20 September 2018 in IEEE Journal on Selected Areas in Communications
This paper studies fog computing systems, in which cloud data centers can be supplemented by a large number of fog nodes deployed in a wide geographical area. Each node relies on harvested energy from the surrounding environment to provide computational services to local users. We propose the concept of dynamic network slicing in which a regional orchestrator coordinates workload distribution among local fog nodes, providing partitions/slices of energy and computational resources to support a specific type of service with certain qualityof- service (QoS) guarantees. The resources allocated to each slice can be dynamically adjusted according to service demands and energy availability. A stochastic overlapping coalition-formation game is developed to investigate distributed cooperation and joint network slicing between fog nodes under randomly fluctuating energy harvesting and workload arrival processes. We observe that the overall processing capacity of the fog computing network can be improved by allowing fog nodes to maintain a belief function about the unknown state and the private information of other nodes. An algorithm based on a belief-state partially observable Markov decision process (B-POMDP) is proposed to achieve the optimal resource slicing structure among all fog nodes. We describe how to implement our proposed dynamic network slicing within the 3GPP network sharing architecture, and evaluate the performance of our proposed framework using the real BS location data of a real cellular system with over 200 BSs deployed in the city of Dublin. Our numerical results show that our framework can significantly improve the workload processing capability of fog computing networks. In particular, even when each fog node can coordinate only with its closest neighbor, the total amount of workload processed by fog nodes can be almost doubled under certain scenarios.
22 October 2018 in IEEE Journal on Selected Areas in Communications
Network slicing is considered one of the key enabling technologies for 5G due to its ability to customize and “slice” a common resource to support diverse services and verticals. This paper introduces a novel inter-operator network slicing framework in which multiple mobile network operators (MNOs) can coordinate and jointly slice their accessible spectrum resources in both licensed and unlicensed bands. For licensed band slicing, we propose an inter-operator spectrum aggregation method that allows two or more MNOs to cooperate and share their licensed bands to support a common set of service types. We then consider the sharing of unlicensed bands. Because all MNOs enjoy equal rights to accessing these bands, we introduce the concept of right sharing for MNOs to share and trade their spectrum access rights. We develop a modified back-of-the-envelope (mBoE) method for MNOs to evaluate their Value-of-Rights (VoR) when coexisting with other wireless technologies. A network slicing game based on the overlapping coalition formation game is formulated to investigate cooperation between MNOs. We prove that our proposed game always has at least one stable slicing structure that maximizes the social welfare. To implement our proposed framework without requiring MNOs to reveal private information to other MNOs, we develop a distributed algorithm called Distributed Alternating Direction Method of Multipliers with Partially Variable Splitting (D-ADMM-PVS). Performance evaluation of our proposed framework is provided using a discrete-event simulator that is driven by real MNO deployment scenarios based on over 400 base station locations deployed by two primary cellular operators in the city of Dublin. Numerical results show that our proposed framework can almost double the capacity for all supported services for each MNO in an urban setting.
13 February 2023 in Artificial Intelligence Review
31 January 2023 in IEEE Transactions on Mobile Computing
With the rising demand for wireless services and increased awareness of the need for data protection, existing network traffic analysis and management architectures are facing unprecedented challenges in classifying and synthesizing the increasingly diverse services and applications. This paper proposes FS-GAN, a federated self-supervised learning framework to support automatic traffic analysis and synthesis over a large number of heterogeneous datasets. FS-GAN is composed of multiple distributed Generative Adversarial Networks (GANs), with a set of generators, each being designed to generate synthesized data samples following the distribution of an individual service traffic, and each discriminator being trained to differentiate the synthesized data samples and the real data samples of a local dataset. A federated learning-based framework is adopted to coordinate local model training processes of different GANs across different datasets. FS-GAN can classify data of unknown types of service and create synthetic samples that capture the traffic distribution of the unknown types. We prove that FS-GAN can minimize the Jensen-Shannon Divergence (JSD) between the distribution of real data across all the datasets and that of the synthesized data samples. FS-GAN also maximizes the JSD among the distributions of data samples created by different generators, resulting in each generator producing synthetic data samples that follow the same distribution as one particular service type. Extensive simulation results show that the classification accuracy of FS-GAN achieves over $20\%$ improvement in average compared to the state-of-the-art clustering-based traffic analysis algorithms. FS-GAN also has the capability to synthesize highly complex mixtures of traffic types without requiring any human-labeled data samples.
16 January 2023 in IEEE Transactions on Mobile Computing
Real-time machine learning (ML) has recently attracted significant interest due to its potential to support instantaneous learning, adaptation, and decision making in a wide range of application domains, including self-driving vehicles, intelligent transportation, and industry automation. In this paper, we investigate real-time ML in a federated edge intelligence (FEI) system, an edge computing system that implements federated learning (FL) solutions based on data samples collected and uploaded from decentralized data networks, e.g., Internet-of-Things (IoT) and/or wireless sensor networks. FEI systems often exhibit heterogenous communication and computational resource distribution, as well as non-i.i.d. data samples arrived at different edge servers, resulting in long model training time and inefficient resource utilization. Motivated by this fact, we propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model with desirable accuracy. Training acceleration solutions for both TS-FL with synchronous coordination (TS-FL-SC) and asynchronous coordination (TS-FL-ASC) are investigated. To address the straggler effect in TS-FL-SC, we develop an analytical solution to characterize the impact of selecting different subsets of edge servers on the overall model training time. A server dropping-based solution is proposed to allow some slow-performance edge servers to be removed from participating in the model training if their impact on the resulting model accuracy is limited. A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, the local epoch number (the number of model training iterations per coordination), and the data batch size (the number of data samples for each model training iteration). Motivated by the fact that data samples at the slowest edge server may exhibit special characteristics that cannot be removed from model training, we develop an analytical expression to characterize the impact of both staleness effect of asynchronous coordination and straggler effect of FL on the time consumption of TS-FL-ASC. We propose a load forwarding-based solution that allows a slow edge server to offload part of its training samples to trusted edge servers with higher processing capability. We develop a hardware prototype to evaluate the model training time of a heterogeneous FEI system. Experimental results show that our proposed TS-FL-SC and TS-FL-ASC can provide up to 63% and 28% of reduction, in the overall model training time, respectively, compared with traditional FL solutions.
20 January 2011 in IEEE/ACM Transactions on Networking
SRSrinivasan Ramasubramanian
Srinivasan Ramasubramanian
We introduce the concepts of monitoring paths (MPs) and monitoring cycles (MCs) for unique localization of shared risk linked group (SRLG) failures in all-optical networks. An SRLG failure causes multiple links to break simultaneously due to the failure of a common resource. MCs (MPs) start and end at the same (distinct) monitoring location(s). They are constructed such that any SRLG failure results in the failure of a unique combination of paths and cycles. We derive necessary and sufficient conditions on the set of MCs and MPs needed for localizing any single SRLG failure in an arbitrary graph. When a single monitoring location is employed, we show that a network must be (k+2)-edge connected for localizing all SRLG failures, each involving up to k links. For networks that are less than (k+2)-edge connected, we derive necessary and sufficient conditions on the placement of monitoring locations for unique localization of any single SRLG failure of up to k links. We use these conditions to develop an algorithm for determining monitoring locations. We show a graph transformation technique that converts the problem of identifying MCs and MPs with multiple monitoring locations to a problem of identifying MCs with a single monitoring location. We provide an integer linear program and a heuristic to identify MCs for networks with one monitoring location. We then consider the monitoring problem for networks with no dedicated bandwidth for monitoring purposes. For such networks, we use passive probing of lightpaths by employing optical splitters at various intermediate nodes. Through an integer linear programming formulation, we identify the minimum number of optical splitters that are required to monitor all SRLG failures in the network. Extensive simulations are used to demonstrate the effectiveness of the proposed monitoring technique.