{"title":"Base Station Traffic Prediction based on STL-LSTM Networks","authors":"Qi Duan, Xin Wei, Yun Gao, Fang Zhou","doi":"10.1109/APCC.2018.8633565","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633565","url":null,"abstract":"Realizing accurate prediction of base station traffic and effectively controlling the entire network has become a major problem that needs to be solved urgently in the rapidly developing mobile communications environment. We propose a base station traffic prediction method based on STL-LSTM model, and introduce a Seasonal and Trend decomposition using Loess (STL) method based on robust local weighted regression to achieve smoothness. By this method, the trend, period, and noise of the base station data are separately decomposed to achieve efficient use of data. Then the paper introduces a long-term short-term memory network (LSTM), uses its back-propagation time training and overcomes the characteristics of the disappearance gradient to predict the processed data to achieve the prediction closest to the true value. The experimental results show that using this algorithm to predict the base station traffic has better performance comparing with the other algorithms. And the high-accuracy prediction can be realized effectively according to the dynamic transformation of the real state of the base station traffic.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126659627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comparison of Routing Protocols for Wireless Sensor Networks under Battery-Powered and Energy Harvesting Conditions","authors":"T. Ueda, A. Idoue, E. Utsunomiya","doi":"10.1109/APCC.2018.8633534","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633534","url":null,"abstract":"Energy consumption is the main theme of wireless sensor networks (WSNs). Since the maintenance of WSNs is hard, the lifespan of WSNs is finite. Energy harvesting (EH) is an appealing new assault to cope with this point, because EH does not need a power supply and can produce energy from the surrounding environment. However, the power source level of Energy Harvesting Wireless Sensor Networks (EH-WSNs) is variable against Battery Powered Wireless Sensor Networks (BP-WSNs). Consequently, each node does not know the energy condition of the neighboring nodes. In this paper, we assume the properties of an EH energy model, and compare the features of the MANETs(Mobile Ad hoc NETworks) routing protocols, AODV(Adhoc on Demand Distance Vector), DSR(Dynamic Source Routing) and ZRP(Zone Routing Protocol) with BP-WSNs and the features of the MANETs routing protocols with EH-WSNs under the same conditions. Consequently, the effects of energy harvesting on routing protocols, i.e. the effects of instability are quantitatively clarified under the same conditions for the first time.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115257808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Information-Theoretic Privacy-Accuracy-Secrecy Tradeoff under the Wire-Tap Channel","authors":"Dongli Dong, Qiang Wang, Y. Liu, Xiaoxuan Zhu","doi":"10.1109/APCC.2018.8633517","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633517","url":null,"abstract":"We investigate a general statistical inference framework based on the wire-tap channel to character the privacy threat. Based on this framework, data is distorted by a privacy-preserving mapping before being released, which can minimize the privacy leakage under distortion constraints. We demonstrate the optimal privacy-preserving mapping can be acquired by convex optimization. Moreover, considering a more practical situation, we provide the upper bounds of the effect on the true privacy leakage and corresponding distortions when the estimated probability distribution is used as an input to the optimization problem. These bounds declare that there is a little impact on privacy-accuracy-secrecy tradeoff if we estimate the joint probability well. Finally, we derive the corresponding lower bounds of the error probability in inferring private data from observations on account of the case where true distribution is known, and other case where there is only the estimate of the prior distribution.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"165 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122977325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Haotong Cao, Jinbo Chen, Yongan Guo, Hongbo Zhu, Longxiang Yang
{"title":"A Novel and One-Stage Embedding Algorithm for Mapping Virtual Networks","authors":"Haotong Cao, Jinbo Chen, Yongan Guo, Hongbo Zhu, Longxiang Yang","doi":"10.1109/APCC.2018.8633537","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633537","url":null,"abstract":"Virtual network embedding (VNE) refers to the resource allocation problem in network virtualization (NV). In the literature, researchers have proposed multiple VNE algorithms. These algorithms aim at embedding more and more requested virtual networks (VNs) onto the underlying networks and maximizing embedding revenues. Prior VNE algorithms mostly belong to the two-stage (separated node and link embedding) mapping algorithm category. Some other VNE algorithms embed each VN in one stage by using mixed integer linear programming (MILP) approach. There is a lack of one-stage heuristic algorithm, enabling to embed nodes and links in one mapping stage. In addition, each requested VN needs to be mapped in polynomial time so as to be promoted to future dynamic VN service application and real-time VNs embedding. Therefore, we propose a real-time and one-stage heuristic mapping algorithm (VNE-RTOS). Numerical simulations are conducted to validate that our VNE-RTOS earns more embedding revenues by approximately 3.4% over typical two-stage heuristic embedding algorithms (e.g. GRD-VNE) while achieving the same substrate resource utilization.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122104029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Impact of Cooperative Spectrum Sensing on the Cognitive Relay Network With A Direct Link","authors":"Xinying Li, Kai Liu, Danyang Wang, Haiyan Huang","doi":"10.1109/APCC.2018.8633509","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633509","url":null,"abstract":"This paper studies the performance of cognitive single-source and multi-relay cooperative communication, considering the two phases of cooperative spectrum sensing and cooperative communication, investigates the system’s reliability. In the phase of spectrum sensing, the cognitive secondary user’s (SU’s) source and relays sense the licensed primary user’s (PU’s) spectrum by the energy detection algorithm respectively, and get the final result by OR rule. Only when the final result of spectrum sensing indicates the presence of a spectrum hole, the cognitive SU can access the licensed frequency band. In the phase of cooperative communicating, for the two cases: (1) the cognitive SU detects the spectrum hole and the PU doesn’t access the frequency band; (2) the cognitive SU senses a spectrum hole but the licensed PU is using the frequency band, the relay selection strategy based on signal-to-interference-plus-noise ratio (SINR) is proposed respectively. In addition, this paper also investigates the system’s reliability with the SU destination adopting maximum ratio combining (MRC) and selection combining (SC), and analyze the performance with the number of relays in the system. It is shown that the increase of the cognitive SU relays can not only improve the performance of the spectrum sensing but also enhance the reliability of the cognitive network.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128283455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Signal Detection Method Using Goodness of Fit Test in Laplacian Noise","authors":"Rui Gao, Danyang Wang","doi":"10.1109/APCC.2018.8633573","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633573","url":null,"abstract":"Signal detection is a challenging problem for many systems especially in the presence of non-Gaussian noise. However, there are few detectors can work well in this case. Motivated by this, we propose a signal detection algorithm based on goodness of fit (GoF) test in Laplacian noise. Processed data rather than original observations were used in the new GoF test. The new GoF test makes full use of the stochastic properties of Laplacian noise and is evaluated by Monte Carlo simulations including detection performance and the influence of noise uncertainty. It is shown that the proposed signal detection method outperforms the energy detection and other GoF tests in Laplacian noise.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129424491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Downlink Channel Reconstruction for FDD 3D Multi-Antenna Systems","authors":"Qi Liu, Yu Han, Chao-Kai Wen, Shi Jin","doi":"10.1109/APCC.2018.8633535","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633535","url":null,"abstract":"This paper faces to the frequency-division-duplex (FDD) three-dimensional (3D) multi-antenna system and proposes a novel downlink channel reconstruction scheme which costs only a small amount of overhead. Uniform planar array (UPA) is employed at the base station (BS) to exploit the 3D space. In the uplink, we first estimate the frequency-independent parameters (delay, vertical and horizontal angles of arrival) by introducing and extending the Newtonized orthogonal matching pursuit (NOMP) algorithm. Both the orthogonal matching pursuit dictionary and the Newton refinement step (NRS) are redesigned according to the spatial propagation model of the signal for the NOMP algorithm. Then, we calculate the downlink gains and feed them back to the BS. The costs for downlink pilots and uplink feedback can be very small. Finally, downlink channel is reconstructed by using the frequency-independent parameters and the downlink gains. Simulation results show that using more antennas helps improve the mean-squared error (MSE) performance of the proposed scheme and can even achieve a better MSE performance than using the linear minimum mean-square error method.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132492084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qiucheng Shan, Jun Xiong, Dongtang Ma, Jiaxun Li, Tiantian Hu
{"title":"Distributed Multi-agent Q-learning for Anti-dynamic Jamming and Collision-avoidance Spectrum Access in Cognitive Radio System","authors":"Qiucheng Shan, Jun Xiong, Dongtang Ma, Jiaxun Li, Tiantian Hu","doi":"10.1109/APCC.2018.8633463","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633463","url":null,"abstract":"Dynamic malicious jamming of spectrum throughout the entire communication band is a major issue confronted by tactical communications. The conventional spectrum access scheme based on the central control node fails to satisfy the demand of tactical communications; it has a number of drawbacks including low battlefield survival rates, high computational complexity, large interactive communication overhead and slow reaction to dynamic jamming. In this paper, we propose a distributed multi-agent spectrum access strategy without the interactive communication overhead to evade dynamic jamming. Furthermore, A simplified Q reinforcement learning algorithm is applied to alleviate collisions of spectrum among nodes. Under the proposed strategy, all nodes can predict and evade dynamic jamming as well as avoid collisions of spectrum usage with other nodes. Simulation results verify the collision-avoidance learning algorithm and indicate that the proposed strategy outperforms the random spectrum access strategy.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133899864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Blind source separation based on NNAE-GCC","authors":"Shan Qin, Ting Jiang","doi":"10.1109/APCC.2018.8633448","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633448","url":null,"abstract":"The performance of blind source separation algorithm based on non-negative matrix factorization is good, but the complexity of algorithm limits to on-line separation. We propose an acoustic separation method based on Non-Negative Automatic Encoder (NNAE) and Generalized Cross Correlation (GCC), which reduces the complexity of the algorithm and provides the possibility of online separation. The time-frequency feature of speech is mapped to high-dimensional space via NNAE. The time delay of sources is calculated by GCC. According to the time delay information, the delay masking vector of each frame of speech is calculated in high-dimensional space. The NNAE-GCC combines high-dimensional feature and spatial position information to implement blind source separation. The complementary spectral and spatial information can be simultaneously exploited to improve the performance of speech separation. Experiments on simulation mixed speech and the real-world data, which is collected from a circular microphone array with a diameter of 4 cm, show the potential of the proposed algorithm for speech separation in reverberant environments. By replacing the NMF with NNAE, we found that the neural network is given a clear physical meaning.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133766123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Joint Uplink and Downlink Scheduling in HetNets with Wireless Self-backhaul","authors":"Qi Liu, Hui Tian, Gaofeng Nie, Hao Wu","doi":"10.1109/APCC.2018.8633480","DOIUrl":"https://doi.org/10.1109/APCC.2018.8633480","url":null,"abstract":"Wireless self-backhaul is an efficient solution to release the backhaul bottleneck of 5G Heterogeneous Networks (HetNets). This paper aims at jointly optimizing uplink and downlink scheduling to improve system throughput of time division duplex (TDD) HetNets. The problem that considers the uplink-downlink requirements and access-backhaul link coordination constraints is formulated, which has coupled variables and non-polynomial calculation complexity. Based on the structure property of the constructed problem, a joint uplink and downlink scheduling (JUDS) scheme is proposed to manage the complex interference and fully obtain the flexibility of wireless self-backhaul. In JUDS scheme, the original problem is decomposed into a transmission time slot (TTI) orchestration sub-problem and a sub-band scheduling sub-problem, both of which owns high efficient solutions. Simulation results address the effectiveness of JUDS scheme. On the one hand, the total system downlink throughput is significantly improved by JUDS scheme comparing with other existing scheduling schemes. On the other hand, The data rates of access links and backhaul links are well matched.","PeriodicalId":299723,"journal":{"name":"2018 24th Asia-Pacific Conference on Communications (APCC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115880387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}