یک الگوریتم خوشهبندی چندهدفه تطبیقی مبتنی بر حراج_پیشبینی برای ردیابی هدف متحرک در شبکههای حسگر بیسیم
محورهای موضوعی : مهندسی برق و کامپیوتررقیه علینژاد 1 , سپیده آدابی 2 * , آرش شريفي 3
1 - دانشگاه آزاد اسلامی واحد علوم و تحقیقات
2 - دانشگاه آزاد اسلامی واحد تهران شمال
3 - دانشگاه آزاد اسلامی واحد علوم و تحقیقات تهران
کلید واژه: شبکههای حسگر بیسیمردیابی هدف متحرکحراجپیشبینیشبکه عصبیخوشهبندی,
چکیده مقاله :
رديابي اهداف متحرك یکی از کاربردهای شبكههای حسگر است. در طراحی یک الگوریتم ردیابیِ هدف متحرک دو مسأله کاهش انرژی مصرفی و بهبود کیفیت ردیابی حایز اهمیت است. یکی از راهکارهای کاهش مصرف انرژی، تشکیل خوشه ردیاب است و دو چالش مهم در تشکیل خوشه ردیاب زمان و چگونگی تشکیل آن است. به منظور کاهش تعداد پیامهای مبادلهشده برای تشکیل خوشه ردیاب، یک مکانیزم حراج تطبیق داده میشود. پیشنهاد هر حسگر در حراج با هدف برقراری موازنهای مناسب میان طول عمر شبکه و دقت ردیابی به صورت پویا و مستقل ارائه میشود. از این گذشته، از آنجایی که خوشه ردیاب میبایست قبل از رسیدن هدف به ناحیه مورد نظر تشکیل شود (خصوصاً زمانی که سرعت هدف بالا است) جلوگیری از تأخیر در تشکیل خوشه ردیاب چالشی دیگر است. عدم توجه به چالش مذکور منجر به افزایش نرخ گمشدگی هدف و به تبع آن اتلاف انرژی میشود. برای غلبه بر این مشکل، پیشبینی موقعیت هدف در دو گام بعد توسط شبکه عصبی و تشکیل همزمان خوشههای ردیاب در یک و دو گام بعد را پیشنهاد میدهیم. نتایج حاصل از شبیهسازی نشاندهنده عملکرد مناسبتر الگوریتم پیشنهادی در مقایسه با الگوریتم AASA است.
One of the applications of sensor networks is to track moving target. In designing the algorithm for target tracking two issues are of importance: reduction of energy consumption and improvement of the tracking quality. One of the solutions for reduction of energy consumption is to form a tracking cluster. Two major challenges in formation of the tracking cluster are when and how it should be formed. To decrease the number of messages which are exchanged to form the tracking cluster an auction mechanism is adopted. The sensor’s bid in an auction is dynamically and independently determined with the aim of establishing an appropriate tradeoff between network lifetime and the accuracy of tracking. Furthermore, since the tracking cluster should be formed and activated before the target arrives to the concerned region (especially in high speed of target), avoidance from delay in formation of the tracking cluster is another challenge. Not addressing the mentioned challenge results in increased target missing rate and consequently energy loss. To overcome this challenge, it is proposed to predict the target’s position in the next two steps by using neural network and then, simultaneously form the tracking clusters in the next one and two steps. The results obtained from simulation indicate that the proposed algorithm outperforms AASA (Auction-based Adaptive Sensor Activation).
[1] J. Zheng, et al., "Auction-based adaptive sensor activation algorithm for target tracking in wireless sensor networks," Special Issue on Ubiquitous Computing and Future Communication Systems, vol. 39, pp. 88-99, Oct. 2014.
[2] J. Chen, C. Zhang, W. Liang, and H. Yu, "Auction based dynamic coalition for single target tracking in wireless sensor networks," in Proc. of the 6th World Congress on Intelligent Control and Automation, pp. 94-98, Dalian, China, 21-23 Jun. 2006.
[3] A. Alaybeyoglu, O. Dagdeviren, K. Erciyes, and A. Kantarci, "Performance evaluation of cluster-based target tracking protocols for wireless sensor networks," in Proc. of the 24th Int. Symp. on Computer and Information Sciences, pp. 357-362, Guzelyurt, Northern Cyprus, 14-16 Sept. 2009.
[4] F. Hamzeloei and M. K. Dermany, "Topsis based cluster head selection for wireless sensor network," Procedia Computer Science, vol. 98, pp. 8-15, 2016.
[5] M. Abdolkarimi, S. Adabi, and A. Sharifi, "A new multi-objective distributed fuzzy clustering algorithm for wireless sensor networks with mobile gateways," AEU-International J. of Electronics and Communications, vol. 89, pp. 92-104, May 2018.
[6] A. Liu and S. Zhao, "High-performance target tracking scheme with low prediction precision requirement in WSNs," International J. of Ad Hoc and Ubiquitous Computing, vol. 29, no. 4, pp. 270-289, 2018.
[7] M. Elhoseny and A. E. Hassanien, "Optimizing cluster head selection in WSN to prolong its existence," Dynamic Wireless Sensor Networks. Studies in Systems, Decision and Control, vol. 165, pp. 93-111, 2019.
[8] J. R. Parvin and C. Vasanthanayaki, "Particle swarm optimization-based energy efficient target tracking in wireless sensor network," Measurement, vol. 147, Article No.: 106882, 8 pp., Dec. 2019.
[9] T. Wang, et al., "Target localization and tracking based improved bayesian enhanced least-squares algorithm in wireless sensor networks," Computer Networks, vol. 167, Article No.: 106968, 11 Feb. 2020.
[10] C. Lersteau, A. Rossi, and M. Sevaux, "Minimum energy target tracking with coverage guarantee in wireless sensor networks," European J. of Operational Research, vol. 265, no. 3, pp. 882-894, 16 Mar. 2018.
[11] F. Delavernhe, C. Lersteau, A. Rossi, and M. Servaux, "Robust scheduling for target tracking using wireless sensor networks," Computers & Operations Research, vol. 116, Article No.: 104873, Apr. 2020
[12] E. Fayazi Barjini, D. Gharavian, and M. Shahgholian, "Target tracking in wireless sensor networks using NGEKF algorithm," J. of Ambient Intelligence and Humanized Computing, vol. 11, pp. 3417-3429, 2020.
[13] X. Lu, Y. Zhang, J. Liu, F. Yuan, and L. Cheng, "Mobile target tracking algorithm for wireless camera sensor networks with adjustable monitoring direction of nodes," International J. of Communication Systems, vol. 32, no. 10, Article No.: e3944, 10 Jul. 2019.
[14] H. Ahmadi, F. Viani, and R. Bouallegue, "An accurate prediction method for moving target localization and tracking in wireless sensor network," Ad Hoc Networks, vol. 70, pp. 14-22, Mar. 2018.
[15] A. Milan, S. H. Rezatofighi, and A. Dick, "Online multi-target tracking using recurrent neural networks," in Proc. of the 31st AAAI Conf. on Artificial Intelligence, AAAI’17, pp. 4225-4232, San Francisco, CA, USA, 4-9 Feb. 2017.
[16] J. Munjani and M. Joshi, "Target tracking in WSN using time delay neural network," J. of Machine Intelligence, vol. 2, no. 2, pp. 16-22, 2017.
[17] G. Han, J. Chao, C. Zhang, L. Shu, and Q. Li, "The impacts of mobility models on DV-hop based localization in mobile wireless sensor networks," J. of Network and Computer Applications, vol. 42, pp. 70-79, Jun. 2014.
[18] F. Zhen, Z. Zhao, D. Geng, Y. Xuan, L. Du, and C. Xunxue, "RSSI variability characterization and calibration method in wireless sensor network," in Proc. Int. Conf. on Information and Automation, Harbin, China, pp. 1532-1537, 20-23 Jun. 2010.