Mobile Edge Computing (MEC), envisioned as a cloud extension, pushes resource from the network core to edge, thereby meeting stringent service requirements of many emerging computation-intensive mobile applications. Many existing works have focused on studying system-wide MEC placement issues, personalized performance optimization yet receives much less attention. Thus, in this paper we propose novel adaptive user-managed mechanism, which jointly optimizes user's perceived-latency and...

The freshness of status information is great importance for time-critical Internet-of-Things (IoT) applications. A metric measuring the Age Information (AoI), which captures time elapsed from being generated at source node (e.g., a sensor) to latest update. However, in intelligent IoT applications such as video surveillance, revealed after some computation-intensive and time-consuming data processing operations, would affect freshness. In this article, we propose novel metric, Processing...

Mobile-edge computing (MEC) is widely envisioned as a promising technique for provisioning artificial intelligence (AI) capability resource-limited Internet of Things (IoT) devices by leveraging edge servers (ESs) executing deep neural network (DNN) inference tasks in proximity. However, scheduling DNN at the under unknown system dynamics (e.g., uncertain availability ESs) may suffer from failures, making it difficult to guarantee reliable services IoT device. To overcome this challenge, we...

Computation offloading is envisioned as a promising technique for prolonging the battery lives and enhancing computation capability of mobile devices. In this paper, we study task resource purchasing problems in an edge-cloud collaborative system. The purpose system to minimize cost while ensuring that tasks can be served before their maximum acceptable delays. Due uncertainty both arrival rates prices computing resources, it impossible make optimal decision online long-running time....

Low Earth orbit (LEO) satellites enable complex observation tasks ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.,</i> remote sensing and cooperative monitoring) by leveraging large-scale satellite-generated imageries state-of-the-art machine learning (ML) techniques. However, due to restricted downlink bandwidth spotty connectivity, it is infeasible for the transmit all ground stations ML model training. To address this issue, we use...

Two-tiered wireless sensor networks offer good scalability, efficient power usage, and space saving. However, storage nodes are more attractive to attackers than sensors because they store collected data processing sink issued queries. A compromised node not only reveals data, but also may reply incomplete or wrong query results. In this paper, we propose QuerySec, a protocol that enables process queries correctly while prevents them from revealing both the sink. To protect privacy, an order...

Abstract Predicting time series has significant practical applications over different disciplines. Here, we propose an Anticipated Learning Machine (ALM) to achieve precise future-state predictions based on short-term but high-dimensional data. From non-linear dynamical systems theory, show that ALM can transform recent correlation/spatial information of variables into future dynamical/temporal any target variable, thereby overcoming the small-sample problem and achieving multistep-ahead...

As mobile edge computing (MEC) hosting applications at the network with limited capacities, service providers are facing new challenge of how to make full use scarce resources maximize system performance. Accommodating this requires careful application placement and request routing coordinate diverse MEC nodes. However, frequent re-placement would greatly increase reconfiguration cost, indicating a performance-cost trade-off. In response, in paper, we study problem joint optimization on...

For many Internet of Things (IoT) applications, the freshness status information is great importance, and age (AoI) a newly proposed metric to quantify system status. However, in cases, original raw data collected by IoT devices needs be preprocessed real-time extract hidden effective information, which usually computationally intensive time consuming. To this end, we promote an edge computing assisted approach aim reduce AoI flexibly offloading server for preprocessing. We consider that can...

With astonishing speed, bandwidth, and scale, mobile-edge computing (MEC) has played an increasingly important role in the next generation of connectivity service delivery. Yet, along with massive deployment MEC servers, ensuing energy issue is now on urgent agenda. In current context, large-scale renewable-energy-supplied servers perhaps most promising solution for incoming issue. Nonetheless, as a result intermittent nature their power sources, these special design must be more cautious...

We propose an optimal consensus design method for solving a finite-time control problem involving second-order multi-agent system. With this method, the can be modeled as parameter selection with continuous state inequality constraints and free terminal time. By virtue of constraint transcription time scaling transform gradient-based optimization algorithm is developed to solve problem. Furthermore, new protocol designed, by which value system velocity chosen arbitrary value. For...

At present, most of the smart systems are based on cloud computing, and massive data generated at end device will need to be transferred where AI models deployed. Therefore, a big challenge for system engineers is that often face issues such as network congestion high latency. In recent years, mobile edge computing (MEC) becoming promising solution which supports computation-intensive tasks deep learning through computation offloading servers located local edge. To take full advantage MEC,...

In this paper, passivity is used to investigate the formation control problem for second-order multi-agent systems (MASs) with linear or nonlinear coupling. Firstly, of a single agent studied by selecting appropriate adaptive state feedback controllers. Moreover, in order ensure that MASs intrinsic dynamics and linear/nonlinear coupling can converge predefined formation, some schemes are designed based on agent. addition, passivity-based double-integrator also studied. Finally, effectiveness...

Abstract Nowadays, the development of human society and daily life are inseparable from power supply. Therefore, people also put forward higher requirements for reliability distribution network, but companies can only passively deal with network failures, which is a bottleneck improvement reliability. The Internet Things (IoT) best solution online equipment status monitoring basic data sharing large, widely distributed, relatively fixed, large numbers equipment. construction IoT faces many...

For the business washing machine industry, most are currently using traditional manual service (the way cost is high, inefficient, low degree of intelligence) status quo. The wireless intelligent laundry system based on ESP8266 communication module developed, which has Wechat payment function and realizes automatic control machine. Firstly, terminal will send a request to center when customer ready wash. Secondly, after receiving request, WeChat Public Accounts, idle number charges, as well...

Multi-user applications generally lag behind in features or compatibility with single-user applications. As a result, users are often not motivated to abandon their favorite for groupware that less frequently used. A well-accepted approach, collaboration transparency, is able convert off-the-shelf into without modifying the source code. However, existing systems have been largely striving develop generic application-sharing mechanisms and undesirably force share same application cooperative...

The freshness of status information is great importance for time-critical Internet Things (IoT) applications. A metric measuring the age-of-information (AoI), which captures time elapsed from being generated at source node (e.g., a sensor) to latest update.However, in intelligent IoT applications such as video surveillance, revealed after some computation intensive and time-consuming data processing operations, would affect freshness. In this paper, we propose novel metric, age-of-processing...

Cartesian product networks are always regarded as a tool for ``combining'' two given with established properties to obtain new one that inherits from both. Generalized $k$-connectivity $\lambda_k(F)$ of graph $F$ is parameter constructing the maximum number edge-disjoint Steiner trees (abbreviated EDSTs) in $F$. In this paper, we give sharp upper and lower bounds $\lambda_k(G\Box H)$, where $\Box$ operation, $G,H$ graphs.