The development of thorough probability models for highly volatile load profiles based on smart meter data is crucial to obtain accurate results when developing grid planning and operational frameworks. This paper proposes a new top-down modeling approach for residential load profiles (RLPs) based on multivariate elliptical copulas that can capture the complex correlation between time steps. This model can be used to generate individual and aggregated daily RLPs to simulate the operation of medium and low voltage distribution networks in flexible time horizons. Additionally, the proposed model can simulate RLPs conditioned to an annual energy consumption and daily weather profiles such as solar irradiance and temperature. The simulated daily profiles accurately capture the seasonal, weekends, and weekdays power consumption trends. Five databases with actual smart meter measurements at different time resolutions have been used for the model’s validation. Results show that the proposed model can successfully replicate statistical properties such as autocorrelation of the time series, and load consumption probability densities for different seasons. The proposed model outperforms other multivariate state-of-the-art methods, such as Gaussian Mixture Models, by one order of magnitude in two different distance metrics for probability distributions.
1 March 2022 in International Journal of Electrical Power & Energy Systems
This paper proposes a framework to identify, visualize, and quantify risk of potential over/under voltage due to annual energy consumption and PV generation growth. The stochastic modeling considers the following: (i) Active and reactive power profiles for distribution transformers, dependent on annual energy consumption and activity in the serviced areas. (ii) Variable solar irradiance profiles that allow a broader range of PV generation scenarios for sunny, overcast, and cloudy days. The proposed framework uses multivariate- $t$ copulas to model temporal correlations between random variables to generate synthetic scenarios. A probabilistic power flow is computed using the generated scenarios to define critical static operating regions. Results show that classical approaches may underestimate the maximum PV capacity of distribution networks when local irradiance conditions are not considered. Moreover, it is found that including annual energy consumption growth is critical to establishing realistic PV installation capacity limits. Finally, a sensitivity analysis shows that taking a 5% of overvoltage risk could increase up to 15% of the PV installed capacity limits.
Load forecasting is more important than ever to enable new monitor and control functionalities of distribution networks aiming to mitigate the impact of the energy transition. Load forecasting at medium voltage (MV) level is becoming more challenging, because these load profiles become more stochastic due to the increasing penetration of photovoltaic (PV) generation in distribution networks. This work combines medium to low voltage (MV/LV) transformer loadings measured with advanced metering infrastructure (AMI) and machine learning (ML) algorithms to propose a new clustering based day-ahead aggregated load forecasting approach. This four-step approach improves the day-ahead load forecast of a city. First, MV/LV transformer loadings are clustered based on the shape of their load pattern. Second, a gradient boosting algorithm is used to forecast the load of each cluster and calculate the related feature importance. Third, feature selection is applied to improve the forecast accuracy of each cluster. Finally, the day-ahead load forecast of all clusters are aggregated. The case study presented uses 519 measured MV/LV transformer loadings in a city to perform 30 day-ahead load forecasts. Compared against the day-ahead aggregated load forecast without clustering, the average normalized root mean squared error (NRMSE) reduced 12.7 %, the average mean absolute percentage error (MAPE) reduced 18.2 % and the average Pearson Correlation Coefficient (PCC) increased 0.37 %. The 95 % confidence interval of the difference between the average NRMSE, MAPE and PCC without clustering and with the proposed method indicates a statistically significant improvement in accuracy.
19 October 2024 in International Journal of Electrical Power & Energy Systems