Analytics & ML · Study deck

Practical Edge Computing: Bandwidth and Inference Budgets

Five hundred vibration sensors can produce about 1 MB each second.

Data Dora is your guide for this deck.

edgepatternspractical
Data Dora, the module guide, in a scene from this chapter.
iotclass.org

After studying this chapter

Learning objectives

You will be able to:

  • Test putting numbers to it with a concrete scenario and pass criteria.
  • Define related chapters and resources with explicit inputs, errors, and change rules.
  • test putting numbers to it with a concrete scenario and pass criteria
  • define related chapters and resources with explicit inputs, errors, and change rules
iotclass.org

Major section

Start With the Decision · Putting Numbers to It

Five hundred vibration sensors can produce about 1 MB each second.

  • An edge FFT can cut that stream before it crosses the link.
  • Actually, with additional on-edge anomaly filtering (transmit only when vibration exceeds threshold), real-world deployments achieve 95% reduction -> 121 GB/month.

Numbers to remember

1 MBFive hundred vibration sensors can produce about 1 MB each second.

Why it matters

The 95% data reduction from edge FFT analysis also dramatically reduces both bandwidth and storage costs.

iotclass.org

Major section

Drone Landing Edge ML Budget · Multi-Model Edge Memory

Scenario: A drone delivery company needs to deploy a landing zone detection model on their drones.

  • The model must run on-device to ensure safe landing even when cellular connectivity is lost.
  • They need to calculate if edge inference meets the strict latency requirements.

Numbers to remember

180 msThe float32 MobileNetV2-SSD result takes 180 ms per frame

Why it matters

The worked example selects the 65 ms result because it leaves the most time inside the stated limit; the selection depends on these measurements and must be repeated on the actual deployed hardware and software stack.

iotclass.org

Major section

Edge ML Latency Calculator · Deployment Patterns and Standards

Industrial sites often expect OPC UA, Modbus, BACnet, IEC 61499, or LWM2M support; cloud-managed edge fleets may use AWS IoT Greengrass, Azure IoT Edge, EdgeX Foundry, or Kubernetes-at-edge tooling.

  • The right answer is the smallest stack that can meet latency, offline, security, and maintainability requirements without creating a second unmanaged platform.
iotclass.org

Major section

Pitfall: Over-Processing at the Edge · Clock Drift and Time Sync Risk

The mistake: Assuming edge devices maintain accurate timestamps without explicit synchronization, leading to out-of-order events, incorrect correlations, and analytics anomalies that are nearly impossible to debug.

  • Network outages prevent NTP synchronization.

Why it matters

The mistake: Running complex ML models or heavy analytics at the edge "because we can," consuming battery and compute resources faster than necessary while providing marginal improvement over simple threshold checks.

iotclass.org

Major section

No OTA Update Strategy · Edge Is Not Always Disconnected

The mistake: Deploying edge devices with firmware/software that cannot be remotely updated, leaving the fleet stuck on buggy or insecure versions, requiring expensive truck rolls to fix issues that could be patched remotely.

  • The fix: Design for the spectrum of connectivity states, not just offline.
iotclass.org

Major section

Summary · Concept Check

Factory monitoring example shows edge-hybrid architecture saves 41% over 3 years while meeting 50 ms latency requirements.

  • Memory optimization example shows 64% savings through activation sharing and INT8 quantization.

Numbers to remember

64%Memory optimization example shows 64% savings through activation sharing
iotclass.org

Major section

Quick Knowledge Check

For low-volume deployments (<1 GB/day), cloud-only is typically cheaper.

  • Q: Why can't you rely on average latency alone when designing edge systems?: Cloud average latency might be 200 ms, but peak spikes can reach 2+ seconds during network congestion.
  • Safety-critical systems must guarantee worst-case latency, not average latency.
iotclass.org

Major section

Try It Yourself · Calculate Edge ROI

Scenario:: You're proposing edge gateways to reduce cloud costs for a sensor deployment.

  • Current cloud costs ($/month): _______.
  • Data reduction factor is the key variable.
iotclass.org

Major section

Key Takeaway · Continue Your Route

Edge computing decisions should be driven by numbers, not assumptions.

  • Hybrid architectures -- edge for time-critical decisions, cloud for complex analytics -- typically deliver the best results, and designing for device failures, clock drift, and OTA updates from day one prevents costly rework later.
iotclass.org

Deck summary

Key takeaways

Five hundred vibration sensors can produce about 1 MB each second.

  • Scenario: A drone delivery company needs to deploy a landing zone detection model on their drones.
  • Industrial sites often expect OPC UA, Modbus, BACnet, IEC 61499, or LWM2M support; cloud-managed edge fleets may use AWS IoT Greengrass, Azure IoT Edge, EdgeX Foundry, or Kubernetes-at-edge tooling.
  • The mistake: Assuming edge devices maintain accurate timestamps without explicit synchronization, leading to out-of-order events, incorrect correlations, and analytics anomalies that are nearly impossible to debug.
  • Factory monitoring example shows edge-hybrid architecture saves 41% over 3 years while meeting 50 ms latency requirements.
iotclass.org

Retrieval practice

Recall check 1 of 5

Data Dora says: answer from memory, then check your reasoning.

Q1Place each edge-deployment responsibility where it lives so you can release a workload that fits the gateway and recover when the field configuration drifts.

AHardware Resource Budget
BSigned Workload Bundle
CSite Network and Device Configuration
DHealth Telemetry and Rollback
Show answer

Answer: A Place each edge-deployment responsibility where it lives so you can release a workload that fits the gateway and recover when the field configuration drifts.

Q2Complete the edge computing data aggregation function:

Aself.buffer = deque(maxlen=window_size)
Bself.buffer = list()
Cself.buffer = np.zeros(window_size)
Dself.buffer = deque()
Show answer

Answer: A Edge aggregation uses a fixed-size deque buffer to maintain a sliding window of readings.

iotclass.org

Retrieval practice

Recall check 2 of 5

Data Dora says: answer from memory, then check your reasoning.

Q3A factory safety system monitors 200 vibration sensors on critical machines. An emergency shutdown must be triggered within 20 ms if any sensor crosses a dangerous threshold. The factory also wants weekly trend reports and predictive-maintenance models trained on historical data. Where should processing for each function primarily live?

AAll processing in the cloud; edge devices simply forward raw data
BThreshold checks and shutdown logic at the edge; aggregation and model training in the cloud
CAll processing on an on-premises fog cluster; edge devices act as dumb sensors
DOnly in a centralized SCADA server; no edge or cloud components are needed
Show answer

Answer: B The edge compute patterns chapter emphasises that time-critical decisions (tens of milliseconds) must be made close to the source.

iotclass.org

Retrieval practice

Recall check 3 of 5

Data Dora says: answer from memory, then check your reasoning.

Q4A remote oil pipeline uses battery-powered pressure sensors connected via intermittent satellite links (sometimes offline for hours). Operators need near-real-time leak alarms when connectivity exists, and a complete history once the link returns. Which edge pattern best fits this scenario?

ACloud-only processing: buffer nothing locally, then recompute from live telemetry after each satellite outage
BStateless edge filtering: drop all readings below threshold and never store history for slow leak review
CStore-and-forward edge node: local buffering plus alarm logic, with delayed upload when connectivity returns
DAlways-on video analytics at the edge, streaming compressed frames over the intermittent satellite link
Show answer

Answer: C Intermittent links are a classic case for the store-and-forward edge pattern described in this chapter.

iotclass.org

Retrieval practice

Recall check 4 of 5

Data Dora says: answer from memory, then check your reasoning.

Q5In the seven-level IoT reference model, which level primarily converts data in motion into data at rest (e.g., persistent storage)?

ALevel 1: Physical Devices
BLevel 2: Connectivity
CLevel 3: Edge/Fog Computing
DLevel 4: Data Accumulation
Show answer

Answer: D Level 4 (Data Accumulation) is where data transitions from in-motion to at-rest.

iotclass.org

Retrieval practice

Recall check 5 of 5

Data Dora says: answer from memory, then check your reasoning.

Q6In edge processing, what does distillation usually mean?

AEncrypting all sensor data at rest while keeping the same raw sample volume and feature payload unchanged
BReducing raw data volume via aggregation/feature extraction while retaining decision-relevant information
CConverting IPv4 packets to IPv6 packets while forwarding the complete sensor payload without summarising it
DIncreasing sampling rate to capture more detail, then sending every raw sample upstream for later cloud filtering
Show answer

Answer: B Distillation reduces bandwidth and storage costs (e.g., summary stats, FFT bins, anomaly features) while keeping the information needed for local decisions or cloud analytics.

iotclass.org

Print reference

Answers 1 of 2

Answer key.

  1. A · Place each edge-deployment responsibility where it lives so you can release a workload that fits the gateway and recover when the field configuration drifts.
  2. A · Edge aggregation uses a fixed-size deque buffer to maintain a sliding window of readings.
  3. B · The edge compute patterns chapter emphasises that time-critical decisions (tens of milliseconds) must be made close to the source.
  4. C · Intermittent links are a classic case for the store-and-forward edge pattern described in this chapter.
iotclass.org

Print reference

Answers 2 of 2

Answer key.

  1. D · Level 4 (Data Accumulation) is where data transitions from in-motion to at-rest.
  2. B · Distillation reduces bandwidth and storage costs (e.g., summary stats, FFT bins, anomaly features) while keeping the information needed for local decisions or cloud analytics.
iotclass.org