[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119978-en":3,"doc-seo-119978-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119978,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Approaching Globally Optimal Energy Efficiency in Interference Networks via Machine Learning - A Machine Learning Approach","This work presents an unsupervised machine learning framework for optimizing energy efficiency in multi-cell wireless interference networks. The energy-efficiency maximization is a non-convex problem with a globally hard-to-find optimum, motivating a low-complexity alternative to both simple suboptimal heuristics and computationally intensive optimal methods. The proposal introduces a novel stochastic-action objective and a permutation-equivariant NN architecture (SINRnet) for power allocation. Results show energy efficiency close to the branch-and-bound global optimum and improved over successive convex approximation with reasonable training and efficient deployment.","Approaching Globally Optimal Energy Efficiency in Interference Networks via Machine Learning  \nBile Peng, Member, IEEE, Karl-Ludwig Besser, Member, IEEE, Ramprasad Raghunath, Student Member, IEEE, and  \nEduard A. Jorswieck, Fellow, IEEE  \narXiv :2212 . 12329v2 [ ee ss . SP] 14 Dec 2023  \nAbstract—This work presents a machine learning approach to optimize the energy efficiency (EE) in a multi-cell wireless network. This optimization problem is non-convex and its global optimum is difficult to find. In the literature, either simple but suboptimal approaches or optimal methods with high complexity are proposed. In contrast, we propose an unsupervised machine learning framework to approach the global optimum. While the neural network (NN) training takes moderate time, application with the trained model requires very low computational complexity. In particular, we introduce a novel objective function based on stochastic actions to solve the non-convex optimization problem. Besides, we design a dedicated NN architecture SINRnet for the power allocation problems in the interference channel that is permutation-equivariant. We encode our domain knowledge into the NN design and shed light into the black box of machine learning. Training and testing results show that the proposed method without supervision and with reasonable computational effort achieves an EE close to the global optimum found by the branch-and-bound algorithm and outperform the successive convex approximation (SCA) algorithm. Hence, the proposed approach balances between computational complexity and performance.  \nIndex Terms—Energy efficiency, non-convex optimization, machine learning, permutation-equivariance, reparameterization trick.  \nI. INTRODUCTION  \nTransmit power control belongs to the most fundamental problems in research on cellular mobile networks [1] and it isan important measure to optimize objectives such as weighted sum-rate [2], energy efficiency (EE) [3] and fairness [4] . These problems share some significant similarities, among which the non-convexity due to the fractional nature of the signal-to-interference-noise ratio (SINR) expression is a major difficulty, because multiple local optima could exist and convex optimization techniques are not applicable.  \nThis paper focuses on the EE optimization since the energy consumption is a key performance indicator of green communication in the fifth-generation (5G) communication  \nB. Peng, R. Raghunath and E. A. Jorswieck are with the Department of Information Theory and Communication Systems, TU Braunschweig, Schleinitzstr. 22, 38112 Braunschweig, Germany (e-mail: {b.peng, r.raghunath, [e.jorswieck}@tu-braunschweig.de](e.jorswieck}@tu-braunschweig.de)). K.-L. Besser was with the Institute for Communications Technology, Technische Universität Braunschweig, 38106 Braunschweig, Germany, and is now with the Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544, USA (email: [kb1717@princeton.edu](kb1717@princeton.edu)).  \nThe work is supported by the Federal Ministry of Education and Research Germany (BMBF) as part of the 6G Research and Innovation Cluster 6G-RIC under Grant 16KISK031 .  \nThis paper is published on IEEE Transactions on Wireless Communications (DOI: 10 . 1109/TWC.2023.3269770) .  \nand beyond. According to the next generation mobile networks (NGMN) alliance 5G white paper [5], the EE is required tobe improved by a factor of 2000 compared to current wireless networks. Among different techniques, transmit power control is an important approach to improve the EE in the air interface. On the other hand, given the similarities of the above-mentioned power control problems in cellular networks and the fact that the EE maximization problem with multiple users is particularly difficult [6], the proposed solution is expected to have good generalizability to other power control problems.  \nIn the literature, multiple globally optimal but complicated methods are prop","cbCaibLa5aehVYNd","https://ap.wps.com/l/cbCaibLa5aehVYNd","pdf",1658352,1,15,"English","en",105,"# Introduction\n# Related Work on Energy Efficiency Optimization\n## Fractional Programming and Branch-and-Bound\n## Successive Convex Approximation and Other Approximations\n## Learning-Based Approaches","[{\"question\":\"Why is global energy-efficiency optimization difficult in interference networks?\",\"answer\":\"The energy-efficiency objective is non-convex and the SINR fractional structure can produce multiple local optima, making convex optimization techniques inapplicable.\"},{\"question\":\"What does the proposed framework use to approach the global optimum?\",\"answer\":\"An unsupervised machine learning framework with a stochastic-action-based objective to handle the non-convex optimization, plus the SINRnet neural architecture for power allocation.\"},{\"question\":\"How do the proposed results compare with existing methods?\",\"answer\":\"The trained model achieves energy efficiency close to the branch-and-bound global optimum and outperforms successive convex approximation (SCA) while balancing computational complexity and performance.\"}]","Approaching Globally Optimal Energy Efficiency in Interference Networks via Machine Learning - A Machine Learning Approach | PDF",1785727410,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"approaching-globally-optimal-energy-efficiency-in-interference-networks-via-machine-learning-a-machine-learning-approach","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/approaching-globally-optimal-energy-efficiency-in-interference-networks-via-machine-learning-a-machine-learning-approach/119978/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is global energy-efficiency optimization difficult in interference networks?","Question",{"text":75,"@type":76},"The energy-efficiency objective is non-convex and the SINR fractional structure can produce multiple local optima, making convex optimization techniques inapplicable.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the proposed framework use to approach the global optimum?",{"text":80,"@type":76},"An unsupervised machine learning framework with a stochastic-action-based objective to handle the non-convex optimization, plus the SINRnet neural architecture for power allocation.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the proposed results compare with existing methods?",{"text":84,"@type":76},"The trained model achieves energy efficiency close to the branch-and-bound global optimum and outperforms successive convex approximation (SCA) while balancing computational complexity and performance.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]