SavedAdd your journal

Journals / Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi / 2022 / Cilt: 5 Sayı: 3

An Evaluation of Autoencoder Neural Network Role in Iot Edge Computing

Nesnelerin İnterneti Uç Bilişimde Otomatik Kodlayıcı Sinir Ağının Rolüne İlişkin Bir Değerlendirme

Aygül Tekin Kakız(OSMANİYE KORKUT ATA ÜNİVERSİTESİ, UZAKTAN EĞİTİM UYGULAMA VE ARAŞTIRMA MERKEZİ)0000-0001-7372-0664
Ar. Gör. Muhammet Talha Kakız(OSMANİYE KORKUT ATA ÜNİVERSİTESİ)0000-0003-4928-6559
Ramazan Coban(ÇUKUROVA ÜNİVERSİTESİ)
Pages
1383–1392
Publication Date
2022-12-12
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The performance results of the proposals that have used autoencoder between edge and cloud layer are evaluated in terms of eliminating big data, network traffic and accuracy.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:With rapid increase in numbers of connected Internet of Things (IoT) devices, huge amount of data is generated and sent to Cloud Computing nodes to be stored and analysed.
📊
Key Findings & Data:Although the deficiencies of cloud computing decrease with edge computing, they are not completely eliminated because computation intensive tasks still should be sent from edge to cloud resources.
💡
Conclusion & Impact:The performance results of the proposals that have used autoencoder between edge and cloud layer are evaluated in terms of eliminating big data, network traffic and accuracy.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:nesnelerin interneti · uç bilişim · bulut bilişim

Abstract

With rapid increase in numbers of connected Internet of Things (IoT) devices, huge amount of data is generated and sent to Cloud Computing nodes to be stored and analysed. Cloud computing is an effective paradigm for storage and data analysis since IoT devices are restricted machines in terms of energy, computation power and storage. Despite the advantages of cloud computing, it causes network congestion and latency due to generally located at long distances. Besides, security and privacy issues are also drawbacks of the cloud. Edge Computing is a promising system to eliminate the flaws of cloud computing by getting computational power closer to data sources. Edge Computing has more computation power than IoTD but lower than cloud computing. Although the deficiencies of cloud computing decrease with edge computing, they are not completely eliminated because computation intensive tasks still should be sent from edge to cloud resources. Since Autoencoder is an unsupervised neural network technique that learns to efficiently encode/compress input data and learns to efficiently decode it as closer to the original input, it is an ideal candidate for reducing data traffic and latency in edge computing and cloud computing. Instead of sending all data to the cloud, the data of bottleneck hidden layers in which input data is encoded are sent from edge to cloud. The compressed data is decoded on the cloud to reconstruct the original input to be analysed and learnt. In this paper, we investigate the studies using AE in edge computing and their performance implications with respect to network traffic and delay. The performance results of the proposals that have used autoencoder between edge and cloud layer are evaluated in terms of eliminating big data, network traffic and accuracy.

Özet

İnternete bağlı IoT cihazların sayısındaki hızlı artış ile çok büyük miktarda veri üretilip, depolanmak ve analiz edilmek üzere Bulut Bilişim düğümlerine gönderilir. IoT cihazlar enerji, hesaplama gücü ve depolama açısından kısıtlı makineler olmasından dolayı, Bulut Bilişim depolama ve veri analizi için etkili bir paradigmadır. Bulut Bilişimin avantajlarına rağmen, genellikle uzun mesafelerde konumlandığı için trafik sıkışıklığı ve gecikmelere neden olur. Bunun yanında, güvenlik ve gizlilik meseleleri de Bulut Bilişimin dezavantajlarındandır. Uç bilişim hesaplama gücünü veri kaynağına yaklaştırarak Bulut Bilişimin kusurlarını bertaraf edecek umut verici bir sistemdir. Uç Bilişim, IoT cihazdan daha fazla; Bulut Bilişimden ise daha az hesaplama gücüne sahip. Uç Bilişim ile, Bulut Bilişimin olumsuzlukları azalmasına rağmen, tamamen ortadan kalkmaz. Çünkü, yoğun hesaplamalı görevlerin hala uçtan bulut kaynaklarına gönderilmesi gerekir. Autoencoder, girdi verisini etkili bir şekilde kodlar/sıkıştırır ve orijinal girdi verisine daha yakın olacak şekilde kodu çözmeyi öğrenen denetimsiz sinir ağı tekniğidir. Uç bilişim ve Bulut Bilişimdeki veri trafiği ve gecikmeyi azaltmak için ideal bir aday. Bütün veriyi buluta göndermek yerine, girdi verilerinin kodlandığı yer olan darboğaz gizli katman verileri uçtan buluta gönderilir. Sıkıştırılmış veri öğrenilmesi ve analiz edilmesi amacıyla orijinal inputa döndürmek için bulutta çözülür. Bu çalışmada, ağ trafiği ve gecikme açısından Autoencoder’ın uç bilişimde kullanan çalışmaları ve performans etkilerini araştırdık. Uç ve bulut katman arasında Autoencoder kullanan çalışmaların performans sonuçları büyük veri, ağ trafiği ve doğruluk açısından değerlendirildi.

🔖

Cite This Article

Kakız, A. T., Kakız, A. G. M. T., Coban, R. (2022). An Evaluation of Autoencoder Neural Network Role in Iot Edge Computing. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt: 5 Sayı: 3, 1383–1392. https://doi.org/10.47495/okufbed.1037534

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (24)

  1. AbdulsalamYa’u G., Job GK., Waziri SM., Jaafar B. SabonGari NA; Yakubu IZ, Deep learning for detecting ransomware in edge computing devices based on autoencoder classifier. 2019 4th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT), 13-14 December 2019, 240–243, India.
  2. Akyildiz IF., Vuran MC. Wireless sensor networks. 1st ed. John Wiley & Sons; 2010.
  3. Alpaydın E. Introduction to machine learning. 3rd ed. London:MIT Press; 2014.
  4. Al-Fuqaha A., Guizani M; Mohammadi M., Aledhari M., Ayyash M. Internet of things: A survey on enabling technologies, protocols, and applications. IEEE communications surveys & tutorials 2015; 17(4): 2347–2376.
  5. Feng Y., Liu Z., Chen J., Lv H., Wang J., Yuan J. Make the rocket intelligent at iot edge: Stepwise gan for anomaly detection of lre with multi-source fusion. IEEE Internet of Things Journal 2021.
  6. Ge M., Bangui H., Buhnova B. Big data for internet of things: a survey. Future generation computer systems 2018; 87: 601–614.
  7. Ghosh AM., Grolinger K. Deep learning: Edgecloud data analytics for iot. 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE), 5-8 May 2019, 1-7, Canada.
  8. Ghosh AM., Grolinger K. Edge-cloud computing for internet of things data analytics: Embedding intelligence in the edge with deep learning. IEEE Transactions on Industrial Informatics 2020; 17(3): 2191–2200.
  9. Goodfellow I., Bengio Y., Courville A. Deep learning. MIT press; 2016.
  10. Jiang F., Wang K., Dong L., Pan C., Yang K. Stacked autoencoder-based deep reinforcement learning for online resource scheduling in large-scale mec networks. IEEE Internet of Things Journal 2020; 7(10): 9278–9290.
  11. Khan WZ., Ahmed E., Hakak S., Yaqoob I., Ahmed A. Edge computing: A survey, Future Generation Computer Systems. 2019; 97: 219–235.
  12. Kim S., Park S., Lee SH., Yang T. Smart parking with learningaided user activity sensing based on edge computing. 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC), 9-12 January 2021, 1–2, Virtual Conference.
  13. Li R., Li Q., Zhou J., Jiang Y. Adriot: An edge-assisted anomaly detection framework against iot-based network attacks. IEEE Internet of Things Journal 2021.
  14. L’heureux A., Grolinger K., Elyamany HF., Capretz MA. Machine learning with big data: Challenges and approaches. IEEE Access 2017; 5: 7776–7797.
  15. Mach P., Becvar Z. Mobile edge computing: A survey on architecture and computation offloading. IEEE Communications Surveys & Tutorials 2017; 19(3): 1628–1656.
  16. Pan J., McElhannon J. Future edge cloud and edge computing for internet of things applications. IEEE Internet of Things Journal 2017; 5(1): 439–449.
  17. Satyanarayanan M., Bahl P., Caceres R., Davies N. The case for vm-based cloudlets in mobile computing. IEEE pervasive Computing 2009; 8(4): 14–23.
  18. Savic M., Lukic M., Danilovic D., Bodroski Z., Bajovi´c D., Mezei I., Vukobratovic D., Skrbic S., Jakoveti´c D. Deep learning anomaly detection for cellular iot with applications in smart logistics. IEEE Access 2021; 9: 59406–59419.
  19. Shi W., Dustdar S. The promise of edge computing. Computer 2016; 49(5): 78–81.
  20. Tzagkarakis C., Petroulakis N., Ioannidis S. Botnet attack detection at the iot edge based on sparse representation. 2019 Global IoT Summit (GIoTS), 17-21 June 2019, 1–6, Denmark.
  21. Ullah R., Ahmed SH., Kim BS. Information-centric networking with edge computing for iot: Research challenges and future directions. IEEE Access 2018; 6: 73465–73488.
  22. Wang F., Zhang M., Wang X., Ma X., Liu J. Deep learning for edge computing applications: A state-of-the-art survey. IEEE Access 2020; 8: 58322–58336.
  23. Zanella A., Bui N., Castellani A., Vangelista L., Zorzi M. Internetof things for smart cities. IEEE Internet of Things journal 2014; 1(1): 22–32.
  24. Challenges in real-world edge computing architecture, https://www.cisco.com/c/en/us/solutions/internet-of-things/iot-edge-computing-architecture.html. Cisco, Accessed:2021-08-15.