Stochastic Multi-Criteria Decision-Making in Energy Systems

Stochastic multi-criteria decision-making in energy systems addresses the challenge of selecting or ranking energy technologies and strategies when both performance indicators and decision-maker preferences are uncertain. By modelling criteria such as cost, efficiency, emissions and reliability as probability distributions rather than fixed values, these methods capture real-world variability in resource availability, demand profiles and policy frameworks. Practitioners employ simulation-based techniques to sample from admissible weight spaces that reflect incomplete or imprecise stakeholder input, thereby generating acceptability indices or ranking probabilities for each alternative. This probabilistic perspective augments traditional multi-criteria decision analysis by quantifying the robustness of decisions under uncertain conditions and revealing the influence of individual criteria on overall preference. Applications span the evaluation of combined heat and power units, the optimisation of district heating networks, and the appraisal of renewable integration at industrial and infrastructural sites. Collectively, the literature demonstrates that stochastic approaches enhance transparency in trade-off assessment, enable sensitivity diagnostics and support more resilient planning of decarbonisation pathways in a rapidly evolving energy landscape.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Stochastic Multi-Criteria Decision-Making in Energy Systems publication trend

The graph below shows the total number of articles in stochastic multi-criteria decision-making in energy systems across all publications each year (not limited to Nature Index journals).

Technical terms

Stochastic multi-criteria decision-making (S-MCDM): A class of decision-analysis methods that model uncertainties in both criteria values and preferences through probability distributions to rank or select alternatives.

Stochastic multicriteria acceptability analysis (SMAA): A simulation-based technique that samples from weight and performance distributions to compute the probability of each alternative achieving a given rank.

PROMETHEE: An outranking method that compares alternatives pairwise across multiple criteria to derive preference flows, extended in stochastic settings by embedding weight uncertainty.

Sigma–mu approach: A closed-form method for calculating the mean (mu) and standard deviation (sigma) of composite scores under uncertain weight distributions without relying on Monte Carlo simulations.

Bayesian network (BN): A graphical probabilistic model that represents uncertain variables and their conditional dependencies, used here to capture the stochastic relationships among performance criteria.

References

1. On the sigma-mu stochastic multicriteria analysis: Exact solutions for common particular cases. Omega (2024).
2. Multicriteria decision support under uncertainty: combining outranking methods with Bayesian networks. Annals of Operations Research (2024).
3. Stochastic Multicriteria Acceptability Analysis for Evaluation of Combined Heat and Power Units. Energies (2014).
4. A Comparison of Multi-Criteria Decision Analysis Methods for Sustainability Assessment of District Heating Systems. Energies (2022).
5. Multicriteria Decision Aiding for Planning Renewable Power Production at Moroccan Airports. Energies (2022).