Recently, Internet of Vehicles (IoV) has become one of the most active research fields in both academic and industry, which exploits resources of vehicles and Road Side Units (RSUs) to execute various vehicular applications. Due to the increasing number of vehicles and the asymmetrical distribution of traffic flows, it is essential for the network operator to design intelligent offloading strategies to improve network performance and provide high-quality services for users. However, the lack of global information and the time-variety of IoVs make it challenging to perform effective offloading and caching decisions under long-term energy constraints of RSUs. Since Artificial Intelligence (AI) and machine learning can greatly enhance the intelligence and the performance of IoVs, we push AI inspired computing, caching and communication resources to the proximity of smart vehicles, which jointly enable RSU peer offloading, vehicle-to-RSU offloading and content caching in the IoV framework. A Mix Integer Non-Linear Programming (MINLP) problem is formulated to minimize total network delay, consisting of communication delay, computation delay, network congestion delay and content downloading delay of all users. Then, we develop an online multi-decision making scheme (named OMEN) by leveraging Lyapunov optimization method to solve the formulated problem, and prove that OMEN achieves near-optimal performance. Leveraging strong cognition of AI, we put forward an imitation learning enabled branch-and-bound solution in edge intelligent IoVs to speed up the problem solving process with few training samples. Experimental results based on real-world traffic data demonstrate that our proposed method outperforms other methods from various aspects.

Intelligent Edge Computing in Internet of Vehicles: A Joint Computation Offloading and Caching Solution

Machine learning has been the corner stone in analysing and extracting information from data and often a problem of missing values is encountered. Missing values occur because of various factors like missing completely at random, missing at random or missing not at random. All these may result from system malfunction during data collection or human error during data pre-processing. Nevertheless, it is important to deal with missing values before analysing data since ignoring or omitting missing values may result in biased or misinformed analysis. In literature there have been several proposals for handling missing values. In this paper, we aggregate some of the literature on missing data particularly focusing on machine learning techniques. We also give insight on how the machine learning approaches work by highlighting the key features of missing values imputation techniques, how they perform, their limitations and the kind of data they are most suitable for. We propose and evaluate two methods, the k nearest neighbor and an iterative imputation method (missForest) based on the random forest algorithm. Evaluation is performed on the Iris and novel power plant fan data with induced missing values at missingness rate of 5% to 20%. We show that both missForest and the k nearest neighbor can successfully handle missing values and offer some possible future research direction.

/pdf/a-survey-on-missing-data-in-machine-learning-5d62yrtdu1.pdf

A survey on missing data in machine learning.

Multiband cooperative networking is being recognized as a new enabling scheme to provide superior user experience and greatly scale up system capacity for 5G cellular networks. This article presents a control/user plane split (CUPS)-based multiband cooperative network architecture. To satisfy the diversified requirements of future 5G applications, the separation of the control and user planes is applied in both the core network and radio access network (RAN). In this proposed network architecture, control information is transmitted through the control plane at sub-6 GHz, and the user equipment (UE) data are forwarded through the user plane in millimeter-wave (mm-wave) bands.

Multiband Cooperation for 5G HetNets: A Promising Network Paradigm

With the increasing scale of antenna arrays in wideband millimeter-wave (mmWave) communications, the physical propagation delays of electromagnetic waves traveling across the whole array will become large and comparable to the time-domain sample period, which is known as the spatial-wideband effect. In this case, different subcarriers in an orthogonal frequency division multiplexing (OFDM) system will “see” distinct angles of arrival (AoAs) for the same path. This effect is known as beam squint , resulting from the spatial-wideband effect, and makes the approaches based on the conventional multiple-input multiple-output (MIMO) model, such as channel estimation and precoding, inapplicable. After discussing the relationship between beam squint and the spatial-wideband effect, we propose a channel estimation scheme for frequency-division duplex (FDD) mmWave massive MIMO-OFDM systems with hybrid analog/digital precoding, which takes the beam squint effect into consideration. A compressive sensing-based approach is developed to extract the frequency-insensitive parameters of each uplink channel path, i.e., the AoA and the time delay, and the frequency-sensitive parameter, i.e., the complex channel gain. With the help of the reciprocity of these frequency-insensitive parameters in FDD systems, the downlink channel estimation can be greatly simplified, where only limited pilots are needed to obtain downlink complex gains and reconstruct downlink channels. Furthermore, the uplink and downlink channel covariance matrices can be constructed from these frequency-insensitive channel parameters rather than through a long-term average, which enables the minimum mean-squared error (MMSE) channel estimation to further enhance performance. Numerical results demonstrate the superiority of the proposed scheme over the conventional methods under general system configurations in mmWave communications.

Beam Squint and Channel Estimation for Wideband mmWave Massive MIMO-OFDM Systems

Vehicular Edge Computing (VEC) is expected to be an effective solution to meet the ultra-low delay requirements of many emerging Internet of Vehicles (IoV) services by shifting the service caching and the computation capacities to the network edge. However, due to the constraints of the multidimensional (storage-computing-communication) resources capacities and the cost budgets of vehicles, there are two main issues need to be addressed: 1) How to collaboratively optimize the service caching decision among edge nodes to better reap the benefits of the storage resource and save the time-correlated service reconfiguration cost? 2) How to allocate resources among various vehicles and where vehicular requests are scheduled to improve the efficiency of the computing and communication resources utilization? In this paper, we formulate an edge caching and computation management problem that jointly optimizes the service caching, the request scheduling, and the resource allocation strategies. Our focus is to minimize the time-average service response delay of the random arriving service requests in a cost-efficient way. To cope with the dynamic and unpredictable challenges of IoVs, we leverage the combined power of Lyapunov optimization, matching theory, and consensus alternating direction method of multipliers to solve the problem in an online and distributed manner. Theoretical analysis shows that the developed approach achieves a close-to-optimal delay performance without relying on any prior knowledge of the future network information. Moreover, simulation results validate the theoretical analysis and demonstrate that our algorithm outperforms the baselines substantially.

Edge Caching and Computation Management for Real-Time Internet of Vehicles: An Online and Distributed Approach

As a development direction of urban rail transit system, the train autonomous circumambulate system (TACS) can operate in a safer, more efficient, and more economical mode. However, most urban rail transit systems transmit signals through industrial, scientific, and medical (ISM) frequency bands or narrow frequency bands, which cannot meet the requirements of TACS. As a promising solution, the 5th generation (5G) mobile communication provides more services for the future urban rail transit systems, and covers the shortages of exiting communication technologies in terms of capacity and reliability. In this paper, we first briefly review the research status of current train control system and introduce its limitations. Next, we propose a novel network architecture, and present new technologies and requirements of the proposed architecture for TACS. Some potential challenges are then discussed to give insights for further research of TACS.

Future 5G-oriented system for urban rail transit: Opportunities and challenges

We propose a transmission scheme that exploits the spatial degrees of freedom from large antenna arrays to maximize the downlink sum-rate of user equipment (UE) in a heterogeneous network. Our scheme incorporates the design of 1) a new precoder for the millimeter wave (mmWave) wireless backhaul; and 2) an enhanced small cell range expansion method for data link transmission. Aside from the advantage of lower implementation and computational complexity, the wireless backhaul precoder can simultaneously support multiple small access points with multi-streams. Under the constraint of wireless backhaul capacity, a downlink cooperation precoding algorithm is proposed to suppress the interference caused by small cell range expansion. Simulation results show that the proposed precoder in backhaul link can use a small number of radio frequency (RF) chains to achieve the sum-rate performance that approaches the one under traditional block diagonalization precoder, which requires the number of the RF chains to be comparable with that of antenna elements. Moreover, we give a lower bound for the overall UE sum-rate of the downlink cooperation precoding algorithm.

Enhancing Downlink Transmission in MIMO HetNet With Wireless Backhaul

The performance of multicell massive multiple-input multiple-output (MIMO) systems is heavily affected by pilot contamination. This study considers the problem of pilot contamination and analytical expressions are presented on the normalised mean square error (NMSE) of the minimum mean square error channel estimation algorithm. Based on the NMSE of the massive MIMO systems, a pilot design criterion is proposed to design the optimal pilot sequences for mitigating the pilot contamination. Following this criterion, Chu sequence with perfect auto-correction and cross-correlation properties are employed to design the optimal pilot sequences. Then the performance of the proposed pilot design-based scheme is investigated, and the exact NMSE expressions are presented. The excellent performance of this pilot design scheme has been confirmed in the authors' simulations.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-com.2016.0889

Optimal pilot design in massive MIMO systems based on channel estimation

Owing to the signal structure difference between the filter bank multicarrier with offset quadrature amplitude modulation (FBMC/OQAM) and the orthogonal frequency-division multiplexing (OFDM) systems, the existing technologies to reduce the peak-to-average power ratio (PAPR) for OFDM systems are not suitable for the FBMC/OQAM systems This paper considers the problem of PAPR in the FBMC/OQAM systems, and to reduce the PAPR of the FBMC/OQAM signal, we propose an improved joint optimization scheme combined with the linear (ie, partial transmit sequence (PTS)) and nonlinear (ie, clipping and filtering (CF)) methods, named improved bilayer partial transmit sequence and iterative clipping and filtering (IBPTS-ICF) scheme The main idea of this joint optimization scheme is clipping and filtering the processed FBMC/OQAM signal, whose probability of the peak value has been reduced by the IBPTS technique Meanwhile, aided by the knowledge of convex optimization, the IBPTS-ICF joint optimization scheme can effectively reduce the signal distortion The excellent PAPR reduction performance of the proposed scheme has been confirmed in our simulations

Shanjin Ni

Papers

Multiband Cooperation for 5G HetNets: A Promising Network Paradigm

Future 5G-oriented system for urban rail transit: Opportunities and challenges

Enhancing Downlink Transmission in MIMO HetNet With Wireless Backhaul

Optimal pilot design in massive MIMO systems based on channel estimation

Peak-to-Average Power Ratio Reduction of FBMC/OQAM Signal Using a Joint Optimization Scheme