Cloud data center (CDC) network virtualization is being regarded as a promising technology to provide performance guarantee for cloud computing applications. One critical issue in CDC network virtualization technology is virtual data center (VDC) embedding, which deals with the CDC physical resource allocation to virtual nodes (virtual switches and virtual servers) and virtual links of a VDC. When node and link constraints (including CPU, memory, network bandwidth, and network delay) are both taken into account, the VDC embedding problem is NP-hard, even in the offline case. Node heterogeneity and CDC network scale bring challenges to the VDC embedding. This paper aims to embed a VDC in a robust and green way. We propose two effective, computation-efficient and energy-efficient embedding algorithms. Extensive simulations under various network scales and topologies are carried out to compare the proposed algorithms with the existing VDC embedding algorithms in terms of the VDC acceptance ratio, the long-term revenue of the cloud service provider (CSP), the CDC’s long-term energy consumption in light-load CDCs, and in terms of CSP's long-term revenue in heavy-load CDCs.

Moving target defense (MTD) has recently emerged as a game-changer in the confrontation between cyberattack and defense. MTD mechanism constantly and randomly changes the system configurations to create uncertainty of the attack surface against cyber-adversaries. To date, researches on the evaluation of MTD techniques either focused on analyzing the effectiveness of MTD or studying the system performance loss due to the use of MTD. The impact on job/service running on the protected system is always ignored. In this paper, we propose an SRN (Stochastic reward net) based analytical modeling approach to investigate how MTD techniques influence the job running on protected system from the perspective of job finish time. The SRN model developed in this paper captures the behaviors of both the adversary and the job execution process. Furthermore, we carry out numerical analysis to study the impact of different system parameters on job finish time and other evaluation metrics. The results in this paper can help defenders choose a better MTD configuration to complete the job execution as soon as possible.

Fog-Cloud framework is being regarded as a more promising technology to provide performance guarantee for IoT applications, which not only have higher requirements on computation resources, but also are delay and/or security sensitive. In this framework, a delay and security-sensitive computation task is usually divided into several sub-tasks, which could be offloaded to either fog or cloud computing servers, referred to as offloading destinations. Sub-tasks may exchange information during their processing and then have requirement on transmission bandwidth. Different destinations produce different completion delays of a sub-task, affecting the corresponding task delay. The existing offloading approaches either considered only a single type of offloading destinations or ignored delay and/or security constraint. This paper studies a computation offloading problem in the fog-cloud scenario where not only computation and security capabilities of offloading destinations may be different, but also bandwidth and delay of links may be different. We first propose a joint offloading approach by formulating the problem as a form of Mixed Integer Programming Multi-Commodity Flow to maximize the fog-cloud provider's revenue without sacrificing performance and security requirements of users. We also propose a greedy algorithm for the problem. Extensive simulation results under various network scales show that the proposed computation offloading mechanism achieves higher revenue than the conventional single-type computation offloading under delay and security constraints.

Embedding virtual network requests in an underlying physical infrastructure, the so-called virtual network embedding (VNE) problem, has attracted significant research interests already. A realistic scenario might entail embedding multiple VN requests (MVNE) that arrive simultaneously (batch arrivals). The existing heuristic MVNE approaches neither consider the coordination among multiple VNR embeddings nor embed all the arriving VNRs simultaneously considering the available physical resources. This paper considers the MVNE problem in the scenario where the available physical resources may not be sufficient to satisfy the physical resource demands of all the VNRs in the batch. We explore applying genetic algorithm (GA) to handle the MVNE problem. We propose an algorithm to decide which VNRs could be mapped together. Extensive simulations are carried out to evaluate the performance of the proposed algorithms in terms of the VN acceptance ratio and the long-term revenue of the service provider.

Localization using multiple base stations (BSs) has gained much attention for its high localization accuracy. However, the performance of the multi-BS system suffers from its limited number of antennas. To solve the above issue, we propose to use reconfigurable intelligent surfaces (RIS) serving as antennas. Existing localization methods enabled by multiple RISs mainly focus on the far-field (FF) region of each RIS. As the scale of RIS increases, the near-field (NF) region of each RIS expands, where FF methods struggle to achieve high localization accuracy. In this letter, a hybrid NF and FF localization method aided by multiple RISs is proposed. In such scenarios, achieving user localization and RIS optimization is challenging due to the high complexity caused by the exhaustive search through all candidate locations to match the signals. Moreover, the interference from multiple RISs degrades the localization accuracy. To address this challenge, we propose a two-phase localization method that first estimates the relative locations of the user to each RIS and fuses the results to obtain the estimation. This approach reduces the complexity by decreasing the number of candidate locations considered in each step. Also, we introduce a constraint in the RIS optimization problem that limits the sidelobe levels directed towards other RISs, minimizing inter-RIS interference. The effectiveness of the proposed method is verified through simulations.

Emergency supplies allocation is a critical task in post-disaster response, as ineffective or delayed decisions can directly lead to increased human suffering and loss of life. In practice, emergency managers must make rapid allocation decisions over multiple periods under incomplete information and highly unpredictable demand, making robust and adaptive decision support essential. However, existing allocation approaches face several challenges: (1) Those traditional approaches rely heavily on predefined uncertainty sets or probabilistic models, and are inherently static, making them unsuitable for multi-period, dynamically allocation problems; and (2) while reinforcement learning (RL) technique is inherently suitable for dynamic decision-making, most existing RL-base approaches assume fixed demand, making them unable to cope with the non-stationary demand patterns seen in real disasters. To address these challenges, we first establish a multi-period and multi-objective emergency supplies allocation problem with demand uncertainty and then formulate it as a two-player zero-sum Markov game (TZMG). Demand uncertainty is modeled through an adversary rather than predefined uncertainty sets. We then propose RESA, a novel RL framework that uses adversarial training to learn robust allocation policies. In addition, RESA introduces a combinatorial action representation and reward clipping methods to handle high-dimensional allocations and nonlinear objectives. Building on RESA, we develop RESA_PPO by employing proximal policy optimization as its policy optimizer. Experiment results with realistic post-disaster data show that RESA_PPO achieves near-optimal performance, with an average gap of only 3.7% in terms of the objective value of the formulated problem, from the theoretical optimum derived by exact solvers. Moreover, RESA_PPO outperforms all baseline methods, including heuristic and standard RL methods, by at least 5.25% on average.