Accurate probabilistic forecasting of intraday electricity prices is critical for market participants to inform trading decisions. Existing studies rely on specific domain features, such as Volume-Weighted Average Price (VWAP) and the last price. However, the rich information in the orderbook remains underexplored. Furthermore, these approaches are often developed within a single country and product type, making it unclear whether the approaches are generalizable. In this paper, we extract 384 features from the orderbook and identify a set of powerful features via feature selection. Based on selected features, we present a comprehensive benchmark using classical statistical models, tree-based ensembles, and deep learning models across two countries (Germany and Austria) and two product types (60-min and 15-min). We further perform a systematic generalization study across countries and product types, from which we reveal an asymmetric generalization phenomenon: models trained on more liquid markets or products transfer well to less liquid ones, whereas the reverse transfer leads to substantial performance degradation. The project page is at https://runyao-yu.github.io/AsymGen/.
This study proposes a two-stage saving reallocation process to provide additional financial support to lower-income households (in a financially volatile situation) participating in ECs. The first stage consists in the withdrawal of a certain amount of savings from regular EC participants; for that, two approaches are proposed, the first being based on fixed shares, the second being saving-based. The second stage consists in the redistribution of previously withdrawn savings to households in need; thereby, three different mechanisms are introduced: based on equal shares, load-based, and inverse. Based on a concrete Austrian case study, the economic impact of including different numbers of lower-income households combined with different permutations of withdrawal and redistribution mechanisms on different EC participants is investigated. Findings reveal significant economic potentials to support households in need: For a PV-based EC with 20 regular participants (mixture of households, enterprises and public buildings), adding six lower-income households has only insignificant (negative) economic impact on the regular members of the EC. At the same time, in addition to general savings obtained through EC participation, lower-income households experience a further increase in savings of at least 80% due to saving reallocation. Assuming that each currently existing EC in Austria would include on average six households facing financial difficulties, the financial situation of approx. 14% of households in need could be alleviated immediately.
Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also. Initially, the primary motivator for spectrogram-based representations was their ability to present sound as a two dimensional signal in the time-frequency plane, which not only provides an interpretable physical basis for analysing sound, but also unlocks the use of a wide range of machine learning techniques such as convolutional neural networks, that had been developed for image processing. A spectrogram is a matrix characterised by the resolution and span of its two dimensions, as well as by the representation and scaling of each element. Many possibilities for these three characteristics have been explored by researchers across numerous application areas, with different settings showing affinity for various tasks. This paper reviews the use of spectrogram-based representations and surveys the state-of-the-art to question how front-end feature representation choice allies with back-end classifier architecture for different tasks.
In the transition toward a green energy system, district heating (DH) systems are pivotal in enhancing the flexibility, resilience, and capacity of integrating local and renewable energy sources in urban areas. District heating networks have traditionally been operated with limited controls to ensure the required supply and optimize economic and environmental performance. In recent years, a new digital infrastructure has emerged in response to new policies, and technological advancements in digital solutions are essential to sustain the transition towards a 4th generation district heating (4GDH) system. This review article comprehensively assesses the current landscape and future prospects of digitalization levels in the operation of DH systems. It provides an overview of the latest improvements in digital technologies and their application in optimizing the operation and management of DH networks. The review delves into various aspects, including digital control strategies, data analytics, fault detection and diagnosis, and predictive maintenance with current applications and developments of digital twins and artificial intelligence (AI). The analysis of results in the literature was organized and clustered into specific macro areas: digitalization of the demand side, digitalization at the system level, and digitalization of infrastructure. Furthermore, the study provides an overview of digitalization implementations based on the experiences of early adopters as a benchmark for the replicability and opportunity of new business models.
Log Anomaly Collaborative Intrusion Detection Systems (CIDS) are designed to detect suspicious activities and security breaches by analyzing log files using anomaly detection techniques while leveraging collaboration between multiple entities (e.g., different systems, organizations, or network nodes). Unlike traditional Intrusion Detection Systems (IDS) that require centralized algorithm updates and data aggregation, CIDS enable decentralized updates without extensive data exchange, improving efficacy, scalability, and compliance with regulatory constraints. Additionally, inter-detector communication helps to reduce the number of false positives. These systems are particularly useful in distributed environments, where individual system have limited visibility into potential threats. This paper reviews the current landscape of Log Anomaly CIDS and introduces an open-source framework designed to create benchmark datasets for evaluating system performance. We categorize log anomaly detectors into three categories: Sequential-wise, Embedding-wise, and Graph-wise. Furthermore, our open framework facilitates rigorous evaluation against different challenges identifying weaknesses in existing methods like Deeplog and enhancing model robustness.
