{"paper":{"title":"Sub-Band Full Duplex Resource Allocation: A Predictive Deep Reinforcement Learning Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"A hybrid Bi-LSTM and DDQN framework enables proactive sub-band allocation in SBFD systems by using traffic forecasts to guide real-time decisions.","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Abdulla P, Abhiram D, Aiswarya Rajan, Arin Shemeem, Vipindev Adat Vasudevan","submitted_at":"2026-05-14T04:03:16Z","abstract_excerpt":"This paper presents a predictive deep learning framework for dynamic sub-band allocation in Sub-Band Full Duplex (SBFD) systems, addressing the challenge of balancing uplink (UL) and downlink (DL) performance under highly dynamic traffic conditions. The key contribution lies in integrating a hybrid Bidirectional Long Short-Term Memory (Bi-LSTM) model for traffic forecasting with a Double Deep Q-Network (DDQN) for real-time resource allocation. Using both predicted traffic and current queue states, the proposed system enables proactive scheduling based on traffic demand. Evaluation results show"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The proposed predictive deep reinforcement learning framework significantly enhances the efficiency and adaptability of SBFD systems, making it a strong candidate for autonomous resource management in future 6G networks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Bi-LSTM predictions remain accurate on unseen real-world traffic patterns and the DDQN agent converges to stable policies without excessive overhead or instability in live deployments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Hybrid Bi-LSTM and DDQN framework predicts traffic and allocates resources to improve spectrum utilization and reduce queues in sub-band full duplex networks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A hybrid Bi-LSTM and DDQN framework enables proactive sub-band allocation in SBFD systems by using traffic forecasts to guide real-time decisions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a64b9c5e9ef3b5f2f9d86d26df4cb4125b438b8496ab0836256ee19d426df140"},"source":{"id":"2605.14339","kind":"arxiv","version":1},"verdict":{"id":"938a58e4-42c7-4be1-a957-727aead9bcb3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:57:24.223269Z","strongest_claim":"The proposed predictive deep reinforcement learning framework significantly enhances the efficiency and adaptability of SBFD systems, making it a strong candidate for autonomous resource management in future 6G networks.","one_line_summary":"Hybrid Bi-LSTM and DDQN framework predicts traffic and allocates resources to improve spectrum utilization and reduce queues in sub-band full duplex networks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Bi-LSTM predictions remain accurate on unseen real-world traffic patterns and the DDQN agent converges to stable policies without excessive overhead or instability in live deployments.","pith_extraction_headline":"A hybrid Bi-LSTM and DDQN framework enables proactive sub-band allocation in SBFD systems by using traffic forecasts to guide real-time decisions."},"references":{"count":15,"sample":[{"doi":"","year":2023,"title":"Augmented reality with mobility awareness in mobile edge computing over 6g network: A survey,","work_id":"eb78910f-f87c-4d0a-ba11-e3bc5869fd56","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Augmented and virtual reality services supported by 6g for improving smart cities,","work_id":"d378794d-7a66-4cfd-a123-6f1ccf149277","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"The road towards 6g: A comprehensive survey,","work_id":"49a38da4-50f3-4746-b850-69a84b8f456c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Performance analysis of subband full duplex for 5g-advanced and 6g networks through simulations and field tests,","work_id":"67bc6b95-5003-482f-8420-976e56c0442b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Subband full-duplex large-scale deployed network designs and tradeoffs,","work_id":"1aef72a1-d442-4e22-94b2-598579a0b10b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"f2bf06fb738642e985b8efa09ca11f8e631b709ba92d351a8aa462ee6b6cae83","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}