- All
- Engineering
- Artificial Intelligence (AI)
Powered by AI and the LinkedIn community
Cisco sponsors Artificial Intelligence (AI) collaborative articles.
Sponsorship does not imply endorsem*nt. LinkedIn's editorial content maintains complete independence.
1
Advantages of edge computing for AI
2
Disadvantages of edge computing for AI
3
Cloud computing vs edge computing for AI
4
Examples of edge computing for AI
5
Future trends of edge computing for AI
6
Hereโs what else to consider
Top experts in this article
Selected by the community from 18 contributions. Learn more
Earn a Community Top Voice badge
Add to collaborative articles to get recognized for your expertise on your profile. Learn more
-
8
- ๐ฉ๐ป๐ Dr. Vivien Dollinger First on-device Vector Database + Data SyncSustainable | Open Source | On-device AI | Edge AI | Local AI ๐
5
1 Advantages of edge computing for AI
One of the main advantages of edge computing for AI is that it can improve the performance and efficiency of AI applications. By processing data locally, edge computing can reduce the network traffic, latency, and bandwidth consumption that would otherwise occur if the data were sent to the cloud. This can enable faster and more accurate responses, especially for time-sensitive and mission-critical tasks, such as autonomous driving, face recognition, and industrial automation. Edge computing can also enhance the reliability and availability of AI applications, as they can operate independently of the cloud in case of network failures or outages.
Help others by sharing more (125 characters min.)
- Steve Wilson CPO at Exabeam | Lead for OWASP Top 10 for Large Language Model AI Security | Driving AI-Powered Product Innovation
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
Beyond the commonly cited performance benefits, a more important consideration may be security and privacy. The major force holding back AI adoption this decade will be worried about security and privacy - and we're already seeing numerous examples of individuals and corporations accidentally exposing too much data to SaaS AI providers. Beyond that, we're seeing government entities (especially in Europe) highly concerned with data locality related to these AI services. Edge computing may be one way to ensure data stays local and secure while still allowing for AI-enhanced functionality.
LikeLike
Celebrate
Support
Love
Insightful
Funny
4
- ๐ฉ๐ป๐ Dr. Vivien Dollinger First on-device Vector Database + Data SyncSustainable | Open Source | On-device AI | Edge AI | Local AI ๐
(edited)
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
While I understand that this is not top of mind for many people when thinking AI, ๐ญ๐ก๐ ๐ฌ๐ฎ๐ฌ๐ญ๐๐ข๐ง๐๐๐ข๐ฅ๐ข๐ญ๐ฒ ๐๐๐๐๐๐ญ ๐จ๐ ๐ซ๐ฎ๐ง๐ง๐ข๐ง๐ ๐๐ ๐จ๐ง ๐ญ๐ก๐ ๐๐๐ ๐, ๐ฐ๐ก๐๐ง ๐ฉ๐จ๐ฌ๐ฌ๐ข๐๐ฅ๐, ๐ข๐ฌ ๐ฌ๐ข๐ ๐ง๐ข๐๐ข๐๐๐ง๐ญ and with the growing number of AI applications absolutely worthwhile to keep in mind and consider... ๐
LikeLike
Celebrate
Support
Love
Insightful
Funny
Load more contributions
2 Disadvantages of edge computing for AI
However, edge computing for AI also has some disadvantages that need to be considered. One of the main challenges is the security and privacy of the data and the devices. Edge computing involves distributing data and computation across multiple nodes, which increases the risk of data breaches, tampering, and unauthorized access. Moreover, edge devices may not have the same level of encryption, authentication, and protection as cloud servers, making them more vulnerable to cyberattacks. Another challenge is the scalability and management of edge computing for AI. As the number and diversity of edge devices grow, so does the complexity and cost of maintaining, updating, and coordinating them. Furthermore, edge computing may not be able to handle the high volume and variety of data that some AI applications require, and may need to integrate with cloud computing to leverage its resources and capabilities.
Help others by sharing more (125 characters min.)
-
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
Loss of data is another disadvantage of edge computing. Data that is deemed "useless" is often discarded after being processed in the edge devise. However, if the usefulness of data was incorrectly assessed or if we need the data at a later stage of the process or for a different aspect of the analysis then we get stuck as the data has been lost.
LikeLike
Celebrate
Support
Love
Insightful
Funny
8
- Dolo Miah
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
Something to think about with edge AI is model drift which can result in degraded output over time. Typically we're training models in the cloud then minifying them to work on constrained devices in the edge and then let them run there. We therefore need to have good edge MLOps to monitor model performance, or even to find ways to correct model drift in the edge itself (these types of feature are becoming available).But first step is to have a plan to monitor and address model drift.
LikeLike
Celebrate
Support
Love
Insightful
Funny
2
- ๐ฉ๐ป๐ Dr. Vivien Dollinger First on-device Vector Database + Data SyncSustainable | Open Source | On-device AI | Edge AI | Local AI ๐
(edited)
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
Depending on the way it is set up, the opposite can also be true: Edge AI can enhance the security of data: If the model runs on the device directly and is using a local vector database, data does not ever need to leave the device and be shared... and thus typically is safer. You can ofc set this up with a central model that runs locally to synchronize the edge models (share updates, propagate learnings...) too... as long as this is on-premise you can set that up very securely.Bonus: no need to worry about sharing your data with a cloud, SaaS, central AI model provider...
LikeLike
Celebrate
Support
Love
Insightful
Funny
1
3 Cloud computing vs edge computing for AI
Cloud computing and edge computing are not mutually exclusive, but rather complementary approaches for AI. Cloud computing offers centralized, scalable, and powerful resources for AI, such as large data sets, advanced algorithms, and specialized hardware. Edge computing offers decentralized, efficient, and responsive resources for AI, such as local data, customized models, and low-power devices. Depending on the needs and constraints of the AI application, a hybrid solution that combines the best of both worlds may be optimal. For example, edge devices can perform initial data processing and filtering, and send only the relevant data to the cloud for further analysis and refinement. Alternatively, cloud servers can train and update AI models, and send them to the edge devices for inference and execution.
Help others by sharing more (125 characters min.)
- ๐ฉ๐ป๐ Dr. Vivien Dollinger First on-device Vector Database + Data SyncSustainable | Open Source | On-device AI | Edge AI | Local AI ๐
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
The Edge vs. Cloud definition seems a bit hazy to me: Edge Computing is a decentralized topology bringing computing to the data source; while this often can mean restricted devices (e.g. ECUs in cars or mobile phones), hardware is not a suitable criterium for distinguishing cloud vs. edge. An edge setup can entail rather capable devices and locations with many devices including big servers. While I see that hybrid solutions are most common so far, I do believe we will also see "edge-only" settings gaining some momentum in the future due to data privacy and security concerns, e.g. on shopfloors, office buildings, on offshore platforms.
LikeLike
Celebrate
Support
Love
Insightful
Funny
5
- Matt Trifiro CMO @ Vapor IO, creators of the Zero Gap AI platform. We deliver the power of nearby NVIDIA GPUs over an outrageously fast and secure private network. I also write about marketing and AI.
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
This is a false dichotomy. Cloud is an operating model; edge is a location (proximity). A cloud can run at the edge. Full stop.
LikeLike
Celebrate
Support
Love
Insightful
Funny
1
4 Examples of edge computing for AI
Edge computing for AI is being used in many different domains and scenarios. Smart cameras, for example, can capture, analyze, and act on visual data such as recognizing faces and objects. Smart speakers can process natural language and speech, enabling commands and questions to be answered. Smart vehicles can sense, navigate, and communicate with their environment, while smart sensors can monitor and measure physical parameters like temperature or humidity. These edge devices can be used for security, home automation, transportation, industrial applications, agriculture, entertainment, education, safety, and more.
Help others by sharing more (125 characters min.)
- Matt Trifiro CMO @ Vapor IO, creators of the Zero Gap AI platform. We deliver the power of nearby NVIDIA GPUs over an outrageously fast and secure private network. I also write about marketing and AI.
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
Here are three salient reasons to use edge computing for AI. Edge AI makes sense when:1. Latency and reliability are paramount.2. The huge amounts of data you need to process (e.g., 1000 4K camera feeds) make long-haul transit costs untenable.3. Local jurisdictions or enterprise requirements demand that data be kept locally.
LikeLike
Celebrate
Support
Love
Insightful
Funny
1
5 Future trends of edge computing for AI
Edge computing for AI is an ever-evolving field that has many potential applications and challenges for the future. Edge AI chips are hardware devices designed for AI tasks on the edge, such as neural network processing, machine learning acceleration, and computer vision enhancement. They can improve the performance, efficiency, and functionality of edge devices. Federated learning is a technique that allows multiple edge devices to collaboratively learn from their local data without sending it to the cloud, preserving privacy and security while improving the accuracy and diversity of the AI models. Edge intelligence is a concept that refers to the integration of AI with other technologies on the edge, such as blockchain, 5G, IoT, and fog computing. It can enable new distributed, autonomous, and adaptive applications and services.
Help others by sharing more (125 characters min.)
- Matt Trifiro CMO @ Vapor IO, creators of the Zero Gap AI platform. We deliver the power of nearby NVIDIA GPUs over an outrageously fast and secure private network. I also write about marketing and AI.
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
Eventually, AI will be embedded in everything. It will be part of the fabric of our built environment, delivered as a utility to serve individuals, households and businesses. This pervasive AI is, by definition, edge. This is the endgame.
LikeLike
Celebrate
Support
Love
Insightful
Funny
4
-
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
In an optimistic future, edge computing could stand as a transformative technology that significantly revolutionizes data handling and processing across industries. It promises a world of hyper-responsive, reliable, and efficient systems, bringing about groundbreaking advancements in areas such as IoT, autonomous vehicles, healthcare, and smart cities. With ongoing innovations in security and robust management tools, edge devices could become less vulnerable and easier to manage, effectively mitigating the risks associated with the technology. Advances in ML and AI could improve real-time insights and decision making and create new business opportunities.
LikeLike
Celebrate
Support
Love
Insightful
Funny
2
Load more contributions
6 Hereโs what else to consider
This is a space to share examples, stories, or insights that donโt fit into any of the previous sections. What else would you like to add?
Help others by sharing more (125 characters min.)
- Mahdi M.
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
More powerful micro processors with better prices and lower power consumption Bigger memory modules with better speed and pricesEmerge of SBC computersAll results in powerful edge devices that handle edge computing easier
LikeLike
Celebrate
Support
Love
Insightful
Funny
3
- Stephen Pittard Data Science, Music Analytics, Bio-HPC
(edited)
- Report contribution
Thanks for letting us know! You'll no longer see this contribution
Edge computing is valuable for on-device data transformation and filtering, especially for feeding models. It can enable efficient sampling from dense data streams, thus reducing latency by sending aggregated and (hopefully) smaller payloads to more powerful compute substrates. However, this requires well-tested pre-processing code to be installed on edge devices. Also, any raw / original data would remain on the devices until cached out, limiting downstream access. A compromise involves including key metadata with filtered data to document essential characteristics without storing all of it. Note, the devices need to be flexibly updateable for bug fixes, performance enhancements, and ongoing compliance. So carefully select the edge device.
LikeLike
Celebrate
Support
Love
Insightful
Funny
2
Load more contributions
Artificial Intelligence
Artificial Intelligence
+ Follow
Rate this article
We created this article with the help of AI. What do you think of it?
Itโs great Itโs not so great
Thanks for your feedback
Your feedback is private. Like or react to bring the conversation to your network.
Tell us more
Tell us why you didnโt like this article.
If you think something in this article goes against our Professional Community Policies, please let us know.
We appreciate you letting us know. Though weโre unable to respond directly, your feedback helps us improve this experience for everyone.
If you think this goes against our Professional Community Policies, please let us know.
More articles on Artificial Intelligence
No more previous content
- Here's how you can secure a raise in your AI career while protecting your current position. 33 contributions
- Here's how you can stay ahead of changing industry demands and trends as an AI expert. 34 contributions
- Here's how you can effectively communicate technical concepts to a non-technical audience as an AI expert. 36 contributions
- Here's how you can determine salary ranges for entry level AI professionals. 5 contributions
- Here's how you can secure your financial future as an AI professional in a constantly evolving industry. 4 contributions
- Here's how you can optimize virtual collaboration for AI startups. 6 contributions
- Here's how you can manage effectively in an AI-driven workplace. 9 contributions
- Here's how you can master logical reasoning in the field of AI. 10 contributions
- Here's how you can enhance your continuing education by focusing on the most sought-after AI skills. 12 contributions
- Here's how you can optimize AI algorithms and models using logical reasoning. 25 contributions
- Here's how you can enhance decision-making in AI-related professions with emotional intelligence. 2 contributions
- Here's how you can tackle more challenging projects with confidence in your AI skills. 5 contributions
No more next content
Explore Other Skills
- Web Development
- Programming
- Agile Methodologies
- Machine Learning
- Software Development
- Computer Science
- Data Engineering
- Data Analytics
- Data Science
- Cloud Computing
More relevant reading
- Algorithms What do you do if your algorithmic data processing needs exceed your cloud computing service's capacity?
- Cloud Storage What are some emerging cloud storage innovations to try?
- Software Engineering What are the most promising research areas in cloud computing?
- Cloud Computing How will edge computing transform cloud services in the next decade?
Help improve contributions
Mark contributions as unhelpful if you find them irrelevant or not valuable to the article. This feedback is private to you and wonโt be shared publicly.
Contribution hidden for you
This feedback is never shared publicly, weโll use it to show better contributions to everyone.