Ocean temperature prediction is significant in climate change research and marine ecosystem management. However, relevant statistical and physical methods focus on assuming relationships between variables and simulating complex physical processes of ocean temperature changes, facing challenges such as high data dependence and insufficient processing of long-term dependencies. This paper comprehensively reviews the development and latest progress of ocean temperature prediction models based on deep learning. We first provide a formulaic definition for ocean temperature prediction and a brief overview of deep learning models widely used in this field. Using data sources and model structures, we systematically divide ocean temperature prediction models into data-driven deep learning models and physically guided deep learning models; and comprehensively explore the relevant literature involved in each method. In addition, we summarize an ocean temperature dataset and sea areas, laying a solid foundation for ocean temperature prediction. Finally, we propose current challenges and future development directions in ocean temperature prediction research based on deep learning. This article aims to analyze existing research, identify research gaps and challenges, provide complete and reliable technical support for climate forecasting, marine disaster prevention, and fishery resource management, and promote the further development of ocean temperature research.

Despite placing services and computing resources at the edge of the network for ultra-low latency, we still face the challenge of centralized scheduling costs, including delays from additional request forwarding and resource selection. To address this challenge, we propose SmartBuoy, a new computing paradigm. Our approach starts with a service coverage concept that assumes users within the coverage have high access availability. To enable users to perceive service status, we design a distributed metric table that synchronizes service status periodically and distributively. We propose coverage indicator updating principles to make the updating process more effective. We then implement two distributed methods, SmartBuoy-Time and SmartBuoy-Reliability, that enable users to perceive service capability directly and immediately. To determine the metric table update window size, we provide an analysis method based on user access patterns and offer a theoretical upper bound in a dynamic environment, making SmartBuoy easy to use. Finally, we implement the proposed methods distributively on an open-source edge computing simulator. Experiments on a real-world network topology dataset demonstrate the efficiency of SmartBuoy in reducing delays and improving the success rate.

Computation and/or communication-intensive collaborative services accompanied by several distributed tasks/components, such as the services in Internet of Things, can be anywhere nowadays. These services are usually used by users at the Internet edge, making cloud computing struggles with the high end-to-end latency. Thanks to edge computing which pushes resources to the edge, the goals with lower latency can be well satisfied. However, in actual scenarios especially under dynamic edge computing networks, changes exist in resources, including computing, bandwidth, and nodes. Meanwhile, data packets (or flow) among collaborative tasks/components of a service can also not be conserved. These characteristics lead the service reliability hard to be guaranteed and make existing reliability evaluation methods no longer accurate. To study the effect of distributed and collaborative service deployment strategies under such background, we propose a reliability evaluation method (REMR). We first look for the solution set which can meet the time constraints. Then, we calculate the reliability of service supported by the solution set based on the principle of inclusion–exclusion with distributions of available transmission bandwidth and computing resources. Finally, we provide an illustrative example with several real-world data sets to make REMR easy to follow. To make REMR more reliable, we also propose and implement a Monte Carlo simulation method. Experiments prove that the reliability calculated by REMR is nearly the same as the simulation results and both the latencies and the jitters are also at a lower level.

In edge computing scenarios, there is a need for modeling dedicated features and heterogeneous devices functions, as well as integrating multiple complex scenarios with diverse objectives and frequent interactions. However, existing platforms modeling for the whole device ignores the independence between functional components resulting in limited scenario support. We propose an open-source simulator named EasiEI. EasiEI addresses the need for higher-level feature replaceability and independence in modeling complex edge scenarios through independent functional component-level modeling and microkernel architecture. This approach enables users to assemble independent functional components in a plug-and-play manner for heterogeneous devices or different application requirements. EasiEI is fully compatible with all the existing built-in modules in NS3 (a powerful network discrete event simulator). To verify the flexibility and extensibility of EasiEI, we implement several centralized and decentralized computing paradigms cases in a step-by-step way. These cases restore and simulate the performance state of various real devices in real-time, meeting the requirements for verifying the edge computing ideas such as task scheduling in a distributed manner. Results show that the simulations have well reflected the characteristics of the real world and can construct complex environment flexibly.

Trajectory-user linking (TUL) aims to match anonymous trajectories to the most likely users who generated them, offering benefits for a wide range of real-world spatio-temporal applications. However, existing TUL methods are limited by high model complexity and poor learning of the effective representations of trajectories, rendering them ineffective in handling large-scale user trajectory data.In this work, we propose a novel Scalable Trajectory-User Linking with dual-stream representation networks for large-scale TUL problem, named ScaleTUL Specifically, ScaleTUL generates two views using temporal and spatial augmentations to exploit supervised contrastive learning framework to effectively capture the irregularities of trajectories. In each view, a dual-stream trajectory encoder consisting of a long-term encoder and a short-term encoder is designed to learn the unified representations of trajectories that fuses different temporal-spatial dependencies. Then, a TUL layer is used to associate the trajectories with the corresponding users in the representation space using a two-stage training model.Experimental results on check-in mobility datasets from three real-world cities and the nationwide U.S. demonstrate the superiority of ScaleTUL over state-of-the-art baselines for large-scale TUL tasks.

Temporal motifs are recurring subgraph patterns in temporal graphs, and are present in various domains such as social networks, fraud detection, and biological networks. Despite their significance, counting temporal motifs efficiently remains a challenge, particularly on moderately sized datasets with millions of motif instances. To address this challenge, we propose a novel algorithm called Scalable Motif Counting with Time-aware Topology Constraint (MoTTo). MoTTo focuses on accurately counting temporal motifs with up to three nodes and three edges. It first utilizes a topology constraint-based pruning strategy to eliminate nodes that cannot participate in forming temporal motifs before the counting process. Then, it adopts a time-aware topology constraint-based pruning strategy to split large-scale datasets into independent partitions and filter out the unrelated ones, ensuring that the counting results remain unaffected. By investigating the second pruning strategy, we also find that MoTTo can be implemented in a multi-thread manner, further accelerating the counting process significantly. Experimental results on several real-world datasets of varying sizes demonstrate that MoTTo outperforms state-of-the-art methods in terms of efficiency, achieving up to a nine-fold improvement in total temporal motif counting. Specifically, the efficiency of counting triangular temporal motifs is enhanced by up to 31 times compared to state-of-the-art baselines.