Given a software defined wide-area network (WAN), how to choose location of controllers and how to assign the controllers to forwarding devices are two significant issues. Previously, most of solutions to these two problems focus on the propagation delay but ignore the balance of controllers, because it's difficult to solve them with consideration of balance of controllers. In this paper, a novel approach which can efficiently and accurately solve SDN controller placement problem and assignment problem for WAN is proposed. The SDN controller assignment problem is formulated as a minimum weight matching of bipartite graph, and it also considers the balance of controllers. The Kuhn- Munkres algorithm based solution is used to find optimal matching between switches and controllers. Then, a genetic algorithm is proposed to solve the controller placement problem based on the controller assignment scheme. The performance shows that our approach has good performance in reducing the average propagation delay between SDN forwarding devices and controllers, and it also achieves better balance of controllers.

Communication is supposed to improve multi-agent collaboration and overall performance in cooperative Multi-agent reinforcement learning (MARL). However, such improvements are prevalently limited in practice since most existing communication schemes ignore communication overheads (e.g., communication delays). In this paper, we demonstrate that ignoring communication delays has detrimental effects on collaborations, especially in delay-sensitive tasks such as autonomous driving. To mitigate this impact, we design a delay-aware multi-agent communication model (DACOM) to adapt communication to delays. Specifically, DACOM introduces a component, TimeNet, that is responsible for adjusting the waiting time of an agent to receive messages from other agents such that the uncertainty associated with delay can be addressed. Our experiments reveal that DACOM has a non-negligible performance improvement over other mechanisms by making a better trade-off between the benefits of communication and the costs of waiting for messages.

Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency.

The software-defined network (SDN) is a new networking paradigm to improve network performance via logically centralized control and open standardized interfaces. However, the introduction of SDN technology faces many difficulties due to operational and economic constraints. Therefore, an incremental deployment scenario, the so-called hybrid SDN, is preferred. The transition from a legacy network to a pure SDN may take a long time; hence, it is of vital importance to consider the network optimization problem for hybrid SDNs. With SDN-enabled devices, multi-paths, where each flow can have multiple alternative paths, can be supported in bandwidth allocation. In contrast to traditional bandwidth allocation mechanisms in pure IP networks and full SDNs, this paper proposes a utility maximization model with the coexistence of single paths and multi-paths in the network, which aims to facilitate the transition to SDNs. We also design a novel algorithm to solve the maximization model, which is no longer strictly concave. Extensive simulations are conducted to evaluate the performance of the proposed bandwidth allocation strategy. Compared with existing strategies, our strategy has a good performance in terms of utility improvement. The results also show that with an increasing number of devices deployed in the SDN, more paths can be used to allocate the bandwidth; thus, a greater network utility can be achieved.

Software Defined Networking (SDN) provides a flexible and convenient way to support fine-grained traffic-engineering (TE). Besides, SDN also provides better Quality of Experience (QoE) for customers. However, the policy of the evolution from legacy networks to the SDNs overemphasizes the controllability of the network or TE while ignoring the customers' benefit. Standing in the customers' position, we propose an optimization scheme, named as Optimal Migration Schedule based on Customers' Benefit (OMSB), to produce an optimized migration schedule and maximize the benefit of customers. Not only the quality and quantity of paths availed by migration, but also the number of flows from the customers that can use these multi-paths are taken into consideration for the scheduling. We compare the OMSB with other six migration schemes in terms of the benefit of customers. Our results suggest that the sequence of the migration plays a vital role for customers, especially in the early stages of the network migration to the SDN.

Video streaming from cameras to backend cloud or edge servers for neural-based analytics has gained significant popularity. However, the transmission of data from cameras to a backend raises substantial privacy concerns, particularly regarding sensitive information like facial data. To offer privacy protection, visual processing techniques, such as Generative Adversarial Networks (GANs), have been employed on cameras to blur and safeguard such data intelligently. However, these techniques frequently face memory challenges, particularly when dealing with high-resolution videos. In this paper, we propose PIMO, a memory-efficient visual privacy protection scheme designed to effectively blur video content leveraging adaptive slicing of frames and resolution degradation. Our extensive experimental evaluations validate that PIMO’s adaptive mechanism proficiently navigates fluctuating memory constraints. Furthermore, utilizing a content-based blur scheme, our approach can maintain an impressive mean precision of 95.2%, as compared to the original, non-blurred images.