edgecenter

Does this mean a build out of infrastructure at the Edge?

you can't do predictive analytics AT the edge without algorithms and models. These need to be built using ALL the data, centrally.

the volume of machine data will significantly restrict the ability to transmit to data centers

data transmission costs and ability will be central to the success of IoT. This will be important on a production line, where currently a small percentage of data is actually used for analysis, but will be more important to field services.

the last mile has always been challenging for networks - #IoT will see this even more. Decisions need to happen on the edge and intelligence as to what comes back to central location.

data from edge doesn't need to reach data center or cloud in real-time, but it DOES need to reach there for doing machine learning and predictive model training.

From an Industrial perspective, most telemetry today runs at 1Hz or lower frequency. Moving to advanced analytic applications that require machine data at 10's to 100's Hz will certainly be cost prohibitive to centralize

Edge offers many benefits including Lower latency, Better determinism, Increased security, Lower data comm costs

Entirely agree. Key is in determining what data at the edge is perishable (only valuable for a limited period of time, and only at the edge), and what data is actually worth storing/analyzing in a historical or trend-based context.

Agree! In industrial installations there are use cases were cloud can play a big role (process analytics) but most use cases still have requirements for edge processing.

@ejkraemer you can put real-time analytics at edge, but you still eventually need data to be central to train models.

The question that I have is "how do edge #IoT device" be agile and intelligent and deal with multiple clouds? Doesn't latency kill in this new model

More businesses will turn to colocation centers in metro areas

You are correct. however, not all data needs to be used to build very accurate predictive models so edge analytics are used to generate actions (alerts) and filter out data that isn't useful for model development or CI efforts.

move to edge analytics and distributed data

A key characteristic of most IoT is machine to machine communication at millisecond speed - 95%-99% of data will stay and die at the edge or close edge. Key data will be uploaded for cloud support and cloud training of edge software.

I agree with this. Edge gateways and hubs will become more powerful along compute and storage, and leverage a decentralized on-prem infrastructure, with only key data assets transferred to the Cloud (or on-prem core) for further analysis.

It can be important to differentiate between decision making, analysis, and data management. There are important distinctions

@yaronhaviv does edge analytics & distributed data mean new software?

@1seanriley if you want to model time series data, you will need to reconstruct your time series in your training data. This doesn't mean that the information shouldn't be compressed and also can be transferred in batch

Totally agree. I see network capacity as a limiting issue. If. for instance, a commercial airliner generates 1TB of data with each flight, multiplied by the number of airliners in the air each data that comes to multi Pbytes of data from airlines

We had a partner look at the cost of passing all data to the cloud for IoT deployments. For a simple sensor module (~15 sensors) it cost ~$800 a month just to ingest & store the data.. that will hurt when you turn on a factory of fleet of sensors

Can anyone find me an unfunded edge analytics startup? This is a huge growth area in industry...winners will help to determine perishable vs. long-term valuable data, vs. don't capture and/or don't store data

I wonder how many people here are industrial vs. infrastructure/network background vs. data scientists?

from data lakes to integrated edge "appliances" stream/db/ML in one

@awf1967 The problem has always been compute/storage scalability in an unforgiving environment - manufacturing floors, for example

I can say with certainty that Autonomous Driving algorithms MUST be built with ALL the data.

@yaronhaviv right - bring the model to the data

where is the edge? Last mile, telco, metro?

@BertLatamore Interesting anecdote. Could we begin to see airports turning into edge server hubs, and sell service to major airlines?

Motion & acoustic modeling - for good accuracy we should be considering sample rates in the 10's of Hz at least. 10-100 samples a second per tag. And you can't just burn a model in and walk away. Conditions in the real world change

as we move towards more "AUTONOMOUS" analytics at the Edge, building the logic will require data also to reach data scientists and Cloud or Data Center.

John DesJardins does timeseries data matter in real time data when the time is changing so the series analysis also changes? thoughts

greater focus on density, power,

@williamgeller new generation of ruggedized Smart Edge gateways and Fog nodes can help

Also think about CONTEXT - Context is missing at the Edge - Weather, Customer, Product, and other enterprise data

Yes.

Time-series data IS the number one type of data at the Edge

@awf1967 all great points! a lot of people overlook the improved security. First it is more secure because you don't have to move everything and second because the intelligence at the edge can make up for less intelligent things including analyzing risks

Also - SEASONALITY - how do you model for seasonal factors when you only have MINUTES of data or less?

When it comes to machine sensor data - we never have all the data with respect to the physics that are being sampled. We have just that - samples that live within the limits of the sensing device and communications infrastructure.

serverless is the new stream processing

@dfloyer We like to call that data 'perishable' - it is only valuable for a split second

just because the INSIGHTS are perishable, doesn't mean that the data doesn't also have value for training models.

@kdtwill Value can assume many forms. Yes, it has a short life for alerting and some level of decision making, but it may live longer for research and analysis (e.g. re-train analytical models).

I expect that a lot of industrial data will be analyzed in real time at the site for actionable info -- e.g. out of range readings indicating a developing mechanical problem.

For those wondering, by "basic physics" we're really focusing on the costs of latency and entropy, which are real and won't change due to 5G.

The vase majority of edge IIOT data will go directly to tape on site. As David Floyer likes to say, a truck full of tapes has the highest bandwidth. & it is cheap transport.

NHTSA has also issued directives for retaining all data used by Autonomous Driving systems.

I say yes to this question bc not all industrial systems are connected to IT systems; converging the data is huge value

YES! @ejkraemer may have a thought or two here. ;)

Yes, because these control towers don't enable Innovation and Differentiation.

we also need analytics at aggregation points

Yes, especially with quality defects. Too often siloed production controls towers are "green" and products come out with defects. Monitoring an entire production zone or an entire line ensures those defects can be eliminated.

A control system is no more an analytics platform than the server running a credit card transaction platform is a "data warehouse". We evolved analytics platforms from production systems decades ago in the enterprise. I see room for this in IoT

Absolutely! A lot of the data produced is perishable (milliseconds), high-volume, low latency, and required immediate action. So IoT edge analytics are a must.

also, these Control Towers do not incorporate context from Enterprise data.

Can these existing systems provide the needed context for this next wave of computing?

better analytics systems will feed control systems. improving the control systems. I'm a fan of virtuous cycles. IIoT at its best would be such a cycle.

yes it can help Extend asset life, Reduce unplanned downtime, Optimize maintenance schedules, Lower parts and inventory costs, Lower maintenance costs

@plburris, thus also gets to the heart of "Why IoT" in the first place, and brings us back to the latency and perishable data points. Any time there is life or death or high finance on the line, edge analytics are critical.

Yes. @plburris mainly, IoT brings harmonisation of services, and connecting with the customers and more.

Spot on. It's that context that drives final performance.

much of this controls data is exponentially more valuable when you can integrate it into IT systems like ERP, but you don't want all the data. The IoT-enabled edge analytics is the span filter from the controls systems

Is it appropriate to look at existing Control Systems and related telemetry as "available" to co-opt as a cloud connected analytics channel? Is that a practical approach?

Absolutely! Specific analytics for different vertical and functions, and cross industry analytics for functionality such a video security

@yaronhaviv Absolutely agree. This will provide the power to store and analyze within hubs, ensuring a lower cost, with high-value data sets and algorithms sent to the core for deeper analysis.

Importance of edge analytics not limited to these use cases, though - even sensing anomalous vibration in a smart factory assembly line more quickly at the edge can mean the difference between 1 misassembled unit and numerous.

@kdtwill Agree! While 100% of the data can be analyzed @ edge, only about 20% of the data (usually aggregated) is useful to centralize

@kdtwill More than just a filter - It is also a point of abstraction and security. Control vs analytics are often different service levels

@Calvinsmith19 So real time analytics at the edge.

IoT data will increase, and machines will become more complex, requiring lower latency - in some cases. in-place edge analytics will be necessary. Consider motor vehicles using data to enhance performance and safety, especially self-driving.

This will be especially important for energy management on production lines as information from the entire line is needed for optimization

Industrial industries like healthcare, retail, automotive, and manufacturing are being impacted by #IoT

@capdevielle At the moment, due to limitations on scalability, a lot of data at the edge is dumped before its true value can be assessed.

real-time at the edge is very important for driving good models with fast reaction times. But training, improving and validating models requires history - more than just the recent "stream". This is tough - real time and historical data buffering

@furrier In healthcare, at least in Brazil, I see a nice trend in IoT for homecare. Health systems won't be able to cope with the exploding costs of traditional hospital settings.

@furrier it's back to the IT + OT data combined for business transformation discussion