235 lines
9.0 KiB
Markdown
235 lines
9.0 KiB
Markdown
file:: [Balouek-Thomert et al_2019_Towards a computing continuum.pdf](file://C:\Users\david\Zotero\/storage/LDNCVMY8/Balouek-Thomert et al_2019_Towards a computing continuum.pdf)
|
|
file-path:: file://C:\Users\david\Zotero\/storage/LDNCVMY8/Balouek-Thomert et al_2019_Towards a computing continuum.pdf
|
|
|
|
- fluid integration of resources at the edge, the core, and along the data path to support dynamic and data-driven application workflows,
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: purple
|
|
id:: 63b99a39-dc30-49a5-b673-f05828ac2abd
|
|
- leverage a computing continuum
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: purple
|
|
id:: 63b99a3e-2479-462b-b56b-9fa25293cdf4
|
|
- edge-tocloud integration to support data-driven workflows.
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: blue
|
|
id:: 63b99a46-34ab-412d-a922-6b6d1ca3108c
|
|
hl-stamp:: 1673108040427
|
|
- The last decade has witnessed a dramatic change in the technology landscape marked by increasing scales and pervasiveness of compute and data.
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99b6c-3291-4925-b2ac-180ee7726b59
|
|
hl-stamp:: 1673108345071
|
|
- significant investment in edge computing to support timely processing close to the data sources
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99b86-4fc0-494b-944c-96e9800b7671
|
|
- performance
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99b8a-50bc-4b2a-a22a-095a0d06c766
|
|
- latency
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99b8b-ad88-453d-b307-10f269f18811
|
|
- interoperability
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99b8c-a8fd-4652-9242-66fca5de6fc4
|
|
- security
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99b8d-3c3d-44ab-b1b8-0623038da0cf
|
|
- privacy
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99b8e-65a1-475d-8647-59144b56de63
|
|
- Knowledge extraction in these applications combines various data sources, such as those coming from the IoT devices, statistical data about cities and its population and data from location-based social network
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b99ce3-1e84-4379-8607-970245d74ae5
|
|
- A framework for enabling continuum computing
|
|
ls-type:: annotation
|
|
hl-page:: 3
|
|
hl-color:: blue
|
|
id:: 63b99eb4-9990-4b0b-b2a7-ba5d945e5134
|
|
- [:span]
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: blue
|
|
id:: 63b99ec9-cbac-43a3-ab54-52fb5d2fff6e
|
|
hl-type:: area
|
|
hl-stamp:: 1673109193303
|
|
- The automotive industry is facing similar challenges as it is developing technologies for autonomous vehicles. To operate safely, these vehicles will need to gather and analyze vast amounts of data pertaining to their surroundings, directions, and weather conditions, not to mention communicating with other vehicles on the road
|
|
ls-type:: annotation
|
|
hl-page:: 1
|
|
hl-color:: green
|
|
id:: 63b9b7bf-d172-4098-a155-51305d01b140
|
|
hl-stamp:: 1673115584878
|
|
- send data back to manufacturers to track usage and maintenance alerts as well as interface with local municipal networks.
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: green
|
|
id:: 63b9b865-d423-4412-8d54-077440ea4dee
|
|
- Similar requirements and challenges are present in many other disciplines, including health care, finance, science and engineering, business analytics, and cybersecurity
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: green
|
|
id:: 63b9b874-62fd-4cc8-a41b-752767f3c3cb
|
|
- while these facilities provide access to the data and data products, they tend to be remote and/or distributed, and transforming these data and data products into insights requires combining it with complex models and access to powerful computing, storage, and networking resources.
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: blue
|
|
id:: 63b9b89a-c3ed-4acc-b755-4d65fc85c0e1
|
|
hl-stamp:: 1673115804162
|
|
- As these emerging classes of applications mature and their data and processing requirements grow, they cannot be sustained by solely using edge resources or by sending all the data to the cloud.
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: blue
|
|
id:: 63b9b8de-0d31-4b3a-80da-5e4697b690df
|
|
- luid integration of resources at the edge, the core, and along the data path to support dynamic and data-driven application workflows, that is, they need to leverage a computing continuum
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: blue
|
|
id:: 63b9b8f3-4553-453e-a9f8-c07dea30e0ad
|
|
- Continuum computing aims at realizing a fluid ecosystem where distributed resources and services are programmatically aggregated on demand to support emerging data-driven application workflows.
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: blue
|
|
id:: 63b9b906-62f2-464d-b9d1-2806380bd4e8
|
|
- Computing in the continuum: combining pervasive devices and services to support data-driven applications
|
|
ls-type:: annotation
|
|
hl-page:: 13
|
|
hl-color:: blue
|
|
id:: 63b9b93d-c0f4-43c2-91bb-1480d6afe32d
|
|
- enabling edge-to-cloud integration to support datadriven workflow
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba16-710a-471c-990e-0589430be280
|
|
hl-stamp:: 1673116185046
|
|
- ederating infrastructure, programming services, and composing dynamic workflows, which are capable of reacting in real time to unpredictable data sizes, availabilities, locations, and rates.
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba22-14d5-4ab8-8feb-05eb1a46d1cf
|
|
- (1) how do we take into account what, where, and when data get collected and analyzed;
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba2e-8cd7-4cf4-a12b-eafd7f57ef4c
|
|
- (2) how do we program services to respond to changes in application behavior or data variability;
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba35-ba74-47d3-9ebe-20021e686dc5
|
|
- (3) how to react to changes and trigger rules associated to the content of the data;
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba4b-4c3b-40f6-b2be-522afc0c4071
|
|
- (4) how to consider users constraints and quality of service to deliver data products.
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba53-82ba-4a5b-b9d9-1d8e29ee7fc5
|
|
- programming approach for data-driven applications that allows the system to respond to dynamic data patterns.
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba67-1fc6-46b2-8ac6-e138326d0921
|
|
- exploiting network resources to run workflows along the data path and deliver data products with respect to application constraints
|
|
ls-type:: annotation
|
|
hl-page:: 2
|
|
hl-color:: purple
|
|
id:: 63b9ba6f-7f19-4fa1-93d4-186ca0db7d53
|
|
- a conceptual framework that implements the vision of computing in the continuum to complement next-generation IoT systems and cyberinfrastructures
|
|
ls-type:: annotation
|
|
hl-page:: 3
|
|
hl-color:: purple
|
|
id:: 63b9ba97-e1c8-47bd-a8da-6da0eb100181
|
|
- Infrastructure
|
|
ls-type:: annotation
|
|
hl-page:: 3
|
|
hl-color:: purple
|
|
id:: 63b9baa5-7b34-4a2b-9bd0-3befd08c3163
|
|
- Federation
|
|
ls-type:: annotation
|
|
hl-page:: 3
|
|
hl-color:: purple
|
|
id:: 63b9bab5-7366-4e8a-bc04-4bd802afeadf
|
|
- low overhe
|
|
ls-type:: annotation
|
|
hl-page:: 3
|
|
hl-color:: purple
|
|
id:: 63b9bac1-32a7-4822-9893-71e6f5cc62e5
|
|
- distributed management
|
|
ls-type:: annotation
|
|
hl-page:: 3
|
|
hl-color:: purple
|
|
id:: 63b9bac5-c5e0-471d-9172-420c5336c419
|
|
- The low runtime overhead is critical when deployed in performance-limited hardware platforms
|
|
ls-type:: annotation
|
|
hl-page:: 3
|
|
hl-color:: purple
|
|
id:: 63b9bad1-5166-4bf3-aec3-90bee56a7ea2
|
|
- The Streaming layer consolidates the data from multiple sources, processing data, and providing data indexing and discover
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: purple
|
|
id:: 63b9bbfa-e358-41f9-a976-fe4ce9172c7a
|
|
- data ingestion, data analysis, data storage, and data query.
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: purple
|
|
id:: 63b9bc09-674a-491c-a14c-ade19b0cc912
|
|
- data processing layer:
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: purple
|
|
id:: 63b9bce9-8628-4ab2-9106-ac4ac9c3b523
|
|
- Distributed
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: purple
|
|
id:: 63b9bceb-0013-4f76-8d3e-759f1eda3213
|
|
- Scalable
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: purple
|
|
id:: 63b9bced-4a7a-4d93-9ce6-9fb9a92b5cdd
|
|
- Real-time
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: purple
|
|
id:: 63b9bcef-c225-45af-bcaa-0081d7f21a2e
|
|
- Application layer
|
|
ls-type:: annotation
|
|
hl-page:: 4
|
|
hl-color:: purple
|
|
id:: 63b9bcf2-2559-460c-90a2-8fac65c63d6f
|
|
- driven programming model for analyzing requests from streaming-based workflows at runtime and deciding how to process the data.
|
|
ls-type:: annotation
|
|
hl-page:: 5
|
|
hl-color:: purple
|
|
id:: 63b9bd5a-e567-4bcf-b1b4-88e860228259
|
|
- discovering and composing heterogeneous computational data pipelines by reacting to the content of the data
|
|
ls-type:: annotation
|
|
hl-page:: 5
|
|
hl-color:: purple
|
|
id:: 63b9bd64-beee-46f1-8024-98eea8dc8384
|
|
- performing in-transit processing by utilizing resources at the edge, at the core, and along the data path, and exploiting network resource capabilities.
|
|
ls-type:: annotation
|
|
hl-page:: 5
|
|
hl-color:: purple
|
|
id:: 63b9bd6f-bc29-409a-ad30-fa55718bbfe9 |