Biased forecast error scenarios?

[junglegobs]

The forecast error scenarios I generated using @asutera's code appear to be biased, both when aggregated and also at the nodal level. This is particularly clear for Wind (day 41, top is for node GOUY, bottom is aggregated over Belgium):

This may be fine, if Antonio didn't correct for this (and we could / should), however it may also be an indication of something being very wrong. It is also so "bad" that there are certain hours (9 - 11) in which there are essentially no scenarios in which a negative imbalance occurs, which is unusual to say the least...

[junglegobs]

So I realised that while this may be the case, it has implications for the probabilities I assign to the upward and downward reserve levels. Taken to the extreme, the upward reserve levels should cover the entire probability space, i.e. probability of reserve level 1 being activated is very close to or equal to 1.

[junglegobs]

It seems that I already taken forecast error biases into account. See for example the below:

julia> vec = vcat(-2:10);

julia> q_cut_up, q_mid_up, p_up, q_cut_down, q_mid_down, p_down = quantiles_and_probabilities(vec; n_up=3, n_down=3);

julia> p_up
3-element Vector{Float64}:
 0.6923076923076923
 0.3846153846153846
 0.15384615384615385

julia> p_down
3-element Vector{Float64}:
 0.15384615384615385
 0.15384615384615385
 0.07692307692307693

julia> vec = vcat(2:10);

julia> q_cut_up, q_mid_up, p_up, q_cut_down, q_mid_down, p_down = quantiles_and_probabilities(vec; n_up=3, n_down=3);

julia> p_up
3-element Vector{Float64}:
 1.0
 0.5555555555555556
 0.2222222222222222

julia> p_down
3-element Vector{Float64}:
 0.0
 0.0
 0.0

[junglegobs]

The bias issue remains as of now, though I realised that I probably had the signs wrong for the net load forecast error calculation.