TU Wien:Advanced Internet Computing VU (Dustdar)/Prüfung 2026-01-15

True/False Question

• Dynamic Neural Networks can decrease throughput.
• Service Level Objectives are coarse-grained metrics that are presented to clients by cloud providers.
• AI on the edge deals with the question of how we can leverage AI for optimization problems to facilitate Edge Computing.
• Software-as-a-Service and Platform-as-a-Service are worse in terms of vendor lock-in than Infrastructure-as-a-Service.
• Knowledge Distillation is exclusively a tool for model compression.
• Within services computing, loose coupling indicates the degree of dependency. Web services are tightly coupled
• Both ZigBee and SigFox are examples of Wireless Personal Area Networks.
• Split inference is faster when partitioning a neural network closer to the output layer.
• In order to reduce the managerial overhead, it is possible for an IoT service provider to connect LoRaWAN devices to community gateways instead of operating private ones.
• Multi-access Edge Computing is dependent on the network operator

Single Choice

• A number of IoT devices are deployed, where each device captures an image and posts it to an edge gateway via HTTP. The gateway then needs to select one out of multiple server instances (replicas) that are running on different hosts in an edge server cluster. When a server instance receives a request, it transcodes the respective image to a different format, and then stores it in a local database. For each request it receives, the gateway executes a machine learning algorithm to predict which server would lead to a minimum response time, and dispatches the request to it.
  • Osmotic Computing
  • AI for Edge
  • AI on Edge
  • AI Operationalization
• Consider a smart parking service which works as follows. A camera is capturing images from parking spots and transmits them to a remote server at a rate of 10 images/s. The server performs an image processing task where it identifies if the parking spot is occupied and, if so, it detects the license plate of the respective car. Which networking technology would you select to connect the camera device to the remote server?
  • a) LoRaWAN
  • b) NB-IoT
  • c) 4G
• An IoT application is in charge of collecting data from thousands of environmental sensors distributed over a country, performing some initial filtering of the data to detect faulty sensor readings, and storing them for future processing. Where would you host the storage?
  • a) On the cloud
  • b) At the edge

Multiple Choice

• A provider of computational resources (e.g., the operator of an IT center offering computational resources to customers) would rather provide virtualized resources like Virtual Machines instead of offering Physical Machines for reasons of (select all statements below that apply):
  • Backend parallelization
  • Customer security
  • Consolidation for energy consumption
  • Multitenancy
• Select all methods used for model compression. (A correct answer includes all the correct statements and only them. A wrong answer gets zero points.)
  • Structured Pruning
  • Transformers and Self-Attention Layers
  • Unstructured Pruning
  • Dark Knowledge-Based Methods
  • Dropout Regularization
  • Image Quantization
  • Activation Functions
• Which of the following statements are correct regarding Agentic Services Computing?
  • Agentic Services enable more predictable workflow execution
  • Testing Agentic Service workflows is simpler than traditional ones, due to the use of Generatice AI to automate test case generation and execution
  • Invoking an Agentic Service is more compute-intensive than invoking a traditional service
  • None of the above
• Which of the following statements are correct?
  • An advantage of artificial bottleneck injection is that it can take place without modifying an existing ML model
  • Applying structured pruning leads to a ML model with a sparser weight martrix
  • Unstructured pruning does not modify the architecture of the neural network it is applied to
  • When executing a ML model on an IoT device, applying quantization on the model uses less memory at the expense of slower inference.

Questions with Calculations

• The figure shows a redundant cloud deployment for a web application. The application can function properly if the load balancer is working, as well as at least one web server and at least one database server. The figure shows 1 load balancer, 2 web servers and 3 database servers. Assume that the individual component availabilities are as given below:
  • availability(load_balancer) = 0.999
  • availability(web_server) = 0.9
  • availability(database) = 0.75 What is the overall availability (AT) of the system?
  • a) AT <= 0.98 and AT >=0.95
  • b) AT > 0.98
  • c) AT < 0.95 What is the minimum number of web server replicas we need to add to the above configuration to achieve an availability of "two nines"?
  • We need to add at least two more web servers.
  • It is not possible to achieve two-nines availability by adding web servers.
  • We need to add at least three more web servers.
  • We need to add at least one more web server.
  • No need to add any web servers. The system's availability is already over two nines.
• Assume a scenario where 3 mobile devices participate in a federated learning task. Before a given training round, the server selects a subset of these devices, which will then perform training on their local data and submit model updates to the server. It is possible that a selected device fails to submit a report at the end of the round (e.g., it may run out of battery during the process, lose its connectivity, etc.). For each device, the probability that it successfully delivers its report in a round is given below:
  • Device 1: p1 = 0.1
  • Device 2: p2 = 0.6
  • Device 3: p3 = 0.5 At the same time, each device has a fixed cost to participate in a round. If selected, the cost of each device is given below:
  • Device 1: c1 = 10
  • Device 2: c2 = 20
  • Device 3: c3 = 25 The server needs to select the subset of devices to participate in the round which maximizes the expected number of reports that will be received by the server, under the constraint that the total cost of the solution is at most C = 30 (The total cost is defined as the sum of the costs of all devices that participate in a round. If a device is not selected, it does not contribute to the overall cost.)
  • (a) What is the optimal subset of devices that the server should select? Provide your answer in the following format: (X,Y,...). For example of the server selects devices 1 and 3, your answer should be (1,3), if the server selects device 2 your answer should be (2) etc. If there is no feasible solution, your answer should be (). This format is strict: Do not use whitespace characters in your answer; keep the parentheses.
  • (b) What is the total cost of the optimal solution? Provide a numerical value. If there is no feasible solution, answer with 0.
  • (c) What is the expected number of reports that the server will receive in this round under the optimal solution? Provide a numerical value. If there is no feasible solution, answer with 0.
• You are the provider of a large social networking service. One of the many functions of this service is the generation of JSON Web Tokens, i.e., cryptographically-signed objects that can be used, e.g., for authenticating user requests to various API endpoints of your service. This function requires 30 MB RAM and is invoked 1 million times per month. Each time it is invoked, it runs for 0.1 s. As a service provider, you have the following two options to host this function:
  • Option 1: Lease an on-demand virtual machine from an IaaS provider and host your function there. The cheapest offering which can fit your memory and other requirements costs 0.1 EUR/hour. There is no free tier.
  • Option 2: Deploy your function at a FaaS provider. In this case, the following charges apply:
    • Compute charges: 0.00001 EUR per MB-s
    • Request charges: 10 EUR per million requests
    • There is a free tier of 1 000 000 MB-s and 500 000 requests per month. You need to select the option with the minimum monthly cost. (Assumption: A month has 30 days.)
  • a) Which of the two options has the minimum monthly cost?
  • b) What is the minimum monthly cost? Please enter a numerical value.