A Comprehensive Model for the Design of a Microgrid under Regulatory Constraints Using Synthetical Data Generation and Stochastic Optimization

Abstract

As renewable energy installation costs decrease and environmentally-friendly policies are progressively applied in many countries, distributed generation has emerged as the new archetype of energy generation and distribution. The design and economic feasibility of distributed generation systems is constrained by the operation of the microgrid, which has to consider the uncertainty of renewable energy sources, consumption habits and electricity market prices. In this paper, a mathematical model intended to optimize the design and economic feasibility of a microgrid is proposed. After a search in the state-of-the-art, weaknesses and strengths of existing models have been identified and taken into account for building the present model. The present model should be seen as a basis on which other models can be built upon, hence a complete definition of the different sub-models is stated: uncertainty modelling, optimization technique, physical constraints and regulatory framework. One of the main features presented is the generation of synthetic data in uncertainty modelling, employed to enhance the reliability of the model by taking into account a longer time horizon and a shorter time step. Results show significant details about energy management and prove the suitability of using a stochastic approach rather than deterministic or intuitive ones to perform the optimization.

Optimization Models under Uncertainty in Distributed Generation Systems: A Review

“…Operating costs can often be minimized along with other variables, such as power losses and overall implementation expenses [54]. Other economic functions can be observed, using indicators such as NPV [93], earning before interests, tax, depreciation and amortization (EBITDA) [19], or social welfare [134] in the case of problems with multiple agents.…”

“…LP/MILP Solver Simulation Platform [19] CPLEX AIMMS [17,21,22,36,53,58,65,84,86,99,115,117,134,136,142,151,154,157,176] GAMS [37,44,83,96,101,[128][129][130]156,160,161,170,179] MATLAB [20,90,118,133,167] IBM [116] Gurobi GAMS [43] MATLAB [82] Python [145,166] Intlinprog MATLAB [46,57,70] Other/Unspecified GAMS [42,66,104,114,…”

Economic and Regulatory Uncertainty in Renewable Energy System Design: A Review

“…For instance, autoregressive time series models are discrete-time equivalents of Ornstein-Uhlenbeck processes. A generalization of this model, the autoregressive-integrated moving average (ARIMA), can be found in forecasting RE [34,49], energy demand [92,111], day-ahead [77,151], and NG prices [20]. ARIMA models comprise an autoregressive component, where the variable of interest y t is forecasted using p past values of the same variable (y d t−1 .…”

A rigorous uncertainty-aware quantification framework is essential for reproducible and replicable machine learning workflows

“…In this context, UQ primarily involves understanding and characterizing this distribution as well as quantifying its impact on the predictions of interest. We can assess existing ML/AI models for the respective impact of diverse factorsstochasticity of the data generation process (e.g., in hydrology 62 and microgrid applications 63 ), potential data corruption issues (noise or missing values), model uncertainty, randomness in the model training process, and so forthon the reproducibility of the results obtained from compositional workows in operational settings.…”