Resource Provisioning for Cloud-Assisted Body Area Network in a Smart Home Environment

Abstract:  

In recent years, Cloud-assisted Body Area Network (CABAN) technologies have made their entrance in the Smart healthcare field such as Smart home environment and play a significant role for healthcare data storage, processing, and efficient decision making. However, currently the CABAN paradigm in the healthcare domain is facing increasing difficulty to handle the huge amount of sensor data that the body sensor devices generate from diverse Smart home applications. Therefore, it is now challenging to timely storing, processing and analyzing of the sensor data in real time to maintain the Quality of Service (QoS) requirements of the caregivers or Smart home applications. QoS here is the capacity to support diverse Smart home applications in healthcare with different priorities, performance and resource requirements. Therefore, in this paper, we present a fast and robust cloud resource allocation model for body sensor devices to ensure QoS for Smart home healthcare applications. We develop the proposed resource allocation algorithm using Agent-Based Modeling (ABM) and ontology. There are few works, which consider ABM and ontology for resource allocation in CABAN platform. Moreover, we used an ABM tool called NetLogo to implement the proposed resource allocation model. The results from the implementation were compared with the results of existing algorithms and found to be promising.

EXISTING  SYSTEM:

Few studies have been conducted related to effective resource allocation to support heterogeneous body area network or Internet of Tings (IoT) tasks in CABAN system along with ensuring quality of services such as real-time processing, storing, sharing, prioritizing, visualizing, and analysis of monitored data as well as acquiring context-awareness. Resource allocation is challenging in a CABAN healthcare environment due to the diversity of context-aware environments, the range of physiological conditions and the dynamic nature of the resource constraint IoTs [23][24]. Moreover, the CABAN platform brings health-related media data like image, audio, video along with text data, which require strict QoS guarantee. It is cumbersome for a cloud provider to perform over commitment of VM resources for IoT services like pre-processing and prioritizing patients’ data, running complex physiological models to analyze the processed information under context, which may have different QoS requirements and unpredictable resource consumption.   The CABAN platform employs various IoT-based body sensors to collect comprehensive physiological information and uses gateways and the cloud to analyze and store the information and then send the analyzed data wirelessly to caregivers for further analysis and review [13-15]. Thus, CABAN can replace the process of having a health professional come by at regular intervals to check the patients’ vital signs at home, instead providing a continuous automated flow of information. In this way, it simultaneously improves the quality of care through constant attention and lowers the cost of care by eliminating the need for a caregiver to actively engage in data collection and analysis [16-18].

PROPOSED  SYSTEM:

In this paper, we present the development of a cloud resource allocation model for body sensor devices to ensure QoS in this framework, which has traditionally proven as NP-hard problem due to various constraints. Our goal is to provide the right resources (computing, storage, etc.) to the right persons at right time and at the right place. We proposed a fast and robust resource allocation algorithm by using Agent-Based Modeling (ABM) and ontology [20-22]. In recent years, Agent-based modeling is becoming an effective method to solve such complex problems. We combine ontology with ABM and show the relation between them. There are few works, which consider ABM and ontology for resource allocation in CABAN platform. Furthermore, we optimize the resource allocation model using Mixed Integer Linear Programming (MILP) to find the most suitable servers for VM allocation. The important agents of the proposed algorithm, the architecture of the proposed solution and the detailed flowchart of the proposed algorithm are also provided. The results from the implementation are compared to the results of existing algorithms and found to be promising. The stability analysis to the implementation exhibits the robustness of the algorithm and ABM. These results motivate future research of using ABM as a tool for solving complex problems within the CABAN framework.

 CONCLUSION:  

This paper mainly tackles the research challenges on how to efficiently manage and allocate cloud resources in accordance with the QoS requirement of pervasive healthcare services and applications in CABAN platform. QoS is a challenging requirement in CABAN healthcare scenario where the delay in treatment for critical patient can create a difference of life and death. To address the problem of cloud resource allocation in this complex framework, a fast and robust resource allocation algorithm is proposed by using Agent Based Modeling (ABM) and ontology. We combine ontology with ABM and show the relation between them. In order to evaluate the efficiency of the proposed solution, an analysis is also performed based on provided input dataset. The evaluation is performed by measuring the execution time of the algorithm that allocates the resources based on given input dataset. A comparative analysis of the proposed solution using agent-based modeling and other existing resource allocation tools, techniques and algorithm based on different theories has been provided. The results demonstrate that the complex problems can be solved using agent based modeling (ABM). The usability and practicality of ABMs has been proved by implementing the solution. In future, we will test the algorithm by considering more resources such as GPU and bandwidth in a real-world scenario.

REFERENCES:  

[1] Liu, L., Stroulia, E., Nikolaidis, I., Miguel-Cruz, A., & Rincon, A. R. (2016). Smart homes and home health monitoring technologies for older adults: A systematic review. International journal of medical informatics, 91, 44-59.

[2] Memon, M., Wagner, S. R., Pedersen, C. F., Beevi, F. H. A., & Hansen, F. O. (2014). Ambient Assisted Living Healthcare Frameworks, Platforms, Standards, and Quality Attributes. Sensors, 14(3), 4312-4341.

[3] Lopez, N. M., Ponce, S., Piccinini, D., Perez, E., & Roberti, M. (2016). From Hospital to Home Care: Creating a Domotic Environment for Elderly and Disabled People. IEEE pulse, 7(3), 38-41

[4] Han, J., Choi, C. S., Park, W. K., Lee, I., & Kim, S. H. (2014, January). Smart home energy management system including renewable energy based on ZigBee and PLC. In Consumer Electronics (ICCE), 2014 IEEE International Conference on (pp. 544-545). IEEE.

[5] Franco Cicirelli, Giancarlo Fortino, Andrea Giordano, Antonio Guerrieri, Giandomenico Spezzano, Andrea Vinci: On the Design of Smart Homes: A Framework for Activity Recognition in Home Environment. J. Medical Systems 40(9): 200:1-200:17 (2016)

[6] Kuang, Z. J., Hu, L., & Chen, F. Y. (2014). Analysis Markov Delay Control Strategy for Smart Home Systems. Applied Mechanics and Materials, 484, 413-417.

[7] Ghayvat, H., Mukhopadhyay, S. C., & Gui, X. (2015). Sensing Technologies for Intelligent Environments: A Review. In Intelligent Environmental Sensing (pp. 1-31). Springer International Publishing.

[8] Azimi, I., Rahmani, A. M., Liljeberg, P., & Tenhunen, H. (2016). Internet of things for remote elderly monitoring: a study from user-centered perspective. Journal of Ambient Intelligence and Humanized Computing, 1-17.

[9] Hassan, M.M., Lin, K., Yue, X. and Wan, J.(2016). A multimedia healthcare data sharing approach through cloud-based body area network. Future Generation Computer Systems. Volume 66, January 2017, Pages 48–58

[10] Lee, G. W., Na, S. H., Kim, K. H., & Huh, E. N. (2013). Cloud-based Smart Home System (CbSH) Architecture Design for Virtual Home Gateway and Cloud Interworking. In The 3rd International Conference on Convergence Technology 2013.