Page 1 of 7
European Journal of Business &
Social Sciences
Available at https://ejbss.org/
ISSN: 2235-767X
Volume 07 Issue 05
May 2019
Available online: https://ejbss.org/ P a g e | 99
Machine Learning As Tool In Network Troubleshooting
ShantKaushik,, Ashok Kumar
D.A.V. College, Ambala City, India
shantdavc@gmail.comashokdavc@gmail.com
Abstract
In the era of machine learning, described as ability of computers to learn without actually being
programmed for the fixture, there is one area where it can be used as troubleshooter. In this paper
an effort has been made to enhance the capabilities of Machine learning as a tool to work in the
process of network healing. Though the paper is more of survey study and proposed solutions yet
it can serve as basic platform to carry out further research on this topic.
I. Introduction:
In 1959, Arthur Samuel coined the term “Machine Learning”, as “the field of study that gives
computers the ability to learn without being explicitly programmed”. The four broad categories
of problems have been identified as; (a) clustering, (b) classification, (c) regression and (d)
rule extraction . In clustering problems, the objective is to group similar data together, while
increasing the gap between the groups. Whereas, in classification and regression problems, the
goal is to map a set of new input data to a set of discrete or continuous valued output,
respectively. Rule extraction problems are intrinsically different, as in this case the goal is to
identify statistical relationships in data. ML techniques have been applied to various problem
domains. A closely related domain consists of data analysis for large databases, called data
mining. Though, ML techniques can be applied to aid in data mining, the goal of data mining
problems is to critically and meticulously analyze data—its features, variables, invariants,
temporal granularity, probability distributions and their transformations. However, ML goes
beyond data mining to predict future events or sequence of events. Machine Learning (ML) has
been enjoying an unprecedented surge in applications that solve problems and enable automation
in diverse domains. Primarily, this is due to the explosion in the availability of data, significant
improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML
has been applied to various mundane and complex problems arising in network operation and
management. There are various surveys on ML for specific areas in networking or for specific
network technologies. In this way, readers will benefit from a comprehensive discussion on the
different learning paradigms and ML techniques applied to fundamental problems in networking
as;
(i) Traffic prediction, routing and classification,
(ii) Congestion control,
(iii)Resource and fault management,
Page 2 of 7
European Journal of Business &
Social Sciences
Available at https://ejbss.org/
ISSN: 2235-767X
Volume 07 Issue 05
May 2019
Available online: https://ejbss.org/ P a g e | 100
(iv)QoS and QoE management, and network security.
(v) To remove data clogs in Transmission lines
(vi)Remove congestion to achieve Packet delivery
(vii) Carrying out self healing
(viii) Trying to achieve maximum throughput
(ix) Reducing delay if possible
(x) Achieving smooth and stable packet delivery
Therefore, this is a timely contribution of the implications of ML for networking, that is pushing
the barriers of autonomic network operation and management.
II. Process Evolution :
Generally, ML is ideal for inferring solutions to problems that have a large representative
dataset. In this way, as illustrated in Fig. 1, ML techniques are designed to identify and exploit
hidden patterns in data for (i) describing the outcome as a grouping of data for clustering
problems, (ii) predicting the outcome of future events for classification and regression problems,
and (iii) evaluating the outcome of a sequence of data points for rule extraction problems.
Though, the figure illustrates data and outcome in a two-dimensional plane, the discussion holds
for multi-dimensional datasets and outcome functions. For instance, in the case of clustering, the
outcome can be a non-linear function in a hyperplane that discriminates between groups of data.
Networking problems can be formulated as one of these problems that can leverage ML. For
example, a classification problem in networking can be formulated to predict the kind of security
attack: Denial-of-Service (DoS), User-to-Root (U2R), Root-to-Local (R2L), or probing, given
network conditions[9]. Whereas, a regression problem can be formulated to predict of when a
future failure will transpire.
Fig 2: Problem categories a Clustering. b Classification. c Regression. d Rule extraction
Though there are different categories of problems that enjoy the benefits of ML, there is a
generic approach to building ML-based solutions. Figure 3 illustrates the key constituents in
Fig. 2
There was a problem loading this page. Retrying...
Page 3 of 7
European Journal of Business &
Social Sciences
Available at https://ejbss.org/
ISSN: 2235-767X
Volume 07 Issue 05
May 2019
Available online: https://ejbss.org/ P a g e | 101
designing ML-based solutions for networking. Data collection pertains to gathering, generating
and, or defining the set of data and the set of classes of interest. Feature engineering is used to
reduce dimensionality in data and identify discriminating features that reduce computational
overhead and increase accuracy. Finally, ML techniques carefully analyze the complex inter- and
intra-relationships in data and learn a model for the outcome.
Fig. 3 :constituents of ML-based solutions
For instance, consider an example of Gold values over time, as illustrated in Fig. 2c. Naïvely, a
linear regression model, shown as a best-fit line through the historical data, can facilitate in
predicting future values of Gold. Therefore, once the ML model is built, it can be deployed to
deduce outcomes from new data. However, the outcomes are periodically validated, since they
can drift over time, known as concept drifting. This can be used as an indicator for incremental
learning and re-training of the ML model. There are four learning paradigms in
ML, supervised, unsupervised, semi-supervisedand reinforcement learning. These paradigms
influence data collection, feature engineering, and establishing ground truth. Recall, the objective
is to infer an outcome, given some dataset. The dataset used in constructing the ML model is
often denoted as training data and labels are associated with training data if the user is aware of
the description of the data. The outcome is often perceived as the identification of membership to
a class of interest.
III Motivation for the Goal: The process has been directed to achieve the target of networking
troubleshooting using Machine learning. ML techniques require representative data, possibly without
Fig. 3
There was a problem loading this page. Retrying...
