Search

District heating is expected to play an essential role in the cost-effective decarbonisation strategy of many countries. Resource-optimised management of district heating networks depends on a wide range of factors, including demand forecasting, operational flexibility, and increasingly volatile market conditions. However, traditional operations often still rely on static models and rather simple heuristics, while holistic optimisation requires dynamic cross-domain interoperability to allow the consideration of all these factors. This paper demonstrates a proof-of-concept for a knowledge graph based optimisation problem to minimise total heat generation cost for a district heating provider. The optimisation follows a hierarchical approach based on a merit-order principle and is embedded in a model predictive control framework to allow the system to incorporate most recent information and react to disturbances promptly. A detailed sensitivity study is conducted to identify key model parameters and assess the impact of anticipated changes in regulation and market conditions. Simulation-based optimisation is used to determine the short-term heat generation mix based on data-driven gas consumption models and day-ahead forecasts for the network's energy demand and grid temperatures. Seasonal autoregressive integrated moving average models with exogenous predictor variables are found to be sufficiently accurate and precise. The effectiveness of the approach is demonstrated for a case study of an existing heating network of a midsize town in Germany, where a reduction of approximately 20% and 40% compared to baseline operational data is obtained for operating cost and CO 2 emissions, respectively. [Display omitted] • Developed heat generation optimisation framework for district heating providers. • Identified key cost drivers and market dynamics using a detailed sensitivity analysis. • Developed high accuracy time series forecasting models for key input variables. • Assessed optimisation effectivity using a German municipal utility case study. • Improvement potential for operational cost and CO 2 emissions both exceed 20%. [ABSTRACT FROM AUTHOR]

Global Horizontal Irradiation forecasts are necessary for an efficient use of fluctuating energy output from photovoltaic plants. The purpose of this paper is to provide efficient, easy-to-implement Global Horizontal Irradiation forecasts on an hourly basis for a medium-term horizon (longer than 48 h). These forecasts are essential for the strategic deployment of tasks including unit commitment, transmission management, trading, hedging, planning, asset optimization, maintenance scheduling and spinning of power units. Nonetheless, forecasting models for medium term horizons are scarce. This work intends to bridge that gap by proposing a method based on an adjusted combination of moving averages which includes the yearly cycle in addition to the day–night cycle. This method is straightforward to implement and easy to integrate into corporate computing systems. We compare our approach with several well-known alternative methods, such as deep recurrent neural networks or autoregressive integrated moving average models, among others. The results show that recurrent neural networks are 10% more accurate than the second best method, and 90% better than our proposal for very short horizons (up to 5 h ahead). However, this advantage is lost when longer horizons are tested, especially for horizons longer than 30 h ahead, for which our method produces forecasts which are 20% more accurate than those made by recurrent neural networks. The reason behind that improvement at longer horizons is the inclusion of the yearly cycle in the proposed approach. • There is a rich literature on short-term photovoltaic energy forecasting methods. • Many tasks in photovoltaic plants need forecasting methods for medium-term horizons. • A new method for medium-term photovoltaic energy forecasting is developed and tested. • Many methods produce accurate forecasts for short-term horizons, deep learning best. • The proposal outperforms many forecasting methods for medium-term horizons. [ABSTRACT FROM AUTHOR]