Optimized sampling strategy for load scenario generation in partially observable distribution grids

Article Energy & Fuels

Scenario generation of residential electricity consumption through sampling of historical data

Jonas Soenen et al.

Summary: The low-voltage grid needs reinforcement to handle increased load from transitioning to renewable energy. Knowledge of typical currents and voltages is needed, but unknown. To address this, two techniques were developed to generate accurate electricity consumption time series scenarios for consumers. The data-driven technique outperforms the expert-based technique and can be applied to various datasets without requiring domain knowledge. These techniques can help distribution system operators estimate the state of the grid accurately.

SUSTAINABLE ENERGY GRIDS & NETWORKS (2023)

Add to Collection

Article Energy & Fuels

Gab-SSDS: An AI-Based Similar Days Selection Method for Load Forecast

Zoran Jankovic et al.

Summary: The article introduces a genetic algorithm-based smart similar days selection method to optimize short-term load forecasting. The experimental results validate that this method can improve forecasting accuracy.

FRONTIERS IN ENERGY RESEARCH (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Dirichlet Sampled Capacity and Loss Estimation for LV Distribution Networks With Partial Observability

Rory Telford et al.

Summary: This study proposes a method for estimating spare capacity of unmonitored LV networks using demand data from customer Smart Meters, which learns daily load profiles across customers with Smart Meters and applies them to unmetered customers to estimate network parameters. By comparing estimations with simulated LV network models and benchmark models, the proposed method outperforms in accurately assessing substation headroom, especially in scenarios with a lower percentage of customers having Smart Meters installed.

IEEE TRANSACTIONS ON POWER DELIVERY (2021)

Add to Collection

Review Energy & Fuels

Centralized Control of Distribution Networks with High Penetration of Renewable Energies

Fco Javier Zarco-Soto et al.

Summary: The traditional method of distributing energy in distribution networks is no longer valid due to the increase in distributed generation and plug-in electric vehicles. This has led to congestion in distribution lines and transformers, as well as increased nodal voltages. The paper discusses centralized control techniques to mitigate these issues and presents a classification of methodologies for voltage control and congestion management.

ENERGIES (2021)

Add to Collection

Article Engineering, Electrical & Electronic