Energy markets · quantitative research

Ashkan (Ash) Yousefi, PhD

I model electricity prices, volatility and risk — combining power-systems engineering with quantitative methods across the NEM, ERCOT, CAISO and PJM. Published research in electricity price forecasting; currently building AI-native grid decision intelligence at FelixFusion.

PhD, Electrical EngineeringIEEE Senior MemberChartered Professional Engineer (EA)San Francisco Bay Area

Selected work Google Scholar LinkedIn

679

Citations

h-index

20+

Publications

12+

Years in energy

Focus

Where power-systems physics meets market economics — the questions a trading or investment desk actually needs answered.

Price & volatility modelling

Time-series and GARCH-family volatility modelling of electricity prices; probabilistic forecasts with explicit confidence bands rather than single-point estimates.

Market mechanics

ISO/RTO market design and dispatch: LMP and congestion, basis risk, loss factors, ancillary services, capacity mechanisms — across NEM, ERCOT, CAISO and PJM.

Optionality & asset valuation

Generation and storage as optionality — spark spreads, peaking economics, and battery arbitrage, where volatility is the primary driver of value.

Grid & connection analysis

Power flow, hosting capacity and contingency (N-1) analysis; connection feasibility and congestion risk for renewables and large loads.

Selected work

Applied projects on real market data.

● Live

FelixFusion — AI-native grid decision intelligence

Co-founder & CEO. A platform producing probabilistic grid-risk profiles for renewable developers, asset managers and infrastructure capital — fusing operator data (constraints, dispatch, congestion, basis), physical network models (power flow, hosting capacity, contingency margins) and GARCH-family volatility modelling. Built across the NEM (AEMO) and ERCOT. Visit the platform →

Research thread

Electricity price forecasting — published research

Peer-reviewed work on forecasting wholesale electricity prices using machine-learning and big-data methods (IEEE ISGT Asia, 2019), alongside market-optimisation research on pumped-storage scheduling across energy and regulation markets. This research thread continues in current work on price and volatility modelling.

Research

Peer-reviewed work in electricity price forecasting, market optimisation and congestion management. Selected publications — full list on Google Scholar.

Long-term electricity price forecast using machine learning techniques

IEEE Innovative Smart Grid Technologies (ISGT Asia), 2019

27 citations

Big data analytics for electricity price forecast

Workshops of the Int. Conf. on Advanced Information Networking & Applications, 2019

A MIP-based optimal operation scheduling of pumped-storage plant in the energy and regulation markets

43rd International Universities Power Engineering Conference, 2008

24 citations

Congestion management using demand response and FACTS devices

International Journal of Electrical Power & Energy Systems, 2012

211 citations

An approach for wind power integration using demand side resources

IEEE Transactions on Sustainable Energy, 2013

81 citations

A probabilistic risk-based approach for spinning reserve provision using day-ahead demand response

Energy, 2010

74 citations

Autonomous household energy management using deep reinforcement learning

IEEE Int. Conf. on Engineering, Technology and Innovation, 2019

29 citations

Background

Utility engineering, market advisory, applied research, and building.

Co-Founder & CEO — FelixFusion

2024 – Present · San Francisco Bay Area

Technical Program / Product Manager — PAXAFE

2021 – 2024 · Predictive modelling under uncertainty, production ML APIs

Postdoctoral Fellow — UC Berkeley (SCET)

Grid AI and behind-the-meter storage strategy

Senior Technology Consultant — EY, Power & Utilities

2019 – 2020 · Electricity market simulation, LMP exposure and price-hedging strategy

Transmission & Distribution Engineer — Western Power

Load flow, fault, contingency and interconnection studies

PhD, Electrical Engineering

Power systems · optimisation · machine learning