In sliced networks, the shared tenancy of slices requires adaptive admission control of data flows, based on measurements of network resources. In this paper, we investigate the design of measurement-based admission control schemes, deciding whether a new data flow can be admitted and in this case, on which slice. The objective is to devise a joint measurement and decision strategy that returns a correct decision (e.g., the least loaded slice) with a certain level of confidence while minimizing the measurement cost (the number of measurements made before committing to the decision). We study the design of such strategies for several natural admission criteria specifying what a correct decision is. For each of these criteria, using tools from best arm identification in bandits, we first derive an explicit information-theoretical lower bound on the cost of any algorithm returning the correct decision with fixed confidence. We then devise a joint measurement and decision strategy achieving this theoretical limit. We compare empirically the measurement costs of these strategies, and compare them both to the lower bounds as well as a naive measurement scheme. We find that our algorithm significantly outperforms the naive scheme (by a factor 2 - 8).

Transfer learning has been proposed as an approach for leveraging already learned knowledge in a new environment, especially when the amount of training data is limited. However, due to the dynamic nature of future networks and cloud infrastructures, a new environment may differ from the one the model is trained and transferred from. In this paper, we propose and evaluate an approach based on neural networks for heterogeneous transfer learning that addresses model transfer between environments with different input feature sets, which is a natural consequence of network and cloud re-orchestration. We quantify the transfer gain, and empirically show positive gain in a majority of cases. Further, we study the impact of neural-network architectures on the transfer gain, providing tradeoff insights for multiple cases. The evaluation of the approach is performed using data traces collected from a testbed that runs a Video-on-Demand service and a Key-Value Store under various load conditions.

Data-driven functions for operation and management require measurements and readings from distributed data sources for model training and prediction. While the number of candidate data sources can be very large, research has shown that it is often possible to reduce the number of data sources significantly while still allowing for accurate prediction. Consequently, there is potential to lower communication and computing resources needed to continuously extract, collect, and process this data. We demonstrate the operation of a novel online algorithm called OSFS, which sequentially processes the collected data and reduces the number of data sources for training prediction models. OSFS builds on two main ideas, namely (1) ranking the available data sources using (unsupervised) feature selection algorithms and (2) identifying stable feature sets that include only the top features. The demonstration shows the search space exploration, the iterative selection of feature sets, and the evaluation of the stability of these sets. The demonstration uses measurements collected from a KTH testbed, and the predictions relate to end-to-end KPIs for network services. 

When verifying that a communications network fulfills its specified performance, it is critical to note sudden shifts in network behavior as quickly as possible. Change point detection methods can be useful in this endeavor, but classical methods rely on measuring with a fixed measurement period, which can often be suboptimal in terms of measurement costs. In this paper, we extend the existing framework of change point detection with a notion of physical time. Instead of merely deciding when to stop, agents must now also decide at which future time to take the next measurement. Agents must now minimize the necessary number of measurements pre- and post-change, while maintaining a trade-off between post-change delay and false alarm rate. We establish, through this framework, the suboptimality of typical periodic measurements and propose a simple alternative, called crisis mode agents. We show analytically that crisis mode agents significantly outperform periodic measurements schemes. We further verify this in numerical evaluation, both on an array of synthetic change point detection problems as well as on the problem of detecting traffic load changes in a 5G test bed through end-to-end RTT measurements. 

While quickest change detection is a well-known problem within sequential analysis, only recently has advances been made in optimizing the pre-change measurement budget while maintaining low detection delay and high average run time to false alarm. Furthermore, all classical models rely on measurements being independent and identically distributed, which allows them to measure very frequently in short burst in order to reduce overall frequency. This assumption is not only unrealistic for some systems, but the high measurement frequency of classical methods cause the assumption to break down. In this paper, we extend the framework of measurement-efficient quickest change detection to the case where measurements are generated by finite-state, continuous time Markov chains pre- and post-change. Imposing the additional restriction that transitions are calculable for arbitrary measurement times, we show that this imposes important fundamental limits on detection delay and post-change measurement volume regardless of frequency. We also propose two heuristic measurement policies for this problem and analyze them, comparing them to fixed measurement intervals. Finally, we propose M/M/1 queues as an important special case for this problem and show the analyzed properties on this special example through simulation.

To maintain efficient scheduling for dynamic spectrum access problems, it is crucial to promptly detect changes in the statistical properties of spectrum occupancy. Compared to traditional change detection problems, this is complicated by the fact that measurements are not independent through time and can instead have Markovian dependencies. Moreover, classical change detection methods neglect the cost associated with measurements and do not consider the potential benefits of adapting the measurement schedule based on the observed state and the perceived likelihood of a change. This may result in high measurement overhead. In this paper, we study measurement-efficient change detection in Markovian models and demonstrate its applicability for spectrum access problems. In particular, we study problems with two states corresponding to spectrum occupancy, so called on-off models, and show important properties of these problems. For these problems, we establish fundamental limits that are imposed when the detection agent must maintain a sufficiently small false alarm rate. We also propose two classes of algorithms designed to adapt to different aspects of the problem. We analyze the behavior of these algorithms and evaluate them, using both synthetic data as well as real Wi-Fi spectrum data.