Solar photovoltaics are on track to becoming the largest renewable energy source by 2029. This means a rapid increase in the number of solar energy generation installations from residential roof-top systems to utility-scale power plants. The current industrial approaches towards predictive maintenance will be insufficient to manage and maintain the increasing numbers of such installations at peak performance. In this paper, we propose hyper-predictive maintenance as a novel approach based on Generative Artificial Intelligence (AI) agents for highly autonomous management of solar energy infrastructure. The proposed Agentic AI framework deploys multiple agents for baseline generation from solar installations, predictive model development, degradation estimation, degradation evaluation and predictive maintenance that combines baseline performance with contextual information to predict faults and potential causes. This framework is empirically evaluated in the real-world solar energy systems of a multi-campus tertiary education institution. The results of these experiments confirm the robust and accelerated performance of Generative AI agents for the hyper predictive maintenance of large-scale solar energy installations.

Crowd monitoring is a primary function in diverse industrial domains, such as smart cities, public transport, and public safety. Recent advancements in low-energy devices and rapid connectivity have enabled the generation of real-time data streams suitable for crowd-monitoring applications. Crowd forecasting is typically achieved using deep learning models that learn the evolving nature of data streams. The computational complexity, execution time, and opaqueness are inherent challenges of deep learning models that also overlook the latent relationships between multiple real-time data streams for improved accuracy. To address these challenges, we propose the global ensemble echo state network approach for explainable crowd forecasting using multiple WiFi data streams. This approach replaces the random input mapping layer with a clustering layer, allowing the network to learn input projections on cluster centroids. It incorporates an ensemble readout comprising a stack of reservoir layers that provide model explainability. It also learns multiple related time series in parallel to construct a global model that leverage latent relationships across the data streams. This approach was empirically evaluated in a multicampus, mixed-use tertiary education setting. The results of which confirm the effectiveness and interpretability of the proposed approach for industrial applications of crowd forecasting.

Accurate energy consumption forecasting is crucial for reducing operational costs, achieving net-zero carbon emissions, and ensuring sustainable buildings and cities of the future. Despite the frequent use of Artificial Intelligence (AI) algorithms for learning energy consumption patterns and predictions in Building Science, relying solely on these techniques for energy demand prediction addresses only a fraction of the challenge. A drift in energy usage can lead to inaccuracies in these AI models and subsequently to poor decision-making and interventions. While drift detection techniques have been reported, a reliable and robust approach capable of explaining identified discrepancies with actionable insights has not been discussed in extant literature. Hence, this paper presents an Artificial Intelligence framework for energy consumption forecasting with explainable drift detection, aimed at addressing these challenges. The proposed framework is composed of energy embeddings, an optimized dimensional model integrated within a data warehouse, and scalable cloud implementation for effective drift detection with explainability capability. The framework is empirically evaluated in the real-world setting of a multi-campus, mixed-use tertiary education setting in Victoria, Australia. The results of these experiments highlight its capabilities in detecting concept drift, adapting forecast predictions, and providing an interpretation of the changes using energy embeddings.

Large Language Models (LLMs) are leading the Generative Artificial Intelligence transformation in natural language understanding. Beyond language understanding, LLMs have demonstrated capabilities in reasoning tasks, including commonsense, logical, and mathematical reasoning. However, their proficiency in causal understanding has been limited due to the complex nature of causal reasoning. Several recent studies have discussed the role of external causal models for improved causal understanding. Building on the success of Retrieval-Augmented Generation (RAG) for factual reasoning in LLMs, this paper introduces a novel approach that utilizes Causal Graphs as external sources for establishing causal relationships between complex vectors. This method is empirically evaluated using two benchmark datasets across the metrics of Context Relevance, Answer Relevance, and Grounding, in its ability to retrieve relevant context with causal alignment. The retrieval effectiveness is further compared with traditional RAG methods that are based on semantic proximity.

Increasing energy consumption and diversified energy generation have led to the proliferation of energy management (EM) systems for optimized grid operations and net zero carbon emissions. Artificial Intelligence (AI) is centric to EM systems to process large volumes of high velocity data for anomalies, predictions, optimization and other actionable insights that unravel the complexities of grid operations. Managing Energy AI capabilities itself is becoming an increasingly complex task that requires extensive resourcing and expertise. In this paper, we aim to address this gap by formalizing the role of Automated Machine Learning (AutoML) by proposing a novel framework for its key functionalities in critical energy infrastructure. This framework provides a generic and cohesive abstraction to assist with integrating and managing the complexities of AI capabilities. The framework is empirically evaluated in the microgrid setting of a multi-campus, multi-functional tertiary education institution. Results from these experiments confirm the performance contributions of the proposed framework in addressing the complexities of AI capabilities of EM systems as they transition towards microgrid energy optimisation and net zero carbon emissions.

People express their opinions and emotions freely in social media posts and online reviews that contain valuable feedback for multiple stakeholders such as businesses and political campaigns. Manually extracting opinions and emotions from large volumes of such posts is an impossible task. Therefore, automated processing of these posts to extract opinions and emotions is an important research problem. However, human emotion detection is a challenging task due to the complexity and nuanced nature. To overcome these barriers, researchers have extensively used techniques such as deep learning, distant supervision, and transfer learning. In this paper, we propose a novel Pyramid Attention Network (PAN) based model for emotion detection in microblogs. The main advantage of our approach is that PAN has the capability to evaluate sentences in different perspectives to capture multiple emotions existing in a single text. The proposed model was evaluated on a recently released dataset and the results achieved the state-of-the-art accuracy of 58.9%.

In this paper, we present the system we have used for the Implicit WASSA 2018 Implicit Emotion Shared Task. The task is to predict the emotion of a tweet of which the explicit mentions of emotion terms have been removed. The idea is to come up with a model which has the ability to implicitly identify the emotion expressed given the context words. We have used a Gated Recurrent Neural Network (GRU) and a Capsule Network based model for the task. Pre-trained word embeddings have been utilized to incorporate contextual knowledge about words into the model. GRU layer learns latent representations using the input word embeddings. Subsequent Capsule Network layer learns high-level features from that hidden representation. The proposed model managed to achieve a macro-F1 score of 0.692.

Social media has gained an immense popularity over the last decade. People tend to express opinions about their daily encounters on social media freely. These daily encounters include the places they traveled, hotels or restaurants they have tried and aspects related to tourism in general. Since people usually express their true experiences on social media, the expressed opinions contain valuable information that can be used to generate business value and aid in decision-making processes. Due to the large volume of data, it is not a feasible task to manually go through each and every item and extract the information. Hence, we propose a social media analytics platform which has the capability to identify discussion pathways and aspects with their corresponding sentiment and deeper emotions using machine learning techniques and a visualization tool which shows the extracted insights in a comprehensible and concise manner. Identified topic pathways and aspects will give a decision maker some insight into what are the most discussed topics about the entity whereas associated sentiments and emotions will help to identify the feedback.