Programming Improvement for Iota based Sheltered and Economical BSN

Presentation Transcript

Programming Development for Atom based Safe and Sustainable BSN IMPACT LAB Project Report on " Safe, Secure and Sustainable Body Area Networks utilizing Intel Atom " subsidized by Intel

Impact Lab Research Goal Environmentally Aware (physical), Performance mindful (digital), Criticality Aware, Safe and Secure Cyber-Physical Systems Body-Area Sensor Networks Objectives Minimize vitality utilization Minimize wellbeing dangers (wellbeing) Ensure security and protection Allow complex applications Approach Infuse vitality mindfulness Introduce high calculation AADL displaying Taxi Cab Scheduling Objectives Compute ideal course with targets Minimize fuel utilization Evaluate arrangements Approach Design proactive, spatio - fleeting calendars AADL demonstrating Data Centers Objectives Minimize Energy Consumption Maintain Performance Approach Integrated Management Infuse Proactive Spatio - Temporal Scheduling AADL Modeling

Project Goal Body Sensor Networks (BSNs) – system of restorative gadgets on human body are little scale digital physical framework Critical foundations – utilized as a part of medicinal applications Require to bolster life sparing applications Involvement of human clients require BSNs to be sheltered (lessen therapeutic risks) and reasonable (give consistent operation) Complex application prerequisites (particularly security conventions) request effective processors in BSN hubs Atom is utilized as the BSN hub processor to give required computational capacities However, higher power scattering of Atom, hampers the protected and economical operation of BSN hubs Software Design of Computationally skilled Safe and Sustainable Atom based BSN

Traditional Body Sensor Network Salient Features Computationally unfit arrangement of hubs Heterogeneous equipment and programming setup Constrained in vitality – battery worked No vitality searching Present

Application necessities Monitoring and Feedback Onlin e identification of solidifying of step [1] in Parkinson's patients from on-body sensors Feedback through on-body actuators Continuous Monitoring Seamless 24 hrs therapeutic observing [2] Requirements Response inside a little time window Fast Computation of windowed FFT and related flag handling Requirements Increased lifetime of the sensors Battery less non-meddling operation Requirements Security Physiological Value based Security [3] Combines flag preparing with security calculations Hogs up 80 % of aggregate RAM References 1. M. B¨achlin et al. Online Detection of Freezing of Gait in Parkinson's Disease Patients: A Performance Characterization. In Proc. of the 4 th Intl. Gathering on Body Area Networks, Apr. 2009 2. K. Venkatasubramanian et al. Ayushman: A Wireless Sensor Network Based Health Monitoring Infrastructure and Testbed. In Distributed Computing in Sensor Systems, pages 406–407, July 2005 3. K. Venkatasubramanian et al. Plethysmogram-based secure between sensor correspondence in body region systems. Military Communications Conference, 2008. IEEE, pages 1–7, Nov. Figure clarifies PVS Implementation

Proposed BSN System Computationally able sensors Use Intel Atom as the sensor processor Addresses the computational necessities of the present day applications Homogeneous equipment and programming stage Sensors running intel particle can have stripped down forms of a similar OS portion Resolves programming similarity issues Energy Scavenging Incorporate vitality searching equipment in the system to support operation of the sensors Supplement battery control Makes the BSN framework greener Future

Challenges of Atom based BSN Atom can give a uniform stage exceptionally fit BSN processors Challenges with Atom Energy Efficiency Relatively higher power impression of Atom Thermal Safety Possible high warm impression of Atom Sustainability How long can vitality rummaged from human sources maintain Atom operation ?

Atom foundation Ultra low power processor for implanted applications However, request of extent higher power dispersal than the condition of-workmanship BSN hub IA-32 microarchitecture helps in simple application advancement Can utilize abnormal state programming dialects to create applications Six low power rest states with ultra low power profound rest state Sleep booking can be utilized to decrease control utilization Intel Speed Step innovation empowers seven distinctive working recurrence levels Clock recurrence control to diminish working force Sleep state and recurrence control performed through simple ACPI bolster (through Model Specific Register (MSR) gets to)

Typical BSN Workload Ayushman [2] wellbeing observing application is considered as the workload Ayushman has three periods of operation – Sensing Phase – Sensing of physiological qualities (Plethysmogram signals) from the sensors and putting away it in the neighborhood memory Transmission Phase – Send the put away information to the base station in a solitary burst Security Phase – Perform organize wide key assention for secure between sensor correspondence utilizing Physiological esteem based Key Agreement Scheme (PKA) [3]. The Security stage happens once in a day The Sensing stage and Transmission stage exchange framing a rest cycle (the processor can rest amid detecting stage while it can be dynamic amid the transmission stage) Ayushman Workload Frequency Throttling amid security stage Sensing Phase Enables Sleep Scheduling Transmission Phase Sleep Cycle Sensor CPU Utilization Security Phase Time

Management Strategies for Safety and Sustainability Challenge - Atom's high TDP (2.2 W) as for present day sensor hubs (~ 80 mW [4]) Remedy – Power planning through rest booking and clock recurrence control Road Blocks – In a rest mode the processor can't register Decrease in clock recurrence expands calculation time Challenge - Increase lifetime of operation Remedy – incorporate searching hubs in the BSN that will charge the Atom hubs remotely and supplement battery Road Blocks – The operation of rummaging sources are discontinuous relying upon the stochastic conduct of the host Often the rummaging hubs neglect to give suitable power levels to the hubs The systems are firmly identified with the applications constant necessities. 4. K. Venkatasubramanian et al. Green and practical digital physical security answers for body range systems. In BSN '09: Proc. of the Sixth Intl. Workshop on Wearable and Implantable Body Sensor Networks, pages 240–245, Washington, DC, USA Intelligent outline is required to accomplish wellbeing and supportability while regarding the constant prerequisites of the applications

Software Design Methodology

BSN Hardware display BSN hub Intel N270 single center processor 1.6 GHz clock recurrence, 1 GB RAM Intel SpeedStep recurrence control innovation – helpful for power administration 6 rest states including one ultra low power rest state (C6) – rest booking Chipcon 2420 radio 2.45 GHz, 802.15.4 remote standard Maximum Power scattering (58 mW [4]) BSN Node Base Station Base Station Atom based cell phone Wireless Charging Scavenging Sources Body Heat, Ambulation, Respiration and Sun Light Wireless charging of BSN hubs from searching sources is accepted Each source has a predetermined range upto which it can charge hubs Scavenging Sources

BSN hub Software The power utilization of Atom processor relies on upon the Operating System utilized Mobile Intel 945 GMCH load up power utilization Open Suse Linux = 11.7 W Moblin OS = 10.4 W ACPI bolster required for getting to Intel SpeedStep recurrence control and rest states Moblin gives ACPI through which one can compose to or read fitting MSR registers to – Control clock recurrence Sleep States Measure center temperature The BSN workload considered is the Ayushman application

Profiling Requirements Thermal Safety – The greatest temperature of the skin in contact with the hub ought not surpass 39 ºC for 24 Hrs of operation Thermal conduct of Atom under the given workload must be assessed Sustainability – The accessible power from the rummaging sources ought to have the capacity to meet the power requests of Atom hub under the given workload Power profiling of Atom processors amid execution of Ayushman

Thermal Profiling Requires center temperature estimations for various working purposes of the Atom processor The Mobile Intel 945 GSE improvement stage (GMCH) gave by Intel has advanced warm sensors The load up warm sensors were perused from Model Specific Registers The most extreme center temperature (43 ºC) was seen amid PKA execution Turn On GMCH load up Set Operating Frequency Read MSR C6 Sleep State Run Ayushman Log Temperature Data Thermal profiling technique

Power Profiling Power Meter PKA is the most power expending calculation in Ayushman [3] The contrast between sit out of gear power and power amid PKA execution was measured utilizing the GMCH load up Idle force of Atom N270 processor was added to it to get PKA control utilization Board Power Lead Intel Atom N270 on Mobile Intel Chipset 945 GSE AC Mains Table indicating Atom control utilization for PKA execution at various working frequencies Power Measurement Set up

Resource Consumption PKA calculation in Ayushman includes flag handling of physiological flags and additionally execution of security calculations Resource impression of PKA is assessed as far as – RAM use, Power Consumption, and Computation Time Atom contrasted with TelosB gives low RAM use and calculation time However of course it has around thrice the power utilization Resource Consumption for PKA execution

Modeling Phase Industry Standard AADL dialect is utilized for demonstrating

Safety Violation for various throttling modes 0.6 Safety Violation versus Percentage Throttle (bend fit) 0.4 0.2 Percentage Safety Violation 0 No Violation Line - 0.