Thanks to their modularity and their capacity to adapt to different contexts, hybrid microgrids are a promising solution to decrease greenhouse gas emissions worldwide. To properly assess their impact in different settings at country or cross-country level, microgrids must be designed for each particular situation, which leads to computationally intractable problems. To tackle this issue, a methodology is proposed to create surrogate models using machine learning techniques and a database of microgrids. The selected regression model is based on Gaussian Processes and allows to drastically decrease the computation time relative to the optimal deployment of the technology. The results indicate that the proposed methodology can accurately predict key optimization variables for the design of the microgrid system. The regression models are especially well suited to estimate the net present cost and the levelized cost of electricity (R² = 0.99 and 0.98). Their accuracy is lower when predicting internal system variables such as installed capacities of PV and batteries (R² = 0.92 and 0.86). A least-cost path towards 100% electrification coverage for the Bolivian lowlands mid-size communities is finally computed, demonstrating the usability and computational efficiency of the proposed framework.

@en

With pressing priorities in the development agenda, policy makers in developing countries are in the difficult situation of prioritizing policy actions. Limited government and utility budgets need cost effective solutions to bring the desired development benefits of electrification, health, education and food security among others. Energy access is a prerequisite for economic activity and for human development as interacts in synergy with other development needs. As rural electrification models usually focus on the supply of electricity solely, thermal energy needs, such as cooking and water heating remain unattended and satisfied by non-renewable energy fuels. To this aim, we explore optimal electrification solutions addressing two types of energy demands, electricity and thermal energy demands for cooking. Our model builds on a 3-step electrification methodology proposed by Peña et al. including electricity as a modern source of clean energy for cooking in rural communities. The total investments needed to build and operate the microgrids, including distribution costs, is 332 million USD. This is equivalent to 1129 USD/per inhabitant. This amount does not account however the health and environment benefits that e-cooking can bring to inhabitants in Bolivian low-lands.

@en

Hybrid microgrids represent a cost-effective and viable option to ensure access to energy in rural areas located far from the main grid. Nonetheless, the sizing of rural microgrids is complicated by the lack of models capable of accounting for the evolution of the energy demand over time, which is likely to occur in such contexts as a result of the modification of users' lifestyles. To tackle this issue, the present study aims at developing a novel, long-term optimisation model formulation, capable of accounting for load evolution and performing suitable investment decisions for capacity expansion along the time horizon. Multiple scenarios of load evolution are considered to evaluate the beneficial effects of this novel approach, through the coupling of the model with a tool for stochastic load profiles generation. The results show how this implementation brings lower Net Present Cost to the project and improved correspondence between actual electricity demand and microgrid sizing. Finally, a sensitivity analysis evaluates the robustness of the approach with respect to input data variability and the Loss of Load parameter.

@en

For decades, electrification planning in the developing world has often focused on extending the national grid to increase electricity access. This article draws attention to the potential complementary role of decentralized alternatives – primarily micro-grids – to address universal electricity access targets. To this aim, we propose a methodology consisting of three steps to estimate the LCOE and to size micro-grids for large-scale geo-spatial electrification modelling. In the first step, stochastic load demand profiles are generated for a wide range of settlement archetypes using the open-source RAMP model. In the second step, stochastic optimization is carried by the open-source MicroGridsPy model for combinations of settlement size, load demand profiles and other important techno-economic parameters influencing the LCOE. In the third step, surrogate models are generated to automatically evaluate the LCOE using a multivariate regression of micro-grid optimization results as a function of influencing parameters defining each scenario instance. Our developments coupled to the OnSSET electrification tool reveal an important increase in the cost-competitiveness of micro-grids compared to previous analyses.@en

Distributed Generation is driving a paradigm shift in traditional power systems, allowing the production of renewable electricity and thermal energy close to the main energy consumption nodes (e.g., buildings). In this sense, thermal networks and electrical grids for Smart districts /cities have a key role, allowing the interconnections of distributed energy resources (renewables, combined heat and power generators, etc storage systems, and loads (electrical and thermal), locally dispatching supply and demand. In the present work, a multi-energy system for a new nearly zero energy and low carbon district near Milan (Italy) is proposed and analysed. After the evaluation of thermal and electrical energy needs of the district, an innovative thermal and electrical multi-energy system is designed with the specific aim to integrate multiple renewable energy sources (i.e., photovoltaics and groundwater energy) and energy storage technologies (i.e., sensible thermal storages), obtaining the best matching with thermal and electrical loads. Final results demonstrate the achievable benefits of the proposed solution, which can be successfully applied in several contexts.@en

Robust sizing of rural micro-grids is hindered by uncertainty associated with the expected load demand and its potential evolution over time. This study couples a stochastic load generation model with a two-stage stochastic micro-grid sizing model to take into account multiple probabilistic load scenarios within a single optimisation problem. As a result, the stochastic-optimal sizing of the system ensures an increased robustness to shocks in the expected load compared to a best-case (lowest-demand) sizing, though with a lower cost and better dispatch flexibility compared to a worst-case (highest-demand) sizing. What is more, allowing just a 1% unmet demand enables to significantly improve the cost-competitiveness and the renewables penetration as all the not supplied energy is located in a negligible fraction of the unlikeliest highest demand scenarios.@en

Countries around the world are preparing to give the last leap to accomplish a 100 % of rural energy access. Nonetheless, country-wide electrification planning requires the analysis of hundreds of un-electrified villages with different social, economical and geographical backgrounds. State-of-the-art planning models typically handle this computationally challenging task relying on highly-simplified technological characterizations, at the expense of a proper estimation of the cost-optimal potential of off-grid technologies, particularly micro-grids. In this paper, we propose a machine-learning method to improve such technological characterization while keeping the computational tractability of the problem under control. Firstly, field surveys from rural un-electrified villages in Bolivia are used as an input for a stochastic load generator model, creating several demand scenarios for a set of different village archetypes; secondly, renewable energy time series for representative locations of Bolivia are created using the NASA database. For each demand and renewables potential combination, a two-stage stochastic sizing model is adopted to obtain the corresponding cost-optimal micro-grid configuration. Finally, these data are used to train a Gaussian process regression with the levelized cost of energy (LCOE) as dependent variable and the daily average demand, renewable energy, and techno-economic characteristics of the components as independent variables. The results show that the trained algorithm is ultimately able to identify the LCOE of microgrids in given conditions, out of the training dataset, with satisfying accuracy and limited computational effort.@en