Partitioning and Multi-core Parallelization of Multi-equation Forecast Models View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2012

AUTHORS

Lars Dannecker , Matthias Böehm , Wolfgang Lehner , Gregor Hackenbroich

ABSTRACT

Forecasting is an important analysis technique used in many application domains such as electricity management, sales and retail and, traffic predictions. The employed statistical models already provide very accurate predictions, but recent developments in these domains pose new requirements on the calculation speed of the forecast models. Especially, the often used multi-equation models tend to be very complex and their estimation is very time consuming. To still allow the use of these highly accurate forecast models, it is necessary to improve the data processing capabilities of the involved data management systems. For this purpose, we introduce a partitioning approach for multi-equation forecast models that considers the specific data access pattern of these models to optimize the data storage and memory access. With the help of our approach we avoid the redundant reading of unnecessary values and improve the utilization of the CPU cache. Furthermore, we utilize the capabilities of modern multi-core hardware and parallelize the model estimation. Our experimental results on real-world data show speedups of up to 73x for the initial model estimation. Thus, our partitioning and parallelization approach significantly increases the efficiency of multi-equation models. More... »

PAGES

106-123

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-31235-9_7

DOI

http://dx.doi.org/10.1007/978-3-642-31235-9_7

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1037989607


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "SAP Research Dresden, SAP AG, Chemnitzer Str. 48, 01187, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.19008.30", 
          "name": [
            "SAP Research Dresden, SAP AG, Chemnitzer Str. 48, 01187, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Dannecker", 
        "givenName": "Lars", 
        "id": "sg:person.016070302115.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016070302115.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Database Technology Group, Technische Universit\u00e4t Dresden, N\u00f6thnitzer Str. 46, 01187, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "Database Technology Group, Technische Universit\u00e4t Dresden, N\u00f6thnitzer Str. 46, 01187, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "B\u00f6ehm", 
        "givenName": "Matthias", 
        "id": "sg:person.010351262023.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010351262023.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Database Technology Group, Technische Universit\u00e4t Dresden, N\u00f6thnitzer Str. 46, 01187, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.4488.0", 
          "name": [
            "Database Technology Group, Technische Universit\u00e4t Dresden, N\u00f6thnitzer Str. 46, 01187, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lehner", 
        "givenName": "Wolfgang", 
        "id": "sg:person.014174244741.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014174244741.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "SAP Research Dresden, SAP AG, Chemnitzer Str. 48, 01187, Dresden, Germany", 
          "id": "http://www.grid.ac/institutes/grid.19008.30", 
          "name": [
            "SAP Research Dresden, SAP AG, Chemnitzer Str. 48, 01187, Dresden, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hackenbroich", 
        "givenName": "Gregor", 
        "id": "sg:person.012241057077.14", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012241057077.14"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2012", 
    "datePublishedReg": "2012-01-01", 
    "description": "Forecasting is an important analysis technique used in many application domains such as electricity management, sales and retail and, traffic predictions. The employed statistical models already provide very accurate predictions, but recent developments in these domains pose new requirements on the calculation speed of the forecast models. Especially, the often used multi-equation models tend to be very complex and their estimation is very time consuming. To still allow the use of these highly accurate forecast models, it is necessary to improve the data processing capabilities of the involved data management systems. For this purpose, we introduce a partitioning approach for multi-equation forecast models that considers the specific data access pattern of these models to optimize the data storage and memory access. With the help of our approach we avoid the redundant reading of unnecessary values and improve the utilization of the CPU cache. Furthermore, we utilize the capabilities of modern multi-core hardware and parallelize the model estimation. Our experimental results on real-world data show speedups of up to 73x for the initial model estimation. Thus, our partitioning and parallelization approach significantly increases the efficiency of multi-equation models.", 
    "editor": [
      {
        "familyName": "Ailamaki", 
        "givenName": "Anastasia", 
        "type": "Person"
      }, 
      {
        "familyName": "Bowers", 
        "givenName": "Shawn", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-31235-9_7", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-642-31234-2", 
        "978-3-642-31235-9"
      ], 
      "name": "Scientific and Statistical Database Management", 
      "type": "Book"
    }, 
    "keywords": [
      "modern multi-core hardware", 
      "specific data access patterns", 
      "data access patterns", 
      "multi-core hardware", 
      "data management system", 
      "multi-core parallelization", 
      "data processing capabilities", 
      "important analysis technique", 
      "real-world data", 
      "accurate forecast model", 
      "redundant readings", 
      "application domains", 
      "access patterns", 
      "parallelization approach", 
      "traffic prediction", 
      "CPU cache", 
      "memory access", 
      "processing capabilities", 
      "data storage", 
      "employed statistical models", 
      "model estimation", 
      "partitioning approach", 
      "management system", 
      "unnecessary values", 
      "forecast model", 
      "new requirements", 
      "multi-equation model", 
      "calculation speed", 
      "electricity management", 
      "statistical model", 
      "experimental results", 
      "analysis techniques", 
      "accurate prediction", 
      "capability", 
      "speedup", 
      "parallelization", 
      "hardware", 
      "cache", 
      "estimation", 
      "domain", 
      "forecasting", 
      "model", 
      "requirements", 
      "prediction", 
      "access", 
      "recent developments", 
      "partitioning", 
      "retail", 
      "approach", 
      "system", 
      "help", 
      "speed", 
      "storage", 
      "technique", 
      "efficiency", 
      "utilization", 
      "management", 
      "data", 
      "sales", 
      "time", 
      "use", 
      "purpose", 
      "development", 
      "results", 
      "values", 
      "reading", 
      "patterns"
    ], 
    "name": "Partitioning and Multi-core Parallelization of Multi-equation Forecast Models", 
    "pagination": "106-123", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1037989607"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-31235-9_7"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-31235-9_7", 
      "https://app.dimensions.ai/details/publication/pub.1037989607"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:49", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_261.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-31235-9_7"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-31235-9_7'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-31235-9_7'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-31235-9_7'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-31235-9_7'


 

This table displays all metadata directly associated to this object as RDF triples.

155 TRIPLES      22 PREDICATES      92 URIs      85 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-31235-9_7 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author Nf43a7652200243d8a7781b8010fe2962
4 schema:datePublished 2012
5 schema:datePublishedReg 2012-01-01
6 schema:description Forecasting is an important analysis technique used in many application domains such as electricity management, sales and retail and, traffic predictions. The employed statistical models already provide very accurate predictions, but recent developments in these domains pose new requirements on the calculation speed of the forecast models. Especially, the often used multi-equation models tend to be very complex and their estimation is very time consuming. To still allow the use of these highly accurate forecast models, it is necessary to improve the data processing capabilities of the involved data management systems. For this purpose, we introduce a partitioning approach for multi-equation forecast models that considers the specific data access pattern of these models to optimize the data storage and memory access. With the help of our approach we avoid the redundant reading of unnecessary values and improve the utilization of the CPU cache. Furthermore, we utilize the capabilities of modern multi-core hardware and parallelize the model estimation. Our experimental results on real-world data show speedups of up to 73x for the initial model estimation. Thus, our partitioning and parallelization approach significantly increases the efficiency of multi-equation models.
7 schema:editor N440b3417a50d45ae9614a5d51096e11e
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N9b0f21fb7ee64df78634d698113b5a0b
11 schema:keywords CPU cache
12 access
13 access patterns
14 accurate forecast model
15 accurate prediction
16 analysis techniques
17 application domains
18 approach
19 cache
20 calculation speed
21 capability
22 data
23 data access patterns
24 data management system
25 data processing capabilities
26 data storage
27 development
28 domain
29 efficiency
30 electricity management
31 employed statistical models
32 estimation
33 experimental results
34 forecast model
35 forecasting
36 hardware
37 help
38 important analysis technique
39 management
40 management system
41 memory access
42 model
43 model estimation
44 modern multi-core hardware
45 multi-core hardware
46 multi-core parallelization
47 multi-equation model
48 new requirements
49 parallelization
50 parallelization approach
51 partitioning
52 partitioning approach
53 patterns
54 prediction
55 processing capabilities
56 purpose
57 reading
58 real-world data
59 recent developments
60 redundant readings
61 requirements
62 results
63 retail
64 sales
65 specific data access patterns
66 speed
67 speedup
68 statistical model
69 storage
70 system
71 technique
72 time
73 traffic prediction
74 unnecessary values
75 use
76 utilization
77 values
78 schema:name Partitioning and Multi-core Parallelization of Multi-equation Forecast Models
79 schema:pagination 106-123
80 schema:productId Nbe9e95e0810e47d7b2116cb0cd016325
81 Nec17ab1162ab4c5f852e14f34ffcf3b6
82 schema:publisher N8290a038eb674f10ad45e2f50d760fd0
83 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037989607
84 https://doi.org/10.1007/978-3-642-31235-9_7
85 schema:sdDatePublished 2022-12-01T06:49
86 schema:sdLicense https://scigraph.springernature.com/explorer/license/
87 schema:sdPublisher N3751dddaa2ee4b3784b9f516f38b31a5
88 schema:url https://doi.org/10.1007/978-3-642-31235-9_7
89 sgo:license sg:explorer/license/
90 sgo:sdDataset chapters
91 rdf:type schema:Chapter
92 N0d757f88597f483d97d7782c8bf34738 rdf:first sg:person.012241057077.14
93 rdf:rest rdf:nil
94 N29e43186935f4769a808401a652d27a9 rdf:first Nc7833ba688e94f6fb38a4b6dae5eb3fe
95 rdf:rest rdf:nil
96 N3751dddaa2ee4b3784b9f516f38b31a5 schema:name Springer Nature - SN SciGraph project
97 rdf:type schema:Organization
98 N440b3417a50d45ae9614a5d51096e11e rdf:first Ne48a8c1e64044640a5a97f168f0003bc
99 rdf:rest N29e43186935f4769a808401a652d27a9
100 N522c2cefcedc4fc6b0c2a7b0ca850527 rdf:first sg:person.014174244741.81
101 rdf:rest N0d757f88597f483d97d7782c8bf34738
102 N8290a038eb674f10ad45e2f50d760fd0 schema:name Springer Nature
103 rdf:type schema:Organisation
104 N9b0f21fb7ee64df78634d698113b5a0b schema:isbn 978-3-642-31234-2
105 978-3-642-31235-9
106 schema:name Scientific and Statistical Database Management
107 rdf:type schema:Book
108 Nbe9e95e0810e47d7b2116cb0cd016325 schema:name doi
109 schema:value 10.1007/978-3-642-31235-9_7
110 rdf:type schema:PropertyValue
111 Nc7833ba688e94f6fb38a4b6dae5eb3fe schema:familyName Bowers
112 schema:givenName Shawn
113 rdf:type schema:Person
114 Ne48a8c1e64044640a5a97f168f0003bc schema:familyName Ailamaki
115 schema:givenName Anastasia
116 rdf:type schema:Person
117 Nec17ab1162ab4c5f852e14f34ffcf3b6 schema:name dimensions_id
118 schema:value pub.1037989607
119 rdf:type schema:PropertyValue
120 Nf32d7ebc2acf4ed99cb97d062d14b37b rdf:first sg:person.010351262023.46
121 rdf:rest N522c2cefcedc4fc6b0c2a7b0ca850527
122 Nf43a7652200243d8a7781b8010fe2962 rdf:first sg:person.016070302115.81
123 rdf:rest Nf32d7ebc2acf4ed99cb97d062d14b37b
124 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
125 schema:name Mathematical Sciences
126 rdf:type schema:DefinedTerm
127 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
128 schema:name Statistics
129 rdf:type schema:DefinedTerm
130 sg:person.010351262023.46 schema:affiliation grid-institutes:grid.4488.0
131 schema:familyName Böehm
132 schema:givenName Matthias
133 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010351262023.46
134 rdf:type schema:Person
135 sg:person.012241057077.14 schema:affiliation grid-institutes:grid.19008.30
136 schema:familyName Hackenbroich
137 schema:givenName Gregor
138 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012241057077.14
139 rdf:type schema:Person
140 sg:person.014174244741.81 schema:affiliation grid-institutes:grid.4488.0
141 schema:familyName Lehner
142 schema:givenName Wolfgang
143 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014174244741.81
144 rdf:type schema:Person
145 sg:person.016070302115.81 schema:affiliation grid-institutes:grid.19008.30
146 schema:familyName Dannecker
147 schema:givenName Lars
148 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016070302115.81
149 rdf:type schema:Person
150 grid-institutes:grid.19008.30 schema:alternateName SAP Research Dresden, SAP AG, Chemnitzer Str. 48, 01187, Dresden, Germany
151 schema:name SAP Research Dresden, SAP AG, Chemnitzer Str. 48, 01187, Dresden, Germany
152 rdf:type schema:Organization
153 grid-institutes:grid.4488.0 schema:alternateName Database Technology Group, Technische Universität Dresden, Nöthnitzer Str. 46, 01187, Dresden, Germany
154 schema:name Database Technology Group, Technische Universität Dresden, Nöthnitzer Str. 46, 01187, Dresden, Germany
155 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...