications closer to data sources such as IoT devices or local edge servers. It is capable of energizing novel mobile applications, especially the ultra-latency-sensitive ones, by providing powerful local computing capabilities and lower end-to-end delays. Nevertheless, various challenges, especially the reliability-guaranteed scheduling of multitask business processes in terms of, e.g., workflows, upon distributed edge resources and servers, are yet to be carefully addressed. In this paper, we propose a novel edge-environment-based multi-workflow scheduling method, which incorporates a reliability estimation model for edge-workflows and a coevolutionary algorithm for yielding scheduling decisions. The proposed approach aims at maximizing the reliability, in terms of success rates, of services deployed upon edge infrastructures while minimizing service invocation cost for users. We conduct simulative experimental case studies based on multiple well-known scientific workflow templates and a well-known dataset of edge resource locations as well. Simulative results clearly suggest that our proposed approach outperforms traditional ones in terms of workflow success rate and monetary cost.

As a relatively new paradigm of evolutionary algorithms, artificial bee colony (ABC) algorithm has shown attractive performance in solving optimization problems. However, for some complex optimization problems, its performance is still not satisfactory. To address this concerning issue, in this paper, we designed an improved ABC variant, called DLABC, based on the division of labor theory. In the DLABC, both of the employed bee phase and the onlooker bee phase are modified by introducing new solution search equations. For the modified employed bee phase, two new control parameters are introduced in the new solution search equation, which aims to control the frequency of perturbation and the magnitude of perturbation, respectively. For the modified onlooker bee phase, a novel depth-first search framework is used which tends to allocate more computing resources to elite solutions for accelerating convergence rate. By combing these two modified phases, we attempt to balance the exploration and exploitation capabilities of ABC. Numerical experiments are conducted on the CEC 2019 100-digit challenge benchmark suite, and the DLABC is compared with the basic ABC and a recently well-established ABC variant (DFSABC_elite). The total scores of these included algorithms have shown that our proposed DLABC algorithm performed best.