Business Research Unit - BRU-IUL

Funder

Organizational Unit

Publications

Short-term load forecasting using time series clustering

Publication . Martins, Ana Alexandra; Lagarto, João; Canacsinh, Hiren; Reis, Francisco; Cardoso, Maria Margarida

Short-term load forecasting plays a major role in energy planning. Its accuracy has a direct impact on the way power systems are operated and managed. We propose a new Clustering-based Similar Pattern Forecasting algorithm (CSPF) for short-term load forecasting. It resorts to a K-Medoids clustering algorithm to identify load patterns and to the COMB distance to capture differences between time series. Clusters' labels are then used to identify similar sequences of days. Temperature information is also considered in the day-ahead load forecasting, resorting to the K-Nearest Neighbor approach. CSPF algorithm is intended to provide the aggregate forecast of Portugal's national load, for the next day, with a 15-min discretization, based on data from the Portuguese Transport Network Operator (TSO). CSPF forecasting performance, as evaluated by RMSE, MAE and MAPE metrics, outperforms three alternative/baseline methods, suggesting that the proposed approach is promising in similar applications.

2022-08-10Journal article

Restricted access

SWHORD simulator: A platform to evaluate energy transition targets in future energy systems with increasing renewable generation, electric vehicles, storage technologies, and hydrogen systems

Publication . Sousa, Jorge A. M.; Lagarto, João; Carvalho, Ezequiel; Martins, Ana

This paper presents the simulation platform SWHORD, specially designed for the analysis of future energy systems under energy transition targets. The model is implemented in GAMS as a cost minimization mixed integer programming problem of a hydro-thermal power system, which includes high penetration of non-dispatchable renewable generation, storage technologies, electric vehicles, and hydrogen systems. Simulations are performed on an hourly basis for one year of operation, enabling the evaluation of both short-term dynamics and the seasonal behaviour of the system and including the hourly power generation profile by technology, fuel and emission costs, CO2 emissions and storage levels, as well as the renewable curtailment needed to balance the system. The model was validated by backtesting with historical data of the Portuguese power system and, from a comprehensive statistical analysis of the dispatchable generation, it is concluded that the simulation results present a good fit with the real data. An illustrative use case is presented to evaluate the consistency of the Portuguese targets for 2030. Simulation results put in evidence the advantages of the SWHORD simulator to study the complex interactions among the new drivers of future energy systems, such as electric vehicles, storage technologies, and hydrogen systems.

2023-05-15Journal article

Restricted access

Funding agency

Fundação para a Ciência e a Tecnologia

Funding programme

6817 - DCRRNI ID

Funding Award Number

UIDB/00315/2020