Edge-centric predictive analytics methodologies use real-time model caching to significantly reduce the communication overhead. We investigate an approach of using different regression techniques at the edge as caching models. Our methodology reports on an edge-centric mechanism to automatically decide when to update the parameters of the cached models to a central location (data center). Through experimentation, we showcase the trade off between accuracy and communication overhead and conclude that for all the experimented regression models, a lower percentage of the cached models should be sent to the data center to significantly decrease the communication overhead.
{"title":"In-network Predictive Analytics in Edge Computing","authors":"Stefanos Nikolaou, C. Anagnostopoulos, D. Pezaros","doi":"10.1109/WD.2019.8734267","DOIUrl":"https://doi.org/10.1109/WD.2019.8734267","url":null,"abstract":"Edge-centric predictive analytics methodologies use real-time model caching to significantly reduce the communication overhead. We investigate an approach of using different regression techniques at the edge as caching models. Our methodology reports on an edge-centric mechanism to automatically decide when to update the parameters of the cached models to a central location (data center). Through experimentation, we showcase the trade off between accuracy and communication overhead and conclude that for all the experimented regression models, a lower percentage of the cached models should be sent to the data center to significantly decrease the communication overhead.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122403402","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}
In this paper, a new multi-carrier candidate waveform for the future generation of mobile (5G) is introduced, explored and evaluated. The newly developed design of the Orthogonal Generalized Frequency division multiplexing (OGFDM) can improve the performance in terms of the channel capacity and Bit Error Rate (BER) for the wireless transmission of the multi-carrier system. In addition, compared to the most candidate waveform, Generalized Frequency Division Multiplexing (GFDM), the innovative multi-carrier OGFDM can double, boost and even maximize the capacity of wireless channel at the acceptable level of the BER. This is essentially achieved due to major adaptations have been made on the Filtration level, Oversampling level and Modulation level of the currently recommended GFDM. Thus, depending on the Digital Hilbert Filter (DHF), the presented solution can attain the orthogonality between the un-orthogonal filtered subcarriers of the multi-carrier GFDM technique. Moreover, by utilizing an adjustable oversampling factor, the examined system can stay reliable even in the worst conditions of the wireless channel. Furthermore, employing the adaptive bit loading instead of the fixed modulation format, the announced waveform can reach the maximum rate of transmission with the venial limit of error. The main parameters of each promoted level are precisely specified in accordance with the optimum system performance. Besides, the different levels of the multi-carrier OGFDM are presented in the physical layer (PHY) of a wireless electrical back-to-back transceiver system. A MATLAB simulation was introduced to evaluate the system performance (BER & channel capacity) in presence of the Additive White Gaussian Noise (AWGN).
{"title":"New Multi-Carrier Candidate Waveform For the 5G Physical Layer of Wireless Mobile Networks","authors":"Mohammad R. Kadhum","doi":"10.1109/WD.2019.8734205","DOIUrl":"https://doi.org/10.1109/WD.2019.8734205","url":null,"abstract":"In this paper, a new multi-carrier candidate waveform for the future generation of mobile (5G) is introduced, explored and evaluated. The newly developed design of the Orthogonal Generalized Frequency division multiplexing (OGFDM) can improve the performance in terms of the channel capacity and Bit Error Rate (BER) for the wireless transmission of the multi-carrier system. In addition, compared to the most candidate waveform, Generalized Frequency Division Multiplexing (GFDM), the innovative multi-carrier OGFDM can double, boost and even maximize the capacity of wireless channel at the acceptable level of the BER. This is essentially achieved due to major adaptations have been made on the Filtration level, Oversampling level and Modulation level of the currently recommended GFDM. Thus, depending on the Digital Hilbert Filter (DHF), the presented solution can attain the orthogonality between the un-orthogonal filtered subcarriers of the multi-carrier GFDM technique. Moreover, by utilizing an adjustable oversampling factor, the examined system can stay reliable even in the worst conditions of the wireless channel. Furthermore, employing the adaptive bit loading instead of the fixed modulation format, the announced waveform can reach the maximum rate of transmission with the venial limit of error. The main parameters of each promoted level are precisely specified in accordance with the optimum system performance. Besides, the different levels of the multi-carrier OGFDM are presented in the physical layer (PHY) of a wireless electrical back-to-back transceiver system. A MATLAB simulation was introduced to evaluate the system performance (BER & channel capacity) in presence of the Additive White Gaussian Noise (AWGN).","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123686094","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}
I. Comsa, Sijing Zhang, Mehmet Emin Aydin, P. Kuonen, R. Trestian, G. Ghinea
The problem of radio resource scheduling subject to fairness satisfaction is very challenging even in future radio access networks. Standard fairness criteria aim to find the best trade-off between overall throughput maximization and user fairness satisfaction under various types of network conditions. However, at the Radio Resource Management (RRM) level, the existing schedulers are rather static being unable to react according to the momentary networking conditions so that the user fairness measure is maximized all time. This paper proposes a dynamic scheduler framework able to parameterize the proportional fair scheduling rule at each Transmission Time Interval (TTI) to improve the user fairness. To deal with the framework complexity, the parameterization decisions are approximated by using the neural networks as non-linear functions. The actor-critic Reinforcement Learning (RL) algorithm is used to learn the best set of non-linear functions that approximate the best fairness parameters to be applied in each momentary state. Simulations results reveal that the proposed framework outperforms the existing fairness adaptation techniques as well as other types of RL-based schedulers.
{"title":"Enhancing User Fairness in OFDMA Radio Access Networks Through Machine Learning","authors":"I. Comsa, Sijing Zhang, Mehmet Emin Aydin, P. Kuonen, R. Trestian, G. Ghinea","doi":"10.1109/WD.2019.8734262","DOIUrl":"https://doi.org/10.1109/WD.2019.8734262","url":null,"abstract":"The problem of radio resource scheduling subject to fairness satisfaction is very challenging even in future radio access networks. Standard fairness criteria aim to find the best trade-off between overall throughput maximization and user fairness satisfaction under various types of network conditions. However, at the Radio Resource Management (RRM) level, the existing schedulers are rather static being unable to react according to the momentary networking conditions so that the user fairness measure is maximized all time. This paper proposes a dynamic scheduler framework able to parameterize the proportional fair scheduling rule at each Transmission Time Interval (TTI) to improve the user fairness. To deal with the framework complexity, the parameterization decisions are approximated by using the neural networks as non-linear functions. The actor-critic Reinforcement Learning (RL) algorithm is used to learn the best set of non-linear functions that approximate the best fairness parameters to be applied in each momentary state. Simulations results reveal that the proposed framework outperforms the existing fairness adaptation techniques as well as other types of RL-based schedulers.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115804681","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}
Ibrahim A. Alghamdi, C. Anagnostopoulos, D. Pezaros
Mobile Edge Computing application domains such as vehicular networks, unmanned aerial vehicles, data analytics tasks at the edge and augmented reality have recently emerged. Under such domains, while mobile nodes are moving and have certain tasks to be offloaded to Edge Servers, choosing an appropriate time and an ideally suited server to guarantee the quality of service can be challenging. We tackle the offloading decision making problem by adopting the principles of Optimal Stopping Theory to minimize the execution delay in a sequential decision manner. A performance evaluation is provided by using real data sets compared with the optimal solution. The results show that our approach significantly minimizes the execution delay for task execution and the results are very close to the optimal solution.
{"title":"Time-Optimized Task Offloading Decision Making in Mobile Edge Computing","authors":"Ibrahim A. Alghamdi, C. Anagnostopoulos, D. Pezaros","doi":"10.1109/WD.2019.8734210","DOIUrl":"https://doi.org/10.1109/WD.2019.8734210","url":null,"abstract":"Mobile Edge Computing application domains such as vehicular networks, unmanned aerial vehicles, data analytics tasks at the edge and augmented reality have recently emerged. Under such domains, while mobile nodes are moving and have certain tasks to be offloaded to Edge Servers, choosing an appropriate time and an ideally suited server to guarantee the quality of service can be challenging. We tackle the offloading decision making problem by adopting the principles of Optimal Stopping Theory to minimize the execution delay in a sequential decision manner. A performance evaluation is provided by using real data sets compared with the optimal solution. The results show that our approach significantly minimizes the execution delay for task execution and the results are very close to the optimal solution.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115167727","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}
Public wireless networks usually comprise of self-interested users who are reluctant to cooperate with other users of the network unless and until they are provided with some incentives. This paper presents a new incentive-based relay selection algorithm, which motivates the self-interested in-range mobile users to act as relays providing network access to the out-of-range users, thus extending the coverage range of a wireless network. The new Credit-based Relay Selection (CRS) algorithm uses Stackelberg game employing a credit-based incentive mechanism, providing instantaneous as well as long-term benefit to the selfish in-range users. In addition to this, the CRS algorithm takes into account both the achievable data rate at the out-of-range user and fair consumption of battery power of in-range user as the relay selection criteria. Simulation results presented in this paper show that when the CRS algorithm is used for relay selection, it is advantageous even for the self-interested in-range users to participate in the relaying process to earn some benefit to utilize it when they move outside the transmission range of access point and need to buy assistance from other users. The CRS algorithm also provides better data rate to the out-of-range users as well as fair utilization of battery power of the in-range users compared to a default algorithm which uses Signal to Interference and Noise Ratio (SINR) as relay selection criterion.
{"title":"Credit-Based Relay Selection Algorithm Using Stackelberg Game","authors":"Naumana Ayub, V. Rakocevic","doi":"10.1109/WD.2019.8734269","DOIUrl":"https://doi.org/10.1109/WD.2019.8734269","url":null,"abstract":"Public wireless networks usually comprise of self-interested users who are reluctant to cooperate with other users of the network unless and until they are provided with some incentives. This paper presents a new incentive-based relay selection algorithm, which motivates the self-interested in-range mobile users to act as relays providing network access to the out-of-range users, thus extending the coverage range of a wireless network. The new Credit-based Relay Selection (CRS) algorithm uses Stackelberg game employing a credit-based incentive mechanism, providing instantaneous as well as long-term benefit to the selfish in-range users. In addition to this, the CRS algorithm takes into account both the achievable data rate at the out-of-range user and fair consumption of battery power of in-range user as the relay selection criteria. Simulation results presented in this paper show that when the CRS algorithm is used for relay selection, it is advantageous even for the self-interested in-range users to participate in the relaying process to earn some benefit to utilize it when they move outside the transmission range of access point and need to buy assistance from other users. The CRS algorithm also provides better data rate to the out-of-range users as well as fair utilization of battery power of the in-range users compared to a default algorithm which uses Signal to Interference and Noise Ratio (SINR) as relay selection criterion.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132363809","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}
M. Leeser, Suranga Handagala, Mohamed Mohamed, Jieming Xu, M. Onabajo
Field Programmable Gate Arrays (FPGAs) are widely used in wireless networking transceivers, however they typically are designed to process one specific wireless protocol. Our research group is investigating how to make FPGA designs more versatile. In this paper, we present an FPGA design that can receive either Wi-Fi or LTE signals by determining which signal is being received, and then applying the appropriate processing. We initially receive all signals at a 30.72 MHz sampling rate, an underlying sampling rate for LTE. A unique matched filter is designed that allows us to detect the Wi-Fi preamble at this rate despite the fact that it is transmitted at 20MHz. Results show that we can successfully distinguish between the two signals and further decode received packets by switching to the appropriate sampling rate after the type of signal has been detected.
{"title":"An FPGA Design Technique to Receive Multiple Wireless Protocols with the Same RF Front End","authors":"M. Leeser, Suranga Handagala, Mohamed Mohamed, Jieming Xu, M. Onabajo","doi":"10.1109/WD.2019.8734199","DOIUrl":"https://doi.org/10.1109/WD.2019.8734199","url":null,"abstract":"Field Programmable Gate Arrays (FPGAs) are widely used in wireless networking transceivers, however they typically are designed to process one specific wireless protocol. Our research group is investigating how to make FPGA designs more versatile. In this paper, we present an FPGA design that can receive either Wi-Fi or LTE signals by determining which signal is being received, and then applying the appropriate processing. We initially receive all signals at a 30.72 MHz sampling rate, an underlying sampling rate for LTE. A unique matched filter is designed that allows us to detect the Wi-Fi preamble at this rate despite the fact that it is transmitted at 20MHz. Results show that we can successfully distinguish between the two signals and further decode received packets by switching to the appropriate sampling rate after the type of signal has been detected.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117228192","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}
Millimeter-wave (mm-Wave) frequency bands are a key technology enabler for the ultra-high data rates of 5G cellular networks, and it is fully expected that 5G smart phones will be equipped with mm-Wave network interfaces. Interestingly, millimeter transmissions have utility beyond communication; previously they been used extensively for short-range radar detection and ranging. We envisage a future in which each person carries a smart phone equipped with mm-Wave which can opportunistically scan the adjacent environment and share the results in a participatory manner to allow accurate 3D models to be constructed and maintained. Applications for such low-cost modelling are numerous and include navigating smart cities and buildings, as well as accident prevention in factories. In this article we provide a brief review of mm-Wave, its detection properties, and the basics of 3D scanning and modeling. We introduce a system architecture to enable participatory scanning based on mm-Wave and show results from experiments to demonstrate its feasibility. A variety of research challenges must be solved in order to realize our vision, and we expound on these with a view to stimulating research on this compelling opportunity.
{"title":"Participatory 3D Scanning and Modeling of Cities and Buildings Using 5G mm-Wave Smart Phones","authors":"H. Ajorloo, C. Sreenan","doi":"10.1109/WD.2019.8734226","DOIUrl":"https://doi.org/10.1109/WD.2019.8734226","url":null,"abstract":"Millimeter-wave (mm-Wave) frequency bands are a key technology enabler for the ultra-high data rates of 5G cellular networks, and it is fully expected that 5G smart phones will be equipped with mm-Wave network interfaces. Interestingly, millimeter transmissions have utility beyond communication; previously they been used extensively for short-range radar detection and ranging. We envisage a future in which each person carries a smart phone equipped with mm-Wave which can opportunistically scan the adjacent environment and share the results in a participatory manner to allow accurate 3D models to be constructed and maintained. Applications for such low-cost modelling are numerous and include navigating smart cities and buildings, as well as accident prevention in factories. In this article we provide a brief review of mm-Wave, its detection properties, and the basics of 3D scanning and modeling. We introduce a system architecture to enable participatory scanning based on mm-Wave and show results from experiments to demonstrate its feasibility. A variety of research challenges must be solved in order to realize our vision, and we expound on these with a view to stimulating research on this compelling opportunity.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133699170","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}
D. Z. Rodríguez, M. A. Ramírez, Leonardo Fernandes Bernardes, Gabriel Mittag, S. Möller
In current communication systems, forward Error Correction (FEC) codes are used to decrease the information losses in the transmission channel to improve the signal quality in the reception point. The speech quality is affected by many factors being packet losses one of the most important. Currently, there are different speech quality assessment methods; for planning purposes, E-model algorithm is the most representative. However, it does not consider wireless network characteristics and techniques. Based on this fact, the main contribution of this work is to adapt the wide-band (WB) E-model algorithm to be able to evaluate the impact of FEC codes on speech quality. For this purpose, a function named GFECx(Ms,SNR) is proposed that quantifies the quality gain reached by FEC codes at different wireless channel conditions. This function is inserted into Ie,eff,WB impairment factor of the WB E-model algorithm. Experimental results demonstrated that the proposed solution gets a high correlation with results obtained by ITU-T Rec. P.863, reaching an average PCC and RMSE of 0.990 and 2.629, respectively. Thus, the methodology introduced in this research makes it possible to estimate the speech quality when FEC codes are implemented in a communication system.
{"title":"Impact of FEC codes on speech communication quality using WB E-model algorithm","authors":"D. Z. Rodríguez, M. A. Ramírez, Leonardo Fernandes Bernardes, Gabriel Mittag, S. Möller","doi":"10.1109/WD.2019.8734270","DOIUrl":"https://doi.org/10.1109/WD.2019.8734270","url":null,"abstract":"In current communication systems, forward Error Correction (FEC) codes are used to decrease the information losses in the transmission channel to improve the signal quality in the reception point. The speech quality is affected by many factors being packet losses one of the most important. Currently, there are different speech quality assessment methods; for planning purposes, E-model algorithm is the most representative. However, it does not consider wireless network characteristics and techniques. Based on this fact, the main contribution of this work is to adapt the wide-band (WB) E-model algorithm to be able to evaluate the impact of FEC codes on speech quality. For this purpose, a function named GFECx(Ms,SNR) is proposed that quantifies the quality gain reached by FEC codes at different wireless channel conditions. This function is inserted into Ie,eff,WB impairment factor of the WB E-model algorithm. Experimental results demonstrated that the proposed solution gets a high correlation with results obtained by ITU-T Rec. P.863, reaching an average PCC and RMSE of 0.990 and 2.629, respectively. Thus, the methodology introduced in this research makes it possible to estimate the speech quality when FEC codes are implemented in a communication system.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121258798","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}
Networking technologies dedicated for the Internet of Things are different from the classical mobile networks in terms of architecture and applications. This new type of network is facing several challenges to satisfy specific user requirements. Sharing the communication medium between (hundreds of) thousands of connected nodes and one base station is one of these main requirements, hence the necessity to imagine new solutions, or to adapt existing ones, for medium access control. In this paper, we start by comparing two classical medium access control protocols, CSMA/CA and Aloha, in the context of Internet of Things dedicated networks. We continue by evaluating a specific adaptation of Aloha, already used in low-power wide area networks, where no acknowledgement messages are transmitted in the network. Finally, we apply the same concept to CSMA/CA, showing that this can bring a number of benefits. The results we obtain after a thorough simulation study show that the choice of the best protocol depends on many parameters (number of connected objects, traffic arrival rate, allowed retransmission number), as well as on the metric of interest (e.g. packet reception probability or energy consumption).
{"title":"Performance Evaluation of Channel Access Methods for Dedicated IoT Networks","authors":"Abderrahman Ben Khalifa, Razvan Stanica","doi":"10.1109/WD.2019.8734186","DOIUrl":"https://doi.org/10.1109/WD.2019.8734186","url":null,"abstract":"Networking technologies dedicated for the Internet of Things are different from the classical mobile networks in terms of architecture and applications. This new type of network is facing several challenges to satisfy specific user requirements. Sharing the communication medium between (hundreds of) thousands of connected nodes and one base station is one of these main requirements, hence the necessity to imagine new solutions, or to adapt existing ones, for medium access control. In this paper, we start by comparing two classical medium access control protocols, CSMA/CA and Aloha, in the context of Internet of Things dedicated networks. We continue by evaluating a specific adaptation of Aloha, already used in low-power wide area networks, where no acknowledgement messages are transmitted in the network. Finally, we apply the same concept to CSMA/CA, showing that this can bring a number of benefits. The results we obtain after a thorough simulation study show that the choice of the best protocol depends on many parameters (number of connected objects, traffic arrival rate, allowed retransmission number), as well as on the metric of interest (e.g. packet reception probability or energy consumption).","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123221632","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}
Hafiza Syeda Zainab Kazmi, N. Javaid, M. Imran, F. Outay
Transmission rate is one of the contributing factors in the performance of Wireless Sensor Networks (WSNs). Congested network causes reduced network response time, queuing delay and more packet loss. To address this issue, we have proposed a transmission rate control method. The current node in a WSN adjusts its transmission rate based on the traffic loading information gained from the downstream node. Multi classification is used to control the congestion using Support Vector Machine (SVM). In order to get less miss classification error, Differential Evolution (DE) and Grey Wolf Optimization (GWO) algorithms are used to tune the SVM parameters. The comparative analysis has shown that the proposed approaches DE–SVM and GWO-SVM are more proficient than the other classification techniques in terms of classification error.
{"title":"Congestion Control in Wireless Sensor Networks based on Support Vector Machine, Grey Wolf Optimization and Differential Evolution","authors":"Hafiza Syeda Zainab Kazmi, N. Javaid, M. Imran, F. Outay","doi":"10.1109/WD.2019.8734265","DOIUrl":"https://doi.org/10.1109/WD.2019.8734265","url":null,"abstract":"Transmission rate is one of the contributing factors in the performance of Wireless Sensor Networks (WSNs). Congested network causes reduced network response time, queuing delay and more packet loss. To address this issue, we have proposed a transmission rate control method. The current node in a WSN adjusts its transmission rate based on the traffic loading information gained from the downstream node. Multi classification is used to control the congestion using Support Vector Machine (SVM). In order to get less miss classification error, Differential Evolution (DE) and Grey Wolf Optimization (GWO) algorithms are used to tune the SVM parameters. The comparative analysis has shown that the proposed approaches DE–SVM and GWO-SVM are more proficient than the other classification techniques in terms of classification error.","PeriodicalId":432101,"journal":{"name":"2019 Wireless Days (WD)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128540930","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：