Distribution System Operators (DSOs) are responsible preventing grid congestion, while accounting for growing demand and the intermittent nature of renewable energy resources. Incentive-based demand response programs promise real-time flexibility to relieve grid congestion. To include residential consumers in these programs, aggregators can financially incentivize participants to reduce their energy demand and make aggregated energy reduction available to DSOs. A key challenge for aggregators is to coordinate heterogeneous preferences from multiple participants while preserving their privacy. This thesis proposes MARL-iDR: a decentralized Multi-Agent Reinforcement Learning approach to an incentive-based demand response program. The approach respects participants' privacy and preferences and makes decisions in real-time when deployed. The aggregator and each participant are controlled by Deep Reinforcement Learning agents that learn to maximize their reward. The aggregator agent learns a policy that dispatches suitable incentives to participants based on total energy demand and a target reduction, while minimizing financial costs. The participant agent learns to respond to these incentives by reducing consumption to a fraction of the original demand. The participant agents curtail or shift requested household appliances based on the selected consumption reduction using a novel Disjunctively Constrained Knapsack Problem optimization, while minimizing residents' dissatisfaction. A case study with real-world electricity data from 25 households demonstrates the capability to induce demand-side flexibility. The approach is compared to the case without demand response and to a centralized myopic baseline approach. A 9% reduction of the Peak-to-Average ratio (PAR) was achieved compared to the original PAR (no demand response).

In nature, all species have their own behaviors and strategies for survival. Some species survive and reproduce, while others become extinct. This paper proposes a model to simulate these strategies and test their performance. Natural behavior is represented as strategies for the iterated Prisoner's Dilemma (IPD). Agents wielding one of ten common IPD strategies are deployed in a natural spatial environment with biologically realistic conditions, where they continuously play Prisoner's Dilemma games. If the payoffs are well enough, agents are able to reproduce. The harshness of the environment is determined by three factors. The cost of living directly controls the climate and age limitation and energy limitation affect an agent's ability to reproduce. Another influencing factor is evolution, which gives agents the option to adopt different strategies in later stages. Harsh environments are defined by high costs of living, high reproduction costs and low life expectancy. Results show that cooperative strategies are more likely to survive and reproduce in harsh environments. Moreover, evolution is in the advantage of cooperative strategies, because many unsuccessful defectors evolve into cooperators.