Abstract
Affective services will become a research hotspot in artificial intelligence (AI) in the next decade. In this paper, a novel service paradigm combined with wireless communication in integrated satellite-terrestrial network (ISTN) is proposed. On this basis, an affective services computing offloading and transmission network (ASCTN) with a three-tier computation architecture is proposed, which is able to assist users to obtain affective computing services and regulate emotions. The optimization problem is investigated in the ASCTN, which is a discrete, non-linear, and non-convex problem with the limitation of computation ability of satellite and transmit power. Specifically, with the objective to minimize the cost utility related to latency and energy consumption, a joint affective services tasks computing offloading strategy, sub-channel, and power allocation algorithm based on dueling deep Q-network (Dueling-DQN) is proposed, which is in possession of better stability. The simulation results reveal the effectiveness of the optimization algorithm in terms of the cost utility in the ASCTN system.
- [1] . 2016. Channel estimation and detection in satellite communication systems. IEEE Transactions on Vehicular Technology 65, 12 (2016), 10173–10179. Google Scholar
Cross Ref
- [2] . 2016. Affective computing and sentiment analysis. IEEE Intelligent Systems 31, 2 (2016), 102–107. Google Scholar
Digital Library
- [3] . 2015. AIWAC: Affective interaction through wearable computing and cloud technology. IEEE Wireless Communications 22, 1 (2015), 20–27. Google Scholar
Digital Library
- [4] . 2020. System integration of terrestrial mobile communication and satellite communication—the trends, challenges and key technologies in B5G and 6G. China Communications 17, 12 (2020), 156–171. Google Scholar
Cross Ref
- [5] . 2015. Decentralized computation offloading game for mobile cloud computing. IEEE Transactions on Parallel and Distributed Systems 26, 4 (2015), 974–983. Google Scholar
Digital Library
- [6] . 2021. Robust design for NOMA-based multibeam LEO satellite Internet of Things. IEEE Internet of Things Journal 8, 3 (2021), 1959–1970. Google Scholar
Cross Ref
- [7] . 2021. Joint offloading and resource allocation for satellite assisted vehicle-to-vehicle communication. IEEE Systems Journal 15, 3 (2021), 3958–3969. Google Scholar
Cross Ref
- [8] . 2020. Power allocation in cache-aided NOMA systems: Optimization and deep reinforcement learning approaches. IEEE Transactions on Communications 68, 1 (2020), 630–644. Google Scholar
Cross Ref
- [9] . 2020. Cooperative computation offloading and resource allocation for blockchain-enabled mobile-edge computing: A deep reinforcement learning approach. IEEE Internet of Things Journal 7, 7 (2020), 6214–6228. Google Scholar
Cross Ref
- [10] . 2015. QoE-based SVC layer dropping in LTE networks using content-aware layer priorities. ACM Trans. Multimedia Comput. Commun. Appl. 12, 1, Article
7 (Aug. 2015), 23 pages. Google ScholarDigital Library
- [11] . 2017. Congestion control for network-aware telehaptic communication. ACM Trans. Multimedia Comput. Commun. Appl. 13, 2, Article
17 (Mar. 2017), 26 pages. Google ScholarDigital Library
- [12] . 2019. Affective content-aware adaptation scheme on QoE optimization of adaptive streaming over HTTP. ACM Trans. Multimedia Comput. Commun. Appl. 15, 3s, Article
100 (Dec. 2019), 18 pages. Google ScholarDigital Library
- [13] . 2020. Deep reinforcement learning for online computation offloading in wireless powered mobile-edge computing networks. IEEE Transactions on Mobile Computing 19, 11 (2020), 2581–2593. Google Scholar
Cross Ref
- [14] . 2019. Inferring emotions from large-scale internet voice data. IEEE Transactions on Multimedia 21, 7 (2019), 1853–1866. Google Scholar
Cross Ref
- [15] . 2020. Reinforcement learning based capacity management in multi-layer satellite networks. IEEE Transactions on Wireless Communications 19, 7 (2020), 4685–4699. Google Scholar
Digital Library
- [16] . 2020. Network utility maximization resource allocation for NOMA in satellite-based Internet of Things. IEEE Internet of Things Journal 7, 4 (2020), 3230–3242. Google Scholar
Cross Ref
- [17] . 2021. SDN enabled QoE and security framework for multimedia applications in 5G networks. ACM Trans. Multimedia Comput. Commun. Appl. 17, 2, Article
39 (Apr. 2021), 29 pages. Google ScholarDigital Library
- [18] . 2021. Deep dyna-reinforcement learning based on random access control in LEO satellite IoT networks. IEEE Internet of Things Journal (2021), 1–1. Google Scholar
Cross Ref
- [19] . 2020. Locally confined modality fusion network with a global perspective for multimodal human affective computing. IEEE Transactions on Multimedia 22, 1 (2020), 122–137. Google Scholar
Digital Library
- [20] . 2019. Deep Q-learning aided networking, caching, and computing resources allocation in software-defined satellite-terrestrial networks. IEEE Transactions on Vehicular Technology 68, 6 (2019), 5871–5883. Google Scholar
Cross Ref
- [21] . 2021. Computation offloading in LEO satellite networks with hybrid cloud and edge computing. IEEE Internet of Things Journal 8, 11 (2021), 9164–9176. Google Scholar
Cross Ref
- [22] . 2015. Deep reinforcement learning with double Q-learning. CoRR abs/1509.06461 (2015).
arXiv:1509.06461 http://arxiv.org/abs/1509.06461.Google Scholar - [23] . 2018. Image captioning with affective guiding and selective attention. ACM Trans. Multimedia Comput. Commun. Appl. 14, 3, Article
73 (Jul. 2018), 15 pages. Google ScholarDigital Library
- [24] . 2021. NOMA-enabled multi-beam satellite systems: Joint optimization to overcome offered-requested data mismatches. IEEE Transactions on Vehicular Technology 70, 1 (2021), 900–913. Google Scholar
Cross Ref
- [25] . 2021. Resource allocation for NOMA based space-terrestrial satellite networks. IEEE Transactions on Wireless Communications 20, 2 (2021), 1065–1075. Google Scholar
Digital Library
- [26] . 2019. Content-based video emotion tagging augmented by users’ multiple physiological responses. IEEE Transactions on Affective Computing 10, 2 (2019), 155–166. Google Scholar
Cross Ref
- [27] . 2015. Modeling emotion influence in image social networks. IEEE Transactions on Affective Computing 6, 3 (2015), 286–297. Google Scholar
Digital Library
- [28] . 2016. Dueling network architectures for deep reinforcement learning. In Proceedings of the 33rd International Conference on Machine Learning- Volume 48 (ICML’16). JMLR.org, 1995–2003.Google Scholar
- [29] . 2021. Exploiting transfer learning for emotion recognition under cloud-edge-client collaborations. IEEE Journal on Selected Areas in Communications 39, 2 (2021), 479–490. Google Scholar
Cross Ref
- [30] . 2020. Satellite-terrestrial integrated edge computing networks: Architecture, challenges, and open issues. IEEE Network 34, 3 (2020), 224–231. Google Scholar
Cross Ref
- [31] . 2021. EC-SAGINs: Edge computing-enhanced space-air-ground integrated networks for internet of vehicles. IEEE Internet of Things Journal (2021), 1–1. Google Scholar
Cross Ref
- [32] . 2018. Computation offloading with data caching enhancement for mobile edge computing. IEEE Transactions on Vehicular Technology 67, 11 (2018), 11098–11112. Google Scholar
Cross Ref
- [33] . 2009. A survey of affect recognition methods: Audio, visual, and spontaneous expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence 31, 1 (2009), 39–58. Google Scholar
Digital Library
- [34] . 2021. Energy efficient resource allocation in terahertz downlink NOMA systems. IEEE Transactions on Communications 69, 2 (2021), 1375–1384. Google Scholar
Cross Ref
- [35] . 2020. Deep learning based radio resource management in NOMA networks: User association, subchannel and power allocation. IEEE Transactions on Network Science and Engineering 7, 4 (2020), 2406–2415. Google Scholar
Cross Ref
- [36] . 2017. Multi-beam doppler beam sharpening approach for airborne forward-looking radar imaging. In 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 6142–6145. Google Scholar
Cross Ref
- [37] . 2019. Sea-surface target angular superresolution in forward-looking radar imaging based on maximum a posteriori algorithm. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12, 8 (2019), 2822–2834. Google Scholar
Cross Ref
- [38] . 2019. Satellite mobile edge computing: Improving QoS of high-speed satellite-terrestrial networks using edge computing techniques. IEEE Network 33, 1 (2019), 70–76. Google Scholar
Digital Library
- [39] . 2019. Affective computing for large-scale heterogeneous multimedia data: A survey. ACM Trans. Multimedia Comput. Commun. Appl. 15, 3s, Article
93 (Dec. 2019), 32 pages. Google ScholarDigital Library
- [40] . 2012. Generic optimization of linear precoding in multibeam satellite systems. IEEE Transactions on Wireless Communications 11, 6 (2012), 2308–2320. Google Scholar
Cross Ref
Index Terms
DRL based Joint Affective Services Computing and Resource Allocation in ISTN
Recommendations
Optimization-based resource allocation for software as a service application in cloud computing
Software as a service (SaaS) is a software that is developed and hosted by the SaaS vendor. SaaS cloud provides software as services to the users through the internet. To provide good quality of service for the user, the SaaS relies on the resources ...
SLA-Based Resource Allocation for Software as a Service Provider (SaaS) in Cloud Computing Environments
CCGRID '11: Proceedings of the 2011 11th IEEE/ACM International Symposium on Cluster, Cloud and Grid ComputingCloud computing has been considered as a solution for solving enterprise application distribution and configuration challenges in the traditional software sales model. Migrating from traditional software to Cloud enables on-going revenue for software ...
A tenant-based resource allocation model for scaling Software-as-a-Service applications over cloud computing infrastructures
Cloud computing provides on-demand access to computational resources which together with pay-per-use business models, enable application providers seamlessly scaling their services. Cloud computing infrastructures allow creating a variable number of ...






Comments