{"id":{"repo_id":"sask","oai_identifier":"oai:harvest.usask.ca:10388/15549"},"canonical_url":"https://search.dev.ndltd.org/etd/sask/oai:harvest.usask.ca:10388/15549","repository":{"repo_id":"sask","name":"University of Saskatchewan","base_url":"https://harvest.usask.ca/server/oai/request"},"display":{"title":"WAVELET-BASED NETWORK TRAFFIC MODELING","abstract":"Ever since its birth, networking has experienced phenomenal growth. This phenomenal growth in terms of traffic volume, bandwidth requirements, network topologies and protocols, medium of communication, and network applications, is constantly changing the nature of network traffic, thus motivating the need for flexible and efficient mathematical models to describe network traffic. Some early traffic models assumed that network packet arrival process was Poisson. Later, the self-similar or monofractal nature of network traffic was discovered and to capture this long range dependence nature, the Norros traffic model was proposed. Recently, multifractal characteristics of network traffic have been discovered and wavelet-based models have been proposed to capture these characteristics. Before adopting wavelet models, their strengths and weaknesses have to be studied. The wavelet models require more parameters (2 + log2N parameters, where N is the number of data points in the modeled trace) than the Norros traffic model (3 parameters). Hence, it is also essential to establish the adequacy or inadequacy of the Norros model for characterizing multifractal traffic, and to understand how (or if) multifractal traffic behaves differently from monofractal traffic on a (simulated) network. In this thesis work, the inadequacy of the Norros traffic model for characterizing multifractal traffic is established. Synthetic traffic generated by different wavelet-based models are compared, and among the proposed multifractal traffic models, the multifractal wavelet model (MWM) is shown to be well suited for modeling empirical traffic traces. Simulation studies are used to show that multifractal traffic behaves differently from monofractal traffic on a network, as well as how it differs and why.","abstract_html":"Ever since its birth, networking has experienced phenomenal growth. This phenomenal growth in terms of traffic volume, bandwidth requirements, network topologies and protocols, medium of communication, and network applications, is constantly changing the nature of network traffic, thus motivating the need for flexible and efficient mathematical models to describe network traffic. Some early traffic models assumed that network packet arrival process was Poisson. Later, the self-similar or monofractal nature of network traffic was discovered and to capture this long range dependence nature, the Norros traffic model was proposed. Recently, multifractal characteristics of network traffic have been discovered and wavelet-based models have been proposed to capture these characteristics. Before adopting wavelet models, their strengths and weaknesses have to be studied. The wavelet models require more parameters (2 + log2N parameters, where N is the number of data points in the modeled trace) than the Norros traffic model (3 parameters). Hence, it is also essential to establish the adequacy or inadequacy of the Norros model for characterizing multifractal traffic, and to understand how (or if) multifractal traffic behaves differently from monofractal traffic on a (simulated) network. In this thesis work, the inadequacy of the Norros traffic model for characterizing multifractal traffic is established. Synthetic traffic generated by different wavelet-based models are compared, and among the proposed multifractal traffic models, the multifractal wavelet model (MWM) is shown to be well suited for modeling empirical traffic traces. Simulation studies are used to show that multifractal traffic behaves differently from monofractal traffic on a network, as well as how it differs and why.","abstract_has_math":false,"creators":["Balakrishnan, Ram"],"institution":"University of Saskatchewan","degree_name":"Master of Science (M.Sc.)","degree_level":"Masters","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Williamson, Carey"],"committee_chairs":[],"committee_members":["McCrosky, Carl","Grassman, Winifried","Bolton, Ronald"],"year":2000,"date_issued":"2000","date_published":"2000","updated_at":"2026-07-24T04:27:04Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10388/15549","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Williamson, Carey"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["McCrosky, Carl","Grassman, Winifried","Bolton, Ronald"]},{"key":"dc:creator","label":"Author","values":["Balakrishnan, Ram"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-04-01T22:46:21Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-04-01T22:46:21Z"]},{"key":"dc:date.issued","label":"Date","values":["2000"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (M.Sc.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Saskatchewan"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10388/15549"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Ever since its birth, networking has experienced phenomenal growth. This phenomenal growth in terms of traffic volume, bandwidth requirements, network topologies and protocols, medium of communication, and network applications, is constantly changing the nature of network traffic, thus motivating the need for flexible and efficient mathematical models to describe network traffic. Some early traffic models assumed that network packet arrival process was Poisson. Later, the self-similar or monofractal nature of network traffic was discovered and to capture this long range dependence nature, the Norros traffic model was proposed. Recently, multifractal characteristics of network traffic have been discovered and wavelet-based models have been proposed to capture these characteristics. Before adopting wavelet models, their strengths and weaknesses have to be studied. The wavelet models require more parameters (2 + log2N parameters, where N is the number of data points in the modeled trace) than the Norros traffic model (3 parameters). Hence, it is also essential to establish the adequacy or inadequacy of the Norros model for characterizing multifractal traffic, and to understand how (or if) multifractal traffic behaves differently from monofractal traffic on a (simulated) network. In this thesis work, the inadequacy of the Norros traffic model for characterizing multifractal traffic is established. Synthetic traffic generated by different wavelet-based models are compared, and among the proposed multifractal traffic models, the multifractal wavelet model (MWM) is shown to be well suited for modeling empirical traffic traces. Simulation studies are used to show that multifractal traffic behaves differently from monofractal traffic on a network, as well as how it differs and why."]},{"key":"dc:title","label":"Title","values":["WAVELET-BASED NETWORK TRAFFIC MODELING"]}]}],"canonical_facts":{"dc:contributor.advisor":["Williamson, Carey"],"dc:contributor.committeemember":["McCrosky, Carl","Grassman, Winifried","Bolton, Ronald"],"dc:creator":["Balakrishnan, Ram"],"dc:date.accessioned":["2024-04-01T22:46:21Z"],"dc:date.available":["2024-04-01T22:46:21Z"],"dc:date.issued":["2000"],"dc:description.abstract":["Ever since its birth, networking has experienced phenomenal growth. This phenomenal growth in terms of traffic volume, bandwidth requirements, network topologies and protocols, medium of communication, and network applications, is constantly changing the nature of network traffic, thus motivating the need for flexible and efficient mathematical models to describe network traffic. Some early traffic models assumed that network packet arrival process was Poisson. Later, the self-similar or monofractal nature of network traffic was discovered and to capture this long range dependence nature, the Norros traffic model was proposed. Recently, multifractal characteristics of network traffic have been discovered and wavelet-based models have been proposed to capture these characteristics. Before adopting wavelet models, their strengths and weaknesses have to be studied. The wavelet models require more parameters (2 + log2N parameters, where N is the number of data points in the modeled trace) than the Norros traffic model (3 parameters). Hence, it is also essential to establish the adequacy or inadequacy of the Norros model for characterizing multifractal traffic, and to understand how (or if) multifractal traffic behaves differently from monofractal traffic on a (simulated) network. In this thesis work, the inadequacy of the Norros traffic model for characterizing multifractal traffic is established. Synthetic traffic generated by different wavelet-based models are compared, and among the proposed multifractal traffic models, the multifractal wavelet model (MWM) is shown to be well suited for modeling empirical traffic traces. Simulation studies are used to show that multifractal traffic behaves differently from monofractal traffic on a network, as well as how it differs and why."],"dc:identifier.uri":["https://hdl.handle.net/10388/15549"],"dc:title":["WAVELET-BASED NETWORK TRAFFIC MODELING"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science (M.Sc.)"],"thesis:institution_name":["University of Saskatchewan"]},"updated_at":"2026-07-24T04:27:04Z"}