In classic Box-Jenkins time series analysis, the operational definition of independence here will be that both the autocorrelation functions of the series and the squared series show no autocorrelation. If there is no serial correlation of the series but there is of the squared series, then we will say there is weak dependence. This will lead us to examine the volatility of the series, since that is exemplified by the squared terms. This is precisely the situation that occurs when one examines wind farm output with a view to forecasting the level of output from a wind farm. In order to construct error bounds on the forecast, one needs to know the structure of the variance. If the series were stationary after any deseasoning and ARMA modelling, the noise could be assumed to homoscedastic. This is not, however, the case and it is shown that a form of generalised autoregressive conditional heteroscedastic (GARCH) model schema is necessary. Since the volatility is unobservable, it is not possible to find maximum likelihood estimates of the model parameters. In the situation where one has high frequency data also available, one can employ the concept of realised volatility to counteract this problem. This work is performed as part of an ARC Linkage Grant with the Australian Energy Market Operator and an ARC Discovery Grant, both focussing on the integration of renewable energy sources into the electricity grid. Dr John Boland is an expert in environmental modelling, specialising in time series and statistical modelling of climate variables and modelling systems under uncertainty. The Electricity Supply Industry Planning Council (ESIPC) of South Australia, a State government research body, have called on Assoc Prof Boland's expertise for several projects. A PhD student, under his guidance, constructed a stochastic electricity demand model to enable the ESIPC – now part of AEMO - to make decisions under uncertainty for electricity grid operation. They also contracted him to study the output variability of windfarms in South Australia so they could better advise the State government on future development of windfarms. At a national level, he coordinated a project to develop the algorithms for quality assurance in construction of climate data files for the Australian Climatic Database, used principally for house energy ratings software. John was co-leader of the research team that calculated the Ecological Footprint of South Australia, under contract from the State government. He has coordinated subsequent projects for the Land Management Corporation in SA for the Lochiel Park Green Village and the Adelaide City Council focussing on optimisation and sensitivity analysis with the goal of identifying the key areas to focus on to reduce the footprint. He has or presently holds 3 ARC Discovery Grants and 3 ARC Linkage Grants, in the areas of electricity supply, water resources, and reducing food waste. John is co-owner of an urban farm in Adelaide, with 50 producing trees on a suburban block, and as well co-curator of a 53 hectare private conservation park in the South Australian Mallee. This event is organised by the Centre for Energy and Environmental Markets (CEEM) at the University of New South Wales. CEEM provides Australian leadership in interdisciplinary research in the design, analysis and performance monitoring of energy and environmental markets and their associated policy frameworks.