With the management of load aggregator (LA), demand-side adjustable resources (DAR) such as electric vehicle (EV) and temperature controlled load can provide tremendous reserve capacity to support the power system. However, DAR users’ decisions are strongly uncertain, which makes it difficult for LA to evaluate reserve capacity accurately. Therefore, a LA-DAR optimal dispatching strategy considering users’ decisions is proposed. First, in view of the spatial mobility characteristics of EV, and influencing factors such as time cost and price incentives, the uncertainty of DAR user's decision under normal and extreme scenarios is characterized. Second, an optimal dispatching model using Stackelberg game is proposed, with LA as the leader and DAR as the follower. To solve the game strategy, we propose an efficient iterative solution method with a transformed decision-making model for participation in LA regulation. It is shown that the proposed optimal strategy significantly improves LA's ability to provide reserve capacity under normal and extreme scenarios, while improving the economy of the LA and DAR users.

Today, convolutional neural networks (CNNs) are widely used in computer vision applications. However, the trends of higher accuracy and higher resolution generate larger networks. The requirements of computation or I/O are the key bottlenecks. In this article, we propose XVDPU: the AI Engine (AIE)-based CNN accelerator on Versal chips to meet heavy computation requirements. To resolve the IO bottleneck, we adopt several techniques to improve data reuse and reduce I/O requirements. An arithmetic logic unit is further proposed that can better balance resource utilization, new feature support, and efficiency of the whole system. We have successfully deployed more than 100 CNN models with our accelerator. Our experimental results show that the 96-AIE-core implementation can achieve 1,653 frames per second (FPS) for ResNet50 on VCK190, which is 9.8× faster than the design on ZCU102 running at 168.5 FPS. The 256-AIE-core implementation can further achieve 4,050 FPS. We propose a tilling strategy to achieve feature-map-stationary for high-definition CNN with the accelerator, achieving 3.8× FPS improvement on the residual channel attention network and 3.1× on super-efficient super-resolution. This accelerator can also solve the 3D convolution task in disparity estimation, achieving end-to-end performance of 10.1 FPS with all the optimizations.

The convolution neural networks (CNNs) are widely used in computer vision applications nowadays. However, the trends of higher accuracy and higher resolution generate larger networks, indicating that computation and I/O bandwidth are key bottlenecks to reach performance. The Xilinx's latest 7nm Versal ACAP platform with AI-Engine (AIE) cores can deliver up-to 8x silicon compute density at 50% the power consumption compared with the traditional FPGA solutions. In this paper, we propose XVDPU: the AIE-based int8-precision CNN accelerator on Versal chips, scaling from 16-AIE-core (C16B1) to 320-AIE-core (C64B5, Peak:109.2 TOPs) to meet computation requirements. To resolve IO bottleneck, we adopt several techniques such as multi-batch (MB), shared-weights (SHRWGT), feature-map-stationary (FMS) and long-load-weights (LLW) to improve data-reuse and reduce I/O requirements. An Arithmetic Logic Unit (ALU) design is further proposed into the accelerator which mainly performs non-convolution layers such as Depthwise-Conv layer, Pooling layer and Non-linear function layers using the same logic resources, which can better balance resource utilization, new feature support and efficiency of the whole system. We have successfully deployed more than 100 CNN models with our accelerator. Our experimental results show that the 96-AIE-core (C32B3, Peak: 32.76 TOPs) implementation can achieve 1653 FPS for ResNet50 on VCK190, which is 9.8x faster than the design on ZCU102 running at 168.5 FPS with peak 3.6 TOPs. The 256-AIE-core (C32B8, Peak: 87.36 TOPs) implementation can further achieve 4050 FPS which better leverages the computing power of Versal AIE devices. The powerful XVDPU will help enable many applications on the embedded system, such as low-latency data center, high level ADAS and complex robotics.

3-Dimensional (3D) convolutional neural networks (CNN) are widely used in the field of disparity estimation. However, 3D CNN is more computationally dense than 2D CNN due to the increase in the disparity dimension. To enable more practical applications in autonomous driving, robotics, and other scenarios on embedded devices, we propose a unified 2D/3D CNN accelerator (A-U3D) design. This design unifies 3D standard / transposed convolution into 2D standard convolution, respectively. Our processing unit can support 2D and 3D convolution in the same mode without additional structures. Based on PSMNet, a 3D-based CNN for disparity estimation, we build a heterogeneous multi-core system integrated with A-U3D in conjunction with CPU, DSP, and AI Engines on the Xilinx Versal ACAP platform. Running the pruned 8-bit model, our A-U3D system achieves 0.289s latency, which is 11.5 × faster than the state-of-the-art solution on the same platform, and reaches an end-to-end (E2E) performance of 10.1 frames per second (FPS). Our proposed system explores the feasibility of deploying 3D CNNs with large workloads on FPGA.

Lipreading is a type of speech recognition based on visual information. It is instructive to design a lipreading model according to the lip movement law. Algorithms in the field of computer vision cannot fully satisfy the characteristics of lipreading, and direct use does not necessarily improve the performance of lipreading. In this paper, we propose that lipreading has fine-grained global synergy by comparing other computer vision tasks and analyzing lip muscle motion patterns. To address this feature, we propose a tailored model and name it Fine-Grained Global Synergy Lipreading (FGSLip). Our model aims to make features synergistic to improve lipreading performance. We introduce global features to represent the overall characteristics of the lip, and local features to learn coarse-grained and fine-grained correlations between features. Then, diffusion and fusion methods are used to make the local features and global features synergistic. Based on the above, several different feature extraction structures are constructed to demonstrate the fine-grained global synergy of lipreading. To verify the effectiveness of the proposed model, extensive experiments are conducted on the laboratory record dataset ICSLR and the public dataset CMLR, and the experimental results show that the proposed method can effectively improve the accuracy of lipreading.

Lipreading is a type of Human–Computer Interaction (HCI) based on visual information. From a linguistic point of view, Chinese is a monosyllabic language with a much higher proportion of homophones than English. Identifying homophones in Chinese Mandarin lipreading is very challenging. Since the lip shape in the context can distinguish homophones, and smaller recognition units can reduce the types of recognition and alleviate data sparsity, we propose to improve the accuracy of lipreading by simultaneously exploiting the correlation of lip features at different distances and smaller modeling units. We implement a long short-term multi-feature space to represent lip features, and CTC–Attention to learn temporal correlations. We also introduce Weight Finite State Transducer (WFST) to enhance the semantic analysis capability of the model. Our model aims to distinguish homophones and improve the accuracy of lipreading. To reduce data sparsity, we use Tonal Initials and Finals (TIF) as the modeling units. We record a sentence-level Chinese lipreading dataset, ICSLR, and label Mandarin characters, syllables, and TIF. We demonstrate the effectiveness of the proposed approach compared to its counterparts through extensive experiments on Grid, ICSLR, and CMLR datasets.

Spectrum sensing (SS) has attracted much attention in the field of Internet of things (IoT) due to its capacity of discovering the available spectrum holes and improving the spectrum efficiency. However, the limited sensing time leads to insufficient sampling data due to the tradeoff between sensing time and communication time. In this paper, deep learning (DL) is applied to SS to achieve a better balance between sensing performance and sensing complexity. More specifically, the two‐dimensional dataset of the received signal is established under the various signal‐to‐noise ratio (SNR) conditions firstly. Then, an improved deep convolutional generative adversarial network (DCGAN) is proposed to expand the training set so as to address the issue of data shortage. Moreover, the LeNet, AlexNet, VGG‐16, and the proposed CNN‐1 network are trained on the expanded dataset. Finally, the false alarm probability and detection probability are obtained under the various SNR scenarios to validate the effectiveness of the proposed schemes. Simulation results state that the sensing accuracy of the proposed scheme is greatly improved.

Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still a challenging problem to search the flexible and accurate architecture that can be shared among multiple tasks. In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL. The main principle of TAAN is to derive flexible activation functions for different tasks from the data with other parameters of the network fully shared. We further propose two functional regularization methods that improve the MTL performance of TAAN. The improved performance of both TAAN and the regularization methods is demonstrated by comprehensive experiments.

Low bit quantization of neural network is required on edge devices to achieve lower power consumption and higher performance. 8bit or binary network either consumes a lot of resources or has accuracy degradation. Thus, a full-process hardware-friendly quantization solution of 4A4W (activations 4bit and weights 4bit) is proposed to achieve better accuracy/resource trade-off. It doesn't contain any additional floating operations and achieve accuracy comparable to full-precision. We also implement a low-precision accelerator for CNN (LPAC) on the Xilinx FPGA, which takes full advantage of its DSP by efficiently mapping convolutional computations. Through on-chip reassign management and resource-saving analysis, high performance can be achieved on small chips. Our 4A4W solution achieves 1.8x higher performance than 8A8W and 2.42x increase in power efficiency under the same resource. On ImageNet classification, the accuracy has a gap less than 1% to full-precision in Top-5. On the human pose estimation, we achieve 261 frames per second on ZU2EG, which is 1.78x speed up compared to 8A8W and the accuracy has only 1.62% gap to full-precision. This proves that our solution has better universality.

Monitoring the performance of a large network is very costly. Instead, a subset of paths or time intervals of the network can be measured while inferring the remaining network data by leveraging their spatiotemporal correlations. The quality of missing data recovery highly relies on the inference algorithms. Tensor completion has attracted some recent attentions with its capability of exploiting the multi-dimensional data structure for more accurate missing data inference. However, current tensor completion algorithms only model the three-order interaction of data features through the inner product, which is insufficient to capture the high-order, nonlinear correlations across different feature dimensions. In this paper, we propose a novel Neural Tensor Completion (NTC) scheme to effectively model three-order interaction among data features with the outer product and build a 3D interaction map. Based on which, we apply 3D convolution to learn features of high-order interaction from the local range to the global range. We demonstrate this will lead to good learning ability. We conduct extensive experiments on two real-world network monitoring datasets, Abilene and WS-DREAM, to demonstrate that NTC can significantly reduce the error in missing data recovery. When the sampling ratio is low at 1%, the recovery error ratios on the testing data are around 0.05 (Abilene) and 0.13 (WS-DREAM) when using NTC, but are 0.99 (Abilene) and 0.99 (WS-DREAM) using the best current tensor completion algorithms, which are 21 times and 8 times larger.

Outfit recommendation requires the answers of some challenging outfit compatibility questions such as 'Which pair of boots and school bag go well with my jeans and sweater?'. It is more complicated than conventional similarity search, and needs to consider not only visual aesthetics but also the intrinsic fine-grained and multi-category nature of fashion items. Some existing approaches solve the problem through sequential models or learning pair-wise distances between items. However, most of them only consider coarse category information in defining fashion compatibility while neglecting the fine-grained category information often desired in practical applications. To better define the fashion compatibility and more flexibly meet different needs, we propose a novel problem of learning compatibility among multiple tuples (each consisting of an item and category pair), and recommending fashion items following the category choices from customers. Our contributions include: 1) Designing a Mixed Category Attention Net (MCAN) which integrates both fine-grained and coarse category information into recommendation and learns the compatibility among fashion tuples. MCAN can explicitly and effectively generate diverse and controllable recommendations based on need. 2) Contributing a new dataset IQON, which follows eastern culture and can be used to test the generalization of recommendation systems. Our extensive experiments on a reference dataset Polyvore and our dataset IQON demonstrate that our method significantly outperforms state-of-the-art recommendation methods.

As a key technology to discover idle spectrum in cognitive radio (CR) networks, classical spectrum sensing schemes mainly focus on the improvement of sensing accuracy and available throughput. However, both sensing performance and sensing complexity are significant elements that influence the performance of a CR in computation‐constrained scenarios. Motivated by this, theproposed study is devoted to computation‐constrained spectrum sensing and a tradeoff is considered between sensing performance and sensing complexity. First, the authors give two functions to evaluate the detection efficiency and communication efficiency of a CR. On this basis, two specific models are provided to obtain the optimal sensing operations in computation‐constrained conditions, respectively. Then they analyse these two models and conclude their advantages and disadvantages. Finally, simulation experiments validate the effectiveness of the proposed schemes. Note that computation‐constrained spectrum sensing works as a significant issue in the internet of things (IoT)‐based applications and the proposed schemes provide effective solutions for it.

Most of existing virtual network embedding (VNE) algorithms only consider how to construct virtual networks more efficiently on a physical infrastructure, without considering the possibility that the constructed virtual networks may be further virtualized to multiple smaller ones. We define the former scenario as single-layer VNE and the later as multi-layer VNE. As the increasing popularity of deploying large datacenter networks and wide area networks with Software Defined Network (SDN) architectures, it becomes a new requirement and possibility to provide multi-layer encapsulated network services for large tenants who have hierarchical organizational structures or need fine-grained service isolation. However, existing VNE algorithm are not specifically designed for the above requirement and not flexible enough to deal with mapping virtual network requirements (VNRs) to a physical network and smaller VNRs to a mapped virtual network. In this paper, we aim to propose a unified and flexible multi-layer VNE algorithm combining with reinforcement learning to solve the embedding of multi-layer VNRs, which can better distinguish the differences between VNRs and physical networks. Simulation results show that our algorithm achieves good performance both in single-layer and multi-layer VNE scenarios.

The attacks, faults, and severe communication/system conditions in Mobile Crowd Sensing (MCS) make false data detection a critical problem. Observing the intrinsic low dimensionality of general monitoring data and the sparsity of false data, false data detection can be performed based on the separation of normal data and anomalies. Although the existing separation algorithm based on Direct Robust Matrix Factorization (DRMF) is proven to be effective, requiring iteratively performing Singular Value Decomposition (SVD) for low-rank matrix approximation would result in a prohibitively high accumulated computation cost when the data matrix is large. In this work, we observe the quick false data location feature from our empirical study of DRMF, based on which we propose an intelligent Light weight Low Rank and False Matrix Separation algorithm (LightLRFMS) that can reuse the previous result of the matrix decomposition to deduce the one for the current iteration step. Depending on the type of data corruption, random or successive/mass, we design two versions of LightLRFMS. From a theoretical perspective, we validate that LightLRFMS only requires one round of SVD computation and thus has very low computation cost. We have done extensive experiments using a PM 2.5 air condition trace and a road traffic trace. Our results demonstrate that LightLRFMS can achieve very good false data detection performance with the same highest detection accuracy as DRMF but with up to 20 times faster speed thanks to its lower computation cost.

Restricted Boltzmann Machine (RBM) is an essential component in many machine learning applications. As a probabilistic graphical model, RBM posits a shallow structure, which makes it less capable of modeling real-world applications. In this paper, to bridge the gap between RBM and artificial neural network, we propose an energy-based probabilistic model that is more flexible on modeling continuous data. By introducing the pair-wise inverse autoregressive flow into RBM, we propose two generalized continuous RBMs which contain deep neural network structure to more flexibly track the practical data distribution while still keeping the inference tractable. In addition, we extend the generalized RBM structures into sequential setting to better model the stochastic process of time series. Performance improvements on probabilistic modeling and representation learning are demonstrated by the experiments on diverse datasets.

Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Neural Networks (NNs) have made a significant breakthrough in many fields, while they also pose a great challenge to hardware platforms since the state-of-the-art neural networks are both communicational- and computational-intensive. Researchers proposed model compression algorithms using sparsification and quantization, along with specific hardware architecture designs, to accelerate various applications. However, the irregularity of memory access caused by the sparsity severely damages the regularity of intensive computation loops. Therefore, the architecture design for sparse neural networks is crucial to better software and hardware co-design for neural network applications. To face these challenges, this paper first analyzes the computation patterns of different NN structures and unify them into the form of sparse matrix-vector multiplication, sparse matrix-matrix multiplication, and element-wise multiplication. On the basis of the EIE which supports only the fully-connected network and recurrent neural network (RNN), we expand it to support the convolution neural network (CNN) using the input vector transform unit. This paper designs a multi-precision multiplier with supporting datapath, which makes the proposed architecture have a better acceleration effect in the low-bit quantization with the same hardware architecture. The proposed accelerator architecture can achieve the equivalent performance and energy efficiency up to 574.2 GOPS, 42.8 GOPS/W for CNN and 110.4 GOPS, 8.24 GOPS/W for RNN under 4-bit quantization on Xilinx XCKU115 FPGA running at 200MHz. And it is the state-of-the-art accelerator supporting CNN-RNN-based models like the long-term recurrent convolutional network with 571.1 GOPS performance and 42.6 GOPS/W energy efficiency under 4-bit data format.

Convolution neural networks (CNNs) have been widely applied in the fields of computer vision tasks. However, it is hard to deploy those standard neural networks into embedded devices because of their large amount of operations and parameters. MobileNet, the state-of-the-art CNN which adopts depthwise separable convolution to replace the standard convolution has significantly reduced operations and parameters with only limited loss in accuracy. A high-performance CNN processor based on FPGA is proposed in this paper. To improve the efficiency, two dedicated computing engines named Conv Engine and Dwcv Engine were designed for pointwise convolution and depthwise convolution respectively. The schedule for Conv Engine and Dwcv Engine has significantly improved the efficiency of our accelerator. Furthermore, we designed a special architecture called Channel Augmentation to improve the efficiency in the first layer of MobileNets. The accelerator can be flexibly deployed to various devices with different configurations to balance hardware resources and computational performance. We implemented our accelerator on ZU2 and ZU9 MPSoC FPGAs. The classification on ImageNet achieved 205.3 frames per second(fps) on ZU2 and 809.8 fps on ZU9, which is 15.4x speedup on ZU2 and 60.7x speedup on ZU9 compared to CPU. We also deployed MobileNet + SSD network on our accelerator for object detection, and achieved 31.0 fps on ZU2 and 124.3 fps on ZU9.

The aim of this work is to more accurately model the stochastic process of music-related data, which is essential for many AI applications in musicology. When music is naturally represented as a sequence of vectorized frames, existing models generally cannot well capture the correlation of the elements inside each frame. We propose an energy-based model called Chain Graphical Recurrent Neural Network (CGRNN) to explore the correlation of elements for more accurate modeling of the dynamics of music. In CGRNN, a probabilistic substructure named Conditional spike and slab Restricted Boltzmann Machine (C-ssRBM) is defined to better model the conditional covariance and joint distribution of elements in a frame. Besides, CGRNN is capable of tracking the evolution of music and extracting sparse features with an efficient design of temporal transition. With the estimated stochastic process of music, we further implement CGRNN to generate melodious music automatically. Extensive empirical evaluations of multiple unsupervised learning tasks are conducted on symbolic MIDI and audio sounds to demonstrate the performance of our model.

With the proliferation of smartphones, a novel sensing paradigm called Mobile Crowd Sensing (MCS) has emerged very recently. However, the attacks and faults in MCS cause a serious false data problem. Observing the intrinsic low dimensionality of general monitoring data and the sparsity of false data, false data detection can be performed based on the separation of normal data and anomalies. Although the existing separation algorithm based on Direct Robust Matrix Factorization (DRMF) is proven to be effective, requiring iteratively performing Singular Value Decomposition (SVD) for low-rank matrix approximation would result in a prohibitively high accumulated computation cost when the data matrix is large. In this work, we observe the quick false data location feature from our empirical study of DRMF, based on which we propose an intelligent Light weight Low Rank and False Matrix Separation algorithm (LightLRFMS) that can reuse the previous result of the matrix decomposition to deduce the one for the current iteration step. Our algorithm can largely speed up the whole iteration process. From a theoretical perspective, we validate that LightLRFMS only requires one round of SVD computation and thus has very low computation cost. We have done extensive experiments using a PM 2.5 air condition trace and a road traffic trace. Our results demonstrate that LightLRFMS can achieve very good false data detection performance with the same highest detection accuracy as DRMF but with up to 10 times faster speed thanks to its lower computation cost.

The need of highly directional communications at mmWave frequencies introduces high overhead for beam training and alignment, which makes the medium access control (MAC) a grand challenge. To harvest the gain for high performance transmissions in mmWave networks, we propose an efficient and integrated MAC design with the concurrent support of three closely interactive components: 1) an accurate and low-cost beam training methodology with a) multiuser, multi-level, bi-directional coarse training for fast user association and beam alignment and b) adaptive fine beam training with compressed channel measurement and multi-resolution block-sparse channel estimation in response to the channel condition and the learning from past measurements; 2) an elastic virtual resource scheduling scheme that jointly considers beam training, beam tracking and data transmissions while enabling burst data transmissions with the concurrent allocation of transmission rate and duration; and 3) a flexible and efficient beam tracking strategy to enable stable beam alignment with beamwidth adaptation and mobility estimation. Compared with literature studies, our performance results demonstrate that our design can effectively reduce the training overhead and thus significantly improve the throughput. Compared to 802.11ad, the training overhead can be reduced more than 60%, and the throughput can be more than 75% higher. In low SNR case, the throughput gain can be more than 90%. Our scheme can also achieve about 50% higher throughput in the presence of user mobility.

Offloading computation intensive applications to mobile cloud is promising for overcoming the problems of limited computational resources and energy of mobile devices. However, without considering the competition relationship of mobile users and cloudlets in the mobile cloud computing system, existing studies lack an incentive mechanism for the system to achieve efficient application offloading and cloud resource provisioning. In this paper, we design MPTMG, a Multi-dimensional Pricing mechanism based on Two-sided Market Game. We propose three types of prices: a multi-dimensional price corresponding to multi-dimensional resource allocation, a penalty price to encourage fair and high quality cloud services, and a benefit discount factor to motivate more even provisioning of resources on different dimensions in the cloud. Based on these prices, we propose a distributed price-adjustment algorithm for efficient resource allocation and QoS-aware offloading scheduling. We prove that the algorithm can converge in a finite number of iterations to the equilibrium core allocation at which the mobile cloud system achieves the Pareto efficiency by maximizing the total system benefit. To the best of our knowledge, this is the first paper that applies economic theories and pricing mechanisms to manage application offloading in mobile cloud systems. The simulation results demonstrate that our proposed pricing mechanism can significantly improve the system performance.

Advanced Driver Assistance Systems (ADAS) help the driver in the driving process by detecting objects, doing basic classification, implementing safety guards and so on. Convolution Neural Networks (CNN) has been proved to be an essential to support ADAS. We designed an architecture named Aristotle to execute neural networks for both object detection and semantic segmentation on FPGA. DNNDK (Deep Learning Development Toolkit), a full-stack software tool, with tens of compilation optimization techniques is proposed to improve the energy efficiency and make it easy to develop. The Aristotle architecture is implemented on Xilinx ZU9 FPGA, and two networks are deployed on it to execute object detection and semantic segmentation, respectively.

Modern communication technologies are expected to be available in the future Smart Grids to enable the control of equipments over the whole power grid. In this paper, we consider such networked control approach to address failures that may occur at any location of the grid, due to attacks or unit malfunction, and provide a wide-scale solution that prevent the failure impacts from spreading over a large area. Different from literature work that focuses on modifying power equations under the standard constraints of the power system, we estimate the impact of controlling different nodes on topological areas of the grid based on social metrics, which are derived from the graph capturing both the topological and electrical properties of the power grid. We propose a failure control algorithm for topological containment of failures in smart grid. Our algorithm also takes careful consideration of the impact the planned control has on the grid to avoid the possibly involuntary failure extension. We show that social metrics can efficiently trade off between the topological and electrical characteristics revealed by the power grid graph representation. We evaluate the performance against networked control strategies that only use power models to determine the actions to be performed at power nodes. Our results show that the proposed control scheme can effectively contain failures within their original location range.

State-of-the-art techniques in Generative Adversarial Networks (GANs) have shown remarkable success in image-to-image translation from peer domain X to domain Y using paired image data. However, obtaining abundant paired data is a non-trivial and expensive process in the majority of applications. When there is a need to translate images across n domains, if the training is performed between every two domains, the complexity of the training will increase quadratically. Moreover, training with data from two domains only at a time cannot benefit from data of other domains, which prevents the extraction of more useful features and hinders the progress of this research area. In this work, we propose a general framework for unsupervised image-to-image translation across multiple domains, which can translate images from domain X to any a domain without requiring direct training between the two domains involved in image translation. A byproduct of the framework is the reduction of computing time and computing resources since it needs less time than training the domains in pairs as is done in state-of-the-art works. Our proposed framework consists of a pair of encoders along with a pair of GANs which learns high-level features across different domains to generate diverse and realistic samples from. Our framework shows competing results on many image-to-image tasks compared with state-of-the-art techniques.

Affected by hardware and wireless conditions in WSNs, raw sensory data usually have notable data loss and corruption. Existing studies mainly consider the interpolation of random missing data in the absence of the data corruption. There is also no strategy to handle the successive missing data. To address these problems, this paper proposes a novel approach based on matrix completion (MC) to recover the successive missing and corrupted data. By analyzing a large set of weather data collected from 196 sensors in Zhu Zhou, China, we verify that weather data have the features of low-rank, temporal stability, and spatial correlation. Moreover, from simulations on the real weather data, we also discover that successive data corruption not only seriously affects the accuracy of missing and corrupted data recovery but even pollutes the normal data when applying the matrix completion in a traditional way. Motivated by these observations, we propose a novel Principal Component Analysis (PCA)-based scheme to efficiently identify the existence of data corruption. We further propose a two-phase MC-based data recovery scheme, named MC-Two-Phase, which applies the matrix completion technique to fully exploit the inherent features of environmental data to recover the data matrix due to either data missing or corruption. Finally, the extensive simulations with real-world sensory data demonstrate that the proposed MC-Two-Phase approach can achieve very high recovery accuracy in the presence of successively missing and corrupted data.

Vehicles equipped with various types of sensors can act as mobile sensors to monitor the road conditions. To speed up the information collection process, the monitoring data can be shared among vehicles upon their encounters to facilitate drivers to find a good route. The vehicular network experiences intermittent connectivity as a result of the mobility, which makes the inter-vehicle contact duration a scarce resource for data transmissions and the support of monitoring applications over vehicular networks a challenge. We propose a novel compressive sensing (CS)-based scheme to enable efficient decentralized context sharing in vehicular delay tolerant networks, called CS-Sharing. To greatly reduce the data transmission overhead and speed up the monitoring processing, CS-sharing exploits two techniques: sending an aggregate message in each vehicle encounter, and quick collection of information taking advantage of data sharing and the sparsity of events in vehicle networks to significantly reduce the number of measurements needed for global information recovery. We propose a novel data structure, and an aggregation method that can take advantage of the random and opportunistic vehicle encounters to form the measurement matrix. We prove that the measurement matrix satisfies the Restricted Isometry Property (RIP) property required by the CS technique. Our results from extensive simulations demonstrate that CS-Sharing allows vehicles in a large network to quickly obtain the full context data with the successful recovery ratio larger than 90%.

With the rapid shift from end-to-end communications to content-based data sharing, there are increasing interests in exploiting mobile social Delay-Tolerant Networks (social DTNs) to deliver data, where the forwarding decision is usually made by comparing the social metrics of encountered nodes. Existing studies mostly derive long-term statistical social metrics without considering the temporal impact from node mobility. We exploit the time-varying contact graphs to analyze the dynamics of social DTNs based on two groups of datasets. Based on the analysis, we derive the time-varying characteristics of node contacts, durative and periodicity, and apply them to more accurately predict the corresponding time-varying social metrics (TSMs). We further propose a two-stage opportunistic forwarding strategy to select relays based on TSMs. Our simulation results verify the importance of the two properties we observe and the effectiveness of our algorithm in tracking time-varying social metrics. We also show the potential of our algorithm in finding general time varying metrics to improve the data dissemination performance of other opportunistic forwarding schemes.

There is a big potential to enable more efficient data dissemination in mobile Delay-Tolerant Networks (DTNs) with the concurrent use of multi-copy forwarding and social metrics. However, this also leads to the possibility of severely overloading the relay nodes with high social metrics, and consequent performance degradation. We propose a fair source quota allocation algorithm to effectively alleviate the load while ensuring their dissemination fairness, i.e, Lexicographical order Max-Min Fairness(LMMF). In this paper, A fair source quota allocation algorithm along with an implementation scheme was presented to take advantage of the features of social networks and social forwarding for higher delivery performance. Extensive simulations based on trace data demonstrate that our mechanism greatly reduces the delivery-ratio degradation caused by uneven load while ensuring fairness among the network users.

With the rapid shift from end-to-end communications to content-based data retrieval, there are increasing interests in exploiting Content-centric Networks (CCN) to deliver data. As the special characteristics of CCN, in-network caching and naming-based routing make traditional TCP-like transmission control protocol unsuitable. Although there are some existing efforts on improving the congestion control in CCN, the big issue of redundant transmissions caused by multiple sources has received little attention. To eliminate the redundancy and speed up the transmission, we propose a complete Network Codes-based Multi-Source Transmission Control Protocol (MSTCP), which provides an efficient and controllable multi-source content retrieval service over CCN. MSTCP takes advantage of random network coding to make full use of the coded data responded by different sources to speed up decoding and data receiving at the request side. Moreover, we design a scheduling algorithm based on a simple Expected Reception Deadline (ERD) to efficiently control the number of coded packets to send at each source. This not only effectively eliminates the redundant transmissions in CCN, but also helps to significantly speed up the information retrieval. Extensive simulations show that our mechanism greatly reduces the redundancy while speeding up the content retrievals by the network users.

End-to-end network monitoring is essential to ensure transmission quality for Internet applications. However, in large-scale networks, full-mesh measurement of network performance between all transmission pairs is infeasible. As a newly emerging sparsity representation technique, matrix completion allows the recovery of a low-rank matrix using only a small number of random samples. Existing schemes often fix the number of samples assuming the rank of the matrix is known, while the data features thus the matrix rank vary over time. In this paper, we propose to exploit the matrix completion techniques to derive the end-to-end network performance among all node pairs by only measuring a small subset of end-to-end paths. To address the challenge of rank change in the practical system, we propose a sequential and information-based adaptive sampling scheme, along with a novel sampling stopping condition. Our scheme is based only on the data observed without relying on the reconstruction method or the knowledge on the sparsity of unknown data. We have performed extensive simulations based on real-world trace data, and the results demonstrate that our scheme can significantly reduce the measurement cost while ensuring high accuracy in obtaining the whole network performance data.

Multi-robot systems (MRS) have many applications and the efficient operation of MRS relies on coordination of robots. However, it is difficult to build network connections among randomly distributed robots in the presence of robot movements and weak wireless channels. In this work, we propose to jointly exploit communications and motion control to efficiently establish robot connections. To achieve this goal, we concurrently use MUSIC and particle filter to more accurately and efficiently estimate robot signal directions, built on which signal strength-based potential field is formed to control robot motion to establish and maintain communication links. Our studies based on test bed and simulations demonstrate the effectiveness of our algorithm in networking robots, with much higher number of robots connected compared to peer algorithms.

Efficient power line monitoring is essential for reliable operation of the Smart Grid. A Power Line Monitoring Network (PLMN) based on wireless sensor nodes can provide the necessary infrastructure to deliver data from the extension of the power grid to one or several control centers. However, the restricted physical topology of the power lines constrains the data paths, and has a great impact on the reporting performance. We discuss the features of power-lines and their impact on the performance of monitoring and transmissions. We present a comprehensive design to guide efficient and flexible relay selection in PLMNs to ensure reliable and energy efficient transmissions while taking into account the restricted topology of power-lines. Specifically, our design applies probabilistic power control along with flexible transmission scheduling to combat the poor channel conditions around power line while maintaining the energy level of transmission nodes. We evaluate the impact of different channel conditions, non-uniform topologies for a power line corridor and the effect of reporting events. Our performance results demonstrate that our data forwarding scheme can well control the energy consumption and delay while ensuring reliability and extended lifetime.

Deploying the IPv6 protocol in Wireless Sensor Network (WSN) is the key issue of ubiquitous intelligence and mobile computing in the future. IETF 6LoWPAN enables the IPv6 protocol over IEEE 802.15.4 Low-power Wireless Personal Area Networks (Low PAN). The paper proposes an extended hierarchical routing protocol (E-HiLow), which reduces the memory requirement and the number of control packages and improve the path recovery and address allocation in HiLow. The simulation results and the analysis validates that the E-HiLow achieves better E2E packet delay and energy consumption performance.

It has been shown that sink mobility provides an energy-efficient approach to data delivery in wireless sensor networks (WSNs). Most of the approaches targeted to WSNs with mobile sinks (MSs) addressed the problem of data delivery where only a few messages are reported during a long time frame. However, transmitting streaming data is becoming relevant in WSNs, as more and more multimedia sensor nodes - equipped with image, audio, and video capabilities - are being used to characterize the sensing environment. In this scenario, a sequence of messages propagates into the network, hence the problem of finding an effective routing path for delivering data to MSs becomes even more challenging, since the communication overhead for reaching the MS might also be significant. In this paper, we present an energy-efficient streaming data delivery (SDD) protocol for cluster-based WSNs with MSs. Different from existing works, we focus on the mobility support for the delivery of streaming data in hierarchical WSNs. By introducing a cross-cluster handover mechanism and a path redirection scheme, SDD maintains the end-to-end connectivity between the source and the MS, while avoiding the constant transmission of the MS location as it moves across multiple clusters. We evaluate the performance of the proposed SDD protocol, and compare it with a hierarchical cluster-based data dissemination protocol. Simulation results demonstrate its effectiveness, in terms of both end-to-end delivery delay and energy-efficiency.

The integration cellular networks, wireless local area networks (WLANs), and the new paradigm of mobile ad hoc networks (MANETs) is the trend for next generation mobile networks. And the multi-hop routing mechanism is an open and challenge issue in this area. In this paper, a multi-hop routing mechanism with fuzzy estimation of links for heterogeneous wireless networks (HWNs) is proposed. The mechanism comprises neighbor discover, gateway discover and route discovery, which supports the mobile hosts (MHs) outside of the service area to access BS/AP by multi-hop route. The quality of links is addressed and evaluated by comprehensive fuzzy estimation approach based on analytic hierarchy process (AHP). Furthermore, the route maintenance overhead is also analyzed and discussed. Simulations reveal that the proposed routing mechanism can effectively provide valid route and improve the quality of service and performance in HWNs.

Deploying multiple mobile sinks is an attractive approach to enhance the performance of wireless sensor networks. In this paper, we address the scenario of two mobile sinks. The two sinks can travel in the same region or in the divided regions separately. The problems are formulated by a lattice-based network model. We deduce the network lifetime and delay of data delivery in different mobility patterns. The relation between network performance and number of mobile sinks is also discussed. Simulation results are provided to validate our theoretic analysis followed by performance comparison of different mobility patterns.

Prolonging the network lifetime and reducing the delay of event delivery are both important in event-driven multi- hop wireless sensor networks. In this paper, an optimum predefined mobility trajectory of the sink was explored to balance the two performance metrics. We focus on a lattice-based analytical model for understanding performance as system and mobility parameters are scaled. Based on the model, the theoretical analysis and the simulation results validate our statements. The case of multiple mobile sinks are also discussed and simulated.