{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/132837"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/132837","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Short-term traffic forecasting for a smart satellite communications system","abstract":"Satellite communications systems are undergoing a modernization to efficient capacity allocation from a traditional \"bent pipe\" or static allocation. One challenge to address with a more precise usage of satellite resources is the change in user terminal traffic during a complete cycle of the system: collecting data, generating a constellation setting solution, transmitting the new solution to each satellite and executing changes to the satellite's parameters. As the system's cycle time grows the user's desired data rate changes causing an optimized solution based on an erroneous traffic model. This thesis proposes a comparison of single user models using a gradient boosting algorithm, and a multi-user model using Long- Short Term Memory neural networks (LSTM) or Gated Recurrent Unit neural networks (GRU) to forecast terminal traffic. Each algorithm was tuned using a two-stage design of experiments process consisting of a fractional screening design to identify impactful hyper-parameters and a central composite design to find optimal model settings. During a holdout period, the mean absolute percentage error using a 15-minute lag was 10.7% with a standard deviation of 2.6% over a month of forecasting. Networks using a GRU layer and tuned with Random Search had the best average performance with an error of 9.6% and standard deviation of 2.6%, outperforming the best found XG Boost models with an error of 9.9% and standard deviation of 3.5%.","abstract_html":"Satellite communications systems are undergoing a modernization to efficient capacity allocation from a traditional "bent pipe" or static allocation. One challenge to address with a more precise usage of satellite resources is the change in user terminal traffic during a complete cycle of the system: collecting data, generating a constellation setting solution, transmitting the new solution to each satellite and executing changes to the satellite's parameters. As the system's cycle time grows the user's desired data rate changes causing an optimized solution based on an erroneous traffic model. This thesis proposes a comparison of single user models using a gradient boosting algorithm, and a multi-user model using Long- Short Term Memory neural networks (LSTM) or Gated Recurrent Unit neural networks (GRU) to forecast terminal traffic. Each algorithm was tuned using a two-stage design of experiments process consisting of a fractional screening design to identify impactful hyper-parameters and a central composite design to find optimal model settings. During a holdout period, the mean absolute percentage error using a 15-minute lag was 10.7% with a standard deviation of 2.6% over a month of forecasting. Networks using a GRU layer and tuned with Random Search had the best average performance with an error of 9.6% and standard deviation of 2.6%, outperforming the best found XG Boost models with an error of 9.9% and standard deviation of 3.5%.","abstract_has_math":false,"creators":["Jones, Damon E., S.M. Massachusetts Institute of Technology."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Engineering and Management Program","school":null,"contributors":[],"advisors":["Edward F. Crawley."],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-22T22:21:11Z","subjects":["Engineering and Management Program.","System Design and Management Program."],"languages":["eng"],"rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/132837","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Edward F. Crawley."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Engineering and Management Program","SysDes"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Engineering and Management Program.","System Design and Management Program."]},{"key":"dc:creator","label":"Author","values":["Jones, Damon E., S.M. Massachusetts Institute of Technology."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-10-08T16:58:59Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-10-08T16:58:59Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Engineering and Management Program.","System Design and Management Program."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/132837"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, System Design and Management Program, May, 2020","Cataloged from the official version of thesis. Page 74 blank.","Includes bibliographical references (pages 71-73)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Satellite communications systems are undergoing a modernization to efficient capacity allocation from a traditional \"bent pipe\" or static allocation. One challenge to address with a more precise usage of satellite resources is the change in user terminal traffic during a complete cycle of the system: collecting data, generating a constellation setting solution, transmitting the new solution to each satellite and executing changes to the satellite's parameters. As the system's cycle time grows the user's desired data rate changes causing an optimized solution based on an erroneous traffic model. This thesis proposes a comparison of single user models using a gradient boosting algorithm, and a multi-user model using Long- Short Term Memory neural networks (LSTM) or Gated Recurrent Unit neural networks (GRU) to forecast terminal traffic. Each algorithm was tuned using a two-stage design of experiments process consisting of a fractional screening design to identify impactful hyper-parameters and a central composite design to find optimal model settings. During a holdout period, the mean absolute percentage error using a 15-minute lag was 10.7% with a standard deviation of 2.6% over a month of forecasting. Networks using a GRU layer and tuned with Random Search had the best average performance with an error of 9.6% and standard deviation of 2.6%, outperforming the best found XG Boost models with an error of 9.9% and standard deviation of 3.5%."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M. in Engineering and Management"]},{"key":"dc:title","label":"Title","values":["Short-term traffic forecasting for a smart satellite communications system"]}]}],"canonical_facts":{"dc:contributor.advisor":["Edward F. Crawley."],"dc:contributor.department":["Massachusetts Institute of Technology. Engineering and Management Program","SysDes"],"dc:contributor.other":["Massachusetts Institute of Technology. Engineering and Management Program.","System Design and Management Program."],"dc:creator":["Jones, Damon E., S.M. Massachusetts Institute of Technology."],"dc:date.accessioned":["2021-10-08T16:58:59Z"],"dc:date.available":["2021-10-08T16:58:59Z"],"dc:date.issued":["2020"],"dc:description":["Thesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, System Design and Management Program, May, 2020","Cataloged from the official version of thesis. Page 74 blank.","Includes bibliographical references (pages 71-73)."],"dc:description.abstract":["Satellite communications systems are undergoing a modernization to efficient capacity allocation from a traditional \"bent pipe\" or static allocation. One challenge to address with a more precise usage of satellite resources is the change in user terminal traffic during a complete cycle of the system: collecting data, generating a constellation setting solution, transmitting the new solution to each satellite and executing changes to the satellite's parameters. As the system's cycle time grows the user's desired data rate changes causing an optimized solution based on an erroneous traffic model. This thesis proposes a comparison of single user models using a gradient boosting algorithm, and a multi-user model using Long- Short Term Memory neural networks (LSTM) or Gated Recurrent Unit neural networks (GRU) to forecast terminal traffic. Each algorithm was tuned using a two-stage design of experiments process consisting of a fractional screening design to identify impactful hyper-parameters and a central composite design to find optimal model settings. During a holdout period, the mean absolute percentage error using a 15-minute lag was 10.7% with a standard deviation of 2.6% over a month of forecasting. Networks using a GRU layer and tuned with Random Search had the best average performance with an error of 9.6% and standard deviation of 2.6%, outperforming the best found XG Boost models with an error of 9.9% and standard deviation of 3.5%."],"dc:description.degree":["S.M. in Engineering and Management"],"dc:identifier.uri":["https://hdl.handle.net/1721.1/132837"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Engineering and Management Program.","System Design and Management Program."],"dc:title":["Short-term traffic forecasting for a smart satellite communications system"],"dc:type":["Thesis"],"thesis:degree_name":["Master"]},"updated_at":"2026-07-22T22:21:11Z"}