Anticipatory Troubleshooting

Authors: Netantel Hasidi, Roni Stern, Meir Kalech, Shulamit Reches

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To evaluate the proposed algorithms, we performed two sets of experiments: one-shot experiments, in which a single TP is solved (evaluates the method in Section 4.1), and long-term experiments, in which troubleshooting costs are accumulated (evaluates the method in Section 5.2).
Researcher Affiliation Academia Ben Gurion University of the Negev Be er Sheva, Israel {hasidi,sternron,kalech}@bgu.ac.il Shulamit Reches Jerusalem College of Technology Jerusalem, Israel shulamit.reches@gmail.com
Pseudocode No The paper describes algorithms and decision rules (DR1) conceptually but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statement about releasing source code or a link to a code repository.
Open Datasets Yes The second system, denoted S2, is the CAR DIAGNOSIS 2 network from the library of benchmark BN made available by Norsys (www.norsys.com/netlib/Car Diagnosis2.dnet).
Dataset Splits No The paper describes the generation of random TPs for experiments but does not provide specific details on train/validation/test splits, percentages, or sample counts for the data used in the evaluation.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as CPU/GPU models, memory, or cloud instance types.
Software Dependencies No The paper mentions using Bayesian networks and an MBD algorithm, but it does not list any specific software components or libraries with their version numbers (e.g., Python, PyTorch, CPLEX version).
Experiment Setup Yes We set the age of each component to be Ageinit plus a random number between zero and Agediff, where Ageinit is a constant set arbitrarily to 0.3 and Agediff is a parameter we varied in our experiments. ... The punish-factor parameter P controls the difference between the after-fix and the regular survival function. ... We experimented with a range of values for these two parameters and studied their impact on the long-term costs. ... All results are averaged over 50 instances.