Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development agility, and scalability. However, the resulting complex and dynamic service topologies introduce intricate inter-service dependencies, which often lead to backpressure effects and queuing delays. These phenomena significantly challenge traditional monolithic and rule-based resource management approaches, which struggle to capture the non-linear performance characteristics and long-term effects of resource allocation decisions in such environments. To address these challenges, we propose DDRM, a two-stage predictor-decider collaborative framework for dynamic resource management in microservice systems. DDRM integrates deep learning to model inter-service interactions and predict the probability of Service Level Objective (SLO) violations, and employs reinforcement learning to optimize resource allocation decisions by maximizing long-term cumulative rewards while meeting SLO targets. Extensive evaluations demonstrate that DDRM outperforms state-of-the-art baselines by up to 29.8 %, while exhibiting strong stability and adaptability under highly varying workloads.

Live migration is essential for service continuity of latency-sensitive applications in resource-constrained edge environments. However, current migration approaches for noncontainerized applications suffer from inefficiency, and existing HTTP-based state reporting methods incur substantial overhead while lacking replica pre-initialization capability, resulting in prolonged downtime. To address these limitations, we implement a prototype system that enables near-zero-downtime live migration of object-detection applications. By introducing lightweight, minimally intrusive state management interfaces, our system supports automated application pre-deployment and seamless state transfer. Experimental evaluations on a constrained 50 Mbps edge network demonstrate that object-detection applications experience an average downtime of 132.8 ms, while our solution maintains low resource consumption.

Current multicast protocols assume prior knowledge of destination locations, leading to excessive message transmissions, especially in sensor networks with mobile sinks. Quorum-based systems, known for efficient information dissemination, have not been explored in the context of multicast. To address this gap, we propose ORM (Orthogonal Rendezvous Multicast), a quorum-based multicast protocol that solves location dissemination and data multicasting as a whole. The protocol utilizes a simple geometric principle to disseminate the information from sinks and sources. By exploiting the footprint of disseminated information, ORM transforms the underlying infrastructure to reveal the hidden multicasting structure. Furthermore, two efficient algorithms are proposed to fetch the optimal efficient multicasting paths based on the built infrastructure. ORM was implemented in the NS-2 simulator. Our detailed simulations demonstrate that ORM achieves significantly enhanced scalability in terms of message overhead and low cost without the burden of complex state maintenance.

Human activity recognition using inertial sensors has gained significant popularity and widespread adoption in various fields, while deep learning has emerged as the dominant approach, playing a pivotal role in enhancing performance. Nevertheless, existing algorithms often neglect the heterogeneity of sensors and fail to effectively extract contextual features from long-term time series data, resulting in low accuracy in activity recognition, especially for complex activities. This paper proposes a novel method called FUsion Transformer hUman activity REcognition(FUTURE). FUTURE exploits the feature fusion mechanism and designs a multi-scaled DenseNet to extract the spatial features so that the relationship between heterogeneous sensors can be captured. Furthermore, a customized multi-head attention model with less computational complexity is employed in FUTURE to capture global dependencies within the sensor data. Experimental results on multiple datasets validate that FUTURE achieves an average recognition accuracy of 95% for complex activities and the evaluation against the state-of-the-art demonstrates the superior performance of the FUTURE model in accurately classifying complex activities.

Energy hole is inherently problematic for sensor networks because of their many-to-one architectures, and a feasible solution has not yet been discovered. This paper aims to provide a possible solution for future underwater sensor networks with the ability of depth control only depending on the buoyancy of water currents. We propose a Depth Rotation-based traffIc oFfloading sTrategy (DRIFT) to balance the traffic load over the entire network. DRIFT joint considers the network deployment and energy allocation to obtain a maximized network lifetime. We provide an approach to calculate the precise rotating scheduling cycle and energy allocation based the proposed network model. Extensive simulation shows that when a network lifetime ends, less than 0.5% of the initial energy is wasted, and the network lifetime is prolonged on average by more than a 5-fold factor.

Underwater sensor network has broad application prospects for performing underwater warning, target detection, and marine environment monitoring. However, traditional cubefilled full-coverage node deployment schemes are costly and infeasible to detect target objects due to the considerably redundant nodes. In this paper, we propose a new scheme with a low cost to detect the target in dynamic waters to reduce the cost of the deployment. Our scheme controls the distributed sensors to move and construct an angular sensor barrier through which the target may pass. The profile-based barrier deployment scheme only needs to adjust node depth to reduce movement costs. During depth adjustment, the proposed method takes the node density, the residual energy of the node and the node movement effect into account so that the randomly distributed nodes are sunk at different depths, and the redundant nodes are removed by the 2-Voronoi diagram lemma. We use the simulation experiment to evaluate the coverage and energy consumption during the movement of the nodes. The analysis of the experimental results shows that the method has good coverage performance. Also, it can reduce and balance energy consumption during the anchor node deployment to extend network uptime.

Protein methylation, an important post-translational modification, plays crucial roles in many cellular processes. The accurate prediction of protein methylation sites is fundamentally important for revealing the molecular mechanisms undergoing methylation. In recent years, computational prediction based on machine learning algorithms has emerged as a powerful and robust approach for identifying methylation sites, and much progress has been made in predictive performance improvement. However, the predictive performance of existing methods is not satisfactory in terms of overall accuracy. Motivated by this, we propose a novel random-forest-based predictor called MePred-RF, integrating several discriminative sequence-based feature descriptors and improving feature representation capability using a powerful feature selection technique. Importantly, unlike other methods based on multiple, complex information inputs, our proposed MePred-RF is based on sequence information alone. Comparative studies on benchmark datasets via vigorous jackknife tests indicate that our proposed MePred-RF method remarkably outperforms other state-of-the-art predictors, leading by a 4.5 percent average in terms of overall accuracy. A user-friendly webserver that implements the proposed method has been established for researchers' convenience, and is now freely available for public use through http://server.malab.cn/MePred-RF. We anticipate our research tool to be useful for the large-scale prediction and analysis of protein methylation sites.

With the urgent demands of multi-parameter testing under the extreme environment,such as the deep water, upper air and deep underground etc., the fiber mechanical and thermal multi-parameter instrument is developed with its redominant advantages of accuracy, reliability, sensitivity and convenience. Most existing system usually defined a fixed threshold for the accident warning, which delayed reactions to the emergency. Thus, selecting an appropriate and adjustable threshold for anomaly detection is very necessary. In order to tackle this problem, a modified time series prediction model M-ARIMA is proposed in this paper. M-ARIMA can detect the emergency and achieve high real-time alarm rate. M-ARIMA is based on the dynamic variance and reduces the error rate of early warning caused by the normal fluctuations. Experimental results show that M-ARIMA can detect abnormities with a median accuracy of more than 92% and a median error of less than 10%.

Recent large-scale deployments of wireless sensor networks have posed a high demand on network throughput, forcing all (discrete) orthogonal ZigBee channels to be exploited to enhance transmission parallelism. However, the interference from widely deployed WiFi networks has severely jeopardized the usability of these discrete ZigBee channels, while the existing CSMA-based ZigBee MAC is too conservative to utilize each channel temporally. In this paper, we propose ART (Adaptive fRequency-Temporal co-existing) as a framework consisting of two components: FAVOR (FrequencyAllocation for Versatile Occupancy of spectRum) and P-CSMA (Probabilistic CSMA), to improve the co-existence between ZigBee and WiFi in both frequency and temporal perspectives. On one hand, FAVOR allocates continuous (center) frequencies to nodes/links in a near-optimal manner, by innovatively converting the problem into a spatial tessellation problem in a unified frequency-spatial space. This allows ART to fully exploit the “frequency white space” left out by WiFi. On the other hand, ART employs P-CSMA to opportunistically tune the use of CSMA for leveraging the “temporal white space” of WiFi interference, according to real-time assessment of transmission quality. We implement ART in MicaZ platforms, and our extensive experiments strongly demonstrate the efficacy of ART in enhancing both throughput and transmission quality.

In this paper, we focus on the problem of clustering faces in videos. Different from traditional clustering on a collection of facial images, a video provides some inherent benefits: faces from a face track must belong to the same person and faces from a video frame can not be the same person. These benefits can be used to enhance the clustering performance. More precisely, we convert the above benefits into must-link and cannot-link constraints. These constraints are further effectively incorporated into our novel algorithm, Video Face Clustering via Constrained Sparse Representation (CS-VFC). The CS-VFC utilizes the constraints in two stages, including sparse representation and spectral clustering. Experiments on real-world videos show the improvements of our algorithm over the state-of-the-art methods.

While the increasing scales of the recent WSN deployments keep pushing a higher demand on the network throughput, the 16 orthogonal channels of the ZigBee radios are intensively explored to improve the parallelism of the transmissions. However, the interferences generated by other ISM band wireless devices (e.g., WiFi) have severely limited the usable channels for WSNs. Such a situation raises a need for a spectrum utilizing method more efficient than the conventional multi-channel access. To this end, we propose to shift the paradigm from discrete channel allocation to continuous frequency allocation in this paper. Motivated by our experiments showing the flexible and efficient use of spectrum through continuously tuning channel center frequencies with respect to link distances, we present FAVOR (Frequency Allocation for Versatile Occupancy of spectRum) to allocate proper center frequencies in a continuous spectrum (hence potentially overlapped channels, rather than discrete orthogonal channels) to nodes or links. To find an optimal frequency allocation, FAVOR creatively combines location and frequency into one space and thus transforms the frequency allocation problem into a spatial tessellation problem. This allows FAVOR to innovatively extend a spatial tessellation technique for the purpose of frequency allocation. We implement FAVOR in MicaZ platforms, and our extensive experiments with different network settings strongly demonstrate the superiority of FAVOR over existing approaches.

Inspired by the recent invention of a high efficiency Wireless Power Transfer (WPT) technique, we propose in this paper the Perpetual Wireless Networks (PWNs) as a novel wireless networking paradigm. Similar to the conventional wireless (data) access point, a PWN has a power access point, from which electrical power is injected and distributed into the network in a form of multi-hop transfer. Consequently, we lay our focus on this new type of multi-hop flow problems concerning not data but power. We formulate and analyze a set of such power flow problems (some are joint with data flow), and we devise algorithms to solve them. The intriguing insights obtained from solving these optimization problems offer instructive guidance for future studies on real PWN constructions.

In this paper, we consider the double-blindness problem in large-scale wireless sensor networks (WSNs) with mobile sinks, where the mobile sink(s) and data do not know the locations of each other a priori. We first propose a random line walk mechanism for message forwarding and based on this forwarding mechanism we further propose an efficient data discovery scheme called Double Cross to address the double-blindness problem. Double Cross exploits a simple geometric property of a planar, i.e., for a couple of pairs of orthogonal lines in a planar, the probability that they intersect within the planar is larger than 99%. However, it does not depend on the geographic location or directional information of a node, which is difficult to obtain in such networks. Instead, each sensor only needs to know the distances between neighbor nodes within its transmission range. Analytical and simulation results show that Double Cross can achieve a high successful discovery rate with low energy consumption.

It is important to protect power supply grid system against various damages for national economics. A high-voltage transmission line monitoring system is an effective way to protect the power supply system. This paper presents an energy-efficient data gathering mechanism for such a system. Our contributions are two-fold: (1) a detailed measurement of the energy consumption for wireless nodes, (2) the collaboration between backbone network nodes and subnets to implement the sleep-wakeup mechanism. To validate the proposed mechanism, we have established an indoor test bed consisting of 8 backbone network nodes. The energy consumption of each node with our mechanism is evaluated and compared to that without sleep. The results show that the energy consumption has decreased by 24% by our scheme.