# An IoT-Oriented Offloading Method with Privacy Preservation for Cloudlet-Enabled Wireless Metropolitan Area Networks

^{1}

^{2}

^{3}

^{4}

^{5}

^{*}

## Abstract

**:**

## 1. Introduction

#### 1.1. Background

#### 1.2. Motivation

#### 1.3. Paper Contributions

- Construct a systematic model of the resource utilization, the energy consumption and the data transmission time of the cloudlets when offloading the IoT data to the cloudlets.
- Adopt the Dijkstra algorithm to calculate the shortest path between AP points in a WMAN in order to reduce the transmission time of data.
- Optimize the multi-objective problem model by the nondominated sorting differential evolution (NSDE) algorithm with privacy preservation considered, and finally the optimal offloading strategies are output.
- Conduct extensive experimental evaluations and comparison analysis to demonstrate the efficiency and effectiveness of the proposed method.

## 2. System Model and Problem Formulation

#### 2.1. Resource Model

_{1}, c

_{2}, …, c

_{N}} (each cloudlet has one host), which are deployed in the WMAN. There are M APs, denoted as A = {a

_{1}, a

_{2}, …, a

_{M}}. The cloudlets are connected through the APs, and M > N. P computing tasks that should be offloaded to the cloudlets for processing are donated as T = {t

_{1}, t

_{2}, …, t

_{P}}. The datasets of the computing tasks are donated as D = {d

_{1}, d

_{2}, …, d

_{P}}.

_{1}, x

_{2}, …, x

_{P}} be the offloading policy for the IoT data of the computing task set T, where x${}_{P\overline{I}}$$\text{}\in $C (p = {1, 2, …, P}) is the cloudlet that the computing task t

_{P}is offloaded to.

_{1}is connected to the cloudlet c

_{2}through four APs, named a

_{1}, a

_{2}, a

_{3}and a

_{4}. If the IoT data of the computing task t

_{1}has privacy conflicts with the other data, t

_{1}will be migrated to the cloudlet c

_{2}for processing, through a

_{1}, a

_{2}, a

_{3}and a

_{4}. In addition, the cloudlet c

_{1}is connected to the cloudlet c

_{3}through three APs, named a

_{1}, a

_{6}and a

_{7}or through APs of a

_{1}, a

_{5}, a

_{6}and a

_{7}.

#### 2.2. Resource Utilization Model

_{n}be the capacity of the n-th cloudlet c

_{n}and let u

_{p,n}be the requirements of the computing task t

_{P}.

#### 2.3. Data Transmission Model

_{p,q}be the number of halfway APs when the computing tasks are offloaded from the cloudlet c

_{p}to c

_{q}. Then, the transmission delay is calculated by

_{p}is the data scale of t

_{p}. Then, the average data transmission time T(X) can be calculated by

#### 2.4. Energy Consumption Model

#### 2.5. Data Privacy Preservation Model of the Comouting Tasks

## 3. An IoT-Oriented Offloading Method with Privacy Preservation

#### 3.1. Shortest Path Acquisition of APs in WMAN Based on Dijkstra Algorithm

#### 3.2. Optimization Problem Model by NSDE

_{n}will be assigned to M cloudlets for execution. Then, the length of this chromosome X

_{j}is N, and each gene will be a real value between 0 and M. However, in the calculation, each real value will be converted into an integer that represents the position of the execution cloudlet. For example, in Figure 2, the second task t

_{1}has a gene value of 3.2, and adopts the “down rounding” method, so the task t

_{1}will be assigned to cloudlet 3 for execution.

_{a}, X

_{b}and X

_{c}from the parent population P, and generating a mutated individual H

_{i}by combining the third individual X

_{a}with the difference vector of X

_{b}and X

_{c}, which is scaled according to the variation factor F. The crossover operation generates every gene V

_{i,j}of the offspring individual V

_{i}by crossing X

_{i,j}of the parent individual X

_{i}and H

_{i,j}of the mutated individual H

_{i}, where X

_{i,j}, H

_{i,j}and V

_{i,j}respectively represent the j-th gene of the parent individual X

_{i}, the mutated individual H

_{i}and the offspring individual V

_{i}.

_{i}. The multiple nondominated layers L

_{i}(i = 0, 1, 2, …) will be generated by the fast nondominated sorting approach, and the individuals in the nondominated layer with the lower nondominated level or the individuals with a better crowding distance in the same nondominated layer are preferentially populated into the parent population P of the next generation until the size of the population P is exactly equal to NP. The method of crowding distance calculation is described as follows:

_{j}= D

_{j}

^{U}+ D

_{j}

^{T}+ D

_{j}

^{E}= |U

^{j+}

^{1}− U

^{j}

^{−1}| + |T

^{j}

^{+1}− T

^{j}

^{−1}| + |E

^{j}

^{+1}− E

^{j}

^{−1}|,

_{j}represents the crowding distance, D

_{j}

^{U}, D

_{j}

^{T}and D

_{j}

^{E}represent the crowding distances of the average resource utilization, the data transmission time and the energy consumption, respectively. Besides, in (16), U

_{j}, T

_{j}and E

_{j}represent the objective function values of the average resource utilization, the data transmission time and the energy consumption, respectively, by the j-th offloading strategy X

_{j}.

Algorithm 1. nondominated sorting differential evolution based offloading strategy acquisition. |

Input: the size of the population NP, the number of the cloudlets M, the number of the iterations G, the mutation factor F, the crossover factor CROutput: the better solution set S01: g = 0 02: P = Initialization (NP, M) 03: while g < G do04: Q = Crossover and mutation(P, F, CR) 05: O = P + Q) 06: L = nondominated sort(O)) 07: P = Ø, Q = Ø, i = 0) 08: while size(P) + num (L_{i}) < NP do09: P += L _{i}10: i ++ 11: end while12: Calculate crowding distance (L _{i}) by (16)13: L _{i,j} = Sort (L_{i}) according to D_{j} from large to small14: j = 0 15: while size(P) < NP do16: P += L _{i,j}17: j ++ 18: end while19: g ++ 20: end while21: return the better solution set S |

## 4. Experimental Evaluation

#### 4.1. Simulation Setup

#### 4.2. Performance Evaluation of IOM

_{i}regarding the three objective functions mentioned above, respectively. $\Psi $

^{max}and $\Psi $

^{min}represent the maximum and minimum fitness values for the resource utilization. If $\Psi $

^{max}= $\Psi $

^{min}, let $\frac{\Psi \left(X\right)-{\Psi}^{\mathrm{min}}}{{\Psi}^{\mathrm{max}}-{\Psi}^{\mathrm{min}}}=1$. Analogously, T

^{max}and T

^{min}represent the maximum and minimum fitness for the data transmission time, and if T

^{max}= T

^{min}, let $\frac{{T}^{\mathrm{max}}-T\left(X\right)}{{T}^{\mathrm{max}}-{T}^{\mathrm{min}}}=1$; E

^{max}and E

^{min}represent the maximum and minimum fitness for the energy consumption, and if E

^{max}= E

^{min}, let $\frac{{E}^{\mathrm{max}}-E\left(X\right)}{{E}^{\mathrm{max}}-{E}^{\mathrm{min}}}=1$. Figure 3 shows the comparison of the utility value of the solutions generated by IOM with different task scales. It is illustrated that when the task scale is 100, 150 or 200, four solutions are generated by IOM. For the solutions generated by IOM, we attempt to obtain the most balanced data offloading strategy by evaluating the utility value given in (17). After statistics and analysis, the solution with the maximum utility value is considered as the most balanced strategy. For instance, in Figure 3a, the final selected strategy is solution 3 because it achieves the highest utility value.

#### 4.3. Comparison Analysis

## 5. Related Work

## 6. Conclusions and Future Work

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Baskaran, S.B.M.; Raja, G. Blind key distribution mechanism to secure wireless metropolitan area network. CSI Trans. ICT
**2016**, 4, 157–163. [Google Scholar] [CrossRef] - Zhou, B.; Dastjerdi, A.V.; Calheiros, R.N.; Srirama, S.N.; Buyya, R. mCloud: A context-aware offloading framework for heterogeneous mobile cloud. Trans. Serv. Comput.
**2015**, 10, 797–810. [Google Scholar] [CrossRef] - Karloff, H.; Subbaraman, R. Designing wireless metropolitan-area networks using mathematical optimization. In Proceedings of the Wireless Telecommunications Symposium (WTS), New York, NY, USA, 15–17 April 2015; pp. 1–8. [Google Scholar]
- Al-Janabi, S.; Al-Shourbaji, I.; Shojafar, M.; Abdelhag, M. Mobile Cloud Computing: Challenges and Future Research Directions. In Proceedings of the 10th International Conference on Developments in eSystems Engineering (DeSE), Paris, France, 14–16 June 2017; pp. 62–67. [Google Scholar]
- Zhaoqing, P.; Jianjun, L.; Yajuan, Z.; Wang, F.L. Adaptive fractional-pixel motion estimation skipped algorithm for efficient HEVC motion estimation. ACM Trans. Multimed. Comput. Commun. Appl.
**2018**, 14, 12–19. [Google Scholar] - Chen, X. Decentralized computation offloading game for mobile cloud computing. Trans. Parallel Distrib. Syst.
**2015**, 26, 974–983. [Google Scholar] [CrossRef] - Jara, A.J. Wearable internet: Powering personal devices with the internet of things capabilities. In Proceedings of the International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI), Beijing, China, 17–18 October 2014; pp. 1–7. [Google Scholar]
- Li, P.; Zhao, S.; Zhang, R. A cluster analysis selection strategy for supersaturated designs. Comput. Stat. Data Anal.
**2010**, 54, 1605–1612. [Google Scholar] [CrossRef] - Keng, D.; Koo, S.G.M. Spatial standards for Internet of Things. In Proceedings of the Conference on Internet of Things (iThings), Taipei, Taiwan, 1–3 September 2014; pp. 284–287. [Google Scholar]
- Tian, G.L.; Wang, M.; Song, L. Variable selection in the high-dimensional continuous generalized linear model with current status data. J. Appl. Stat.
**2014**, 41, 467–483. [Google Scholar] [CrossRef] [Green Version] - Li, S.; Zhang, Y. On-Line Scheduling on Parallel Machines to Minimize the Makespan. J. Syst. Sci. Complex.
**2016**, 29, 472–477. [Google Scholar] [CrossRef] - Wang, Y.; Sun, X.; Meng, F. On the conditional and partial trade credit policy with capital constraints: A Stackelberg model. Appl. Math. Model.
**2016**, 40, 1–18. [Google Scholar] [CrossRef] - Meng, S.; Wang, S.; Wu, T.; Li, D.; Huang, T.; Wu, X.; Xu, X.; Dou, W. An uncertainty-aware evolutionary scheduling method for cloud service provisioning. In Proceedings of the IEEE International Conference on Web Services (ICWS), San Francisco, CA, USA, 27 June–2 July 2016; pp. 506–513. [Google Scholar]
- Wang, G.; Huang, X.X.; Zhang, J. Levitin-Polyak well-posedness in generalized equilibrium problems with functional constraints. Pac. J. Optim.
**2010**, 6, 441–453. [Google Scholar] - Qu, B.; Zhao, J. Methods for Solving Generalized Nash Equilibrium. J. Appl. Math.
**2013**. [Google Scholar] [CrossRef] - Zhang, J.; Qu, B.; Xiu, N. Some projection-like methods for the generalized Nash equilibria. Comput. Optim. Appl.
**2010**, 45, 89–109. [Google Scholar] [CrossRef] - Li, Y.; Gao, W. Code offload with least context migration in the mobile cloud. In Proceedings of the Conference on Computer Communications (ICCC), Kowloon, Hong Kong, 26 April–1 May 2015; pp. 1876–1884. [Google Scholar]
- Soyata, T.; Muraleedharan, R.; Funai, C.; Kwon, M.; Heinzelman, W. Cloud-vision: Real-time face recognition using a mobile cloudlet-cloud acceleration architecture. In Proceedings of the IEEE Symposium on Computers and Communications (ISCC), Cappadocia, Turkey, 1–4 July 2012; pp. 59–66. [Google Scholar]
- Li, Y.; Anh, N.T.; Nooh, A.S.; Ra, K.; Jo, M. Dynamic Mobile Cloudlet Clustering for Fog Computing. In Proceedings of the International Conference on Electronics, Information, and Communication (CEIC), Honolulu, HI, USA, 24–27 January 2018; pp. 1–4. [Google Scholar]
- Shen, J.; Tan, H.-W.; Wang, J.; Wang, J.-W.; Lee, S.-Y. A novel routing protocol providing good transmission reliability in underwater sensor networks. J. Internet Technol.
**2015**, 16, 171–178. [Google Scholar] - Xiang, H.; Xu, X.; Zheng, H.; Li, S.; Wu, T.; Dou, W.; Yu, S. An adaptive cloudlet placement method for mobile applications over cloud. In Proceedings of the Global Communications Conference (GLOBECOM), Washington, DC, USA, 4–8 December 2016. [Google Scholar]
- Li, H.; Wang, S. Partial condition number for the equality constrained linear least squares problem. Calcolo
**2017**, 54, 1121–1146. [Google Scholar] [CrossRef] - Li, P.; Li, T.; Ye, H.; Li, J.; Chen, X.; Xiang, Y. Privacy-preserving machine learning with multiple data providers. Future Gener. Comput. Syst.
**2018**, 87, 341–350. [Google Scholar] [CrossRef] - He, K.; Chen, J.; Du, R.; Wu, Q.; Xue, G.; Zhang, X. Deypos: Deduplicatable dynamic proof of storage for multi-user environments. IEEE Trans. Comput.
**2016**, 65, 3631–3645. [Google Scholar] [CrossRef] - Namjoshi, J.; Gupte, A. Service oriented architecture for cloud based travel reservation software as a service. In Proceedings of the 2009 IEEE International Conference on Cloud Computing (ICCC), Bangalore, India, 21–25 September 2009; pp. 147–150. [Google Scholar]
- Xue, S.; Zhang, Y.; Xu, X.; Xing, G.; Xiang, H.; Ji, S. QET: A QoS-Based Energy-Aware Task Scheduling Method in Cloud Environment. Clust. Comput.
**2017**. [Google Scholar] [CrossRef] - Yang, J.; Xu, X.; Dou, W. A Task Scheduling Method for Energy-Performance Trade-off in Clouds. In Proceedings of the 18th International Conference on High Performance Computing and Communications (HPCC), Sydney, Australia, 12–14 December 2016; pp. 1029–1036. [Google Scholar]
- Su, M.; Zhang, L.; Wu, Y.; Chen, K.; Li, K. Systematic data placement optimization in multi-cloud storage for complex requirements. IEEE Trans. Comput.
**2016**, 65, 1964–1977. [Google Scholar] [CrossRef] - Jia, M.; Liang, W.; Xu, Z.; Huang, M.; Ma, Y. QoS-Aware Cloudlet Load Balancing in Wireless Metropolitan Area Networks. IEEE Trans. Cloud Comput.
**2018**. [Google Scholar] [CrossRef] - Jia, M.; Liang, W.; Xu, Z.; Huang, M. Cloudlet load balancing in wireless metropolitan area networks. In Proceedings of the Conference on Computer Communications (INFOCOM), San Francisco, CA, USA, 10–14 April 2016; pp. 1–9. [Google Scholar]
- Khan, A.M.; Freitag, F. On Edge Cloud Service Provision with Distributed Home Servers. In Proceedings of the IEEE International Conference on Cloud Computing Technology and Science (CloudCom), Hong Kong, China, 11–14 December 2017; pp. 223–226. [Google Scholar]
- Barbera, M.; Kosta, S.; Mei, A.; Stefa, J. To offload or not to offload? the bandwidth and energy costs of mobile cloud computing. In Proceedings of the IEEE International Conference on Computer Communications (INFOCOM), Turin, Italy, 14–19 April 2013; pp. 1285–1293. [Google Scholar]
- Zhang, Z.; Li, S. A Survey of Computational Offloading in Mobile Cloud Computing. In Proceedings of the IEEE International Conference on Mobile Cloud Computing, Services, and Engineering (MobileCloud), Oxford, UK, 29 March–1 April 2016; pp. 81–82. [Google Scholar]
- Wang, P.; Zhao, L. Some geometrical properties of convex level sets of minimal graph on 2-dimensional Riemannian manifolds. Nonlinear Anal.
**2016**, 130, 1–17. [Google Scholar] [CrossRef] - Wang, S.; Huang, L.; Hsu, C.-H.; Yang, F. Collaboration reputation for trustworthy Web service selection in social networks. J. Comput. Syst. Sci.
**2016**, 82, 130–143. [Google Scholar] [CrossRef] - Xu, Z.; Liang, W.; Xu, W.; Jia, M.; Guo, S. Capacitated cloudlet placements in wireless metropolitan area networks. In Proceedings of the IEEE International Conference on Local Computer Networks (LCN), Clearwater Beach, FL, USA, 26–29 October 2015; pp. 570–578. [Google Scholar]
- Hoang, D.T.; Niyato, D.; Wang, P. Optimal admission control policy for mobile cloud computing hotspot with cloudlet. In Proceedings of the Conference on Wireless Communications and Networking Conference (IWCNC), Shanghai, China, 1–4 April 2012; pp. 3145–3149. [Google Scholar]
- Whaiduzzaman, M.; Gani, A.; Naveed, A. Pefc: Performance enhancement framework for cloudlet in mobile cloud computing. In Proceedings of the Symposium on Robotics and Manufacturing Automation, Kuala Lumpur, Malaysia, 15–16 December 2014; pp. 224–229. [Google Scholar]
- Artail, A.; Frenn, K.; Safa, H.; Artail, H. A framework of mobile cloudlet centers based on the use of mobile devices as cloudlets. In Proceedings of the Conference on Advanced Information Networking and Applications (AINA), Gwangiu, Korea, 24–27 March 2015; pp. 777–784. [Google Scholar]
- Ciobanu, R.I.; Negru, C.; Pop, F.; Dobre, C. Drop computing: Ad-hoc dynamic collaborative computing. Future Gener. Comput. Syst.
**2017**. [Google Scholar] [CrossRef] - Mao, Y.; Zhang, J.; Letaief, K.B. Joint task offloading scheduling and transmit power allocation for mobile-edge computing systems. In Proceedings of the in Wireless Communications and Networking Conference (WCNC), San Francisco, CA, USA, 19–22 March 2017; pp. 1–6. [Google Scholar]
- Lian, S.; Duan, Y. Smoothing of the lower-order exact penalty function for inequality constrained optimization. J. Inequal. Appl.
**2016**, 2016, 185. [Google Scholar] [CrossRef] - Wu, H.; Ren, Y.; Hu, F. Continuous dependence property of BSDE with constraints. Appl. Math. Lett.
**2015**, 45, 41–46. [Google Scholar] [CrossRef] - Wang, C.; Ma, C.; Zhou, J. A new class of exact penalty functions and penalty algorithms. J. Glob. Optim.
**2014**, 58, 51–73. [Google Scholar] [CrossRef] - Fan, Q.; Ansari, N.; Sun, X. Energy driven avatar migration in green cloudlet networks. IEEE Commun. Lett.
**2017**, 21, 1601–1604. [Google Scholar] [CrossRef] - Wang, S.; Lei, T.; Zhang, L.; Hsu, C.-H.; Yang, F. Offloading Mobile Data Traffic for QoS-aware Service Provision in Vehicular Cyber-Physical Systems. Future Gener. Comput. Syst.
**2016**, 61, 118–127. [Google Scholar] [CrossRef] - Jia, M.; Cao, J.; Liang, W. Optimal cloudlet placement and user to cloudlet allocation in wireless metropolitan area networks. IEEE Trans. Cloud Comput.
**2017**, 5, 725–737. [Google Scholar] [CrossRef] - Satyanarayanan, M.; Simoens, P.; Xiao, Y.; Pillai, P.; Chen, Z.; Ha, K.; Hu, W.; Amos, B. Edge analytics in the internet of things. IEEE Perv. Comput.
**2015**, 2, 24–31. [Google Scholar] [CrossRef] - ARahman; Hassanain, E; Hossain, M.S. Towards a secure mobile edge computing framework for Hajj. IEEE Access
**2017**, 5, 11768–11781. [Google Scholar] - Chen, M.; Qian, Y.; Chen, J.; Hwang, K.; Mao, S.; Hu, L. Privacy protection and intrusion avoidance for cloudlet-based medical data sharing. IEEE Trans. Cloud Comput.
**2016**. [Google Scholar] [CrossRef] - Liu, B.; Qu, B.; Zheng, N. A Successive Projection Algorithm for Solving the Multiple-Sets Split Feasibility Problem. Numer. Funct. Anal. Optim.
**2014**, 35, 1459–1466. [Google Scholar] [CrossRef] - Cai, J.Q.; Li, H. An implicit degree condition for relative length of long paths and cycles in graphs. Acta Math. Appl. Sin.
**2016**, 32, 365–372. [Google Scholar] [CrossRef] - Li, L.; Meng, F.; Ju, P. Some new integral inequalities and their applications in studying the stability of nonlinear integro-differential equations with time delay. J. Math. Anal. Appl.
**2011**, 377, 853–862. [Google Scholar] [CrossRef]

**Figure 3.**Comparison of the utility value of the solutions generated with different task scales by IOM.

**Figure 4.**Comparison of the number of the employed cloudlets with different task scales by Benchmark and IOM.

**Figure 5.**Comparison of the average resource utilization of the cloudlets with different task scales by Benchmark and IOM.

**Figure 7.**Comparison of the different components of the energy consumption with different task scales by Benchmark and IOM.

Terms | Descriptions |
---|---|

C | The cloudlet collection |

A | The AP(Access Point) collection |

T | The computing task collection |

D | The dataset collection of the computing tasks |

X | The data offloading policy collection for T |

P | The number of computing tasks |

l_{n}(X) | The resource utilization rate of the cloudlet c_{n} |

σ(X) | The number of the occupied cloudlets |

ψ(X) | The average of l_{n}(X) |

TT(X) | The propagation delay time of the computing tasks |

T(X) | The average of propagation delay time |

β_{P}_{,n}(X) | The execution time of the task x_{p} in the cloudlet c_{n} |

ST(X) | The maximal execution time of the task in the cloudlet c_{n} |

${E}_{VM}^{idle}\left(X\right)$ | The energy consumption of the idle VMs (Virtual Machines) |

${E}_{VM}^{active}\left(X\right)$ | The energy consumption of the active VMs |

E_{c}(X) | The energy consumption of the cloudlets |

E(X) | The total energy consumption |

Parameter Description | Value |
---|---|

The total number of cloudlets | 50 |

The maximum number of VMs a cloudlet owns | 10 |

The transmission speed of AP | 540 M/s |

The transmission speed of the cloudlet | 1200 M/s |

The execution speed of the VMs | 2000 MHz |

The power rate of the active VMs | 50 W |

The power rate of the idle VMs | 30 W |

The power rate of the cloudlets | 300 W |

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Xu, Z.; Gu, R.; Huang, T.; Xiang, H.; Zhang, X.; Qi, L.; Xu, X.
An IoT-Oriented Offloading Method with Privacy Preservation for Cloudlet-Enabled Wireless Metropolitan Area Networks. *Sensors* **2018**, *18*, 3030.
https://doi.org/10.3390/s18093030

**AMA Style**

Xu Z, Gu R, Huang T, Xiang H, Zhang X, Qi L, Xu X.
An IoT-Oriented Offloading Method with Privacy Preservation for Cloudlet-Enabled Wireless Metropolitan Area Networks. *Sensors*. 2018; 18(9):3030.
https://doi.org/10.3390/s18093030

**Chicago/Turabian Style**

Xu, Zhanyang, Renhao Gu, Tao Huang, Haolong Xiang, Xuyun Zhang, Lianyong Qi, and Xiaolong Xu.
2018. "An IoT-Oriented Offloading Method with Privacy Preservation for Cloudlet-Enabled Wireless Metropolitan Area Networks" *Sensors* 18, no. 9: 3030.
https://doi.org/10.3390/s18093030