In recent years, Internet Service Providers (ISPs) are expected to enable various practical services. To meet the requirements of services, the infrastructure of networks has become more and more complex. In telecom networks, the complex infrastructure implies that it would be difficult to analyze the root causes and to locate the faults. In the telecom companies, network maintenance staffs need to spend a lot of time to trace the root cause and solve the network problems. An intelligent fault location approach allows ISPs to be cost-effective, and can assist humans in decision-making and increase automation. To automatically locate the faults, we apply both the Ant Colony Optimization (ACO) algorithm and fuzzy logic methods, and the main contributions of this paper are threefold: (1) we apply the pheromones of the ACO algorithm to quantify the risks that network devices might fail; (2) based on the risks, we leverage fuzzy logic, including the fuzzy relation matrix and the max-min composition method, to infer the fault location; (3) for improving autonomous network, we implemented and evaluated the proposed intelligent fault location approach using the real data in telecom networks.

In recent years, IP surveillance networks are expected to enable various practical applications, such as finding suspects, monitoring pedestrians, and securing societies (e.g., securing a city, a company and a data center). With these applications, IP surveillance network is regarded as one of the potential technologies toward developing smart cities. To support the concept of IP surveillance networks, automatic attribute recognition systems have emerged as a promising intelligent management system. To automatically recognize attributes of pedestrians (e.g., gender and clothing), we apply deep convolutional neural networks (CNNs), and the main contributions of this paper are threefold: (1) we proposed a practical system architecture for intelligent management of surveillance networks; (2) we implemented different deep CNNs, and an ensemble-learning method that leverages these multiple deep-learning models; (3) we evaluated the models using the real data of IP surveillance networks.

Quality of user Experience (QoE) is one of the most important issues for scalable video over OFDMA networks. Given the OFDMA frame structure, scheduling tasks can be classified into 1) intraframe scheduling and 2) interframe scheduling. While many studies have focused on how to enhance the QoE through intraframe scheduling, few studies have examined the potential of interframe scheduling. The only previous work on video interframe scheduling has considered which OFDMA frame the video traffic should start from; it is the single parameter that is adjustable, which leads to some loss of flexibility in scheduling. To enhance the QoE, this paper considers the video-transmission time point to be fully adjustable as long as the video delay bound can be satisfied. Accordingly, we formulate the interframe scheduling problem as an optimization problem with strong NP-hardness, and we propose a multiple-knapsack-based algorithm (MKBA) to solve the problem efficiently.

IEEE 802.16m resource scheduling remains a challenging issue for video multicast. Given the OFDMA frame structure, the IEEE 802.16m scheduling task is comprised of: (1) intraframe scheduling; and (2) interframe scheduling. In the literature, while many studies concentrated on the development of intraframe scheduling mechanisms, few studies looked at the potential of interframe scheduling mechanisms. This paper is the first attempt to investigate the energy efficiency potential of interframe scheduling algorithms to support scalable-video multicast services over IEEE 802.16m networks. Under the premise that the bandwidth requirements of scalable-video subscribers must be satisfied, we first prove that the interframe scheduling problem of minimizing video-subscriber energy consumption is NP-hard. To tackle the NP-hard problem, we propose a multiple bin-packing algorithm, MBPA, for energy-efficient scheduling. The proposed MBPA has full compatibility with the existing intraframe scheduling mechanisms and with the IEEE 802.16m sleep-mode operations. By applying the divide-and-conquer strategy, MBPA effectively eliminates unnecessary wake-up periods and unnecessary state transitions (between wake-up and sleep states), and thus achieves high energy-efficiency. Through theoretical analysis, we show that MBPA is a p-approximation algorithm, where p is a finite value no less than one. Finally, the simulation results show the effectiveness of the proposed MBPA in energy efficiency, user satisfaction, and computational complexity.

This paper proposes the first resource allocation scheme in the literature to support scalable-video multicast for WiMAX relay networks. We prove that when the available bandwidth is limited, the bandwidth allocation problems of 1) maximizing network throughput and 2) maximizing the number of satisfied users are NP-hard. To find the near-optimal solutions to this type of maximization problem in polynomial time, this study first proposes a greedy weighted algorithm, GWA, for bandwidth allocation. By incorporating table-consulting mechanisms, the proposed GWA can intelligently avoid redundant bandwidth allocation and thus accomplish high network performance (such as high network throughput or large number of satisfied users). To maintain the high performance gained by GWA and simultaneously improve its worst case performance, this study extends GWA to a bounded version, BGWA, which guarantees that its performance gains are lower bounded. This study shows that the computational complexity of BGWA is also in polynomial time and proves that BGWA can provide at least 1/ρ times the performance of the optimal solution, where \rho is a finite value no less than one. Finally, simulation results show that the proposed BGWA bandwidth allocation scheme can effectively achieve different performance objectives with different parameter settings.

Many multi-channel Media Access Control (MAC) protocols have been studied in the past decade. With an eye to hardware cost and device capability, many researchers have proposed protocols using only one transceiver, even though the potential capacity of a multiple-transceiver network is higher than that of one with a single transceiver. In this paper, we introduce a novel, cooperative, multi-channel MAC protocol that incorporates the concept of cooperative communication into multi-channel MAC protocols, enabling a single transceiver to carry out the work of multiple transceivers. The proposed protocol, based on the well-known Slotted Seeded Channel Hopping (SSCH) multi-channel protocol, requires only one transceiver per device. For use in an IEEE 802.11 multi-channel multi-hop wireless network environment, our approach selects a relay node to become a virtual node with an intermediate node. We also design a channel assignment mechanism to let the virtual node transmit and receive data simultaneously on different channels, thus improving network performance. Simulation results show that our protocol significantly outperforms the original SSCH in terms of network capacity and average packet delay.

Mobile WiMAX is a promising technology to enable the wireless video multicast services, such as mobile IPTV and live athletic events. For supporting such bandwidth-eager and energy-hungry applications, the efficient bandwidth-allocation and energy-saving mechanisms should be simultaneously employed. In this paper, we first investigate how the WiMAX energy-saving mechanism significantly degrades the performance of the bandwidth-allocation mechanisms. We present a theoretical model for illustrating this interaction problem. To solve the problem, we propose a novel sleep-mode interleaving algorithm beyond the existing mechanisms. By appropriately adjusting one sleep-mode parameter, the proposed algorithm effectively guarantees the bandwidth efficiency of the video multicast mechanisms while the mobile stations can execute the standard sleep-mode operations. Simulation results demonstrate the effectiveness of our proposed algorithm in terms of the user satisfaction, power consumption and computational complexity.

This paper targets to investigate the interaction between IEEE 802.16e scheduling algorithms and sleep-mode operations. To achieve high energy efficiency, an energy-efficient scheduling architecture is first proposed. Based on this architecture, a state transition mechanism is designed for IEEE 802.16e mobile subscriber stations (MSSs) to switch their real-time connections between awake mode and sleep mode. The proposed energy-efficient scheduling algorithm is different from the existing scheduling algorithms in terms of the scheduling priority order and the state transition mechanism for MSSs. The simulation results highlight that with proper scheduling priority and state transition mechanism, scheduling algorithms can effectively improve QoS for IEEE 802.16e networks while achieving high MSS energy efficiency.