This document discusses a system of systems approach for IoT systems to support smart food and farming use cases. It analyzes 19 use case architectures for meat, arable crops, vegetables, fruits and dairy. There are many commonalities across the use cases in terms of the types of data collected on animals, crops, weather conditions and soil. Technically, there are also commonalities in connectivity standards, device architectures and platforms used. The document recommends developing reusable components, reference data models and joint business models to promote synergies across the different but related use cases.
Blepharitis inflammation of eyelid symptoms cause everything included along w...
Systems of IoT Systems for Smart Food and Farming
1. SYSTEMS OF IOT SYSTEMS FOR
SMART FOOD AND FARMING
Cor Verdouw, Jeroen van Grondelle, Robbert Robbemond, Sjaak Wolfert
Wageningen University & Research
AgEng2018, July 10th 2018, Wageningen, The Netherlands
3. IOF2020 > SUM OF THE USE CASES
Synergies across use cases crucial for large-scale take-up
3
4. OUTLINE OF THE PRESENTATION
4
Systems of Systems approach
Analysis Use Case Architectures
Main Commonalities
Recommended synergy actions
5. SYSTEM OF SYSTEMS
arrangement of systems that results when independent
and useful systems are integrated into a larger system
that delivers unique capabilities
(Tekinerdogan, 2017)
5
Porter, M. E., & Heppelmann, J. E. (2014). How smart, connected products
are transforming competition. Harvard Business Review, 92(11), 64-88.
6. CRITERIA SYSTEM OF SYSTEMS (MAIER 1998)
• Operational Independence of Elements
• Managerial Independence of Elements
• Evolutionary Development
• Emergent Behavior
• Geographical Distribution of Elements
6
Heterogeneity
Not prescribing
particular tools or
technologies!
Convergence through Synergy and Reuse
In all life cycle phases
10. ANALYSIS APPROACH
• Tag at the level of use cases first
• Logical (functions and data) and
technical dimension
• Validation by the use case owners
10
Measures: Humidity
Predicts: Crop Growth
Controls: Water supply
(to influence: Yield)
Lora Connectivity
Deployed near Animals
16. PRELIMINARY DATA MODEL ANALYSIS
• We see common underlying information modeling questions
• How to model time and location of sensor measurements
• Time dimension
• Continuous time series from static sensors
• Measurements from incidentally/nomadic deployed sensors
• Measurements from machine operation
• Location, measurements of different granularity
• Crop growth/m2, rain measurements for complete field
• Crop growth measurement after each weeding, rain every 15 minutes
• Comparing/correlating data from different resolution granularity
• Critical for sharing and reusing data for new use cases
16
17. CONNECTIVITY MODELS
13 of the UCs use some
form of LPWAN or LR-
WPAN
Existing tech such as
Wifi, Bluetooth, Ethernet
and Serial Bus remain
very relevant
NB-IoT not used
23. MAIN COMMONALITIES TECH PERSPECTIVE
• Connectivity
• Low Power Long Range
Connectivity (Lora/Sigfox)
• Short range (LR-WPANs
• Localization
• GPS
• Lora/Sigfox localization
• Beacons
• Device architecture
• autonomous
deployment/solar/battery
23
• IoT data management
• FIWARE Context Broker
• FIWARE IoT Agent
• EPCIS
• 365FarmNet
• Supporting IoT
capabilities
• Device management
• Security
24. RECOMMENDED NEXT STEPS
24
Catalogue &
Market Place
Task Forces &
Guidelines
Identify Gaps
for Open Call
Develop
Reusable
Components
Reference Data
Models
Joint business models/
exploitation of solutions
25. MANY THANKS FOR
YOUR ATTENTION!
Cor Verdouw, Jeroen van Grondelle, Robbert Robbemond, Sjaak Wolfert
Editor's Notes
The core of the project lies within 5 trials. These cover 5 sectors (arable, dairy, fruits, vegetables and meat).
To showcase each of the trials, the project is organized around 19 use cases.
Information-centric
Provides user with up-to-date and historic sensor data for better decision making
In architectures: Dashboards, descriptive analytics
Task-oriented Decision Support
Actively supports users in specific, task oriented decisions using intervention suggestions, i.e. irrigation map, machine settings. User decides.
In architectures: Statistical Models, Algorithms, Predictive Analytics
Automated Control and/or Planning
The system (semi-) autonomously intervenes based on sensor data to reach preset objectives or optimize selected outcome variables
Farmer in principle accepts systems interventions, but may override/adjust
In architectures: Actuation based on models, prescriptive analytics