AI-optimised maintenance planning for energy networks

Network maintenance is a multi-period decision: measures do not just have an impact ‘this year’, but influence system reliability over several years. At the same time, budgets, crew capacities and logical dependencies are hard constraints. The key question is: Which combination and sequence of measures maximises grid reliability over a 5-year horizon?

Objective

Maximising the improvement in system reliability over 5 years – measurable, for example, via SAIDI reduction, outage frequency, asset criticality or risk reduction in critical grid sections.

Assessment Inputs

• Reliability gain per measure (e.g. ΔSAIDI / ΔSAIFI / risk reduction)
• Costs and duration of the maintenance task
• Crew requirements (skills, team size, availability)
• Precedence dependencies (dependencies / sequencing relationships)

Evaluation and selection mechanism

Each measure i is assigned a value representing its direct contribution to reliability:

Vᵢ = ΔReliabilityᵢ

StratePlan then calculates a multi-period selection: Measures are not only selected, but also scheduled across years and time windows in such a way that the cumulative reliability gain is maximised – subject to real-world budget and resource constraints.

Multi-period scheduling (5-year plan)

Instead of an annual plan, a robust 5-year roadmap is created: Which inspections, maintenance tasks, refurbishments or replacements take place in which period, with which crew and in which sequence – including the rationale for why this order is optimal.

Constraints

• Annual budget and crew caps : Annual CAPEX/OPEX limits and limited teams/skills
• Minimum reliability threshold : Minimum reliability level that must be maintained at all times
• Logical sequencing : e.g. ‘inspect before replace’, Approvals, lockout periods, dependencies

Result

• 5-year maintenance plan with maximum reliability improvement
• Explicit compliance with budget, crew and threshold requirements per year
• Traceable sequence logic (precedence, inspection chains, replacement paths)
• Transparent prioritisation: which measure contributes what to reliability

Technology

StratePlan MPS (Multi-Period Solution) calculates multi-period decisions with vectorised constraints (budget, crew, time window, sequence rules). MAVT (Multi-Attribute Value Theory) structures the evaluation, so that reliability improvements can be mapped in a consistent, auditable and decision-ready manner.

Common Patterns Across Cases

Assessment

Qualitative and quantitative factors are converted into comparable scores – using scales, evaluation models or structured expert assessment. The aim is to establish a consistent, decision-ready evaluation basis.

Ranking

Elements are prioritised. However, ranking is rarely the final decision. In complex environments, prioritisation is frequently embedded directly into a combinatorial optimisation process in order to systematically account for interactions and constraints.

Group Selection

The final selection goes beyond a simple ‘Top-k’ approach. StratePlan solves structured selection problems such as knapsack, portfolio or scheduling models and calculates the optimal combination under real-world constraints.

Constraints

Constraints reflect real-world scarcity: capital, time, resources, risk appetite, regulatory requirements, strategic mandates or sustainability requirements. They are an integral part of the decision-making logic.

Technologies

Hybrid use of MCDA methods (e.g. AHP, TOPSIS) for structured evaluation combined with StratePlan for constraint-aware group or portfolio selection.

These cases demonstrate how StratePlan evolves decision-making processes from pure ranking to intelligent, constraint-aware portfolio construction. Evaluation data is translated into actionable, optimised group decisions – aligned with financial, strategic and sustainability-related objectives.

The underlying core logic – structured evaluation → quantitative prioritisation → constrained group selection – scales across different sectors and is adapted in each case to domain-specific success metrics and constraints.