Скачать презентацию REAL TIME Live Full-scale Giga-Places Peta-Bytes Tera-OPS Скачать презентацию REAL TIME Live Full-scale Giga-Places Peta-Bytes Tera-OPS

d1afba350828c07975de0b1289f39a9a.ppt

  • Количество слайдов: 20

REAL TIME REAL TIME

Live, Full-scale Giga-Places Peta-Bytes, Tera-OPS Femto-time Learn Observe Interoperable, pervasive networking Ubiquitous sensors 7/10/11 Live, Full-scale Giga-Places Peta-Bytes, Tera-OPS Femto-time Learn Observe Interoperable, pervasive networking Ubiquitous sensors 7/10/11 Now Digitized: Sense/Observe Collect/Distribute Analyze Simulate Decide Act Real-time, massive analysis Automated learning Vast, evolving knowledge stores

What is “real time”? What If? e m Ti ate o. L To In What is “real time”? What If? e m Ti ate o. L To In Now Then Real Time Systems: Live, always-on, reactive, interactive, stable, controllable, adaptive

What If? Now Then Rate-1 7/10/11 Rate-1 Later Rate-1 What If? Now Then Rate-1 7/10/11 Rate-1 Later Rate-1

Time Frames and Operation Rates Observation time – measure, discriminate Analysis time – communicate, Time Frames and Operation Rates Observation time – measure, discriminate Analysis time – communicate, contextualize, understand Decision time – choose, formulate, distribute Action time – energize, drive 7/10/11

Sample rates vary with applications Pico to milliseconds Speed of a process Days to Sample rates vary with applications Pico to milliseconds Speed of a process Days to weeks Decades Stock trading incl’d programmed trading Automobile controls engines to driverless control Water resources measurement, modeling & controls SCIENCE Surveillance Memory recall Climate change Content distribution Power grid demand

It all begins with simulation… Sensors* Simulator with Human *Sensors may be people Model It all begins with simulation… Sensors* Simulator with Human *Sensors may be people Model of System e. g. airplane

MIT Whirlwind (c 1951) first real time computer. Begot SAGE (Semi-Automatic Ground Environment) MIT Whirlwind (c 1951) first real time computer. Begot SAGE (Semi-Automatic Ground Environment)

Sample rate versus utility Pico to milliseconds Speed of a process Days to weeks Sample rate versus utility Pico to milliseconds Speed of a process Days to weeks Stock trading incl’d programmed trading Automobile controls engines to driverless control; Power grid demand Water resources SCIENCE measurement, modeling & controls Surveillance Memory recall Content distribution Decades Climate change

Wes Clark, Lincoln Laboratory, and LINC, first PC. LINC: Laboratory Instrument Computer c. 1962 Wes Clark, Lincoln Laboratory, and LINC, first PC. LINC: Laboratory Instrument Computer c. 1962 Real time processing for bio-medical research.

Real time Sensing e. g. laboratory control, simulators Observers, Model Builders e. g. Scientists Real time Sensing e. g. laboratory control, simulators Observers, Model Builders e. g. Scientists Sensors* REAL WORLD System Cha nne *Sensors may be people l to effe ct b eha vior

LINC 2007 Vintage Computer Fair (At age 45 … turns 50 next year) LINC 2007 Vintage Computer Fair (At age 45 … turns 50 next year)

Some other real time computers Whirlwind: Bright Boys 1962 LINC that influenced PDP-5 8/1963 Some other real time computers Whirlwind: Bright Boys 1962 LINC that influenced PDP-5 8/1963 PDP-5 for interfacing a Canadian research reactor to a PDP-4 (controller) RT-11 from OS/8 begot CPM >> DOS RSX-11

Sensing… Observations by human operators Sensors* REAL WORLD System *Sensor/effector may be people Sharing Sensing… Observations by human operators Sensors* REAL WORLD System *Sensor/effector may be people Sharing of data To effect change

Real time Control Plain old closed loop control Model of REAL WORLD System Advice Real time Control Plain old closed loop control Model of REAL WORLD System Advice (t+1) Controller Sensors* REAL WORLD System Effectors* *Sensor/effector may be people (Processing, policies and people)

Real time and Control with/wo Real World Modeling Model of REAL WORLD System Advice Real time and Control with/wo Real World Modeling Model of REAL WORLD System Advice (t+1) Delays and Noise Sensor s* REAL WORLD System Effector s* *Sensor/effector may be people Delays and Noise Controller (Processing, policies and people)