Benchmark-Modell
dispatchatlas.bench definiert Benchmark-Belege, bevor Solver oder Kampagnen sie
konsumieren. Eine Benchmark-Familie deklariert ihre Taxonomie, ihr Domänenprofil, ihre
Profilklasse, ihre Annahmen, ihren Zitationsbeleg, ihre Skalenhülle, ihren
Seed-Namensraum, und ihr Ausgabeschema. Die Materialisierung validiert jedes generierte
Problem mit dispatchatlas.core, charakterisiert die Instanz, hüllt sie in einen
Provenienz-Umschlag, und zeichnet stabile Hashes auf.
Der Katalog deckt generische kombinatorisch-optimierungs Planungsfamilien und Distributed-Computing-Planung als co-gleiche Peers ab, sodass die Plattform kein nur-Distributed-Computing-Werkzeug ist.
Ausführbares Beispiel: examples/benchmark_continuum.py generiert, charakterisiert, und katalogisiert einen Kontinuum-Benchmark-Atlas im Flug.
Planungsfamilien
Jede Planungsfamilie wird als erstklassiger Katalog-Peer mit mindestens einem Generatorprofil materialisiert. Die Katalogtabelle unten wird aus der Benchmark-Generator-Registry und der Zitationsmatrix generiert, sodass ihre Familien-Summen und Quellzitationen aus den Zeilen selbst zählbar sind. Ein Familien-Verteilungs-Diagramm über der Tabelle zeigt, wie sich die Familienprofile über die Planungsfamilien-Kategorien verteilen.
Generated from the benchmark generator registry and the citation matrix: 69 family profiles across 8 scheduling families — distributed-computing (47), flow-shop (7), job-shop (6), machine-scheduling (3), open-shop (1), rcpsp (3), rcpsp-max (1), setup-flow-shop (1).
Showing 69 of 69 family profiles.
| Distinctive against | Evidence | Citation status | Source citations | |||
|---|---|---|---|---|---|---|
accelerator-coschedulingaccelerator-coscheduling a heterogeneous datacenter job needs a compute resource and a scarce accelerator at the same time, so every job co-allocates two simultaneous resource demands held together for its whole run; the accelerator pool is scarce, so jobs sharing an accelerator serialize on it while jobs on disjoint resources run in parallel, and the scheduler reasons over a multi-resource co-allocation problem rather than a single-unit-demand one | distributed-computing | ioe-complete | published single-resource continuum schedulers (one unit resource demand per task, not the simultaneous co-allocation of a compute resource and a scarce accelerator held together under a Pareto contract) | smoke | citation-backed |
|
aerial-edgeaerial-edge a loitering UAV is a flying fog node that serves the ground region beneath it for a fixed loiter window before moving to the next pass, so sorties group into successive loiter passes pinned to the fog tier the platform embodies while overhead | distributed-computing | ioe-complete | aerial-edge MEC simulators (no flying-fog loiter placement) | smoke | citation-backed |
|
anytime-inferenceanytime-inference an edge accelerator serves deep-learning inference requests that each complete a mandatory minimal-accuracy early-exit branch and may run an optional refinement to full accuracy when their latency deadline allows; every request declares a mandatory duration below its full duration and a tight latency deadline, and arrivals are spaced shorter than a full inference so requests queue and contend, so the scheduler decides which requests refine and which deliver the early-exit result -- an imprecise-computation quality-versus-timeliness trade-off | distributed-computing | ioe-complete | published edge-cloud split inference and datacenter inference serving (a fixed full-accuracy computation per request), neither of which lets a request drop an optional refinement to meet its deadline so the schedule order trades accuracy for timeliness | smoke | citation-backed |
|
blocking-flow-shopblocking-flow-shop | flow-shop | classical | — | smoke | citation-backed |
|
bulk-synchronous-graphbulk-synchronous-graph an iterative graph computation runs as a sequence of supersteps separated by global barriers, so each superstep's vertex partitions compute and exchange messages and every partition of the next superstep waits on all partitions of the prior one; the slowest partition therefore gates each superstep, and the scheduler reasons over a barrier-synchronized partition-balancing problem rather than an overlap-friendly pipeline or an independent-task one | distributed-computing | ioe-complete | published pipeline or independent-task schedulers (an overlap-friendly wavefront or unsynchronized tasks, not supersteps separated by global barriers where the slowest partition gates each round under a Pareto contract) | smoke | citation-backed |
|
carbon-awarecarbon-aware flexible jobs defer to low-carbon-intensity windows under a time-varying grid carbon signal while honoring their SLA deadlines | distributed-computing | ioe-complete | Electricity-Maps grid carbon-intensity and CityLearn carbon-aware community signals | smoke | citation-backed |
|
cloud-independentcloud-edge-independent | distributed-computing | domain-specific | — | smoke | citation-backed |
|
coflow-schedulingcoflow-scheduling a distributed-computing stage completes only when the last network transfer of its coflow lands, not the first, so a coflow's completion time is the maximum over its member flows; every coflow emits data-heavy flow tasks that place freely across the fabric plus a barrier task that depends on all of them, so the barrier gates the group and the coflow-completion-time is an all-or-nothing footprint | distributed-computing | ioe-complete | datacenter coflow schedulers (no continuum tier-placement barrier) | smoke | citation-backed |
|
compact-job-shopcompact-job-shop | job-shop | classical | — | smoke | citation-backed |
|
confidential-edgeconfidential-edge tasks are classified by data sensitivity -- a confidential task that touches protected data must execute inside the enclave-capable trusted tier so its data never leaves the trusted boundary, while a public task draws a free placement affinity across the fabric | distributed-computing | ioe-complete | edge enclave runtimes (no security-classified Pareto placement) | smoke | citation-backed |
|
cyber-physicalcyber-physical control cycles arrive periodically under a time-varying tariff | distributed-computing | ioe-complete | periodic hard-real-time task models and smart-grid demand-side scheduling formulations (no edge-fog-cloud tier placement under a Pareto contract) | smoke | citation-backed |
|
data-localitydata-locality a query over a large dataset is cheaper to run where the data already resides than to ship the data across the WAN fabric; each task's input lives on one tier (edge sensor logs, fog warm aggregates, or cloud cold archives) and the task pins to that tier so its heavy input never crosses the fabric, with the data tiers cycled so placement spans the whole edge-fog-cloud continuum | distributed-computing | ioe-complete | cluster locality schedulers (no continuum data-residency placement) | smoke | citation-backed |
|
datacenter-colocationdatacenter-colocation latency-sensitive service jobs and deferrable batch jobs share multi-tenant cells, so high-priority-band jobs claim capacity ahead of low-band jobs under contention | distributed-computing | ioe-complete | Google Borg ClusterData2019 priority-tiered cell traces | smoke | citation-backed |
|
digital-twin-syncdigital-twin-sync each physical asset periodically syncs its state to its fog/cloud twin and must finish within a freshness (Age-of-Information) window before the twin's state goes stale | distributed-computing | ioe-complete | digital-twin edge frameworks (no joint Pareto placement) | smoke | citation-backed |
|
disaggregated-memorydisaggregated-memory a CXL-pooled cloud platform backs each socket with a small local DRAM tier and a shared far-memory pool, and every VM draws a long-tailed memory working set, so a few memory-hungry tenants dominate a socket's local budget while far-memory access inflates a VM's runtime in proportion to the working set it spills to the pool; the scheduler reasons over local-versus-pool placement rather than core-count placement | distributed-computing | ioe-complete | published CXL memory-pooling and tiered-memory systems (socket-local page placement, no edge-fog-cloud tier scheduling under a Pareto contract) | smoke | citation-backed |
|
distributed-assembly-flow-shopdistributed-assembly-flow-shop | flow-shop | classical | — | smoke | citation-backed |
|
distributed-flexible-job-shopdistributed-flexible-job-shop | job-shop | structurally-complex | — | smoke | citation-backed |
|
distributed-permutation-flow-shopdistributed-permutation-flow-shop | flow-shop | classical | — | smoke | citation-backed |
|
distributed-training-gangdistributed-training-gang a GPU cluster runs synchronous data-parallel training jobs; each job is a gang of workers that must START TOGETHER on distinct accelerators (every all-reduce step synchronizes the workers), so a job cannot begin until enough accelerators are free simultaneously; the workers reuse the accelerator pool and jobs arrive over time, so jobs queue and the scheduler decides which job acquires a full simultaneously-free worker set first -- an all-or-nothing gang co-start, not an independent placement of each worker | distributed-computing | ioe-complete | published GPU-cluster and inference-serving families that place each task independently; none requires a whole job's worker set to co-start simultaneously on distinct accelerators, so no other family forbids a partial start -- the gang-scheduling all-or-nothing constraint under a Pareto contract | smoke | citation-backed |
|
distributed-transactiondistributed-transaction a partitioned database runs transactions that each acquire exclusive locks on a variable read/write set of data shards, so every transaction co-allocates a randomly drawn subset of shards held together for its whole run; two transactions whose shard sets intersect serialize while disjoint transactions commit in parallel, so the scheduler reasons over a variable-cardinality lock-conflict graph rather than a fixed two-resource hold | distributed-computing | ioe-complete | published replica-placement schedulers (a single shard pinned per task for locality, not a variable-cardinality exclusive lock set co-allocated per transaction forming a conflict graph under a Pareto contract) | smoke | citation-backed |
|
edge-offloadingedge-offloading-mec each task chooses between local edge execution and remote offload | distributed-computing | ioe-complete | iFogSim MEC offloading scenarios | smoke | citation-backed |
|
edge-placementedge-placement services place on edge servers near their user population and migrate as demand shifts across base-station coverage cells | distributed-computing | ioe-complete | EUA edge-user-allocation and Shanghai-Telecom base-station placement traces | smoke | citation-backed |
|
elastic-serverless-autoscaleelastic-serverless-autoscale a serverless platform serves function invocations on a shared worker pool, and every invocation is moldable: it may run on one, two, or four concurrent workers, where a wider allocation runs shorter by a sublinear speedup but spends more total worker-seconds; each request declares its execution modes and arrivals are spaced shorter than a base invocation so the pool is contended, so the scheduler picks each invocation's worker width -- a moldable latency-versus-cost choice rather than a fixed resource hold | distributed-computing | ioe-complete | published serverless cold-start and fixed-width co-allocation families (accelerator co-scheduling, fpga partitioning), each of which holds one fixed resource set per task; none lets a request choose among several worker-count modes so the schedule order trades latency for resource cost under a Pareto contract | smoke | citation-backed |
|
facility-assignmentfacility-assignment | machine-scheduling | classical | — | smoke | citation-backed |
|
failure-recoveryfailure-recovery a failed task re-places its checkpoint state to a surviving tier | distributed-computing | ioe-complete | Borg cluster failure-event traces | smoke | citation-backed |
|
federated-learningfederated-learning each training round selects a subset of heterogeneous, straggler-prone edge clients that train on non-IID local data, then a fog or cloud aggregator combines their updates | distributed-computing | ioe-complete | FedScale and Oort federated-learning device-participation benchmarks | smoke | citation-backed |
|
flexible-job-shopflexible-job-shop | job-shop | classical | — | smoke | citation-backed |
|
flow-shoppermutation-flow-shop | flow-shop | classical | — | smoke | citation-backed |
|
fpga-partitioningfpga-partitioning a multi-tenant reconfigurable FPGA hosts tenant kernels that each occupy a contiguous region of fabric tiles, so every kernel co-allocates a contiguous run of tiles held together for its whole residency; two kernels whose tile intervals overlap cannot be co-resident and serialize while kernels on disjoint tile spans run in parallel, so the scheduler reasons over an interval-overlap conflict graph rather than a fixed two-resource hold or a random-subset lock set | distributed-computing | ioe-complete | published accelerator co-scheduling (a fixed compute-plus-accelerator pair) and shard-lock transactions (a random subset of resources), neither of which constrains the co-allocated set to a spatially contiguous tile interval whose overlaps form an interval conflict graph under a Pareto contract | smoke | citation-backed |
|
frontierco-fjspfrontierco-fjsp | job-shop | classical | — | smoke | citation-backed |
|
generative-inference-servinggenerative-inference-serving a transformer inference replica batches autoregressive requests that each hold key-value-cache memory proportional to their token count for the whole decode, so a long-tailed sequence mix fragments a fixed cache budget and the scheduler reasons over memory-bound admission rather than GPU-count placement; every request's decode duration and KV-cache demand scale with its drawn token count | distributed-computing | ioe-complete | published single-replica generative-model serving systems (no edge-fog-cloud tier placement under a Pareto contract) | smoke | citation-backed |
|
gpu-mlgpu-ml training and inference jobs claim accelerators and gang-schedule replicas | distributed-computing | ioe-complete | Alibaba PAI, Philly, and Helios GPU-cluster traces | smoke | citation-backed |
|
hybrid-flow-shophybrid-flow-shop | flow-shop | classical | — | smoke | citation-backed |
|
immersive-xrimmersive-xr each extended-reality frame runs a latency-critical perception, render, and display pipeline placed across the device, edge, and cloud within a hard motion-to-photon deadline | distributed-computing | ioe-complete | ILLIXR extended-reality systems testbed | smoke | citation-backed |
|
intermittent-edgeintermittent-edge a batteryless sensor harvests ambient energy into a small buffer, runs until the buffer depletes, then sleeps to recharge; a job too large for one duty-cycle window is checkpointed at power loss and resumed in the next, so it is a precedence chain of edge-pinned per-window segments each bounded by the constant energy window | distributed-computing | ioe-complete | intermittent-computing runtimes (no continuum energy-window placement) | smoke | citation-backed |
|
iot-edgeiot-edge many small sensor readings arrive periodically and aggregate at the edge | distributed-computing | ioe-complete | published wireless-sensor-network telemetry datasets and in-network aggregation deployments (raw sensor readings, not edge-fog-cloud tier scheduling under a Pareto contract) | smoke | citation-backed |
|
job-shopjob-shop | job-shop | classical | — | smoke | citation-backed |
|
kv-cache-placementkv-cache-placement a distributed key-value cache tier serves a catalog of cache objects whose request rate follows a heavy Zipfian popularity skew, so a few hot objects absorb most of the traffic; each object is placement-flexible, carrying one single-node mode per cache-tier node, so the scheduler chooses which tier node hosts it, and an object's working set -- the transfer volume staged onto its host tier -- scales with its popularity rank, so the hottest object carries the largest working set and a cold-tail object the smallest; a naive uniform placement strands a hot, large-working-set object on a far tier and pays its transfer across the fabric, while a locality-aware placement pins the hottest objects to near tiers to shrink makespan and cost | distributed-computing | ioe-complete | published cache and content-placement families (consistent-hashing replica placement, CDN content distribution) that place each object uniformly or by a hash; none scales each object's working set with a Zipfian popularity rank so the hot objects carry a strictly larger transfer volume, making popularity-skewed near-tier pinning the lever a locality-aware placement pulls under the Pareto contract | smoke | citation-backed |
|
machine-schedulingmachine-scheduling-unrelated | machine-scheduling | classical | — | smoke | citation-backed |
|
microservice-dagmicroservice-dag services form an acyclic call graph pinned by role to a tier | distributed-computing | ioe-complete | Alibaba v2021 microservice-trace call graphs | smoke | citation-backed |
|
mixed-criticalitymixed-criticality a safety-critical real-time mix runs tasks of differing criticality, and a high-criticality task is budgeted with a conservative high-assurance worst-case execution time and a tight deadline while a low-criticality task carries a smaller best-effort budget and a loose deadline, so the criticality tiering lives in the duration and deadline structure; the scheduler reasons over which assured-criticality tasks to guarantee under contention rather than a uniform-assurance deadline-scheduling one | distributed-computing | ioe-complete | published uniform-assurance real-time deadline schedulers (one worst-case execution time and deadline class per task, not criticality-tiered WCET budgets with tighter high-assurance deadlines under a Pareto contract) | smoke | citation-backed |
|
moe-expert-parallelmoe-expert-parallel a sparsely-activated mixture-of-experts model routes each token batch to one expert and the experts are spread across devices, and expert popularity is long-tailed, so a few hot experts receive most token batches while many stay cold and the all-to-all routing exchange dominates fabric traffic; the scheduler reasons over an expert-placement and load-balancing problem rather than a dense uniform-replica serving one | distributed-computing | ioe-complete | published dense generative-model serving systems (uniform per-replica KV-cache admission, not sparse token-to-expert routing under load imbalance and a Pareto contract) | smoke | citation-backed |
|
multi-objective-pfspmulti-objective-pfsp | flow-shop | classical | — | smoke | citation-backed |
|
multi-project-rcpspmulti-project-rcpsp | rcpsp | structurally-complex | — | smoke | citation-backed |
|
multi-tenant-fair-sharemulti-tenant-fair-share a shared cluster serves several tenants whose workloads compete for one node pool; each task is placement-flexible, carrying one single-node mode per pool node, so the scheduler chooses which node it occupies; tenants are sized asymmetrically, so even a load-balanced placement leaves the heavy tenants holding a larger fraction of their busiest node -- a higher dominant resource share -- than the light ones, and a fairness-aware scheduler rebalances placement to shrink the dominant-share spread | distributed-computing | ioe-complete | published multi-tenant colocation families (Borg-style priority colocation, vm allocation) that fix each task's resource and score makespan or cost; none lets the scheduler choose each tenant task's node and scores the dominant-resource-share spread between tenants as a fairness objective | smoke | citation-backed |
|
network-slicingnetwork-slicing isolated slice classes (latency-critical, broadband, massive-IoT) each carry their own service-level deadline and placement, and same-class slices spread across tiers for resilience | distributed-computing | ioe-complete | 5G slicing orchestration (no joint Pareto placement) | smoke | citation-backed |
|
no-wait-flow-shopno-wait-flow-shop | flow-shop | classical | — | smoke | citation-backed |
|
open-shopopen-shop | open-shop | classical | — | smoke | citation-backed |
|
orbital-edgeorbital-edge tasks schedule across ground terminals, moving low-earth-orbit satellites, and cloud backhaul under time-varying connectivity as satellites enter and leave coverage and hand work over | distributed-computing | ioe-complete | LENS real-measurement LEO satellite-network traces | smoke | citation-backed |
|
pipeline-parallel-trainingpipeline-parallel-training a deep network is split into successive pipeline stages pinned across edge-to-cloud tiers and the training mini-batch is divided into micro-batches, so each micro-batch flows forward stage by stage while each stage runs its micro-batches in issue order; the two precedence families form a diagonal wavefront whose warm-up and cool-down idle slots are the pipeline bubbles, and deeper stages carry rising compute, so the scheduler reasons over a stage-partition and bubble-minimizing problem rather than a synchronous data-parallel all-reduce one | distributed-computing | ioe-complete | published data-parallel / gang-scheduled training systems (synchronous all-reduce over co-located replicas, not a stage-by-micro-batch pipeline wavefront with warm-up and cool-down bubbles under a Pareto contract) | smoke | citation-backed |
|
rcpsprcpsp-renewable | rcpsp | structurally-complex | — | smoke | citation-backed |
|
rcpsp-maxrcpsp-max | rcpsp-max | structurally-complex | — | smoke | citation-backed |
|
rcpsp-multi-modercpsp-multi-mode | rcpsp | structurally-complex | — | smoke | citation-backed |
|
reentrant-fabreentrant-fab | job-shop | structurally-complex | — | smoke | citation-backed |
|
replica-placementreplica-placement a replica runs where its data shard already lives | distributed-computing | ioe-complete | CRUSH replicated-data placement | smoke | citation-backed |
|
serverless-cold-startserverless-cold-start a cold invocation pays a container provisioning penalty | distributed-computing | ioe-complete | Azure Functions serverless-in-the-wild traces | smoke | citation-backed |
|
service-function-chainservice-function-chain an NFV packet flow traverses a linear ordered chain of typed virtual network functions -- firewall, intrusion detection, deep packet inspection, address translation -- each pinned to a tier that hosts its function type, so the chain is a strict total order and the flow crosses the edge-fog-cloud fabric in a fixed sequence; the scheduler reasons over a chain-placement problem under an end-to-end latency budget rather than the branching role-pinned call graph of a microservice | distributed-computing | ioe-complete | published microservice call-graph schedulers (a branching role-pinned acyclic call graph, not a strict linear chain of function-typed network functions under an end-to-end latency budget and a Pareto contract) | smoke | citation-backed |
|
setup-flow-shopsetup-flow-shop | setup-flow-shop | classical | — | smoke | citation-backed |
|
smartnic-offloadsmartnic-offload a SmartNIC-accelerated server pairs a fast host CPU with a low-power on-NIC processor, and every microservice draws a long-tailed compute intensity, so most are light enough to offload onto the energy-frugal NIC cores while a few compute-heavy services must stay host-bound; a service's runtime scales with its intensity, so the scheduler reasons over an energy-versus-latency offload-placement problem rather than a uniform host placement one | distributed-computing | ioe-complete | published mobile-edge computation-offloading models (device-to-edge latency offload, not in-server host-to-NIC energy offload under a Pareto contract) | smoke | citation-backed |
|
split-inference-servingsplit-inference-serving each inference request partitions a deep model at a layer cut -- a light head runs the early layers on the edge near the sensor and a heavy tail runs the later layers in the cloud, consuming the head's intermediate feature map under a per-request end-to-end latency SLO | distributed-computing | ioe-complete | datacenter inference serving (no edge-cloud partition placement) | smoke | citation-backed |
|
spot-preemptiblespot-preemptible a cloud provider rents idle capacity at a discount as revocable spot instances reclaimed after a short lease; eviction-tolerant batch work pins to the cloud spot tier under a hard lease deadline (the eviction horizon), while latency-critical interactive work pins to the stable edge on-demand tier with no eviction deadline | distributed-computing | ioe-complete | cloud spot schedulers (no continuum eviction-deadline placement) | smoke | citation-backed |
|
storage-io-tieringstorage-io-tiering a tiered storage pool serves I/O-bound jobs whose runtime is dominated by moving a job's I/O volume through the storage node it lands on; each job is placement-flexible, carrying one single-node mode per tier node, and the mode duration is tier-dependent -- a seek floor plus the I/O volume divided by that tier's I/O bandwidth, which differs by tier (a fast cloud array sustains far more bytes/second than a slow edge disk); a job's I/O volume follows a heavy-tailed falloff over its I/O-demand rank, so a few I/O-heavy jobs carry most of the bytes and have a large cross-tier duration spread, while the light tail barely varies; a naive placement strands an I/O-heavy job on a low-bandwidth tier and pays its volume slowly, while a bandwidth-aware placement pins the heavy jobs to fast tiers to shrink makespan and cost | distributed-computing | ioe-complete | published storage-tiering and hierarchical-storage-management families that migrate blocks between fast and slow tiers by access frequency; none models the heterogeneous-tier I/O bandwidth as a placement-flexible per-tier mode whose duration is the I/O volume divided by that tier's bandwidth, so an I/O-heavy job's cross-tier duration spread is the bottleneck-relief lever a bandwidth-aware placement pulls under the Pareto contract | smoke | citation-backed |
|
streaming-windowstreaming-window events arrive online in bounded windows and must close within one | distributed-computing | ioe-complete | Parallel Workloads Archive online arrivals | smoke | citation-backed |
|
time-sensitive-networkingtime-sensitive-networking each time-triggered flow releases on a fixed period and must finish within one cycle under a hard, jitter-free deadline | distributed-computing | ioe-complete | EdgeCloudSim best-effort scenarios (no gating) | smoke | citation-backed |
|
unrelated-parallel-setupunrelated-parallel-setup | machine-scheduling | structurally-complex | — | smoke | citation-backed |
|
vehicular-offloadingvehicular-offloading a vehicle's tasks share an arrival time and a roadside-unit dwell deadline, and hand over from the roadside unit to the fog tier as the vehicle drives on | distributed-computing | ioe-complete | EdgeCloudSim / SUMO vehicular-edge mobility scenarios | smoke | citation-backed |
|
video-analyticsvideo-analytics each camera streams frames that must be analyzed within a tight real-time latency bound, placed hierarchically with edge inference near the camera and cloud aggregation | distributed-computing | ioe-complete | edge video-analytics clusters (no joint Pareto placement) | smoke | citation-backed |
|
vm-allocationvm-allocation size-heterogeneous virtual-machine deployments pack onto hosts while each deployment's members spread across distinct failure domains for availability | distributed-computing | ioe-complete | Azure Public Dataset Resource Central VM-allocation traces | smoke | citation-backed |
|
workflow-dagworkflow-dag | distributed-computing | structurally-complex | — | smoke | citation-backed |
|
Per-instance characterization and download eligibility live in the benchmark catalog; this table is the family-and-citation inventory.
Die Komponente oben trägt das vollständige generierte Inventar — die klassischen und Distributed-Computing-Kernfamilien unten plus das Kontinuum der Edge–Fog–Cloud-Familien. Diese grundlegenden Kernfamilien in Dokumentform:
| Familie | Profil | Profilklasse | Primärkorpus |
|---|---|---|---|
| Maschinenplanung (R||Cmax, unverwandte Maschine) | machine-scheduling-unrelated | classical | OR-Library |
| Job-Shop | job-shop-classical | classical | OR-Library, Taillard |
| Flexibler Job-Shop (FJSP) | flexible-job-shop | classical | Brandimarte; Hurink-Jurisch-Thole |
| Permutations-Flow-Shop | permutation-flow-shop | classical | Taillard |
| Sequenzabhängiger-Setup-Flow-Shop (SDST) | setup-flow-shop | classical | Allahverdi et al. (2008); Allahverdi (2015) |
| Ressourcen-beschränkte Projektplanung (RCPSP) | rcpsp-renewable | structurally-complex | PSPLIB |
| Distributed-Computing (cloud/edge) | cloud-edge-capacity | domain-specific | CloudSim; DynamicCloudSim; Edge vision |
| Distributed-Computing (workflow DAG) | workflow-dag | structurally-complex | Standard Task Graph Set |
Die unverwandte-Maschine- und flexible-Job-Shop-Familien hängen eine
CostModel-Ausführungszeit-Matrix an jede Instanz, exportiert als materialisierte Matrix
neben dem Problem-JSON. Die sequenzabhängige-Setup-Flow-Shop-Familie hängt stattdessen
eine CostModel-Setup-Matrix an: ein Wechsel zwischen Jobs verschiedener Familien auf
einer Maschine kostet Setup-Zeit, sodass das Setup-Ziel das Gruppieren ähnlicher Jobs
belohnt. Die genannten Standardkorpora werden nur zitiert und verlinkt und werden niemals
innerhalb des Repositorys weiterverteilt.
Mehrere Kontinuum-Familien üben Multi-Ressourcen-Co-Allokation: jede Aufgabe fordert
mehr als eine Ressource gleichzeitig und der Konstruktor hält sie für ihre ganze Dauer
zusammen (siehe Domänenverträge). Die Familie
accelerator-coscheduling co-allokiert einen Rechenknoten und einen knappen Beschleuniger
pro Job; die Familie distributed-transaction co-allokiert eine
variabel-kardinale Sperr-Menge von Daten-Shards pro Transaktion; und die Familie
fpga-partitioning co-allokiert einen räumlich zusammenhängenden Lauf von
rekonfigurierbaren Gewebe-Kacheln pro Mandanten-Kernel. Aufgaben, deren Ressourcen-Mengen
sich schneiden, serialisieren, während disjunkte Aufgaben gleichzeitig laufen — das
ausführbare examples/inspect_coallocation.py
macht den Hebel explizit.
Über die Co-Allokation hinaus üben drei Kontinuum-Familien ihre eigenen strukturellen
Hebel. Die Familie elastic-serverless-autoscale übt formbare Ausführung: jede
Funktionsaufrufung deklariert mehr als einen Ausführungsmodus — einen schmalen
Nur-Zuhause-Modus und einen weiten Modus, der einen Worker von einem kleinen geteilten
Burst-Pool leiht, um früher fertig zu werden — sodass der Plan einen Modus pro Aufgabe
wählt und die Reihenfolge entscheidet, welche Aufrufungen den knappen weit-und-schnellen
Modus beanspruchen. Die Familie distributed-training-gang übt Gang-Co-Scheduling: die
Worker eines synchronen daten-parallelen Trainingsjobs teilen einen Gang und müssen auf
distinkten Beschleunigern in einem Alles-oder-Nichts-Start co-starten — die Worker
wiederverwenden den Beschleunigerpool und Jobs treffen über die Zeit ein, sodass ein Job
nicht beginnen kann, bis genug Beschleuniger gleichzeitig frei werden, und die Reihenfolge
entscheidet, welcher Job zuerst seine volle Worker-Menge erwirbt. Die Familie
multi-tenant-fair-share übt Dominant-Ressourcen-Fairness: mehrere
asymmetrisch-große Mandanten platzieren platzierungs-flexible Aufgaben auf einem geteilten
Knotenpool, und das Dominant-Ressourcen-Anteil-Ziel bewertet die Spreizung zwischen dem
dominanten Anteil des meist- und am wenigsten-bedienten Mandanten — sodass die
Platzierung, welche Ressourcen jeder Mandant belegt, der Hebel ist, der sie ausbalanciert
oder verzerrt. Die ausführbaren
examples/serverless_autoscale_study.py,
examples/distributed_training_gang_study.py,
und
examples/multi_tenant_fairshare_study.py
machen diese drei Hebel explizit.
Profilklassen
| Profilklasse | Bedeutung |
|---|---|
classical | Leitet aus einem standard kombinatorisch-optimierungs Korpus ab. |
structurally-complex | Trägt Präzedenz-, DAG-, oder Ressourcen-Netzwerk-Struktur. |
ioe-complete | Internet-of-Everything-vollständiges verteiltes Szenario. |
trace-backed | In einer benannten Real-World-Workload-Trace begründet. |
domain-specific | Auf eine einzige operative Domäne zugeschnitten. |
Beleglabels
| Label | Verwendung |
|---|---|
smoke | Kleine deterministische Instanzen für Tests, Beispiele, Docs, und Vorschauen. |
exploratory | Plausibles Material, das noch nicht zitations-gestützt oder vollständig charakterisiert ist. |
| Kandidaten-Belegstufe | Zitations-gestütztes Material, das auf Piloten-, statistische, und Kampagnen-Gates wartet. |
| Vollkampagnen-Belegstufe | Beleg, der die Zitations-, Charakterisierungs-, statistischen, Offenlegungs-, und Qualitäts-Gates bestanden hat. |
Smoke-Kataloge sind niemals finale Evaluationsbelege. Sie existieren, um zu beweisen, dass
Generatoren, Validierung, Charakterisierung, Zitationsprüfungen, und Persistenz schnell
funktionieren. Der Portal-Katalog und die Downloads zeigen jede Kontinuum-Familie in
dieser kleinen Smoke-Skala (einem Drei-Ressourcen-Pool) als Vorschau; eine
Co-Allokations-Familie kann disjunkt-Ressourcen-Parallelismus auf einem so kleinen Pool
nicht zeigen, sodass die distinktive Struktur eine Forschungs-Skala-Eigenschaft ist.
build_continuum_full_catalog() materialisiert jede Familie in ihrer deklarierten
Forschungsskala -- dem größeren Ressourcenpool und der Aufgabenanzahl, wo sich die
Co-Allokations-, Contention-, und Platzierungsstruktur wahrhaft manifestiert -- für
Forschungs-Grade-Benchmark-Pakete.
Taxonomie
Die Taxonomie deckt Planungsstrukturen, Umgebungen, Infrastruktur-Realismus, Zielmerkmale, Constraint-Merkmale, Ungewissheit, und Dynamik ab. Beispiele umfassen DAG-Workflows, unabhängige Aufgaben-Batches, serverlose Funktionen, Container- und VM-Konsolidierung, Edge- und Cloud-Umgebungen, öffentliche Traces, Mehrziel-Optimierung, Deadlines, Datenlokalität, Churn, und dynamische Ankünfte.
Zitationsmatrix
Benchmark-Aussagen werden gegen CitationMatrix geprüft. Kandidaten- und
Vollkampagnen-Belegstufe-Aussagen bestehen die Validierung nicht, sofern sie nicht
zitations-gestützte Quellen referenzieren. Nicht-gestütztes Material muss exploratory
bleiben, bis Beleg hinzugefügt wird.
Die Quellmenge wird in default_citation_matrix() mit stabilen Quell-Identifiern,
auflösbaren Referenzen, und einer aufgezeichneten Lizenzhaltung deklariert. Sie umspannt
drei Stufen: die standard kombinatorisch-optimierungs Korpora (nur zitiert und verlinkt,
nie gebündelt), Produktions-Cluster-Traces, und eine breite Menge zeitgenössischer
Real-World-Edge–Fog–Cloud-Kontinuum-Datensätze — GPU- und Machine-Learning-Cluster-Traces,
Microservice- und Serverless-Benchmark-Suiten, Wissenschafts-Workflow-Traces,
Supercomputer-Job-Traces, Edge-Placement- und Mobilitäts-Datensätze, IoT- und
Mobilfunk-Nachfrage-Datensätze, Netz-Carbon- und -Energie-Signale,
Stream-Verarbeitungs-Workloads, Federated-Learning-Geräte-Teilnahme-Benchmarks,
Extended-Reality-Systeme-Testbeds, und Low-Earth-Orbit-Satelliten-Netz-Traces:
Kanonische Referenz-Suiten
Die Registry in default_reference_suites() zeichnet die kanonischen publizierten
Instanz-Suiten auf, an denen jede generische Planungsfamilie verankert ist: Identität,
Familie, Instanzanzahl, Abruf-Verweis, und die Best-Known-Solution-Tracker, die Schranken
für die Suite publizieren. Klassische Suiten werden nur zitiert und verlinkt —
DispatchAtlas bündelt oder verteilt niemals Instanzdateien Dritter weiter.
| Suite | Familie | Instanzen | Download | BKS-Tracker |
|---|---|---|---|---|
fisher-thompson | Job-Shop | 3 | OR-Library | van-hoorn-2018, scheduleopt-benchmarks |
lawrence | Job-Shop | 40 | JSPLIB-Spiegel | van-hoorn-2018, scheduleopt-benchmarks |
adams-balas-zawack | Job-Shop | 5 | JSPLIB-Spiegel | van-hoorn-2018, scheduleopt-benchmarks |
applegate-cook-orb | Job-Shop | 10 | JSPLIB-Spiegel | van-hoorn-2018, scheduleopt-benchmarks |
storer-wu-vaccari | Job-Shop | 20 | JSPLIB-Spiegel | van-hoorn-2018, scheduleopt-benchmarks |
yamada-nakano | Job-Shop | 4 | JSPLIB-Spiegel | van-hoorn-2018, scheduleopt-benchmarks |
taillard-jsp | Job-Shop | 80 | JSPLIB-Spiegel | van-hoorn-2018, scheduleopt-benchmarks |
demirkol-dmu | Job-Shop | 80 | JSPLIB-Spiegel | scheduleopt-benchmarks |
brandimarte-mk | Job-Shop (flexibel) | 15 | SchedulingLab-Spiegel | scheduleopt-benchmarks |
hurink-fjsp | Job-Shop (flexibel) | 198 | SchedulingLab-Spiegel | scheduleopt-benchmarks |
dauzere-peres-paulli | Job-Shop (flexibel) | 18 | SchedulingLab-Spiegel | scheduleopt-benchmarks |
taillard-pfsp | Flow-Shop | 120 | OR-Library | zenodo-pfsp-bks-2021 |
vrf-pfsp | Flow-Shop | 480 | SOA-Gruppen-Website | zenodo-pfsp-bks-2021 |
sdst-taillard-ruiz | Setup-Flow-Shop | 480 | SOA-Gruppen-Website | Bestlösungen werden mit den Instanzen ausgeliefert |
cicirello-wt-sds | Maschinenplanung | 120 | Harvard Dataverse | cicirello-wtsds-benchmark |
or-library-smtwt | Maschinenplanung | 375 | OR-Library | crauwels-potts-vanwassenhove-1998 |
vallada-ruiz-upmsp | Maschinenplanung | 1640 (berichtet) | SOA-Gruppen-Website | — |
psplib | RCPSP | 2040 | PSPLIB-Website | psplib-1997 |
mmlib | RCPSP | 4320 (berichtet) | OR&S-Startseite | solutionsupdate-ugent-rcpsp |
rg300 | RCPSP | 480 | OR&S-Startseite | solutionsupdate-ugent-rcpsp |
Suiten mit einem gebündelten Parser (Standard-Job-Shop-Text, Taillard-Flow-Shop-Matrizen,
flexibler .fjs-Job-Shop, WfCommons-WfFormat-JSON) werden mit
load_reference_suite(suite_id, instances_root=...) aus Dateien ingestiert, die der
Operator herunterlädt und unter einem lokalen resources/-Baum ablegt. Die Ingestion
läuft vollständig offline, nutzt dieselbe Validierung, Charakterisierung, dasselbe
Hashing, und denselben Provenienz-Umschlag wie die synthetischen Generatoren, und stempelt
jedes Problem mit seiner suite_id und upstream_instance_id. Nur-Registry-Suiten werden
mit ihren Zitationen und Abruf-Verweisen ohne gebündelten Parser aufgezeichnet.
Best-Known-Solution-Registries
Best-Known-Werte pro Instanz werden niemals mit DispatchAtlas ausgeliefert. Der Operator
ingestiert sie als JSON-Dateien unter einem privaten Verzeichnis
resources/benchmarks/bks/, eine Datei pro Suite, jede mit schema_version, der
suite_id, der Tracker-source_id, dem Abrufdatum, und den Wert-Einträgen (Instanz-Id,
Ziel, Wert, Optimum-oder-Oberschranke-Art, optionale Unterschranke).
load_best_known_registry validiert jede Datei gegen die Referenz-Suiten und die
Zitationsmatrix und schlägt bei unbekannten Suiten, unbekannten Trackern, doppelten
Einträgen, oder inkonsistenten Schranken schließend fehl. Ohne eine ingestierte Registry
sind Relativ-Abweichungs-Metriken schlicht nicht verfügbar — sie werden niemals teilweise
berechnet, und kein Best-Known-Wert erscheint auf irgendeiner öffentlichen Oberfläche.
Kalibrierungs-Divergenzen
Die synthetischen generischen Familien sind an den kanonischen Suiten verankert, ohne zu beanspruchen, deren Generierungsschemata zu reproduzieren. Die bekannten Divergenzen werden dokumentiert statt versteckt:
| Familie | Publizierte Konvention | Synthetische Konvention |
|---|---|---|
| Setup-Flow-Shop | SDST-Taillard-Setups bei 10/50/100/125% der Bearbeitungszeit | drei Setup-Familien, Kosten = Familie + 1 |
| Maschinenplanung (R||Cmax) | U[1,100]-Dauerklassen und korrelierte-Maschinen-Varianten | Geschwindigkeitsfaktoren 0.5–2.0 pro Paar |
Vergleiche gegen die publizierten Konventionen laufen über die ingestierten kanonischen Instanzen, nicht über die synthetischen Familien.
Charakterisierung
Jedes materialisierte Problem erhält normalisierte Deskriptoren für:
- Gelegenheitsdichte
- Kompatibilitäts-Sparsity
- Contention und Überlast
- Abhängigkeitstiefe
- Kommunikationsdruck
- Setup-Intensität
- Lastschiefe und Heterogenität
- Zielkonflikt
- Ungewissheit und Dynamik
- Solver-Sensitivität
Distribution-Distance-Brücke
Jedes Vollkampagnen-Belegstufe-Profil deklariert eine Distribution-Distance-Brücke: ihren Status
(synthetic, calibrated-synthetic, trace-backed, oder externally-sourced), ihren
Kalibrierungsbeleg, ihr Domänenszenario, ihre Transfer- und Disruptionsabdeckung, und ihr
verbleibendes Distribution-Distance-Risiko. Die Beförderung zur Vollkampagnen-Belegstufe schlägt
schließend fehl, sofern Transfer- und Disruptionsabdeckungen nicht deklariert sind, und
ein calibrated-synthetic-Profil muss die trace-backed-Referenz nennen, gegen die es
kalibriert. Calibrated-synthetic-Familien nennen ihre Trace-Referenz explizit;
ingestierte kanonische Suiten tragen eine externally-sourced-Brücke, und der
WfCommons-Adapter ist die erste extern-geparste trace-backed-Instanzquelle, wodurch
distribution_distance_score ein echtes trace-backed-Referenz-Standbein erhält.
Die benannte Kalibrierungsmetrik berichtet die 1-Wasserstein-(Erdbeweger-)Distanz
pro-Merkmal zwischen den Charakterisierungs-Merkmals-Verteilungen eines
calibrated-synthetic-Profils und denen seiner trace-backed-Referenzinstanzen. Die
pro-Merkmal-Distanzen werden zu einer einzigen Distribution-Distance-Bewertung aggregiert; eine
Bewertung über dem Maximal-Divergenz-Schwellenwert (Standard 0.25) bedeutet, dass das
Profil zu weit von seiner Referenz abgedriftet ist und die Kalibrierung nicht besteht. Die
Metrik ist aus den materialisierten Instanzen und der benannten Referenz-Trace
reproduzierbar.
from dispatchatlas.bench import (
build_smoke_catalog,
metrics_from_instance_set,
distribution_distance_score,
)
catalogs = {c.config.profile_id: c for c in build_smoke_catalog()}
synthetic = metrics_from_instance_set(catalogs["cloud-edge-capacity"])
reference = metrics_from_instance_set(catalogs["workflow-dag"])
score = distribution_distance_score(
synthetic, reference, reference_trace_id="google-cluster-data"
)Stratifizierung und Teilmengenauswahl
difficulty_score aggregiert die Contention-, Überlast-, Abhängigkeitstiefe-, und
Solver-Sensitivitäts-Deskriptoren in eine normalisierte Schwierigkeitsbewertung, und
stratify_instances teilt materialisierte Instanzen in niedrige, mittlere, und hohe
Schwierigkeitsstrata. select_benchmark_subset wählt eine deterministische Teilmenge,
gefiltert nach Familie, Profilklasse, und Schwierigkeitsstratum, geordnet nach
Problem-Identifier, sodass die Auswahl reproduzierbar ist.
Smoke-Katalog
from dispatchatlas.bench import build_smoke_catalog, smoke_benchmark_provider
catalogs = build_smoke_catalog(root_seed=20260527)
provider = smoke_benchmark_provider(root_seed=20260527)
first_problem = provider.get_problem(provider.list_problem_ids()[0])Der gebündelte Smoke-Katalog umfasst die zwei Distributed-Computing-Familien (cloud/edge unabhängige-Aufgabe und workflow DAG) neben den vierzehn generischen Planungsfamilien (Maschinenplanung, Job-Shop, flexibler Job-Shop, Permutations-Flow-Shop, sequenzabhängiger-Setup-Flow-Shop, RCPSP, Open-Shop, hybrider Flow-Shop, verteilter Permutations-Flow-Shop, No-Wait-Flow-Shop, Blocking-Flow-Shop, verteilter Montage-Flow-Shop, Mehrziel-Permutations-Flow-Shop, und RCPSP/max) als co-gleiche Peers. Jede Instanz ist vom Wurzel-Seed deterministisch und nutzt zitations-gestützte Generator-Metadaten, während sie als Smoke-Entwicklungsmaterial gekennzeichnet bleibt.
Kandidaten-Vollkataloge
Kandidaten-Vollkampagnen-Kataloge nutzen denselben Materialisierungspfad mit größeren konfigurierten Problemanzahlen und strengeren Beleglabels:
from dispatchatlas.bench import build_full_catalog, full_benchmark_provider
catalogs = build_full_catalog(root_seed=2026052713, problem_count_per_profile=30)
provider = full_benchmark_provider(
root_seed=2026052713,
problem_count_per_profile=30,
)Diese Vollkampagnen-Belegstufe-Kataloge sind zitations-gestützt, charakterisiert, hash-verknüpft, und weiterhin als Kalibrierungsbeleg gekennzeichnet, bis Kampagnen-, Offenlegungs-, und Publikations-Gates spezifische Aussagen befördern.