Abstract
As the access to consumption data available in household smart meters is now very common in several developed countries, this kind of information is assuming a providential role for different players in the energy sector. The proposed study was applied to data available from the Smart Meter Energy Consumption Data in the London Households dataset, provided by UK Power Networks, containing half-hourly readings from an original sample of 5567 households (71 households were hereby carefully selected after a justified filtering process). The main aim is to forecast the day-ahead load profile, based only on previous load values and some auxiliary variables. During this research different forecasting models are applied, tested and compared to allow comprehensive analyses integrating forecasting accuracy, processing times and the interpretation of the most influential features in each case. The selected models are based on Multivariate Adaptive Regression Splines, Random Forests and Artificial Neural Networks, and the accuracies resulted from each model are compared and confronted with a baseline (Naive model). The different forecasting approaches being evaluated have been revealed to be effective, ensuring a mean reduction of 15% in Mean Absolute Error when compared to the baseline. Artificial Neural Networks proved to be the most accurate model for a major part of the residential consumers.

Abstract
Renewable energy has a key role to play in the transition towards a low-carbon society. Despite its importance, relatively little attention has been focused on the crucial impact of weather and climate on energy demand and supply, or the generation or operational planning of renewable technologies. In particular, to improve the operation and longer-term planning of renewables, it is essential to consider seasonal and subseasonal weather forecasting. Unfortunately, reports that focus on these issues are not common in scientific literature. This paper presents a systematic review of the seasonal forecasting of wind and wind power for the Iberian Peninsula and the Canary Islands, a region leading the world in the development of renewable energies (particularly wind) and thus an important illustration in global terms. To this end, we consider the scientific literature published over the last 13 years (2008–2021). An initial search of this literature produced 14,293 documents, but our review suggests that only around 0.2% are actually relevant to our purposes. The results show that the teleconnection patterns (North Atlantic Oscillation [NAO], East Atlantic [EA] and Scandinavian [SCAND]) and the stratosphere are important sources of predictability of winds in the Iberian Peninsula. We conclude that the existing literature in this crucial area is very limited, which points to the need for increased research efforts, that could lead to great returns. Moreover, the approach and methods developed here could be applied to other areas for which systematic reviews might be either useful or necessary.

Abstract

Abstract
With the increased penetration of renewables, energy storage has become a critical issue in microgrid and small household applications. Accordingly, this paper undertakes a feasability study the varying limitations from conventional batteries in residential buildings, such as capacity-loss over time and aging, as well as the alternative application and challenges of hydrogen-based storage for the domestic sector. The paper considers a test case study where an analysis is performed on the practicality of hydrogen-based storage, in addition to lithium-ion battery storage. Various scenarios are considered based on solar installation sizes, self-consumption, battery capacity, autonomy rates and grid extraction. A detailed analysis is carried out on both thermal and electrical demands of a residential household, which also includes the energy performance and applications of heat pumps. While the obtained results from various scenarios are compared and analysed, these anticipate that the potential integration of hydrogen can improve the autonomy rate of residential buildings, The cost of hydrogen storage is expected to reduce significantly, opening opportunities for hydrogen application.

Abstract
This paper proposes a novel real option (RO)-based network investment assessment method to quantify the flexibility value of battery energy storage systems (BESS) in distribution network planning (DNP). It applied geometric Brownian motion (GBM) to simulate the long-term load growth uncertainty. Compared with commonly used stochastic models (e.g. normal probability model) that assume a constant variance, it reflects the fact that from the point of prediction, uncertainty would increase as time elapses. Hence, it avoids the bias of traditional net present value (NPV) frameworks towards lumpy investments that cannot provide strategic flexibility relative to more flexible alternatives. It is for the first time to adopt the option pricing method to evaluate the flexibility value of distribution network planning strategies. To optimize the planning scheme, this paper compares the static NPVs and flexibility values of different investment strategies. A 33-bus system is used to verify the effectiveness of the formulated model. Results indicate that flexibility values of BESS are of utmost importance to DNP under demand growth uncertainties. It provides an analytical tool to quantify the flexibility of planning measures and evaluate the well-timed investment of BESS, thus supporting network operators to facilitate flexibility services and hedge risks from the negative impact of long-term uncertainty.

Abstract
The present work aims to compare several load disaggregation methods. While the supervised alternative was found to be the most competent, the semi-supervised is proved to be close in terms of potential, while the unsupervised alternative seems insufficient. By the same token, the tests with long-lasting data prove beneficial to confirm the long-term performance since no significant loss of performance is noticed with the scalar of the time-horizon. Finally, the patchwork of new parametrization and methodology fine-tuning also proves interesting for improving global performance in several methods.