Meerkat: Scalable, Network-Aware Failure Recovery for the Internet of Things

Summary: Meerkat: a network-aware fault-tolerance protocol for IoT achieving zero-downtime recovery via redundant operator execution on disjoint network paths and efficient duplicate detection, designed for hierarchical, resource-constrained topologies. Adds dynamic, load-balanced operator placement to adapt to device volatility, yielding up to 70× throughput with only 28% network overhead. (summarized by gpt-5-mini on Mar 13 2026)

Paper ID: h75ece14299388aa7
Venue: VLDB
Year: 2026
Pagerank: 4.9793485e-05
Overall Rank: 10,846 | 27.08%
DOI: 10.14778/3778092.3778094

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Anastasiia Kozar (Berlin Institute for the Foundations of Learning and Data; Technical University of Berlin)
2. Ankit Chaudhary (Berlin Institute for the Foundations of Learning and Data; Technical University of Berlin)
3. Steffen Zeuch (Berlin Institute for the Foundations of Learning and Data; Technical University of Berlin)
4. Volker Markl (Berlin Institute for the Foundations of Learning and Data; German National Research Center for Information Technology; Technical University of Berlin)

BibTeX Citation

@article{kozar_vldb26,
        title = {{Meerkat: Scalable, Network-Aware Failure Recovery for the Internet of Things}},
        author = {Kozar, Anastasiia and Chaudhary, Ankit and Zeuch, Steffen and Markl, Volker},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {3},
        pages = {306--319},
        doi = {10.14778/3778092.3778094},
        url = {https://doi.org/10.14778/3778092.3778094},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 16 of 16 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
112	TelegraphCQ: Continuous Dataflow Processing for an Uncertain World	2003	CIDR	0.00032459277
606	Twitter Heron: Stream Processing at Scale	2015	SIGMOD	0.00015635133
1,123	Structured Streaming: A Declarative API for Real-Time Applications in Apache Spark	2018	SIGMOD	0.0001193233
1,233	Dhalion: Self-Regulating Stream Processing in Heron	2017	VLDB	0.00011405873
1,402	State Management in Apache Flink: Consistent Stateful Distributed Stream Processing	2017	VLDB	0.00010771949
1,946	Aurora: A Data Stream Management System	2003	SIGMOD	9.3249193e-05
3,033	Chi: A Scalable and Programmable Control Plane for Distributed Stream Processing Systems	2018	VLDB	7.7337998e-05
3,370	Frontier: Resilient Edge Processing for the Internet of Things	2018	VLDB	7.3695613e-05
3,398	Megaphone: Latency-conscious state migration for distributed streaming dataflows	2019	VLDB	7.3353479e-05
4,613	Efficient Placement of Decomposable Aggregation Functions for Stream Processing over Large Geo-Distributed Topologies	2024	VLDB	6.5016725e-05
4,866	Clonos: Consistent Causal Recovery for Highly-Available Streaming Dataflows	2021	SIGMOD	6.3754084e-05
5,343	The NebulaStream Platform: Data and Application Management for the Internet of Things	2020	CIDR	6.1708665e-05
5,356	Load Management and High Availability in the Medusa Distributed Stream Processing System	2004	SIGMOD	6.1620521e-05
6,441	Grizzly: Efficient Stream Processing Through Adaptive Query Compilation	2020	SIGMOD	5.7834762e-05
10,773	Incremental Stream Query Deployment under Continuous Infrastructure Changes in the Cloud-Edge Continuum	2026	VLDB	4.9793485e-05
11,521	Fault Tolerance Placement in the Internet of Things	2024	SIGMOD	4.9793485e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,419	The Tree Quorum Protocol: An Efficient Approach for Managing Replicated Data	1990	VLDB
2	13,378	Improving Fault Tolerance and Supporting Partial Writes in Structured Coterie Protocols for Replicated Objects	1992	SIGMOD
3	9,773	Cost-based Fault-tolerance for Parallel Data Processing	2015	SIGMOD
4	13,998	RAFT at Work: Speeding-Up MapReduce Applications under Task and Node Failures	2011	SIGMOD
5	8,406	In-Network Leaderless Replication for Distributed Data Stores	2022	VLDB
6	7,749	Efficient Distributed Transaction Processing in Heterogeneous Networks	2023	VLDB
7	8,214	Log-Based Recovery for Middleware Servers	2007	SIGMOD
8	10,880	Orca: Flexible Quorums Meet Dynamic Quorums	2026	VLDB
9	3,370	Frontier: Resilient Edge Processing for the Internet of Things	2018	VLDB
10	11,521	Fault Tolerance Placement in the Internet of Things	2024	SIGMOD