Supervised and Semi-Supervised Learning for Failure Identification in Microwave Networks

Musumeci, Francesco; Magni, Luca; Ayoub, Omran; Rubino, Roberto; Capacchione, Massimiliano; Rigamonti, Gabriele; Milano, Michele; Passera, Claudio; Tornatore, Massimo

doi:10.1109/tnsm.2020.3039938

Cited by 16 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We consider three different ML algorithms, namely, Artificial Neural Network (ANN), Random Forest (RF) and Extreme Gradient Boosting (XGB) for failure-cause identification. In particular, ANN and RF were adopted in our previous work [1], where details on hyperparameter selection can be found. Similarly, also for XGB algorithm we tested different combinations of hyperparameters and used the classifier with highest classification accuracy.…”

Section: B Supervised ML Modelsmentioning

confidence: 99%

“…RQ3: Can we determine why the model systematically misclassifies instances of one class as instances of another particular class? We address RQ3 by analyzing and comparing contributions of features towards 1) the true label and 2) the predicted wrong label using LIME 1 . In particular, we consider an observation with Low Margin as true label that was classified as Deep Fading, shown in Figure 5(a) and 5(b), respectively.…”

Section: B Xai-assisted Failure-cause Identificationmentioning

confidence: 99%

“…Automated failure-cause identification allows operators to reduce service unavailability by repairing failures much more rapidly than when relying on time-consuming manual analysis of failure logs. In our previous work [1], we modeled the problem of failure-cause identification in microwave networks as a classification problem and proposed supervised ML algorithms that were able to discriminate with high accuracy among different failure-causes. Based on the ML model decision, network operators can timely take the most appropriate countermeasure to repair a failure, which may, e.g., consist of an on-site intervention vs. a remote equipment configuration.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Using Explainable Artificial Intelligence for Failure Identification in Microwave Networks

Ayoub

Musumeci

Ezzeddine

et al. 2022

2022 25th Conference on Innovation in Clouds, Internet and Networks (ICIN)

View full text Add to dashboard Cite

Artificial Intelligence (AI) has demonstrated superhuman capabilities in solving a significant number of tasks, leading to widespread industrial adoption. For in-field networkmanagement application, AI-based solutions, however, have often risen skepticism among practitioners as their internal reasoning is not exposed and their decisions cannot be easily explained, preventing humans from trusting and even understanding them. To address this shortcoming, a new area in AI, called Explainable AI (XAI), is attracting the attention of both academic and industrial researchers. XAI is concerned with explaining and interpreting the internal reasoning and the outcome of AI-based models to achieve more trustable and practical deployment. In this work, we investigate the application of XAI for automated failure-cause identification in microwave networks. We first show how existing supervised ML algorithms can be used to solve the problem of failure-cause identification, achieving an accuracy around 94%. Then, we explore the application of wellknown XAI frameworks (such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME)) to address important practical questions rising during the actual deployment of automated failure-cause identification in microwave networks. These questions, if answered, allow for a deeper understanding of the behavior of the ML algorithm adopted. Precisely, we exploit XAI to understand the main reasons leading to ML algorithm's decisions and to explain why the model makes identification errors over specific instances.

show abstract

Section: B Supervised ML Modelsmentioning

confidence: 99%

Section: B Xai-assisted Failure-cause Identificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Using Explainable Artificial Intelligence for Failure Identification in Microwave Networks

Ayoub

Musumeci

Ezzeddine

et al. 2022

2022 25th Conference on Innovation in Clouds, Internet and Networks (ICIN)

View full text Add to dashboard Cite

show abstract

“…When the data is available, the following step is to choose which learning technique is best suited to the data's labeled or unlabeled nature. Supervised learning is defined by its use of labeled datasets for classification or regression problems [76]. Given the unlabeled nature of the crowdsourced data, we believe that unsupervised clustering assisted by real network data can reveal insights into the highest traffic density area.…”

Section: Clustering For Network Planningmentioning

confidence: 99%

Unsupervised Clustering for 5G Network Planning Assisted by Real Data

et al. 2022

View full text Add to dashboard Cite

The fifth-generation (5G) of networks is being deployed to provide a wide range of new services and to manage the accelerated traffic load of the existing networks. In the present-day networks, data has become more noteworthy than ever to infer about the traffic load and existing network infrastructure to minimize the cost of new 5G deployments. Identifying the region of highest traffic density in megabyte (MB) per km 2 has an important implication in minimizing the cost per bit for the mobile network operators (MNOs). In this study, we propose a base station (BS) clustering framework based on unsupervised learning to identify the target area known as the highest traffic cluster (HTC) for 5G deployments. We propose a novel approach assisted by real data to determine the appropriate number of clusters k and to identify the HTC. The algorithm, named as NetClustering, determines the HTC and appropriate value of k by fulfilling MNO's requirements on the highest traffic density MB/km 2 and the target deployment area in km 2 . To compare the appropriate value of k and other performance parameters, we use the Elbow heuristic as a benchmark. The simulation results show that the proposed algorithm fulfills the MNO's requirements on the target deployment area in km 2 and highest traffic density MB/km 2 with significant cost savings and achieves higher network utilization compared to the Elbow heuristic. In brief, the proposed algorithm provides a more meaningful interpretation of the underlying data in the context of clustering performed for network planning.

show abstract

“…[5] investigates the problem of microwave link failure detection using a Long/Short-Term Memory (LSTM)based feature fusion network. In our previous work [6], we tackle the problem of failure-cause identification in microwave networks in a semi-supervised fashion, and in Ref. [7] we exploit explainable artificial intelligence to explain ML-based models for failure-cause identification.…”

Section: Related Workmentioning

confidence: 99%

Federated-Learning-Assisted Failure-Cause Identification in Microwave Networks

Tandel

Ayoub

Musumecil

et al. 2022

2022 12th International Workshop on Resilient Networks Design and Modeling (RNDM)

View full text Add to dashboard Cite

Machine Learning (ML) adoption for automated failure management is becoming pervasive in today's communication networks. However, ML-based failure management typically requires that monitoring data is exchanged between network devices, where data is collected, and centralized locations, e.g., servers in data centers, where data is processed. ML algorithms in this centralized location are then trained to learn mappings between collected data and desired outputs, e.g., whether a failure exists, its cause, location, etc. This paradigm poses several challenges to network operators in terms of privacy as well as in terms of computational and communication resource usage, as a massive amount of sensible failure data is transmitted over the network. To overcome such limitations, Federated Learning (FL) can be adopted, which consists of training multiple distributed ML models at multiple decentralized locations (called "clients") using a limited amount of locally-collected data, and of sharing these trained models to a centralized location (called "server"), where these models are aggregated and shared again with clients. FL reduces data exchange between clients and a server and improves algorithms' performance thanks to sharing knowledge among different domains (i.e., clients), leveraging different sources of local information in a collaborative environment. In this paper, we focus on applying FL to perform failure-cause identification in microwave networks. The problem is modeled as a multi-class ML classification problem with six pre-defined failure causes. Specifically, using real failure data from an operational microwave network composed of more than 10000 microwave links, we emulate a multi-operator scenario in which one operator has partial knowledge of failure causes during the training phase. Thanks to knowledge sharing, numerical results show that FL achieves up to 72% precision in identifying an unknown particular class concerning traditional ML (non-FL) approaches where training is performed without knowledge sharing.

show abstract

Supervised and Semi-Supervised Learning for Failure Identification in Microwave Networks

Cited by 16 publications

References 14 publications

On Using Explainable Artificial Intelligence for Failure Identification in Microwave Networks

On Using Explainable Artificial Intelligence for Failure Identification in Microwave Networks

Unsupervised Clustering for 5G Network Planning Assisted by Real Data

Federated-Learning-Assisted Failure-Cause Identification in Microwave Networks

Contact Info

Product

Resources

About