https://medium.com/google-developers/computing-at-the-edge-of-iot-140a888007b
We’ve seen that demand for low latency, offline access, and enhanced machine learning capabilities is fueling a move towards decentralization with more powerful computing devices at the edge.
Nevertheless, many distributed applications benefit more from a centralized architecture and the lowest cost hardware powered by MCUs.
Let’s examine how hardware choice and use case requirements factor into different IoT system architectures.
314 Comments
Tomi Engdahl says:
Automation at the edge
Read seven unique industry examples and use cases for automation at the edge in this enriched e-book.
https://red.ht/3dJr6es
Tomi Engdahl says:
Koneoppimista verkon reunalla
https://etn.fi/index.php/13-news/14243-koneoppimista-verkon-reunalla
MACHINER LEARNING AT THE EDGE
https://etn.fi/index.php/tekniset-artikkelit/14242-machiner-learning-at-the-edge
Many customers fail to assess and demonstrate the benefits AI will bring to their application. To jumpstart applications on the right foot, STMicroelectronics ́ Edge AI Sprint brings a whole support system of experts that can guide developers through the minefields inherent to their application and use case.
Traditionally, large companies looking to benefit from machine-learning must hire one or more data scientists to collect a massive amount of data for months, clean them, and create AI models. Embedded developers then port the implementation on microcontrollers or use dedicated tools to convert neural networks into optimized code for MCUs.
When a company wrestles with tight budget constraints, hiring one or more data scientists may be out of the question. Additionally, it may not be possible to outsource the job. Some situations are sensitive, while others require someone to be constantly on staff.
Even with the right people and all the time in the world, obtaining quality data is still an issue. Despite all the advances in machine learning, getting reliable training samples can be a severe problem. For instance, if an application tries to detect abnormal behaviors, data may be unavailable. Indeed, while many datasets work for classification problems, such as anomaly detection, they’re useless when trying to detect new situations. It is also critical to obtain good quality data, which is far from obvious. When samples aren’t plagued by typos or missing information, recording clean sets and precisely labeling them can demand serious investments.
NanoEdge AI Studio is a utility that speaks to embedded developers, even to those with no data-science expertise. The magic lies in running the training phase that learns a complex nominal behavior and the inference on the same device. The entire process can thus run on the same STM32 microcontroller.
Tomi Engdahl says:
Powering the Next Generation of Edge-Compute Capable Satellites
A November 30th Electronic Design-hosted webinar sponsored by Renesas Electronics
https://www.electronicdesign.com/resources/webinars/webinar/21253838/powering-the-next-generation-of-edgecompute-capable-satellites?sti=ED2&pk=ED2&utm_source=EG+ED++Webcasts&utm_medium=email&utm_campaign=CPS221118158&o_eid=7211D2691390C9R&rdx.identpull=omeda|7211D2691390C9R&oly_enc_id=7211D2691390C9R
There’s no question that the amount of data that needs to be processed only increases with time and the space industry is no exception. While the current generation of satellites act mostly as relays between ground stations with very little on-board processing, the projected increase in the amount of data in space puts a strain on the already limited uplink and downlink bandwidth. The solution is to make satellites edge-compute capable such that the data transmitted can be limited to more relevant processed data as opposed to raw data.
Satellites with such capabilities are more of a reality these days thanks to the new FPGAs and ASICs that have come into the space market. The increased compute capability provided by these new processors open many new possibilities for satellites but also comes at the cost of power. These new processors utilize much smaller process nodes that have much lower core voltages and tolerances.
Tomi Engdahl says:
https://www.hackster.io/news/sipeed-launches-maix-iii-axera-pi-module-for-high-performance-low-power-edge-ai-vision-work-602feeb24f12
Tomi Engdahl says:
Korona kiihdytti koneoppimista verkon reunalla
https://etn.fi/index.php/tekniset-artikkelit/14357-korona-kiihdytti-koneoppimista-verkon-reunalla
Covid-19-pandemialla on ollut oma vaikutuksensa sulautettujen järjestelmien markkinakehityksessä ja se on merkittävästi lisännyt koneoppimiseen liittyvän automaation, ilmaisun ja edge-prosessoinnin suosiota.
Siinä missä nopeat ethernet-verkot ovat yhä yleisemmin käytössä teollisissa edge-sovelluksissa, reunalaitteessa oleva FPGA-ratkaisu mahdollistaa, että suunnittelijat voivat konfiguroida järjestelmän eri teollisuusverkoille kuten Profibus- tai Hart-verkolle. Verkkoprotokollien joustavasti tapahtuva lisääminen FPGA-suunnitteluun vähentää verkkosolmujen ja yhdyskäytävien tarvitseman koon ja monimutkaisuuden määrää, mikä onkin ollut pääasiallinen suuntaus nyt ja ensi vuonna.
Koneoppiminen on myös mahdollista toteuttaa laajassa valikoimassa mikro-ohjaimia, joita käytetään esimerkiksi reunalaitteiden ennakoivan huollon ja ylläpidon sovelluksissa.
Mitä useampia laitteita ollaan yhdistämässä IoT-järjestelmään, tulee suunnittelijoiden ottaa huomioon sovellusten lisääntyvä haavoittuvuus vihamielisille kaappauksille ja se, että edge-solmut ovat yleisesti varsin alttiita turvallisuutta uhkaaville hakkeroinneille. Tästä syystä on ilmeinen tarve langattomasti (OTA) suoritettaville päivityksille, jotta edge-järjestelmän IoT-laitteiden turvallisuusominaisuudet pysyvät ajan tasalla.
OTA-päivitykset ovat jo nyt pääosin käytössä turvallisuudeltaan kriittisissä järjestelmissä, muutoinhan verkkoon olisi helppo ujuttaa haitallista koodia edge-solmusta käsin. Microchip on yhteistyössä kaikkien merkittävien pilvipalveluiden toimittajien kanssa takaamassa, että noudatetaan viimeisimpiä turvallisuusstandardeja. Tällä toimialalla markkinat kasvavat nopeasti tällä hetkellä.
Tomi Engdahl says:
Explaining an AI Edge-Computing Solution—Plus Live IoT Demos
Dec. 20, 2022
The two solution demonstrations by STMicroelectronics, which took place at electronica 2022, focused on AI computing and the new Matter IoT protocol.
https://www.electronicdesign.com/technologies/iot/video/21256566/electronic-design-explaining-an-ai-edge-computing-solution-and-live-iot-demonstrations?utm_source=EG+ED+Connected+Solutions&utm_medium=email&utm_campaign=CPS221212111&o_eid=7211D2691390C9R&rdx.identpull=omeda|7211D2691390C9R&oly_enc_id=7211D2691390C9R
Tomi Engdahl says:
FPGAs for the Intelligent Edge – Intelligent Embedded Vision
FPGAs and SoCs are enabling IoT devices to analyze image and video without the help of a central server.
https://community.element14.com/learn/learning-center/the-tech-connection/w/documents/28303/fpgas-for-the-intelligent-edge—intelligent-embedded-vision
Tomi Engdahl says:
A growing number of companies are turning to edge computing for their organizational needs, with worldwide spending on edge expected to reach $208 billion in 2023, according to IDC. This is an increase of 13.1% over 2022 and IDC has also identified more than 400 named use cases across various industries and domains.
Tomi Engdahl says:
https://etn.fi/index.php/13-news/15462-cube-ratkaisee-tekoaelyn-ongelmat-verkon-reunalla
Tomi Engdahl says:
https://www.uusiteknologia.fi/2023/11/10/teknologia23-tarjosi-passiivijaahdytysta-reunalaskentaan/
Tomi Engdahl says:
https://www.dna.fi/dnabusiness/blogi/-/blogs/edge-computing-private-networks-and-autonomous-drones-how-modern-technology-can-secure-your-business?utm_source=facebook&utm_medium=social&utm_content=LAA-artikkeli-edge-computing-private-networks-and-autonomous-drones-how-modern-technology-can-secure-your-business&utm_campaign=P_LAA_24-22-26_artikkelikampanja_enkku_&fbclid=IwAR3bJ00N_cBOdONEJplEzscCI9zNr3uLCPSMMbYyLs9APPR288Og2ZZuXjE_aem_AWZH8hmKwXLSJNbZV6v4TGPHVqeUgPGPWIXDlJYTJgK0Mqfd6tRAmWCstLjPCAoxlGDZuNW6xbx1YEh_Omc1Q5C6
Tomi Engdahl says:
Reunalaskennan alta vedettiin matto – ”Pilvipalvelut täyttävät useimmissa maissa tiukimmatkin vasteajan vaatimukset”
https://www.tivi.fi/uutiset/reunalaskennan-alta-vedettiin-matto-pilvipalvelut-tayttavat-useimmissa-maissa-tiukimmatkin-vasteajan-vaatimukset/2521541c-6892-41a8-a232-965c2364a825
Pilvipalveluiden latenssin ongelmaan ratkaisuksi on povattu reunalaskentaa (edge computing) viimeisten 10–15 vuoden ajan. Käytännössä ideana on ollut, että pilven ja käyttäjän väliin syntyisi pienempiä saarekkeita, jotka välittäisivät dataa lyhyemmän matkan päästä.
Tomi Engdahl says:
https://etn.fi/index.php/13-news/16869-advantechin-reuna-alusta-palkittiin
Tomi Engdahl says:
Paul Sawers / TechCrunch:
Ditto, which aims to enable “resilient” edge device connectivity, raised an $82M Series B at a $462M post-money valuation, after a $45M Series A in April 2023
Ditto lands $82M to synchronize data from the edge to the cloud
https://techcrunch.com/2025/03/12/ditto-lands-82m-to-synchronize-data-from-the-edge-to-the-cloud/
Ditto, a company that’s setting out to bring “resilient” connectivity to edge devices, has raised $82 million in a Series B round of funding at a post-money valuation of $462 million, more than double its Series A valuation from 2023.
“Edge,” in the context of Ditto’s industry, refers to a distributed computing model that brings data processing and storage closer to where it’s generated (e.g. IoT sensors, 5G routers, or smartphones) rather than having to rely on centralized data centers and cloud platforms. It’s all about reducing latency and optimizing bandwidth requirements by processing data either on a device itself, or on dedicated “edge servers” located near where the data is generated.
In the age of AI and computationally intensive machine learning models, this can be vital, particularly when real-time decisions are paramount, or any situation where connectivity is patchy. Speed is the name of the game.
Ditto bypasses physical edge servers, which its CEO and co-founder Adam Fish says is a costly, labor-intensive endeavor that customers can do without.
Instead, Ditto uses the hardware that companies’ workforce already employ, such as smartphones.
“We replace hardware with software — a no-brainer choice,” Fish added.
Ditto’s platform constitutes a core “edge sync” component, which is an embeddable software development kit (SDK) that device-makers can integrate with their application. This allows companies to tap into devices’ built-in Bluetooth, Wi-Fi, or local LAN capabilities to create “ad-hoc mesh networks,” whereby apps can discover and communicate with each other independently of a centralized cloud server. Ditto serves as a mobile database that apps read and write to locally.
It’s this approach that has led Ditto to attract several major airlines as customers, including Delta, Japan Airlines, and Lufthansa.
“Airlines require constant crew collaboration, especially while in-air, but cabin connectivity is often unstable,” Fish said. “This means the apps [that] cabin crew use to stay in touch during takeoff, in-flight, and landing can often be disrupted, leading to poor communication among the team and, at times, a poor customer experience.”
Delta, for example, has built a mobile app for its flight attendants that integrates Ditto’s SDK and works on standard company-issued iPhones.
“Flight attendants can now chat with each other from anywhere in the cabin, making it easy to collaborate with team members consistently during the flight and provide the best customer experience,” Fish added.
From the edge to the cloud
There’s no ignoring the power of modern cloud computing, though, and certain functions require the kind of computing power only a remote server can provide. For instance, autonomous vehicles pack a bunch of sensors and cameras to capture real-time data on their surroundings, and they need to be able to process this data locally in real time to safely maneuver around vehicles rather than relying on cloud connectivity.
At the same time, an AV company will also need to pool vast swathes of data to perform more advanced machine learning tasks and improve its AI models. Such tasks would typically require the company to pass data to the cloud.
The same principle applies to myriad other industry verticals, from point-of-sale (POS) systems in retail to IoT sensors in factories.
Ditto bridges edge devices and the cloud, letting developers store and sync data “peer-to-peer” (P2P) across their systems while remaining synchronized with data stored elsewhere. As such, Ditto offers distinct pricing for customers that only want to sync between the cloud and their edge devices, without the mesh networking element.
Ultimately, it’s all about creating resilient software infrastructure, where bottlenecks or bandwidth issues don’t impede a company’s ability to operate.
“The goal is that your architecture does not rely on the cloud, but it doesn’t mean the cloud and centralized systems don’t have a place,” Fish said. “Instead with Ditto, they can do what they are best at — large-scale data integration and long-term storage, but not act as a bottleneck for operational data.”