Generative AI has rapidly progressed from chatbots and assistants to agents across diverse applications and domains. Generative AI agents demonstrate sophisticated operation through autonomy, tool use and decision making with minimal human input. Despite these performance gains, agents are still impacted by the foundational limitations of Generative AI models. Among these, hallucinations are a major limitation that affects agent operation in real-world settings, leading to risk and loss. Several recent work aim to address hallucinations through methods such as retrieval-augmented generation and reflection prompting, however, these only provide partial improvements. An effective yet underexplored approach is in the observability data generated by an agent in its deployed and operational settings. Drawing on agent observability data, this paper proposes a dual memory knowledge graph approach that integrates Semantic and Observability Memory to address hallucinations in Generative AI agents. Semantic Memory provides organized domain knowledge for precise factual grounding. Observability Memory transforms logs, traces, and execution results into agent validated planning histories. Hallucinations are then addressed by grounded planning in verified past interactions with known, reliable outcomes. This approach is evaluated in a two-stage experimental setup aligned with its dual memory design. Observability memory is evaluated on the HotpotQA dataset to assess its impact on reasoning grounding, using metrics that capture both factual accuracy and reasoning hallucinations. The SM3-Text-to-Query benchmark and Synthea-based medical QA datasets are used to assess factual grounding of the semantic memory. Results from both experiments demonstrate reductions in hallucinations, with semantic memory for contextual grounding reducing factual hallucinations, and observability memory for reasoning grounding reducing faithfulness hallucinations.

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.

This work addresses the challenge of accurately forecasting electricity prices within the volatile Australian market, especially during extreme conditions. It leverages advanced generative pre-trained Large Language Models (LLMs) to analyze the content of electricity market notices with the goal of identifying the drivers behind extreme price fluctuations. Additionally, this approach employs LLMs for an in-depth time-series analysis of electricity prices, providing Australian electricity company traders with insights to refine their trading strategies. To enhance forecasting accuracy this study adopts the QLoRA method for fine-tuning open access LLMs, enabling the analysis of market notices to generate a time series event dataset. A CNN-LSTM network architecture is designed to process both electricity price data and market notice information, thereby improving forecast precision in periods of extreme price volatility. The proposed decision support framework undergoes simulation and evaluation using data from the Australian electricity market, demonstrating its potential to significantly benefit traders in navigating the complexities of the energy sector.

Contemporary energy platforms are leveraging advanced data management and Artificial Intelligence (AI) capabilities in response to the increasing complexity of energy systems and grids. Despite these advances, it is a non-trivial and challenging task to support the decision-making needs of the human operators of such complex energy-related implementations. Conversational agents or chatbots are a potential emerging technology that can be utilized to address this challenge. Although there is a large body of literature on chatbots in general, they are not robust as they rely on predefined conversational pathways that are inadequate to efficiently address the complexities of dynamic data spaces in energy platforms. The capability of generating answers in real-time by communicating with the dynamic dataspace is crucial as energy management decisions are real-time and time sensitive. In this paper, we present the design and development of Cooee, a chatbot for conversational engagement with the dynamic data spaces of complex energy environments. Cooee leverages state-of-art language models along with rule-based language processing methods for a conversational interaction with dynamic data spaces, which consequently supports and enables decision-making by human experts. We have developed Cooee as a standalone application and then integrated into a real-world energy AI platform deployed within a multi-campus tertiary education institution setting. Cooee was empirically evaluated in this setting and compared with several state-of-the-art Q&A approaches.

Microgrids and energy platforms have become increasingly intricate in nature. This is especially true in platforms adopted in large multi functional complexes which are spread across geographies of varying climactic conditions. Many of these complexes have evolved over time as organisations have grown and diversified, this has resulted in a mix of infrastructure, technology, networks, systems and equipment woven in an inextricable web. Often managing such complex hierarchies involve interacting with heterogeneous management platforms from various vendors and built on different platforms each providing the solution to a piece of the ’energy puzzle’ of the organisation. The complexities involved in managing such a network of systems are manifold and require extensive resourcing and expertise. Sustainability and Net Zero carbon emission initiatives that aim to achieve international and national targets add a further layer of complexity to the task at hand. In this paper, we propose a Cloud Edge architecture that leverages Artificial Intelligence (AI) and data analytics for microgrid energy optimisation and net zero carbon emissions. This architecture provides an intelligent and cohesive abstraction to assist in cataloging, unifying and managing the complexities of microgrids and enabling sustainable management of energy. The proposed architecture has been operationalised as the energy management and optimisation platform at a multi-campus, multi-functional tertiary education institution. Empirical evaluations conducted on this deployment have generated results that confirm the function and effectiveness of this architecture in addressing the emerging and evolving challenges of microgrid energy optimisation and net zero carbon emissions.

In this paper we introduce UNICON, a large-scale open dataset on UNIversity CONsumption of utilities, electricity, gas and water. This dataset is publicly released as part of La Trobe University’s commitment to Net Zero Carbon Emissions by 2029, for which we are building the La Trobe Energy AI/Analytics Platform (LEAP) that leverages Artificial Intelligence (AI) and Data Analytics to analyse, predict and optimize the consumption, generation and utilization of electricity, renewables, gas and water resources. UNICON contains consumption data for La Trobe’s five campuses in geographically distributed regions, across four years, 2018-2021 inclusive. This includes the COVID-19 global pandemic timeline of university shutdown and work from home measures that led to a significant decrease in the consumption of utilities. The consumption data consists of smart electricity meter readings at 15-minute granularity, gas meter readings at hourly intervals and water meter readings at 15-minute intervals. UNICON also contains weather data from the closest weather station to each campus, collected at two-speed latency of 1 minute and 10 minutes. The dataset is annotated with internal events of significance, such as energy conservation measures (ECMs) and other measurement and validation (M&V) activities conducted as part of LEAP optimization. To the best of our knowledge, this is the first large-scale, comprehensive, open dataset for the three main utilities, electricity, gas, and water consumption in a multi-campus university setting. A high granularity data dictionary and technical validation of the dataset for consumption trends, baseline modelling and forecasting are further contributions of this article that will enable interested research scientists, academics, industry practitioners, sustainability and energy consultants to experiment and evaluate their AI algorithms, models, forecasts, as well as inform the development of energy benchmarks, guidelines and much needed data-driven energy policies.

Recent advancements in Artificial intelligence (AI) have led to its widespread adoption in healthcare applications and services. The global pandemic has further hastened the integration of AI into telehealth services, such as service quality improvement and new models of care. This paper focuses on the service quality improvement of telehealth, specifically, cancer information and telephone support services, in terms of its human system interaction. We present an AI framework for the detection of patient emotions and emotion transitions based on call recordings of telehealth services. The call recordings are typically a conversation between the caller (patient or carer) and the healthcare practitioner (nurse or counsellor). All primary emotions are expressed across diverse topics during these calls. It is anticipated that the caller emotion state improves during the call due to the information and support received. The proposed AI framework is designed to detect emotions expressed at all stages of the call and based on these expressions, formulate the emotion transition during the call. We have evaluated the proposed AI framework on a large real-world dataset of 60,000 call recordings of cancer information and telephone support services provided by Cancer Council Victoria, Australia. The results confirm the effectiveness of this AI framework in detection of emotions and emotion transitions during the provision of telehealth services.

Time series forecasting is a critical requirement for the optimal operation of energy grids, systems, and platforms, where the forecasting challenge itself can span across energy consumption, renewables generation, and energy utilisation. Artificial Intelligence (AI) algorithms and models have been leveraged to predict these time series forecasts with increasing levels of accuracy. In contrast to local models that are developed separately for each time series, Global Models, which are trained across many sets of time series drawing on characteristics of ’relatedness’, have produced more accurate forecasts. In this paper, we propose a transformer architecture based global model as a generalist forecaster of energy time series data, where we frame a sequence forecasting model and represent numerical values of the corresponding time series as vector embeddings in this model. We evaluate this transformer architecture based global model on real-world time-series energy data generated by the La Trobe Energy AI platform (LEAP), a functional and operational microgrid deployed in the multicampus tertiary education setting of La Trobe University, Australia. The results of these experiments confirm that the proposed generalist forecasting approach outperforms specialist local models trained on individual time series. We also demonstrate the ability of this approach to forecast dissimilar time series from the same model.

Humans have continuously endeavored to enhance their sensory perception and awareness of the physical surroundings for the betterment of themselves as individuals as well as communities. Advancing this notion to the present day, the Internet of Things (IoT) provides a unique opportunity to attempt the same in an increasingly digital landscape. The prevalence and pervasiveness of IoT data streams gives us this ability to represent a situation with clarity and nuance, leading to a refined awareness of the environment. However, there are several challenges in managing the scale, velocity, and magnitude of IoT data streams, as well as the cohesive representation of these varied sources in a single frame of reference. In this article, we present a new algorithm, the deep growing self-organizing map (deep GSOM) algorithm that addresses these challenges. Deep GSOM incrementally generates a latent representation of situational awareness from high entropy to low entropy IoT data streams. It utilizes an implementation of the fuzzy integral to define a metric that can be moved across spatial and temporal situations to profile the density of congestion. We have also expanded deep GSOM into an IoT platform that can collate, aggregate, and process an entire network of IoT data streams. We demonstrate the workings of deep GSOM on the real-life scenario of profiling vehicular and pedestrian movement using IoT data streams of two highly urbanized cities. The results of these experiments confirm the validity and effectiveness of the proposed approach for generating situational awareness from multiple IoT data streams.