Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Machine Learning and Simulations for Asset Mana...
Search
Gijs Molenaar
March 13, 2020
Science
1
85
Machine Learning and Simulations for Asset Management at Alliander
Gijs Molenaar
March 13, 2020
Tweet
Share
More Decks by Gijs Molenaar
See All by Gijs Molenaar
Easy to deploy and easy to modify data reduction pipelines using KERN and CWL
gijzelaerr
1
68
Research Engineering in Radio Astronomy
gijzelaerr
3
110
The story of CWLifying Apercal
gijzelaerr
0
87
Deep Vacuum Cleaner
gijzelaerr
1
68
EOSC LOFAR pilot final presentation
gijzelaerr
1
140
Software packaging and data pipelines
gijzelaerr
1
160
Docker - 3 years later
gijzelaerr
0
160
Radio astronomy data reduction at PyData Amsterdam
gijzelaerr
3
250
Data reduction pipelines using Docker for the MeerKAT telescope
gijzelaerr
0
110
Other Decks in Science
See All in Science
Trend Classification of InSAR Displacement Time Series Using SAE–CNN
satai
3
450
03_草原和博_広島大学大学院人間社会科学研究科教授_デジタル_シティズンシップシティで_新たな_学び__をつくる.pdf
sip3ristex
0
470
データベース10: 拡張実体関連モデル
trycycle
PRO
0
690
LayerXにおける業務の完全自動運転化に向けたAI技術活用事例 / layerx-ai-jsai2025
shimacos
1
1.1k
サイゼミ用因果推論
lw
1
7.3k
モンテカルロDCF法による事業価値の算出(モンテカルロ法とベイズモデリング) / Business Valuation Using Monte Carlo DCF Method (Monte Carlo Simulation and Bayesian Modeling)
ikuma_w
0
170
深層学習を用いた根菜類の個数カウントによる収量推定法の開発
kentaitakura
0
160
04_石井クンツ昌子_お茶の水女子大学理事_副学長_D_I社会実現へ向けて.pdf
sip3ristex
0
490
機械学習 - pandas入門
trycycle
PRO
0
260
データベース09: 実体関連モデル上の一貫性制約
trycycle
PRO
0
680
オンプレミス環境にKubernetesを構築する
koukimiura
0
260
メール送信サーバの集約における透過型SMTP プロキシの定量評価 / Quantitative Evaluation of Transparent SMTP Proxy in Email Sending Server Aggregation
linyows
0
930
Featured
See All Featured
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Why Our Code Smells
bkeepers
PRO
337
57k
The Art of Programming - Codeland 2020
erikaheidi
54
13k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.3k
The Straight Up "How To Draw Better" Workshop
denniskardys
234
140k
Into the Great Unknown - MozCon
thekraken
39
1.9k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
For a Future-Friendly Web
brad_frost
179
9.8k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
670
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
357
30k
VelocityConf: Rendering Performance Case Studies
addyosmani
330
24k
Transcript
Machine Learning and Simulations for Asset Management March 13, 2020,
NL-RSE Meetup Gijs Molenaar
pythonic.nl • Me! • Freelance Software/Research Engineer • MSc AI
(UvA) • PhD astronomy (South Africa)
• Public Utility company • 5.7 million client connections •
5700 FTE
None
None
The problem • Fixed budget • How to optimally distribute
budget over departments • Balance between long term and short term goals
Amsterdam • Go fully electric by 2030 • 900.000 people
• 230.000 private cars • 10 years • 2610 working days • 1000 charging stations a day?
Our solution • Build agent based simulation of company •
Run millions of simulations up to 40 years in the future • Let Reinforcement Learning agent explore and optimize problem space
What do we need? • A physical model • A
bunch of agents manipulating this model
None
None
Reinforcement Learning
Reinforcement Learning st st+1 a
Deep-Q learning Simulation agent != Reinforcent learning Agent
State • Number of connection issues Reward • function of
• Budget spend • Average waiting time for new connection • Average Waiting time for fix of broken connection Action Decision of budget split
Project structure • 3 teams: • Data Engineers • Data
Scientists • Software Engineers
None
Evaluating 2 strategies • Compute in neo4j • Compute in
NumPy + NetworkIt
None
Rpy2 R has NA values in int arrays, numpy has
NaN in float arrays
Status report • Still working on simulations • Underestimated the
effort required to get this right • Maybe too ambitious? • Useful nonetheless
Research Engineer in Corporate environment • Different setting • Requires
different mindset • More budget • A lot of politics
pythonic.nl available again! • 1 June 2020 • First getting
married in Namibia • If we don’t get Corona banned
Questions?