PhD · AI · Energy · Smart Grid
Qashtalani
Haramaini

Electrical Engineer · AI Researcher
Expert in Power Systems & Distribution
Building intelligence for Indonesia's grid

Add photo
Qashtalani Haramaini
Energy Transaction Manager
PT PLN · Indramayu

Researcher
Universitas Indonesia

IEEE Professional Member
Profile

10+ years in Indonesia's electricity sector. I specialize in power distribution, smart metering, and non-technical loss reduction — combining deep operational expertise with applied research in AI and machine learning.

Passionate about how digital technologies and AI can transform the way Indonesia's electrical infrastructure operates, from theft detection to satellite-based asset inventory.

Education
Master of Electrical Engineering2018 – 2020
Universitas Indonesia · Depok
GPA 3.76 / 4.00 · Power Systems & Machine Learning · Supervisor: Prof. Iwa Garniwa
Bachelor of Electrical Engineering2012 – 2016
Universitas Indonesia · Depok
GPA 3.48 / 4.00
Experience
Energy Transaction Manager2023 – Now
PT PLN (Persero) · Indramayu
Energy transaction points management, non-technical loss programs, illegal usage enforcement.
Operational Unit Manager2021 – 2023
PT PLN (Persero) · Cimahi
300,000+ customers. Distribution operations, complaint resolution, SAIDI/SAIFI reliability targets.
Operation Distribution Team Leader2018 – 2021
PT PLN (Persero) · Cikarang
Network reliability, maintenance planning, fault response coordination.
Operation Analyst2016 – 2017
Engie · Paiton Power Plant
Power plant performance — operations, maintenance, and procurement optimization.
Innovation Project
CERDAS
Complaint Prediction · PLN Jabar Innovation Champion 2025
ML-based proactive complaint management system using keyword analysis for data-driven response strategies.
Research Interests
AI for Power Distribution Non-Technical Loss Detection Smart Metering & AMI Energy-to-Bitcoin Blockchain EV Charging Solar PV Policy Dynamic Tariffs Demand Side Management
Awards
2025PLN Jabar Innovation Champion — CERDAS
2023Australia Awards Awardee — Waste to Energy, Griffith University
2022Outstanding Participant — PLN Leadership Development Program
2021PLN English Olympiads 3rd Winner
Certifications
IELTS 6.5 · British Council 2025 (L:6.5 R:7.0 W:6.0 S:6.5)
Electrical Technician & Enforcement Supervisor · ESDM 2025
Assistant Manager — Distribution to End-User · ESDM 2025
Assistant Manager — Low-Voltage Distribution · ESDM 2022
Technical Skills
Python · Scikit-learnETAP · Power Systems YOLOv8 · MediaPipeLightGBM · CatBoost Claude API · LangGraphLeaflet.js · GIS VIIRS SatelliteAMR · Smart Metering Next.js · VercelTelegram Bot
Publications · 9 Papers
IEEE · Elsevier · IOP
IOP PUBLISHING · 2025 EnerBit Energy to Bitcoin: Strategy Model for Monetizing Indonesia's Power Surplus 7 GW capacity · ~56,640 BTC/year
IOP Publishing2025
EnerBit: Monetizing Idle Power Surplus via Bitcoin
IEEE ICTPEP 2024 · BALI, INDONESIA Anti-Theft Power Smart Metering System MCU STPM10 GPS/GPRS STM32F103C8T6 · AI Thinker A9G Non-Technical Loss Reduction · PLN DOI: 10.1109/ICTPEP63827.2024.10732892
IEEE ICTPEP · Bali2024
Anti-Theft Power Smart Metering System
J. ELECTRICAL SYSTEMS · 2024 Exploring Solar Panel Adoption & Socio-Economic Factors Pearson Correlation · Urban Indonesia NP ↔ TKE r = 0.857** NP ↔ HDI r = 0.622** NP ↔ PCS r = 0.651** DOI: 10.52783/jes.2756
J. Electrical Systems2024
Solar Panel Adoption & Socio-Economic Factors
IEEE CGEE 2022 · ISTANBUL Comparison of Medium-Term Load Forecasting Methods Actual load Forecast DOI: 10.1109/CGEE55282.2022.9976521
IEEE CGEE · Istanbul2023
Comparison of Medium-Term Load Forecasting Methods
IEEE CGEE 2022 · ISTANBUL Policy Assessment of Net Metering Medium Voltage Industrial Consumer Cumulative Cost (US$) · 2020–2022 Capacity charge Surplus export Case: 21MW · 7.13MWp PV · Bekasi DOI: 10.1109/CGEE55282.2022.9976670
IEEE CGEE · Istanbul2022
Policy Assessment of Net Metering — Industrial Consumer
ENERGY PROCEDIA · ELSEVIER · 2019 Economic Analysis of PV Distributed Generation Investment NPV Sensitivity · PV Penetration Scenarios Optimistic Base case DOI: 10.1016/j.egypro.2018.11.115 · Nagoya 2018
Energy Procedia · Elsevier2019
Economic Analysis of PV Distributed Generation Investment
ENERGY PROCEDIA · ELSEVIER · 2019 Sensitivity Analysis of Financial Parameters in Varying PV Penetrations Sensitivity Tornado · NPV Response IRR Tariff CapEx Optimum PV Location · Feeder Analysis DOI: 10.1016/j.egypro.2018.11.108
Energy Procedia · Elsevier2019
Sensitivity Analysis of Financial Parameters in Varying PV Penetrations
ENERGY PROCEDIA · ELSEVIER · 2019 Determination of Optimal PV Locations in Radial Distribution PV PV Radial feeder · Optimal placement DOI: 10.1016/j.egypro.2018.11.108 · CPESE 2018
Energy Procedia · Elsevier2019
Determination of Optimal PV Locations in Radial Distribution System
UNIVERSITAS INDONESIA · 2018 Scenario Analysis of Dynamic Electricity Tariffs · MV Industrial Time-of-Use Tariff Scenarios (Rp/kWh) OFF 00-07 MID-PEAK 07-17 PEAK 17-22 OFF 22-24 30 pelanggan · PLN Bekasi · MV 200kVA+ ▼ 2.59%/hari biaya pembangkitan Jawa-Madura-Bali ≈ Rp 3.645 triliun/tahun penghematan potensial Thesis · Universitas Indonesia · 2018
Universitas Indonesia2018
Scenario Analysis of Dynamic Electricity Tariffs — MV Industrial Customers
View all 9 papers on Google Scholar
Apps & Platforms · 10 Live Projects
Built from the inside out
PJU Indramayu VIIRS · YOLOv8 PJU 0.94 PJU 0.91 MISSING 2,847 Active 312 Missing 70% saved Satellite street light detection · NASA VIIRS · 70% field survey reduction
Satellite · VIIRS + YOLOv8
PJU Indramayu
pjuindramayu.vercel.app
PLNlytics Distribution Analytics LOSS 3.8% ANOMALY 2/12 ENERGY 8.7GWh Loss per Feeder 8.2%! ⚠ Feeder PLY-04 · 8.2% loss exceeds threshold · Inspect immediately PLN distribution analytics · Real-time AMR data · Auto-alert engine
Analytics · PLN Distribution
PLNlytics
plnlytics.vercel.app
PLN AI Agent Claude API · Multi-Agent LOSS 3.4% CUSTOMERS 24,182 AI Agent Analyzing TG-047 loss… ● Recommendation ready Daily Load (MW) ● Telegram Bot · Online · 18 features · Auto-report active Multi-agent PLN operations platform · Claude API · Python · Reporting · Automation · AI Decision
Multi-Agent · Claude API
PLN AI Agent
plnaiagent.vercel.app
Envisor AI AI Energy Advisor · envisor.org Reduce Energy Bills with AI insights Get Started → Your Energy Score B+ ▼ Rp 2.4M saved vs last quarter 💡 Shift AC to 19:00 · Save 18% AI Energy Consultant How can I reduce factory electricity bills? ● Shift compressor to off-peak (22:00–06:00) · Potential saving: 24% AI SaaS · SME & commercial buildings · PLN tariff-aware · Automated audit · envisor.org
AI SaaS · Energy Consulting
Envisor AI
envisor.org
AlQuranVocab alquranvocab.com رَحْمَة rahmah · mercy Al-Fatiha 1:1 ✓ Know it ✗ Again Today 47/60 Streak 🔥14 Retention ~75% 6,236 words 114 surahs FREE forever Quranic vocabulary · spaced repetition · 6,236 unique words · 114 surahs · completely free
Islamic Education · SRS
AlQuranVocab
alquranvocab.com
ScoutVision Football AI · 90min + 4GB 9 7 10 Player #9 Live 6.2km · 8.4km/h · 23 sprints 4 shots · 37 passes · Left 76% Fitness: 84% · ~72min remaining PDF per player Heatmap YOLOv8 · ByteTrack · Mac M4 MPS · 90-minute full match · 4GB+ files supported
Football AI · YOLOv8 + ByteTrack
ScoutVision
scoutvision-tau.vercel.app
Indramayuku Data Platform Local Data Platform Indramayu Region · Next.js Community monitoring · Public services · Local data visualization
Data Platform · Next.js
Indramayuku
indramayuku.vercel.app
Kronos Productivity · Focus Timer Today's Focus 4h 32m Sessions: 6 · Daily goal: 75% Pomodoro timer · daily session tracking · goal progress · personal productivity analytics
Productivity · Pomodoro
Kronos
kronos-olive.vercel.app
Tenis Indramayu Sports Community Active Tournaments 3 Registered Players 124 Tennis community Indramayu · Tournaments · Scheduling · Bracket management
Sports Community · Tournament
Tenis Indramayu
tenisindramayu.vercel.app
All 10+ projects · github.com/qastill
Personal Thoughts · Open Discussion
Ideas worth talking about
Energy Transition
Indonesia's grid isn't ready for rooftop solar — and PLN's net metering policy is making it worse

The current 1:0.65 export ratio penalizes industrial prosumers while grid infrastructure remains underprepared for bidirectional flow. My research on the 21MW Bekasi case showed cumulative consumer loss of -$2,102 over two years under current policy. Indonesia needs dynamic net metering — not a static punitive multiplier.

Renewable Energy
PLN's idle geothermal capacity is a missed opportunity at national scale

Indonesia has 40% of the world's geothermal potential but utilizes less than 10%. The baseload stability of geothermal — paired with the right monetization model — could transform PLN's financial position. The EnerBit concept explores one path: using surplus capacity for regulated Bitcoin mining as an intermediate value capture while renewable buildout continues.

Smart Grid
Time-of-Use tariffs could cut Java-Madura-Bali peak load costs by Rp 3.6 trillion annually

30 industrial customers in PLN Bekasi showed mid-peak demand elasticity of -0.3 — meaning they will shift load when the incentive is real. The math works out to 2.59% daily generation cost reduction across the Java-Madura-Bali interconnection. Dynamic pricing isn't complex to implement; it requires political will more than technology.

Digital Economy
Bitcoin is not a currency — it's a settlement layer for sovereign-scale value storage

Countries with unstable fiat — Argentina, Turkey, Nigeria — aren't using Bitcoin as a medium of exchange; they're using it as a hedge against monetary policy failure. Indonesia's fiscal position is stronger, but the principle holds: states that hold Bitcoin early will have structural advantages over those that don't. El Salvador and Bhutan are running the experiment.

Islamic Economics
The riba prohibition in Islamic finance is ultimately about risk-sharing — and Bitcoin respects it

Classical Islamic scholars banned guaranteed returns on capital deployment because they distort risk distribution. Bitcoin, as a fixed-supply asset with no guaranteed yield, aligns more naturally with Islamic economic principles than fractional reserve banking. The debate isn't Bitcoin vs. gold — it's about what unit best represents productive economic participation without embedded exploitation.

Indonesia Economy
Indonesia's energy subsidies are a transfer from future taxpayers to present consumers — and we need to talk about that

Electricity subsidies in Indonesia exceed Rp 70 trillion annually, disproportionately benefiting wealthier consumers with larger consumption. A well-designed TOU + targeted subsidy system would be more equitable and fiscally sustainable. The political difficulty is real, but so is the cost of inaction as renewable transition accelerates globally.

AI in Utilities
PLN doesn't need better dashboards — it needs AI agents that can act autonomously on what they see

Every digitalization wave in utilities builds better visualizations but doesn't close the loop to action. An operator sees a loss anomaly on a dashboard — then what? The next frontier is agentic AI that detects the anomaly, cross-references historical patterns, generates a work order, and notifies the field team — all without a human middle step. OctoAgent is my attempt to build that.

AI Adoption
The biggest barrier to AI adoption in Indonesian SOEs isn't technology — it's the question of accountability

When an AI system makes a wrong recommendation that causes operational loss, who is responsible? The engineer who deployed it, the vendor, or the system itself? Until there are clear frameworks for AI accountability in government-linked companies, adoption will be slow regardless of capability. This is a governance problem before it's a technology problem.

Machine Learning
MAGNETO proved ML can catch electricity thieves better than experienced field inspectors — but we rarely talk about why

Going from a 15% to 77% fraud detection hit rate wasn't because the model was brilliant — it was because human inspectors were working from intuition and social pressure while the model worked from patterns. ML doesn't get tired, doesn't know the customer personally, and doesn't fear conflict. The lesson: AI outperforms humans most where human judgment is biased by relationships.

Get in touch
Let's connect
& build

Open to research partnerships, AI collaborations, consulting conversations, and anything about Indonesia's energy future.

Jakarta, Indonesia · UTC+7