Pierluigi Mancarella

Victor Schmitt, Farzaneh Pourahmadi, Angela Flores-Quiroz et al.

Transmission expansion planning (TEP) plays a critical role in ensuring power system reliability and facilitating the integration of renewable energy resources. However, this process requires planners to constantly deal with significant uncertainty. While multistage stochastic TEP models provide a robust framework for identifying investment plans under uncertainty, the rapid growth in problem size hinders their computational tractability. To address this challenge, this paper develops a hybrid machine learning-optimisation framework for stochastic TEP. The proposed approach uses investment decisions and uncertainty scenarios as input features to train surrogate neural networks, which are then reformulated as mixed-integer linear constraints and embedded within an optimisation model. The surrogate model approximates expected operational costs to inform TEP decisions, reducing the burden arising from large operational problems. Case study applications on IEEE test systems demonstrate that, after training, the proposed approach achieves near-optimal investment costs while reducing total computational time by up to a factor of around 13 compared to a single full-optimisation stochastic formulation. This enables performing extensive multi-scenario analysis and stress testing that would otherwise be computationally prohibitive at scale.

Eduardo Alejandro Martinez-Cesena, Pierluigi Mancarella, Mamadou Ndiaye et al.

Detailed knowledge of the energy needs at relatively high spatial and temporal resolution is crucial for the electricity infrastructure planning of a region. However, such information is typically limited by the scarcity of data on human activities, in particular in developing countries where electrification of rural areas is sought. The analysis of society-wide mobile phone records has recently proven to offer unprecedented insights into the spatio-temporal distribution of people, but this information has never been used to support electrification planning strategies anywhere and for rural areas in developing countries in particular. The aim of this project is the assessment of the contribution of mobile phone data for the development of bottom-up energy demand models, in order to enhance energy planning studies and existing electrification practices. More specifically, this work introduces a framework that combines mobile phone data analysis, socioeconomic and geo-referenced data analysis, and state-of-the-art energy infrastructure engineering techniques to assess the techno-economic feasibility of different centralized and decentralized electrification options for rural areas in a developing country. Specific electrification options considered include extensions of the existing medium voltage (MV) grid, diesel engine-based community-level Microgrids, and individual household-level solar photovoltaic (PV) systems. The framework and relevant methodology are demonstrated throughout the paper using the case of Senegal and the mobile phone data made available for the 'D4D-Senegal' innovation challenge. The results are extremely encouraging and highlight the potential of mobile phone data to support more efficient and economically attractive electrification plans.

Markus Schläpfer, Pierluigi Mancarella

Increasing shares of fluctuating renewable energy sources induce higher and higher power flow variability at the transmission level. The question arises as to what extent existing networks can absorb additional fluctuating power injection without exceeding thermal limits. At the same time, the resulting power flow characteristics call for revisiting classical approaches to line temperature prediction. This paper presents a probabilistic modeling and simulation methodology for estimating the occurrence of critical line temperatures in the presence of fluctuating power flows. Cumbersome integration of the dynamic thermal equations at each Monte Carlo simulation trial is sped up by a specific algorithm that makes use of a variance reduction technique adapted from the telecommunications field. The substantial reduction in computational time allows estimations closer to real time, relevant to short-term operational assessments. A case study performed on a single line model provides fundamental insights into the probability of hitting critical line temperatures under given power flow fluctuations. A transmission system application shows how the proposed method can be used for a fast yet accurate operational assessment.